Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using d...Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using deep learning algorithms further enhances performance;nevertheless,it is challenging due to the nature of small-scale and imbalanced PD datasets.This paper proposed a convolutional neural network-based deep support vector machine(CNN-DSVM)to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets.A customized kernel function reduces the impact of biased classification towards the majority class(healthy candidates in our consideration).An improved generative adversarial network(IGAN)was designed to generate additional training data to enhance the model’s performance.For performance evaluation,the proposed algorithm achieves a sensitivity of 97.6%and a specificity of 97.3%.The performance comparison is evaluated from five perspectives,including comparisons with different data generation algorithms,feature extraction techniques,kernel functions,and existing works.Results reveal the effectiveness of the IGAN algorithm,which improves the sensitivity and specificity by 4.05%–4.72%and 4.96%–5.86%,respectively;and the effectiveness of the CNN-DSVM algorithm,which improves the sensitivity by 1.24%–57.4%and specificity by 1.04%–163%and reduces biased detection towards the majority class.The ablation experiments confirm the effectiveness of individual components.Two future research directions have also been suggested.展开更多
Image captioning,a pivotal research area at the intersection of image understanding,artificial intelligence,and linguistics,aims to generate natural language descriptions for images.This paper proposes an efficient im...Image captioning,a pivotal research area at the intersection of image understanding,artificial intelligence,and linguistics,aims to generate natural language descriptions for images.This paper proposes an efficient image captioning model named Mob-IMWTC,which integrates improved wavelet convolution(IMWTC)with an enhanced MobileNet V3 architecture.The enhanced MobileNet V3 integrates a transformer encoder as its encoding module and a transformer decoder as its decoding module.This innovative neural network significantly reduces the memory space required and model training time,while maintaining a high level of accuracy in generating image descriptions.IMWTC facilitates large receptive fields without significantly increasing the number of parameters or computational overhead.The improvedMobileNet V3 model has its classifier removed,and simultaneously,it employs IMWTC layers to replace the original convolutional layers.This makes Mob-IMWTC exceptionally well-suited for deployment on lowresource devices.Experimental results,based on objective evaluation metrics such as BLEU,ROUGE,CIDEr,METEOR,and SPICE,demonstrate that Mob-IMWTC outperforms state-of-the-art models,including three CNN architectures(CNN-LSTM,CNN-Att-LSTM,CNN-Tran),two mainstream methods(LCM-Captioner,ClipCap),and our previous work(Mob-Tran).Subjective evaluations further validate the model’s superiority in terms of grammaticality,adequacy,logic,readability,and humanness.Mob-IMWTC offers a lightweight yet effective solution for image captioning,making it suitable for deployment on resource-constrained devices.展开更多
With network attack technology continuing to develop,traditional anomaly traffic detection methods that rely on feature engineering are increasingly insufficient in efficiency and accuracy.Graph Neural Network(GNN),a ...With network attack technology continuing to develop,traditional anomaly traffic detection methods that rely on feature engineering are increasingly insufficient in efficiency and accuracy.Graph Neural Network(GNN),a promising Deep Learning(DL)approach,has proven to be highly effective in identifying intricate patterns in graph⁃structured data and has already found wide applications in the field of network security.In this paper,we propose a hybrid Graph Convolutional Network(GCN)⁃GraphSAGE model for Anomaly Traffic Detection,namely HGS⁃ATD,which aims to improve the accuracy of anomaly traffic detection by leveraging edge feature learning to better capture the relationships between network entities.We validate the HGS⁃ATD model on four publicly available datasets,including NF⁃UNSW⁃NB15⁃v2.The experimental results show that the enhanced hybrid model is 5.71%to 10.25%higher than the baseline model in terms of accuracy,and the F1⁃score is 5.53%to 11.63%higher than the baseline model,proving that the model can effectively distinguish normal traffic from attack traffic and accurately classify various types of attacks.展开更多
Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression...Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices.展开更多
