Improving the quality assurance (QA) processes and acquiring accreditation are top priorities for academic programs. The learning outcomes (LOs)assessment and continuous quality improvement represent core components o...Improving the quality assurance (QA) processes and acquiring accreditation are top priorities for academic programs. The learning outcomes (LOs)assessment and continuous quality improvement represent core components ofthe quality assurance system (QAS). Current assessment methods suffer deficiencies related to accuracy and reliability, and they lack well-organized processes forcontinuous improvement planning. Moreover, the absence of automation, andintegration in QA processes forms a major obstacle towards developing efficientquality system. There is a pressing need to adopt security protocols that providerequired security services to safeguard the valuable information processed byQAS as well. This research proposes an effective methodology for LOs assessment and continuous improvement processes. The proposed approach ensuresmore accurate and reliable LOs assessment results and provides systematic wayfor utilizing those results in the continuous quality improvement. This systematicand well-specified QA processes were then utilized to model and implement automated and secure QAS that efficiently performs quality-related processes. Theproposed system adopts two security protocols that provide confidentiality, integrity, and authentication for quality data and reports. The security protocols avoidthe source repudiation, which is important in the quality reporting system. This isachieved through implementing powerful cryptographic algorithms. The QASenables efficient data collection and processing required for analysis and interpretation. It also prepares for the development of datasets that can be used in futureartificial intelligence (AI) researches to support decision making and improve thequality of academic programs. The proposed approach is implemented in a successful real case study for a computer science program. The current study servesscientific programs struggling to achieve academic accreditation, and gives rise tofully automating and integrating the QA processes and adopting modern AI andsecurity technologies to develop effective QAS.展开更多
The rapid development of artificial intelligence(AI),machine learning(ML),and deep learning(DL)in recent years has transformed many sectors.A fundamental shift has occurred in approaches to solving complex problems an...The rapid development of artificial intelligence(AI),machine learning(ML),and deep learning(DL)in recent years has transformed many sectors.A fundamental shift has occurred in approaches to solving complex problems and making decisions in many different fields.These advanced technologies have enabled significant breakthroughs in sectors including entertainment,finance,transportation,and healthcare.AI systems,which can analyze vast volumes of data,have significantly driven efficiency and innovation.With remarkable accuracy,patterns can be identified and predictions generated,improving decision-making processes and facilitating the development of more intelligent solutions.The increasing adoption of these technologies by organizations has expanded the potential for AI to change processes and improve results.展开更多
Presently,precision agriculture processes like plant disease,crop yield prediction,species recognition,weed detection,and irrigation can be accom-plished by the use of computer vision(CV)approaches.Weed plays a vital ...Presently,precision agriculture processes like plant disease,crop yield prediction,species recognition,weed detection,and irrigation can be accom-plished by the use of computer vision(CV)approaches.Weed plays a vital role in influencing crop productivity.The wastage and pollution of farmland's natural atmosphere instigated by full coverage chemical herbicide spraying are increased.Since the proper identification of weeds from crops helps to reduce the usage of herbicide and improve productivity,this study presents a novel computer vision and deep learning based weed detection and classification(CVDL-WDC)model for precision agriculture.The proposed CVDL-WDC technique intends to prop-erly discriminate the plants as well as weeds.The proposed CVDL-WDC technique involves two processes namely multiscale Faster RCNN based object detection and optimal extreme learning machine(ELM)based weed classification.The parameters of the ELM model are optimally adjusted by the use of farmland fertility optimization(FFO)algorithm.A comprehensive simulation analysis of the CVDL-WDC technique against benchmark dataset reported the enhanced out-comes over its recent approaches interms of several measures.展开更多
Information transmission is studied in the cases of amplitude and frequency modulations where there is an impulsive jamming in the signal. By using the array approach of nonlinear elements, we find that for both the p...Information transmission is studied in the cases of amplitude and frequency modulations where there is an impulsive jamming in the signal. By using the array approach of nonlinear elements, we find that for both the periodic and aperiodic modulations, the information transmission can be enhanced by adding independent external noise on every element of the array. The dependence of information transmission on the size of array and the impulsive interval of the jamming are also studied.展开更多
The learning status of learners directly affects the quality of learning.Compared with offline teachers,it is difficult for online teachers to capture the learning status of students in the whole class,and it is even ...The learning status of learners directly affects the quality of learning.Compared with offline teachers,it is difficult for online teachers to capture the learning status of students in the whole class,and it is even more difficult to continue to pay attention to studentswhile teaching.Therefore,this paper proposes an online learning state analysis model based on a convolutional neural network and multi-dimensional information fusion.Specifically,a facial expression recognition model and an eye state recognition model are constructed to detect students’emotions and fatigue,respectively.By integrating the detected data with the homework test score data after online learning,an analysis model of students’online learning status is constructed.According to the PAD model,the learning state is expressed as three dimensions of students’understanding,engagement and interest,and then analyzed from multiple perspectives.Finally,the proposed model is applied to actual teaching,and procedural analysis of 5 different types of online classroom learners is carried out,and the validity of the model is verified by comparing with the results of the manual analysis.展开更多
Privacy preservation(PP)in Digital forensics(DF)is a conflicted and non-trivial issue.Existing solutions use the searchable encryption concept and,as a result,are not efficient and support only a keyword search.Moreov...Privacy preservation(PP)in Digital forensics(DF)is a conflicted and non-trivial issue.Existing solutions use the searchable encryption concept and,as a result,are not efficient and support only a keyword search.Moreover,the collected forensic data cannot be analyzed using existing well-known digital tools.This research paper first investigates the lawful requirements for PP in DF based on the organization for economic co-operation and development OECB)privacy guidelines.To have an efficient investigation process and meet the increased volume of data,the presented framework is designed based on the selective imaging concept and advanced encryption standard(AES).The proposed framework has two main modules,namely Selective Imaging Module(SIM)and Selective Analysis Module(SAM).The SIM and SAM modules are implemented based on advanced forensic format 4(AFF4)and SleuthKit open source forensics frameworks,respectively,and,accordingly,the proposed framework is evaluated in a forensically sound manner.The evaluation result is compared with other relevant works and,as a result,the proposed solution provides a privacy-preserving,efficient forensic imaging and analysis process while having also sufficient methods.Moreover,the AFF4 forensic image,produced by the SIM module,can be analyzed not only by SAM,but also by other well-known analysis tools available on the market.展开更多
Identifying human actions and interactions finds its use in manyareas, such as security, surveillance, assisted living, patient monitoring, rehabilitation,sports, and e-learning. This wide range of applications has at...Identifying human actions and interactions finds its use in manyareas, such as security, surveillance, assisted living, patient monitoring, rehabilitation,sports, and e-learning. This wide range of applications has attractedmany researchers to this field. Inspired by the existing recognition systems,this paper proposes a new and efficient human-object interaction recognition(HOIR) model which is based on modeling human pose and scene featureinformation. There are different aspects involved in an interaction, includingthe humans, the objects, the various body parts of the human, and the backgroundscene. Themain objectives of this research include critically examiningthe importance of all these elements in determining the interaction, estimatinghuman pose through image foresting transform (IFT), and detecting the performedinteractions based on an optimizedmulti-feature vector. The proposedmethodology has six main phases. The first phase involves preprocessing theimages. During preprocessing stages, the videos are converted into imageframes. Then their contrast is adjusted, and noise is removed. In the secondphase, the human-object pair is detected and extracted from each image frame.The third phase involves the identification of key body parts of the detectedhumans using IFT. The fourth phase relates to three different kinds of featureextraction techniques. Then these features are combined and optimized duringthe fifth phase. The optimized vector is used to classify the interactions in thelast phase. TheMSRDaily Activity 3D dataset has been used to test this modeland to prove its efficiency. The proposed system obtains an average accuracyof 91.7% on this dataset.展开更多
A news agency is an organization that gathers news reports and sells them to subscribing news organization, such as newspapers, magazines, radio and television broadcasters. A news agency may also be referred to as a ...A news agency is an organization that gathers news reports and sells them to subscribing news organization, such as newspapers, magazines, radio and television broadcasters. A news agency may also be referred to as a wire service, newswire, or news service. The main purpose of this paper is to evaluate the security policies and analyze the content of five press agencies in gulf countries which are (Kuwait News Agency (KUNA), Emirates News Agency (WAM), Saudi Press Agency (SPA), Bahrain News Agency (BNA), and Oman News Agency (OMA)) by using a fuzzy VIKOR approach where linguistic variables are applied to solve the uncertainties and subjectivities in expert decision making. Fuzzy VIKOR approach is one of the best Multi-Criteria Decision Making (MCDM) techniques working in fuzzy environment. This study benefits security and content analysis experts know which press agency has the mandate and the competence to educate the public on news agencies. Besides, this paper contributes to Gulf agencies in helping them in their resolve to ensure the quality of content information and information security policies over the internet.展开更多
Bone age assessment(BAA)aims to determine whether a child’s growth and development are normal concerning their chronological age.To predict bone age more accurately based on radiographs,and for the left-hand X-ray im...Bone age assessment(BAA)aims to determine whether a child’s growth and development are normal concerning their chronological age.To predict bone age more accurately based on radiographs,and for the left-hand X-ray images of different races model can have better adaptability,we propose a neural network in parallel with the quantitative features from the left-hand bone measurements for BAA.In this study,a lightweight feature extractor(LFE)is designed to obtain the featuremaps fromradiographs,and amodule called attention erasermodule(AEM)is proposed to capture the fine-grained features.Meanwhile,the dimensional information of the metacarpal parts in the radiographs is measured to enhance the model’s generalization capability across images fromdifferent races.Ourmodel is trained and validated on the RSNA,RHPE,and digital hand atlas datasets,which include images from various racial groups.The model achieves a mean absolute error(MAE)of 4.42 months on the RSNA dataset and 15.98 months on the RHPE dataset.Compared to ResNet50,InceptionV3,and several state-of-the-art methods,our proposed method shows statistically significant improvements(p<0.05),with a reduction in MAE by 0.2±0.02 years across different racial datasets.Furthermore,t-tests on the features also confirm the statistical significance of our approach(p<0.05).展开更多
Terrain Aided Navigation(TAN)technology has become increasingly important due to its effectiveness in environments where Global Positioning System(GPS)is unavailable.In recent years,TAN systems have been extensively r...Terrain Aided Navigation(TAN)technology has become increasingly important due to its effectiveness in environments where Global Positioning System(GPS)is unavailable.In recent years,TAN systems have been extensively researched for both aerial and underwater navigation applications.However,many TAN systems that rely on recursive Unmanned Aerial Vehicle(UAV)position estimation methods,such as Extended Kalman Filters(EKF),often face challenges with divergence and instability,particularly in highly non-linear systems.To address these issues,this paper proposes and investigates a hybrid two-stage TAN positioning system for UAVs that utilizes Particle Filter.To enhance the system’s robustness against uncertainties caused by noise and to estimate additional system states,a Fuzzy Particle Filter(FPF)is employed in the first stage.This approach introduces a novel terrain composite feature that enables a fuzzy expert system to analyze terrain non-linearities and dynamically adjust the number of particles in real-time.This design allows the UAV to be efficiently localized in GPS-denied environments while also reducing the computational complexity of the particle filter in real-time applications.In the second stage,an Error State Kalman Filter(ESKF)is implemented to estimate the UAV’s altitude.The ESKF is chosen over the conventional EKF method because it is more suitable for non-linear systems.Simulation results demonstrate that the proposed fuzzy-based terrain composite method achieves high positional accuracy while reducing computational time and memory usage.展开更多
The concept of“STEM+”integrates art,humanistic literacy,and social values in the traditional STEM education concept,advocates cross-disciplinary integration,and aims to cultivate compound talents equipped to tackle ...The concept of“STEM+”integrates art,humanistic literacy,and social values in the traditional STEM education concept,advocates cross-disciplinary integration,and aims to cultivate compound talents equipped to tackle future challenges.In 2022,the Ministry of Education issued the“Compulsory Education Information Technology Curriculum(2022 Edition),”emphasizing the core literacy of information science and technology and the integration of interdisciplinary disciplines,and encouraging the teaching mode suitable for discipline characteristics.The 6E teaching mode is a student-centered teaching strategy characterized by active exploration and cross-disciplinary integration.This article innovatively designed the“STEM+”6E teaching mode,which is applied to junior high school information technology teaching,which can better achieve core literacy teaching goals.展开更多