critical for guiding treatment and improving patient outcomes.Traditional molecular subtyping via immuno-histochemistry(IHC)test is invasive,time-consuming,and may not fully represent tumor heterogeneity.This study pr...critical for guiding treatment and improving patient outcomes.Traditional molecular subtyping via immuno-histochemistry(IHC)test is invasive,time-consuming,and may not fully represent tumor heterogeneity.This study proposes a non-invasive approach using digital mammography images and deep learning algorithm for classifying breast cancer molecular subtypes.Four pretrained models,including two Convolutional Neural Networks(MobileNet_V3_Large and VGG-16)and two Vision Transformers(ViT_B_16 and ViT_Base_Patch16_Clip_224)were fine-tuned to classify images into HER2-enriched,Luminal,Normal-like,and Triple Negative subtypes.Hyperparameter tuning,including learning rate adjustment and layer freezing strategies,was applied to optimize performance.Among the evaluated models,ViT_Base_Patch16_Clip_224 achieved the highest test accuracy(94.44%),with equally high precision,recall,and F1-score of 0.94,demonstrating excellent generalization.MobileNet_V3_Large achieved the same accuracy but showed less training stability.In contrast,VGG-16 recorded the lowest performance,indicating a limitation in its generalizability for this classification task.The study also highlighted the superior performance of the Vision Transformer models over CNNs,particularly due to their ability to capture global contextual features and the benefit of CLIP-based pretraining in ViT_Base_Patch16_Clip_224.To enhance clinical applicability,a graphical user interface(GUI)named“BCMS Dx”was developed for streamlined subtype prediction.Deep learning applied to mammography has proven effective for accurate and non-invasive molecular subtyping.The proposed Vision Transformer-based model and supporting GUI offer a promising direction for augmenting diagnostic workflows,minimizing the need for invasive procedures,and advancing personalized breast cancer management.展开更多
WiFi-based human activity recognition(HAR)provides a non-intrusive approach for ubiquitous monitoring;however,achieving both high accuracy and robustness simultaneously remains a significant challenge.This paper propo...WiFi-based human activity recognition(HAR)provides a non-intrusive approach for ubiquitous monitoring;however,achieving both high accuracy and robustness simultaneously remains a significant challenge.This paper proposes a Convolutional Neural Network with Enhanced Convolutional Block Attention Module(CNN-ECBAM)framework.The approach systematically converts raw Channel State Information(CSI)into pseudo-color images,effectively preserving essential signal characteristics for deep neural network processing.The core innovation is an Enhanced Convolutional Block Attention Module(ECBAM),tailored to CSI data characteristics,which integrates Efficient Channel Attention(ECA)and Multi-Scale Spatial Attention(MSSA).By employing learnable adaptive fusion weights,it achieves dynamic synergy between channel and spatial features,enabling the network to capture highly discriminative spatiotemporal patterns.The ECBAM module is integrated into a unified Convolutional Neural Network(CNN)to form the overall CNN-ECBAM model.Experimental results on the UT-HAR and NTU-Fi_HAR datasets demonstrate that CNN-ECBAM achieves competitive performance in recognition accuracy and outperforms mainstream baseline models.Specifically,it attains 99.20%accuracy on UT-HAR(surpassing ResNet-18 at 98.60%)and achieves 100%accuracy on NTU-Fi_HAR(exceeding GAF-CNN at 99.62%).These results validate the effectiveness of the proposed method for high-precision and reliable WiFi-based HAR.展开更多
The prediction of sea surface partial pressure of carbon dioxide(pCO_(2))in the South China Sea is crucial for understanding the region’s contribution to the global carbon budget and its interactions with climate cha...The prediction of sea surface partial pressure of carbon dioxide(pCO_(2))in the South China Sea is crucial for understanding the region’s contribution to the global carbon budget and its interactions with climate change.We applied the Spatiotemporal Convolutional Long Short-Term Memory(STConvLSTM)model,integrating key environmental factors including sea surface temperature(SST),sea surface salinity(SSS),and chlorophyll a(Chl a),to predict and analyze sea surface pCO_(2)in the South China Sea.The model demonstrated high accuracy in short-term predictions(1 month),with a mean absolute error(MAE)of 0.394,a root mean square error(RMSE)of 0.659,and a coefficient of determination(R^(2))of 0.998.For long-term predictions(12 months),the model maintained its predictive capability,with an MAE of 0.667,RMSE of 1.255,and R^(2)of 0.994.Feature importance analysis revealed that sea surface pCO_(2)and SST were the main drivers of the model’s predictions,whereas Chl a and SSS had relatively minor impacts.The model’s generalization ability was further validated in the northwest Pacific Ocean and tropical Pacific Ocean,where it successfully captured the spatiotemporal variation in pCO_(2)with small prediction errors.The ST-ConvLSTM model provides an efficient and accurate tool for forecasting and analyzing sea surface pCO_(2)in the South China Sea,offering new insights into global carbon cycling and climate change.This study demonstrates the potential of deep learning in marine science and provides a significant technical support for global changes and marine ecosystem research.展开更多