The rapid integration of artificial intelligence(AI)into software development,driven by large language models(LLMs),is reshaping the role of programmers from traditional coders into strategic collaborators within Indu...The rapid integration of artificial intelligence(AI)into software development,driven by large language models(LLMs),is reshaping the role of programmers from traditional coders into strategic collaborators within Industry 4.0 ecosystems.This qualitative study employs a hermeneutic phenomenological approach to explore the lived experiences of Information Technology(IT)professionals as they navigate a dynamic technological landscape marked by intelligent automation,shifting professional identities,and emerging ethical concerns.Findings indicate that developers are actively adapting to AI-augmented environments by engaging in continuous upskilling,prompt engineering,interdisciplinary collaboration,and heightened ethical awareness.However,participants also voiced growing concerns about the reliability and security of AI-generated code,noting that these tools can introduce hidden vulnerabilities and reduce critical engagement due to automation bias.Many described instances of flawed logic,insecure patterns,or syntactically correct but contextually inappropriate suggestions,underscoring the need for rigorous human oversight.Additionally,the study reveals anxieties around job displacement and the gradual erosion of fundamental coding skills,particularly in environments where AI tools dominate routine development tasks.These findings highlight an urgent need for educational reforms,industry standards,and organizational policies that prioritize both technical robustness and the preservation of human expertise.As AI becomes increasingly embedded in software engineering workflows,this research offers timely insights into how developers and organizations can responsibly integrate intelligent systems to promote accountability,resilience,and innovation across the software development lifecycle.展开更多
The rapid evolution of malware presents a critical cybersecurity challenge,rendering traditional signature-based detection methods ineffective against novel variants.This growing threat affects individuals,organizatio...The rapid evolution of malware presents a critical cybersecurity challenge,rendering traditional signature-based detection methods ineffective against novel variants.This growing threat affects individuals,organizations,and governments,highlighting the urgent need for robust malware detection mechanisms.Conventional machine learning-based approaches rely on static and dynamicmalware analysis and often struggle to detect previously unseen threats due to their dependency on predefined signatures.Although machine learning algorithms(MLAs)offer promising detection capabilities,their reliance on extensive feature engineering limits real-time applicability.Deep learning techniques mitigate this issue by automating feature extraction but may introduce computational overhead,affecting deployment efficiency.This research evaluates classical MLAs and deep learningmodels to enhance malware detection performance across diverse datasets.The proposed approach integrates a novel text and imagebased detection framework,employing an optimized Support Vector Machine(SVM)for textual data analysis and EfficientNet-B0 for image-based malware classification.Experimental analysis,conducted across multiple train-test splits over varying timescales,demonstrates 99.97%accuracy on textual datasets using SVM and 96.7%accuracy on image-based datasets with EfficientNet-B0,significantly improving zero-day malware detection.Furthermore,a comparative analysis with existing competitive techniques,such as Random Forest,XGBoost,and CNN-based(Convolutional Neural Network)classifiers,highlights the superior performance of the proposed model in terms of accuracy,efficiency,and robustness.展开更多
The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the ...The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the continuously advancing level of sophistication.To resolve this problem,efficient and flexible malware detection tools are needed.This work examines the possibility of employing deep CNNs to detect Android malware by transforming network traffic into image data representations.Moreover,the dataset used in this study is the CIC-AndMal2017,which contains 20,000 instances of network traffic across five distinct malware categories:a.Trojan,b.Adware,c.Ransomware,d.Spyware,e.Worm.These network traffic features are then converted to image formats for deep learning,which is applied in a CNN framework,including the VGG16 pre-trained model.In addition,our approach yielded high performance,yielding an accuracy of 0.92,accuracy of 99.1%,precision of 98.2%,recall of 99.5%,and F1 score of 98.7%.Subsequent improvements to the classification model through changes within the VGG19 framework improved the classification rate to 99.25%.Through the results obtained,it is clear that CNNs are a very effective way to classify Android malware,providing greater accuracy than conventional techniques.The success of this approach also shows the applicability of deep learning in mobile security along with the direction for the future advancement of the real-time detection system and other deeper learning techniques to counter the increasing number of threats emerging in the future.展开更多
Voice, motion, and mimicry are naturalistic control modalities that have replaced text or display-driven control in human-computer communication (HCC). Specifically, the vocals contain a lot of knowledge, revealing de...Voice, motion, and mimicry are naturalistic control modalities that have replaced text or display-driven control in human-computer communication (HCC). Specifically, the vocals contain a lot of knowledge, revealing details about the speaker’s goals and desires, as well as their internal condition. Certain vocal characteristics reveal the speaker’s mood, intention, and motivation, while word study assists the speaker’s demand to be understood. Voice emotion recognition has become an essential component of modern HCC networks. Integrating findings from the various disciplines involved in identifying vocal emotions is also challenging. Many sound analysis techniques were developed in the past. Learning about the development of artificial intelligence (AI), and especially Deep Learning (DL) technology, research incorporating real data is becoming increasingly common these days. Thus, this research presents a novel selfish herd optimization-tuned long/short-term memory (SHO-LSTM) strategy to identify vocal emotions in human communication. The RAVDESS public dataset is used to train the suggested SHO-LSTM technique. Mel-frequency cepstral coefficient (MFCC) and wiener filter (WF) techniques are used, respectively, to remove noise and extract features from the data. LSTM and SHO are applied to the extracted data to optimize the LSTM network’s parameters for effective emotion recognition. Python Software was used to execute our proposed framework. In the finding assessment phase, Numerous metrics are used to evaluate the proposed model’s detection capability, Such as F1-score (95%), precision (95%), recall (96%), and accuracy (97%). The suggested approach is tested on a Python platform, and the SHO-LSTM’s outcomes are contrasted with those of other previously conducted research. Based on comparative assessments, our suggested approach outperforms the current approaches in vocal emotion recognition.展开更多
Dementia is a neurological disorder that affects the brain and its functioning,and women experience its effects more than men do.Preventive care often requires non-invasive and rapid tests,yet conventional diagnostic ...Dementia is a neurological disorder that affects the brain and its functioning,and women experience its effects more than men do.Preventive care often requires non-invasive and rapid tests,yet conventional diagnostic techniques are time-consuming and invasive.One of the most effective ways to diagnose dementia is by analyzing a patient’s speech,which is cheap and does not require surgery.This research aims to determine the effectiveness of deep learning(DL)and machine learning(ML)structures in diagnosing dementia based on women’s speech patterns.The study analyzes data drawn from the Pitt Corpus,which contains 298 dementia files and 238 control files from the Dementia Bank database.Deep learning models and SVM classifiers were used to analyze the available audio samples in the dataset.Our methodology used two methods:a DL-ML model and a single DL model for the classification of diabetics and a single DL model.The deep learning model achieved an astronomic level of accuracy of 99.99%with an F1 score of 0.9998,Precision of 0.9997,and recall of 0.9998.The proposed DL-ML fusion model was equally impressive,with an accuracy of 99.99%,F1 score of 0.9995,Precision of 0.9998,and recall of 0.9997.Also,the study reveals how to apply deep learning and machine learning models for dementia detection from speech with high accuracy and low computational complexity.This research work,therefore,concludes by showing the possibility of using speech-based dementia detection as a possibly helpful early diagnosis mode.For even further enhanced model performance and better generalization,future studies may explore real-time applications and the inclusion of other components of speech.展开更多
Cyberbullying on social media poses significant psychological risks,yet most detection systems over-simplify the task by focusing on binary classification,ignoring nuanced categories like passive-aggressive remarks or...Cyberbullying on social media poses significant psychological risks,yet most detection systems over-simplify the task by focusing on binary classification,ignoring nuanced categories like passive-aggressive remarks or indirect slurs.To address this gap,we propose a hybrid framework combining Term Frequency-Inverse Document Frequency(TF-IDF),word-to-vector(Word2Vec),and Bidirectional Encoder Representations from Transformers(BERT)based models for multi-class cyberbullying detection.Our approach integrates TF-IDF for lexical specificity and Word2Vec for semantic relationships,fused with BERT’s contextual embeddings to capture syntactic and semantic complexities.We evaluate the framework on a publicly available dataset of 47,000 annotated social media posts across five cyberbullying categories:age,ethnicity,gender,religion,and indirect aggression.Among BERT variants tested,BERT Base Un-Cased achieved the highest performance with 93%accuracy(standard deviation across±1%5-fold cross-validation)and an average AUC of 0.96,outperforming standalone TF-IDF(78%)and Word2Vec(82%)models.Notably,it achieved near-perfect AUC scores(0.99)for age and ethnicity-based bullying.A comparative analysis with state-of-the-art benchmarks,including Generative Pre-trained Transformer 2(GPT-2)and Text-to-Text Transfer Transformer(T5)models highlights BERT’s superiority in handling ambiguous language.This work advances cyberbullying detection by demonstrating how hybrid feature extraction and transformer models improve multi-class classification,offering a scalable solution for moderating nuanced harmful content.展开更多
Accurate and efficient brain tumor segmentation is essential for early diagnosis,treatment planning,and clinical decision-making.However,the complex structure of brain anatomy and the heterogeneous nature of tumors pr...Accurate and efficient brain tumor segmentation is essential for early diagnosis,treatment planning,and clinical decision-making.However,the complex structure of brain anatomy and the heterogeneous nature of tumors present significant challenges for precise anomaly detection.While U-Net-based architectures have demonstrated strong performance in medical image segmentation,there remains room for improvement in feature extraction and localization accuracy.In this study,we propose a novel hybrid model designed to enhance 3D brain tumor segmentation.The architecture incorporates a 3D ResNet encoder known for mitigating the vanishing gradient problem and a 3D U-Net decoder.Additionally,to enhance the model’s generalization ability,Squeeze and Excitation attention mechanism is integrated.We introduce Gabor filter banks into the encoder to further strengthen the model’s ability to extract robust and transformation-invariant features from the complex and irregular shapes typical in medical imaging.This approach,which is not well explored in current U-Net-based segmentation frameworks,provides a unique advantage by enhancing texture-aware feature representation.Specifically,Gabor filters help extract distinctive low-level texture features,reducing the effects of texture interference and facilitating faster convergence during the early stages of training.Our model achieved Dice scores of 0.881,0.846,and 0.819 for Whole Tumor(WT),Tumor Core(TC),and Enhancing Tumor(ET),respectively,on the BraTS 2020 dataset.Cross-validation on the BraTS 2021 dataset further confirmed the model’s robustness,yielding Dice score values of 0.887 for WT,0.856 for TC,and 0.824 for ET.The proposed model outperforms several state-of-the-art existing models,particularly in accurately identifying small and complex tumor regions.Extensive evaluations suggest integrating advanced preprocessing with an attention-augmented hybrid architecture offers significant potential for reliable and clinically valuable brain tumor segmentation.展开更多
Currently,challenges such as small object size and occlusion lead to a lack of accuracy and robustness in small object detection.Since small objects occupy only a few pixels in an image,the extracted features are limi...Currently,challenges such as small object size and occlusion lead to a lack of accuracy and robustness in small object detection.Since small objects occupy only a few pixels in an image,the extracted features are limited,and mainstream downsampling convolution operations further exacerbate feature loss.Additionally,due to the occlusionprone nature of small objects and their higher sensitivity to localization deviations,conventional Intersection over Union(IoU)loss functions struggle to achieve stable convergence.To address these limitations,LR-Net is proposed for small object detection.Specifically,the proposed Lossless Feature Fusion(LFF)method transfers spatial features into the channel domain while leveraging a hybrid attentionmechanism to focus on critical features,mitigating feature loss caused by downsampling.Furthermore,RSIoU is proposed to enhance the convergence performance of IoU-based losses for small objects.RSIoU corrects the inherent convergence direction issues in SIoU and proposes a penalty term as a Dynamic Focusing Mechanism parameter,enabling it to dynamically emphasize the loss contribution of small object samples.Ultimately,RSIoU significantly improves the convergence performance of the loss function for small objects,particularly under occlusion scenarios.Experiments demonstrate that LR-Net achieves significant improvements across variousmetrics onmultiple datasets compared with YOLOv8n,achieving a 3.7% increase in mean Average Precision(AP)on the VisDrone2019 dataset,along with improvements of 3.3% on the AI-TOD dataset and 1.2% on the COCO dataset.展开更多
Sonic Hedgehog Medulloblastoma(SHH-MB)is one of the four primary molecular subgroups of Medulloblastoma.It is estimated to be responsible for nearly one-third of allMB cases.Using transcriptomic and DNA methylation pr...Sonic Hedgehog Medulloblastoma(SHH-MB)is one of the four primary molecular subgroups of Medulloblastoma.It is estimated to be responsible for nearly one-third of allMB cases.Using transcriptomic and DNA methylation profiling techniques,new developments in this field determined four molecular subtypes for SHH-MB.SHH-MB subtypes show distinct DNAmethylation patterns that allow their discrimination fromoverlapping subtypes and predict clinical outcomes.Class overlapping occurs when two or more classes share common features,making it difficult to distinguish them as separate.Using the DNA methylation dataset,a novel classification technique is presented to address the issue of overlapping SHH-MBsubtypes.Penalizedmultinomial regression(PMR),Tomek links(TL),and singular value decomposition(SVD)were all smoothly integrated into a single framework.SVD and group lasso improve computational efficiency,address the problem of high-dimensional datasets,and clarify class distinctions by removing redundant or irrelevant features that might lead to class overlap.As a method to eliminate the issues of decision boundary overlap and class imbalance in the classification task,TL enhances dataset balance and increases the clarity of decision boundaries through the elimination of overlapping samples.Using fivefold cross-validation,our proposed method(TL-SVDPMR)achieved a remarkable overall accuracy of almost 95%in the classification of SHH-MB molecular subtypes.The results demonstrate the strong performance of the proposed classification model among the various SHH-MB subtypes given a high average of the area under the curve(AUC)values.Additionally,the statistical significance test indicates that TL-SVDPMR is more accurate than both SVM and random forest algorithms in classifying the overlapping SHH-MB subtypes,highlighting its importance for precision medicine applications.Our findings emphasized the success of combining SVD,TL,and PMRtechniques to improve the classification performance for biomedical applications with many features and overlapping subtypes.展开更多
基金Author extends his appreciation to the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University for funding and supporting this work through Graduate Student Research Support Program.