Handling missing data accurately is critical in clinical research, where data quality directly impacts decision-making and patient outcomes. While deep learning (DL) techniques for data imputation have gained attentio...Handling missing data accurately is critical in clinical research, where data quality directly impacts decision-making and patient outcomes. While deep learning (DL) techniques for data imputation have gained attention, challenges remain, especially when dealing with diverse data types. In this study, we introduce a novel data imputation method based on a modified convolutional neural network, specifically, a Deep Residual-Convolutional Neural Network (DRes-CNN) architecture designed to handle missing values across various datasets. Our approach demonstrates substantial improvements over existing imputation techniques by leveraging residual connections and optimized convolutional layers to capture complex data patterns. We evaluated the model on publicly available datasets, including Medical Information Mart for Intensive Care (MIMIC-III and MIMIC-IV), which contain critical care patient data, and the Beijing Multi-Site Air Quality dataset, which measures environmental air quality. The proposed DRes-CNN method achieved a root mean square error (RMSE) of 0.00006, highlighting its high accuracy and robustness. We also compared with Low Light-Convolutional Neural Network (LL-CNN) and U-Net methods, which had RMSE values of 0.00075 and 0.00073, respectively. This represented an improvement of approximately 92% over LL-CNN and 91% over U-Net. The results showed that this DRes-CNN-based imputation method outperforms current state-of-the-art models. These results established DRes-CNN as a reliable solution for addressing missing data.展开更多
This paper addresses the performance degradation issue in a fast radio burst search pipeline based on deep learning.This issue is caused by the class imbalance of the radio frequency interference samples in the traini...This paper addresses the performance degradation issue in a fast radio burst search pipeline based on deep learning.This issue is caused by the class imbalance of the radio frequency interference samples in the training dataset,and one solution is applied to improve the distribution of the training data by augmenting minority class samples using a deep convolutional generative adversarial network.Experi.mental results demonstrate that retraining the deep learning model with the newly generated dataset leads to a new fast radio burst classifier,which effectively reduces false positives caused by periodic wide-band impulsive radio frequency interference,thereby enhancing the performance of the search pipeline.展开更多
Gastrointestinal(GI)diseases,including gastric and colorectal cancers,signi-ficantly impact global health,necessitating accurate and efficient diagnostic me-thods.Endoscopic examination is the primary diagnostic tool;...Gastrointestinal(GI)diseases,including gastric and colorectal cancers,signi-ficantly impact global health,necessitating accurate and efficient diagnostic me-thods.Endoscopic examination is the primary diagnostic tool;however,its accu-racy is limited by operator dependency and interobserver variability.Advance-ments in deep learning,particularly convolutional neural networks(CNNs),show great potential for enhancing GI disease detection and classification.This review explores the application of CNNs in endoscopic imaging,focusing on polyp and tumor detection,disease classification,endoscopic ultrasound,and capsule endo-scopy analysis.We discuss the performance of CNN models with traditional dia-gnostic methods,highlighting their advantages in accuracy and real-time decision support.Despite promising results,challenges remain,including data availability,model interpretability,and clinical integration.Future directions include impro-ving model generalization,enhancing explainability,and conducting large-scale clinical trials.With continued advancements,CNN-powered artificial intelligence systems could revolutionize GI endoscopy by enhancing early disease detection,reducing diagnostic errors,and improving patient outcomes.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
BACKGROUND Artificial intelligence,such as convolutional neural networks(CNNs),has been used in the interpretation of images and the diagnosis of hepatocellular cancer(HCC)and liver masses.CNN,a machine-learning algor...BACKGROUND Artificial intelligence,such as convolutional neural networks(CNNs),has been used in the interpretation of images and the diagnosis of hepatocellular cancer(HCC)and liver masses.CNN,a machine-learning algorithm similar to deep learning,has demonstrated its capability to recognise specific features that can detect pathological lesions.AIM To assess the use of CNNs in examining HCC and liver masses images in the diagnosis of cancer and evaluating the accuracy level of CNNs and their performance.METHODS The databases PubMed,EMBASE,and the Web of Science and research books were systematically searched using related keywords.Studies analysing pathological anatomy,cellular,and radiological images on HCC or liver masses using CNNs were identified according to the study protocol to detect cancer,differentiating cancer from other lesions,or staging the lesion.The data were extracted as per a predefined extraction.The accuracy level and performance of the CNNs in detecting cancer or early stages