文摘Improving the quality assurance (QA) processes and acquiring accreditation are top priorities for academic programs. The learning outcomes (LOs)assessment and continuous quality improvement represent core components ofthe quality assurance system (QAS). Current assessment methods suffer deficiencies related to accuracy and reliability, and they lack well-organized processes forcontinuous improvement planning. Moreover, the absence of automation, andintegration in QA processes forms a major obstacle towards developing efficientquality system. There is a pressing need to adopt security protocols that providerequired security services to safeguard the valuable information processed byQAS as well. This research proposes an effective methodology for LOs assessment and continuous improvement processes. The proposed approach ensuresmore accurate and reliable LOs assessment results and provides systematic wayfor utilizing those results in the continuous quality improvement. This systematicand well-specified QA processes were then utilized to model and implement automated and secure QAS that efficiently performs quality-related processes. Theproposed system adopts two security protocols that provide confidentiality, integrity, and authentication for quality data and reports. The security protocols avoidthe source repudiation, which is important in the quality reporting system. This isachieved through implementing powerful cryptographic algorithms. The QASenables efficient data collection and processing required for analysis and interpretation. It also prepares for the development of datasets that can be used in futureartificial intelligence (AI) researches to support decision making and improve thequality of academic programs. The proposed approach is implemented in a successful real case study for a computer science program. The current study servesscientific programs struggling to achieve academic accreditation, and gives rise tofully automating and integrating the QA processes and adopting modern AI andsecurity technologies to develop effective QAS.
基金funded by the Research,Development,and Innovation Authority(RDIA),Kingdom of Saudi Arabia,with grant number 13382-PSU-2023-PSNU-R-3-1-EIsupported by the Automated Systems and Computing Lab(ASCL),Prince Sultan University,Riyadh,Saudi Arabia.
文摘The rapid development of artificial intelligence(AI),machine learning(ML),and deep learning(DL)in recent years has transformed many sectors.A fundamental shift has occurred in approaches to solving complex problems and making decisions in many different fields.These advanced technologies have enabled significant breakthroughs in sectors including entertainment,finance,transportation,and healthcare.AI systems,which can analyze vast volumes of data,have significantly driven efficiency and innovation.With remarkable accuracy,patterns can be identified and predictions generated,improving decision-making processes and facilitating the development of more intelligent solutions.The increasing adoption of these technologies by organizations has expanded the potential for AI to change processes and improve results.
文摘Presently,precision agriculture processes like plant disease,crop yield prediction,species recognition,weed detection,and irrigation can be accom-plished by the use of computer vision(CV)approaches.Weed plays a vital role in influencing crop productivity.The wastage and pollution of farmland's natural atmosphere instigated by full coverage chemical herbicide spraying are increased.Since the proper identification of weeds from crops helps to reduce the usage of herbicide and improve productivity,this study presents a novel computer vision and deep learning based weed detection and classification(CVDL-WDC)model for precision agriculture.The proposed CVDL-WDC technique intends to prop-erly discriminate the plants as well as weeds.The proposed CVDL-WDC technique involves two processes namely multiscale Faster RCNN based object detection and optimal extreme learning machine(ELM)based weed classification.The parameters of the ELM model are optimally adjusted by the use of farmland fertility optimization(FFO)algorithm.A comprehensive simulation analysis of the CVDL-WDC technique against benchmark dataset reported the enhanced out-comes over its recent approaches interms of several measures.
基金Supported by the National Natural Science Foundation of China under Grant No 10475027, by SRF for R0CS, SEM under Grant No 44020460, and the Pujiang Project of Shanghai under Grant No 05PJ14036.
文摘Information transmission is studied in the cases of amplitude and frequency modulations where there is an impulsive jamming in the signal. By using the array approach of nonlinear elements, we find that for both the periodic and aperiodic modulations, the information transmission can be enhanced by adding independent external noise on every element of the array. The dependence of information transmission on the size of array and the impulsive interval of the jamming are also studied.
基金supported by the Chongqing Normal University Graduate Scientific Research Innovation Project (Grants YZH21014 and YZH21010).
文摘The learning status of learners directly affects the quality of learning.Compared with offline teachers,it is difficult for online teachers to capture the learning status of students in the whole class,and it is even more difficult to continue to pay attention to studentswhile teaching.Therefore,this paper proposes an online learning state analysis model based on a convolutional neural network and multi-dimensional information fusion.Specifically,a facial expression recognition model and an eye state recognition model are constructed to detect students’emotions and fatigue,respectively.By integrating the detected data with the homework test score data after online learning,an analysis model of students’online learning status is constructed.According to the PAD model,the learning state is expressed as three dimensions of students’understanding,engagement and interest,and then analyzed from multiple perspectives.Finally,the proposed model is applied to actual teaching,and procedural analysis of 5 different types of online classroom learners is carried out,and the validity of the model is verified by comparing with the results of the manual analysis.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Saud University for funding this work through research group no(RG-1441-531).
文摘Privacy preservation(PP)in Digital forensics(DF)is a conflicted and non-trivial issue.Existing solutions use the searchable encryption concept and,as a result,are not efficient and support only a keyword search.Moreover,the collected forensic data cannot be analyzed using existing well-known digital tools.This research paper first investigates the lawful requirements for PP in DF based on the organization for economic co-operation and development OECB)privacy guidelines.To have an efficient investigation process and meet the increased volume of data,the presented framework is designed based on the selective imaging concept and advanced encryption standard(AES).The proposed framework has two main modules,namely Selective Imaging Module(SIM)and Selective Analysis Module(SAM).The SIM and SAM modules are implemented based on advanced forensic format 4(AFF4)and SleuthKit open source forensics frameworks,respectively,and,accordingly,the proposed framework is evaluated in a forensically sound manner.The evaluation result is compared with other relevant works and,as a result,the proposed solution provides a privacy-preserving,efficient forensic imaging and analysis process while having also sufficient methods.Moreover,the AFF4 forensic image,produced by the SIM module,can be analyzed not only by SAM,but also by other well-known analysis tools available on the market.
基金This research was supported by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)support program(IITP-2023-2018-0-01426)supervised by the IITP(Institute for Information&Communications Technology Planning&Evaluation)This work has also been supported by PrincessNourah bint Abdulrahman UniversityResearchers Supporting Project Number(PNURSP2022R239),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.Alsothis work was partially supported by the Taif University Researchers Supporting Project Number(TURSP-2020/115),Taif University,Taif,Saudi Arabia.
文摘Identifying human actions and interactions finds its use in manyareas, such as security, surveillance, assisted living, patient monitoring, rehabilitation,sports, and e-learning. This wide range of applications has attractedmany researchers to this field. Inspired by the existing recognition systems,this paper proposes a new and efficient human-object interaction recognition(HOIR) model which is based on modeling human pose and scene featureinformation. There are different aspects involved in an interaction, includingthe humans, the objects, the various body parts of the human, and the backgroundscene. Themain objectives of this research include critically examiningthe importance of all these elements in determining the interaction, estimatinghuman pose through image foresting transform (IFT), and detecting the performedinteractions based on an optimizedmulti-feature vector. The proposedmethodology has six main phases. The first phase involves preprocessing theimages. During preprocessing stages, the videos are converted into imageframes. Then their contrast is adjusted, and noise is removed. In the secondphase, the human-object pair is detected and extracted from each image frame.The third phase involves the identification of key body parts of the detectedhumans using IFT. The fourth phase relates to three different kinds of featureextraction techniques. Then these features are combined and optimized duringthe fifth phase. The optimized vector is used to classify the interactions in thelast phase. TheMSRDaily Activity 3D dataset has been used to test this modeland to prove its efficiency. The proposed system obtains an average accuracyof 91.7% on this dataset.
文摘A news agency is an organization that gathers news reports and sells them to subscribing news organization, such as newspapers, magazines, radio and television broadcasters. A news agency may also be referred to as a wire service, newswire, or news service. The main purpose of this paper is to evaluate the security policies and analyze the content of five press agencies in gulf countries which are (Kuwait News Agency (KUNA), Emirates News Agency (WAM), Saudi Press Agency (SPA), Bahrain News Agency (BNA), and Oman News Agency (OMA)) by using a fuzzy VIKOR approach where linguistic variables are applied to solve the uncertainties and subjectivities in expert decision making. Fuzzy VIKOR approach is one of the best Multi-Criteria Decision Making (MCDM) techniques working in fuzzy environment. This study benefits security and content analysis experts know which press agency has the mandate and the competence to educate the public on news agencies. Besides, this paper contributes to Gulf agencies in helping them in their resolve to ensure the quality of content information and information security policies over the internet.
基金supported by the grant from the National Natural Science Foundation of China(No.72071019)grant from the Natural Science Foundation of Chongqing(No.cstc2021jcyj-msxmX0185).
文摘Bone age assessment(BAA)aims to determine whether a child’s growth and development are normal concerning their chronological age.To predict bone age more accurately based on radiographs,and for the left-hand X-ray images of different races model can have better adaptability,we propose a neural network in parallel with the quantitative features from the left-hand bone measurements for BAA.In this study,a lightweight feature extractor(LFE)is designed to obtain the featuremaps fromradiographs,and amodule called attention erasermodule(AEM)is proposed to capture the fine-grained features.Meanwhile,the dimensional information of the metacarpal parts in the radiographs is measured to enhance the model’s generalization capability across images fromdifferent races.Ourmodel is trained and validated on the RSNA,RHPE,and digital hand atlas datasets,which include images from various racial groups.The model achieves a mean absolute error(MAE)of 4.42 months on the RSNA dataset and 15.98 months on the RHPE dataset.Compared to ResNet50,InceptionV3,and several state-of-the-art methods,our proposed method shows statistically significant improvements(p<0.05),with a reduction in MAE by 0.2±0.02 years across different racial datasets.Furthermore,t-tests on the features also confirm the statistical significance of our approach(p<0.05).
文摘Terrain Aided Navigation(TAN)technology has become increasingly important due to its effectiveness in environments where Global Positioning System(GPS)is unavailable.In recent years,TAN systems have been extensively researched for both aerial and underwater navigation applications.However,many TAN systems that rely on recursive Unmanned Aerial Vehicle(UAV)position estimation methods,such as Extended Kalman Filters(EKF),often face challenges with divergence and instability,particularly in highly non-linear systems.To address these issues,this paper proposes and investigates a hybrid two-stage TAN positioning system for UAVs that utilizes Particle Filter.To enhance the system’s robustness against uncertainties caused by noise and to estimate additional system states,a Fuzzy Particle Filter(FPF)is employed in the first stage.This approach introduces a novel terrain composite feature that enables a fuzzy expert system to analyze terrain non-linearities and dynamically adjust the number of particles in real-time.This design allows the UAV to be efficiently localized in GPS-denied environments while also reducing the computational complexity of the particle filter in real-time applications.In the second stage,an Error State Kalman Filter(ESKF)is implemented to estimate the UAV’s altitude.The ESKF is chosen over the conventional EKF method because it is more suitable for non-linear systems.Simulation results demonstrate that the proposed fuzzy-based terrain composite method achieves high positional accuracy while reducing computational time and memory usage.
基金2024 Chongqing Normal University Graduate Research Innovation Project“Construction and Application of Information Technology Knowledge Map based on the Three-Layer Architecture”(CYS240395)。
文摘The concept of“STEM+”integrates art,humanistic literacy,and social values in the traditional STEM education concept,advocates cross-disciplinary integration,and aims to cultivate compound talents equipped to tackle future challenges.In 2022,the Ministry of Education issued the“Compulsory Education Information Technology Curriculum(2022 Edition),”emphasizing the core literacy of information science and technology and the integration of interdisciplinary disciplines,and encouraging the teaching mode suitable for discipline characteristics.The 6E teaching mode is a student-centered teaching strategy characterized by active exploration and cross-disciplinary integration.This article innovatively designed the“STEM+”6E teaching mode,which is applied to junior high school information technology teaching,which can better achieve core literacy teaching goals.
文摘The rapid integration of artificial intelligence(AI)into software development,driven by large language models(LLMs),is reshaping the role of programmers from traditional coders into strategic collaborators within Industry 4.0 ecosystems.This qualitative study employs a hermeneutic phenomenological approach to explore the lived experiences of Information Technology(IT)professionals as they navigate a dynamic technological landscape marked by intelligent automation,shifting professional identities,and emerging ethical concerns.Findings indicate that developers are actively adapting to AI-augmented environments by engaging in continuous upskilling,prompt engineering,interdisciplinary collaboration,and heightened ethical awareness.However,participants also voiced growing concerns about the reliability and security of AI-generated code,noting that these tools can introduce hidden vulnerabilities and reduce critical engagement due to automation bias.Many described instances of flawed logic,insecure patterns,or syntactically correct but contextually inappropriate suggestions,underscoring the need for rigorous human oversight.Additionally,the study reveals anxieties around job displacement and the gradual erosion of fundamental coding skills,particularly in environments where AI tools dominate routine development tasks.These findings highlight an urgent need for educational reforms,industry standards,and organizational policies that prioritize both technical robustness and the preservation of human expertise.As AI becomes increasingly embedded in software engineering workflows,this research offers timely insights into how developers and organizations can responsibly integrate intelligent systems to promote accountability,resilience,and innovation across the software development lifecycle.