of cancer were analysed.The primary outcomes of the study were analysing the type of cancer or liver mass and identifying the type of images that showed optimum accuracy in cancer detection.RESULTS A total of 11 studies that met the selection criteria and were consistent with the aims of the study were identified.The studies demonstrated the ability to differentiate liver masses or differentiate HCC from other lesions(n=6),HCC from cirrhosis or development of new tumours(n=3),and HCC nuclei grading or segmentation(n=2).The CNNs showed satisfactory levels of accuracy.The studies aimed at detecting lesions(n=4),classification(n=5),and segmentation(n=2).Several methods were used to assess the accuracy of CNN models used.CONCLUSION The role of CNNs in analysing images and as tools in early detection of HCC or liver masses has been demonstrated in these studies.While a few limitations have been identified in these studies,overall there was an optimal level of accuracy of the CNNs used in segmentation and classification of liver cancers images.展开更多
Liver tumors segmentation from computed tomography (CT) images is an essential task for diagnosis and treatments of liver cancer. However, it is difficult owing to the variability of appearances, fuzzy boundaries, het...Liver tumors segmentation from computed tomography (CT) images is an essential task for diagnosis and treatments of liver cancer. However, it is difficult owing to the variability of appearances, fuzzy boundaries, heterogeneous densities, shapes and sizes of lesions. In this paper, an automatic method based on convolutional neural networks (CNNs) is presented to segment lesions from CT images. The CNNs is one of deep learning models with some convolutional filters which can learn hierarchical features from data. We compared the CNNs model to popular machine learning algorithms: AdaBoost, Random Forests (RF), and support vector machine (SVM). These classifiers were trained by handcrafted features containing mean, variance, and contextual features. Experimental evaluation was performed on 30 portal phase enhanced CT images using leave-one-out cross validation. The average Dice Similarity Coefficient (DSC), precision, and recall achieved of 80.06% ± 1.63%, 82.67% ± 1.43%, and 84.34% ± 1.61%, respectively. The results show that the CNNs method has better performance than other methods and is promising in liver tumor segmentation.展开更多
Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly acc...Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly accomplish driving functions. Speaking of machine vision, deep learning techniques, and specifically convolutional neural networks, have been proven to be the state of the art technology in the field. As these networks typically involve millions of parameters and elements, designing an optimal architecture for deep learning structures is a difficult task which is globally under investigation by researchers. This study experimentally evaluates the impact of three major architectural properties of convolutional networks, including the number of layers, filters, and filter size on their performance. In this study, several models with different properties are developed,equally trained, and then applied to an autonomous car in a realistic simulation environment. A new ensemble approach is also proposed to calculate and update weights for the models regarding their mean squared error values. Based on design properties,performance results are reported and compared for further investigations. Surprisingly, the number of filters itself does not largely affect the performance efficiency. As a result, proper allocation of filters with different kernel sizes through the layers introduces a considerable improvement in the performance.Achievements of this study will provide the researchers with a clear clue and direction in designing optimal network architectures for deep learning purposes.展开更多
The development of precision agriculture demands high accuracy and efficiency of cultivated land information extraction. As a new means of monitoring the ground in recent years, unmanned aerial vehicle （UAV） low-hei...The development of precision agriculture demands high accuracy and efficiency of cultivated land information extraction. As a new means of monitoring the ground in recent years, unmanned aerial vehicle （UAV） low-height remote sensing technique, which is flexible, efficient with low cost and with high resolution, is widely applied to investing various resources. Based on this, a novel extraction method for cultivated land information based on Deep Convolutional Neural Network and Transfer Learning （DTCLE） was proposed. First, linear features （roads and ridges etc.） were excluded based on Deep Convolutional Neural Network （DCNN）. Next, feature extraction method learned from DCNN was used to cultivated land information extraction by introducing transfer learning mechanism. Last, cultivated land information extraction results were completed by the DTCLE and eCognifion for cultivated land information extraction （ECLE）. The location of the Pengzhou County and Guanghan County, Sichuan Province were selected for the experimental purpose. The experimental results showed that the overall precision for the experimental image 1, 2 and 3 （of extracting cultivated land） with the DTCLE method was 91.7%, 88.1% and 88.2% respectively, and the overall precision of ECLE is 9o.7%, 90.5% and 87.0%, respectively. Accuracy of DTCLE was equivalent to that of ECLE, and also outperformed ECLE in terms of integrity and continuity.展开更多