基金supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2504).
文摘The rapid evolution of malware presents a critical cybersecurity challenge,rendering traditional signature-based detection methods ineffective against novel variants.This growing threat affects individuals,organizations,and governments,highlighting the urgent need for robust malware detection mechanisms.Conventional machine learning-based approaches rely on static and dynamicmalware analysis and often struggle to detect previously unseen threats due to their dependency on predefined signatures.Although machine learning algorithms(MLAs)offer promising detection capabilities,their reliance on extensive feature engineering limits real-time applicability.Deep learning techniques mitigate this issue by automating feature extraction but may introduce computational overhead,affecting deployment efficiency.This research evaluates classical MLAs and deep learningmodels to enhance malware detection performance across diverse datasets.The proposed approach integrates a novel text and imagebased detection framework,employing an optimized Support Vector Machine(SVM)for textual data analysis and EfficientNet-B0 for image-based malware classification.Experimental analysis,conducted across multiple train-test splits over varying timescales,demonstrates 99.97%accuracy on textual datasets using SVM and 96.7%accuracy on image-based datasets with EfficientNet-B0,significantly improving zero-day malware detection.Furthermore,a comparative analysis with existing competitive techniques,such as Random Forest,XGBoost,and CNN-based(Convolutional Neural Network)classifiers,highlights the superior performance of the proposed model in terms of accuracy,efficiency,and robustness.
基金funded by the Deanship of Scientific Research at Princess Nourah bint Abdulrahman University,through the Research Funding Program,Grant No.(FRP-1443-15).
文摘The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the continuously advancing level of sophistication.To resolve this problem,efficient and flexible malware detection tools are needed.This work examines the possibility of employing deep CNNs to detect Android malware by transforming network traffic into image data representations.Moreover,the dataset used in this study is the CIC-AndMal2017,which contains 20,000 instances of network traffic across five distinct malware categories:a.Trojan,b.Adware,c.Ransomware,d.Spyware,e.Worm.These network traffic features are then converted to image formats for deep learning,which is applied in a CNN framework,including the VGG16 pre-trained model.In addition,our approach yielded high performance,yielding an accuracy of 0.92,accuracy of 99.1%,precision of 98.2%,recall of 99.5%,and F1 score of 98.7%.Subsequent improvements to the classification model through changes within the VGG19 framework improved the classification rate to 99.25%.Through the results obtained,it is clear that CNNs are a very effective way to classify Android malware,providing greater accuracy than conventional techniques.The success of this approach also shows the applicability of deep learning in mobile security along with the direction for the future advancement of the real-time detection system and other deeper learning techniques to counter the increasing number of threats emerging in the future.
基金The author Dr.Arshiya S.Ansari extends the appreciation to the Deanship of Postgraduate Studies and Scientific Research at Majmaah University for funding this research work through the project number(R-2025-1538).
文摘Voice, motion, and mimicry are naturalistic control modalities that have replaced text or display-driven control in human-computer communication (HCC). Specifically, the vocals contain a lot of knowledge, revealing details about the speaker’s goals and desires, as well as their internal condition. Certain vocal characteristics reveal the speaker’s mood, intention, and motivation, while word study assists the speaker’s demand to be understood. Voice emotion recognition has become an essential component of modern HCC networks. Integrating findings from the various disciplines involved in identifying vocal emotions is also challenging. Many sound analysis techniques were developed in the past. Learning about the development of artificial intelligence (AI), and especially Deep Learning (DL) technology, research incorporating real data is becoming increasingly common these days. Thus, this research presents a novel selfish herd optimization-tuned long/short-term memory (SHO-LSTM) strategy to identify vocal emotions in human communication. The RAVDESS public dataset is used to train the suggested SHO-LSTM technique. Mel-frequency cepstral coefficient (MFCC) and wiener filter (WF) techniques are used, respectively, to remove noise and extract features from the data. LSTM and SHO are applied to the extracted data to optimize the LSTM network’s parameters for effective emotion recognition. Python Software was used to execute our proposed framework. In the finding assessment phase, Numerous metrics are used to evaluate the proposed model’s detection capability, Such as F1-score (95%), precision (95%), recall (96%), and accuracy (97%). The suggested approach is tested on a Python platform, and the SHO-LSTM’s outcomes are contrasted with those of other previously conducted research. Based on comparative assessments, our suggested approach outperforms the current approaches in vocal emotion recognition.
基金funded by the Deanship of Scientific Research at Princess Nourah bint Abdulrahman University,through the Research Groups Program Grant No.(RGP-1444-0057).
文摘Dementia is a neurological disorder that affects the brain and its functioning,and women experience its effects more than men do.Preventive care often requires non-invasive and rapid tests,yet conventional diagnostic techniques are time-consuming and invasive.One of the most effective ways to diagnose dementia is by analyzing a patient’s speech,which is cheap and does not require surgery.This research aims to determine the effectiveness of deep learning(DL)and machine learning(ML)structures in diagnosing dementia based on women’s speech patterns.The study analyzes data drawn from the Pitt Corpus,which contains 298 dementia files and 238 control files from the Dementia Bank database.Deep learning models and SVM classifiers were used to analyze the available audio samples in the dataset.Our methodology used two methods:a DL-ML model and a single DL model for the classification of diabetics and a single DL model.The deep learning model achieved an astronomic level of accuracy of 99.99%with an F1 score of 0.9998,Precision of 0.9997,and recall of 0.9998.The proposed DL-ML fusion model was equally impressive,with an accuracy of 99.99%,F1 score of 0.9995,Precision of 0.9998,and recall of 0.9997.Also,the study reveals how to apply deep learning and machine learning models for dementia detection from speech with high accuracy and low computational complexity.This research work,therefore,concludes by showing the possibility of using speech-based dementia detection as a possibly helpful early diagnosis mode.For even further enhanced model performance and better generalization,future studies may explore real-time applications and the inclusion of other components of speech.
基金funded by Scientific Research Deanship at University of Hail-Saudi Arabia through Project Number RG-23092.