Nowadays,the amount of wed data is increasing at a rapid speed,which presents a serious challenge to the web monitoring.Text sentiment analysis,an important research topic in the area of natural language processing,is...Nowadays,the amount of wed data is increasing at a rapid speed,which presents a serious challenge to the web monitoring.Text sentiment analysis,an important research topic in the area of natural language processing,is a crucial task in the web monitoring area.The accuracy of traditional text sentiment analysis methods might be degraded in dealing with mass data.Deep learning is a hot research topic of the artificial intelligence in the recent years.By now,several research groups have studied the sentiment analysis of English texts using deep learning methods.In contrary,relatively few works have so far considered the Chinese text sentiment analysis toward this direction.In this paper,a method for analyzing the Chinese text sentiment is proposed based on the convolutional neural network(CNN)in deep learning in order to improve the analysis accuracy.The feature values of the CNN after the training process are nonuniformly distributed.In order to overcome this problem,a method for normalizing the feature values is proposed.Moreover,the dimensions of the text features are optimized through simulations.Finally,a method for updating the learning rate in the training process of the CNN is presented in order to achieve better performances.Experiment results on the typical datasets indicate that the accuracy of the proposed method can be improved compared with that of the traditional supervised machine learning methods,e.g.,the support vector machine method.展开更多
Compressive strength of concrete is a significant factor to assess building structure health and safety.Therefore,various methods have been developed to evaluate the compressive strength of concrete structures.However...Compressive strength of concrete is a significant factor to assess building structure health and safety.Therefore,various methods have been developed to evaluate the compressive strength of concrete structures.However,previous methods have several challenges in costly,time-consuming,and unsafety.To address these drawbacks,this paper proposed a digital vision based concrete compressive strength evaluating model using deep convolutional neural network(DCNN).The proposed model presented an alternative approach to evaluating the concrete strength and contributed to improving efficiency and accuracy.The model was developed with 4,000 digital images and 61,996 images extracted from video recordings collected from concrete samples.The experimental results indicated a root mean square error(RMSE)value of 3.56(MPa),demonstrating a strong feasibility that the proposed model can be utilized to predict the concrete strength with digital images of their surfaces and advantages to overcome the previous limitations.This experiment contributed to provide the basis that could be extended to future research with image analysis technique and artificial neural network in the diagnosis of concrete building structures.展开更多
Safety is one of the important topics in the field of civil aviation. Auxiliary Power Unit(APU) is one of important components in aircraft, which provides electrical power and compressed air for aircraft. The hazards ...Safety is one of the important topics in the field of civil aviation. Auxiliary Power Unit(APU) is one of important components in aircraft, which provides electrical power and compressed air for aircraft. The hazards in APU are prone to cause economic losses and even casualties. So,actively identifying the hazards in APU before an accident occurs is necessary. In this paper, a Hybrid Deep Neural Network(HDNN) based on multi-time window convolutional neural network-Bidirectional Long Short-Term Memory(CNN-Bi LSTM) neural network is proposed for active hazard identification of APU in civil aircraft. In order to identify the risks caused by different types of failures, the proposed HDNN simultaneously integrates three CNN-Bi LSTM basic models with different time window sizes in parallel by using a fully connected neural network. The CNN-Bi LSTM basic model can automatically extract features representing the system state from the input data and learn the time information of irregular trends in the time series data. Nine benchmark models are compared with the proposed HDNN. The comparison results show that the proposed HDNN has the highest identification accuracy. The HDNN has the most stable identification performance for data with imbalanced samples.展开更多