文摘Cyberbullying on social media poses significant psychological risks,yet most detection systems over-simplify the task by focusing on binary classification,ignoring nuanced categories like passive-aggressive remarks or indirect slurs.To address this gap,we propose a hybrid framework combining Term Frequency-Inverse Document Frequency(TF-IDF),word-to-vector(Word2Vec),and Bidirectional Encoder Representations from Transformers(BERT)based models for multi-class cyberbullying detection.Our approach integrates TF-IDF for lexical specificity and Word2Vec for semantic relationships,fused with BERT’s contextual embeddings to capture syntactic and semantic complexities.We evaluate the framework on a publicly available dataset of 47,000 annotated social media posts across five cyberbullying categories:age,ethnicity,gender,religion,and indirect aggression.Among BERT variants tested,BERT Base Un-Cased achieved the highest performance with 93%accuracy(standard deviation across±1%5-fold cross-validation)and an average AUC of 0.96,outperforming standalone TF-IDF(78%)and Word2Vec(82%)models.Notably,it achieved near-perfect AUC scores(0.99)for age and ethnicity-based bullying.A comparative analysis with state-of-the-art benchmarks,including Generative Pre-trained Transformer 2(GPT-2)and Text-to-Text Transfer Transformer(T5)models highlights BERT’s superiority in handling ambiguous language.This work advances cyberbullying detection by demonstrating how hybrid feature extraction and transformer models improve multi-class classification,offering a scalable solution for moderating nuanced harmful content.
基金the National Science and Technology Council(NSTC)of the Republic of China,Taiwan,for financially supporting this research under Contract No.NSTC 112-2637-M-131-001.
文摘Accurate and efficient brain tumor segmentation is essential for early diagnosis,treatment planning,and clinical decision-making.However,the complex structure of brain anatomy and the heterogeneous nature of tumors present significant challenges for precise anomaly detection.While U-Net-based architectures have demonstrated strong performance in medical image segmentation,there remains room for improvement in feature extraction and localization accuracy.In this study,we propose a novel hybrid model designed to enhance 3D brain tumor segmentation.The architecture incorporates a 3D ResNet encoder known for mitigating the vanishing gradient problem and a 3D U-Net decoder.Additionally,to enhance the model’s generalization ability,Squeeze and Excitation attention mechanism is integrated.We introduce Gabor filter banks into the encoder to further strengthen the model’s ability to extract robust and transformation-invariant features from the complex and irregular shapes typical in medical imaging.This approach,which is not well explored in current U-Net-based segmentation frameworks,provides a unique advantage by enhancing texture-aware feature representation.Specifically,Gabor filters help extract distinctive low-level texture features,reducing the effects of texture interference and facilitating faster convergence during the early stages of training.Our model achieved Dice scores of 0.881,0.846,and 0.819 for Whole Tumor(WT),Tumor Core(TC),and Enhancing Tumor(ET),respectively,on the BraTS 2020 dataset.Cross-validation on the BraTS 2021 dataset further confirmed the model’s robustness,yielding Dice score values of 0.887 for WT,0.856 for TC,and 0.824 for ET.The proposed model outperforms several state-of-the-art existing models,particularly in accurately identifying small and complex tumor regions.Extensive evaluations suggest integrating advanced preprocessing with an attention-augmented hybrid architecture offers significant potential for reliable and clinically valuable brain tumor segmentation.
基金supported by Chongqing Municipal Commission of Housing and Urban-Rural Development(Grant No.CKZ2024-87)China Chongqing Municipal Science and Technology Bureau(Grant No.2024TIAD-CYKJCXX0121).
文摘Currently,challenges such as small object size and occlusion lead to a lack of accuracy and robustness in small object detection.Since small objects occupy only a few pixels in an image,the extracted features are limited,and mainstream downsampling convolution operations further exacerbate feature loss.Additionally,due to the occlusionprone nature of small objects and their higher sensitivity to localization deviations,conventional Intersection over Union(IoU)loss functions struggle to achieve stable convergence.To address these limitations,LR-Net is proposed for small object detection.Specifically,the proposed Lossless Feature Fusion(LFF)method transfers spatial features into the channel domain while leveraging a hybrid attentionmechanism to focus on critical features,mitigating feature loss caused by downsampling.Furthermore,RSIoU is proposed to enhance the convergence performance of IoU-based losses for small objects.RSIoU corrects the inherent convergence direction issues in SIoU and proposes a penalty term as a Dynamic Focusing Mechanism parameter,enabling it to dynamically emphasize the loss contribution of small object samples.Ultimately,RSIoU significantly improves the convergence performance of the loss function for small objects,particularly under occlusion scenarios.Experiments demonstrate that LR-Net achieves significant improvements across variousmetrics onmultiple datasets compared with YOLOv8n,achieving a 3.7% increase in mean Average Precision(AP)on the VisDrone2019 dataset,along with improvements of 3.3% on the AI-TOD dataset and 1.2% on the COCO dataset.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2024-02-01137).
文摘Sonic Hedgehog Medulloblastoma(SHH-MB)is one of the four primary molecular subgroups of Medulloblastoma.It is estimated to be responsible for nearly one-third of allMB cases.Using transcriptomic and DNA methylation profiling techniques,new developments in this field determined four molecular subtypes for SHH-MB.SHH-MB subtypes show distinct DNAmethylation patterns that allow their discrimination fromoverlapping subtypes and predict clinical outcomes.Class overlapping occurs when two or more classes share common features,making it difficult to distinguish them as separate.Using the DNA methylation dataset,a novel classification technique is presented to address the issue of overlapping SHH-MBsubtypes.Penalizedmultinomial regression(PMR),Tomek links(TL),and singular value decomposition(SVD)were all smoothly integrated into a single framework.SVD and group lasso improve computational efficiency,address the problem of high-dimensional datasets,and clarify class distinctions by removing redundant or irrelevant features that might lead to class overlap.As a method to eliminate the issues of decision boundary overlap and class imbalance in the classification task,TL enhances dataset balance and increases the clarity of decision boundaries through the elimination of overlapping samples.Using fivefold cross-validation,our proposed method(TL-SVDPMR)achieved a remarkable overall accuracy of almost 95%in the classification of SHH-MB molecular subtypes.The results demonstrate the strong performance of the proposed classification model among the various SHH-MB subtypes given a high average of the area under the curve(AUC)values.Additionally,the statistical significance test indicates that TL-SVDPMR is more accurate than both SVM and random forest algorithms in classifying the overlapping SHH-MB subtypes,highlighting its importance for precision medicine applications.Our findings emphasized the success of combining SVD,TL,and PMRtechniques to improve the classification performance for biomedical applications with many features and overlapping subtypes.