Automatic modulation classification(AMC)aims at identifying the modulation of the received signals,which is a significant approach to identifying the target in military and civil applications.In this paper,a novel dat...Automatic modulation classification(AMC)aims at identifying the modulation of the received signals,which is a significant approach to identifying the target in military and civil applications.In this paper,a novel data-driven framework named convolutional and transformer-based deep neural network(CTDNN)is proposed to improve the classification performance.CTDNN can be divided into four modules,i.e.,convolutional neural network(CNN)backbone,transition module,transformer module,and final classifier.In the CNN backbone,a wide and deep convolution structure is designed,which consists of 1×15 convolution kernels and intensive cross-layer connections instead of traditional 1×3 kernels and sequential connections.In the transition module,a 1×1 convolution layer is utilized to compress the channels of the previous multi-scale CNN features.In the transformer module,three self-attention layers are designed for extracting global features and generating the classification vector.In the classifier,the final decision is made based on the maximum a posterior probability.Extensive simulations are conducted,and the result shows that our proposed CTDNN can achieve superior classification performance than traditional deep models.展开更多
Image based individual dairy cattle recognition has gained much attention recently. In order to further improve the accuracy of individual dairy cattle recognition, an algorithm based on deep convolutional neural netw...Image based individual dairy cattle recognition has gained much attention recently. In order to further improve the accuracy of individual dairy cattle recognition, an algorithm based on deep convolutional neural network( DCNN) is proposed in this paper,which enables automatic feature extraction and classification that outperforms traditional hand craft features. Through making multigroup comparison experiments including different network layers,different sizes of convolution kernel and different feature dimensions in full connection layer,we demonstrate that the proposed method is suitable for dairy cattle classification. The experimental results show that the accuracy is significantly higher compared to two traditional image processing algorithms: scale invariant feature transform( SIFT) algorithm and bag of feature( BOF) model.展开更多
基金The work described in this paper was fully supported by a grant from Hong Kong Metropolitan University(RIF/2021/05).
文摘Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using deep learning algorithms further enhances performance;nevertheless,it is challenging due to the nature of small-scale and imbalanced PD datasets.This paper proposed a convolutional neural network-based deep support vector machine(CNN-DSVM)to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets.A customized kernel function reduces the impact of biased classification towards the majority class(healthy candidates in our consideration).An improved generative adversarial network(IGAN)was designed to generate additional training data to enhance the model’s performance.For performance evaluation,the proposed algorithm achieves a sensitivity of 97.6%and a specificity of 97.3%.The performance comparison is evaluated from five perspectives,including comparisons with different data generation algorithms,feature extraction techniques,kernel functions,and existing works.Results reveal the effectiveness of the IGAN algorithm,which improves the sensitivity and specificity by 4.05%–4.72%and 4.96%–5.86%,respectively;and the effectiveness of the CNN-DSVM algorithm,which improves the sensitivity by 1.24%–57.4%and specificity by 1.04%–163%and reduces biased detection towards the majority class.The ablation experiments confirm the effectiveness of individual components.Two future research directions have also been suggested.
基金funded by National Social Science Fund of China,grant number 23BYY197.
文摘Image captioning,a pivotal research area at the intersection of image understanding,artificial intelligence,and linguistics,aims to generate natural language descriptions for images.This paper proposes an efficient image captioning model named Mob-IMWTC,which integrates improved wavelet convolution(IMWTC)with an enhanced MobileNet V3 architecture.The enhanced MobileNet V3 integrates a transformer encoder as its encoding module and a transformer decoder as its decoding module.This innovative neural network significantly reduces the memory space required and model training time,while maintaining a high level of accuracy in generating image descriptions.IMWTC facilitates large receptive fields without significantly increasing the number of parameters or computational overhead.The improvedMobileNet V3 model has its classifier removed,and simultaneously,it employs IMWTC layers to replace the original convolutional layers.This makes Mob-IMWTC exceptionally well-suited for deployment on lowresource devices.Experimental results,based on objective evaluation metrics such as BLEU,ROUGE,CIDEr,METEOR,and SPICE,demonstrate that Mob-IMWTC outperforms state-of-the-art models,including three CNN architectures(CNN-LSTM,CNN-Att-LSTM,CNN-Tran),two mainstream methods(LCM-Captioner,ClipCap),and our previous work(Mob-Tran).Subjective evaluations further validate the model’s superiority in terms of grammaticality,adequacy,logic,readability,and humanness.Mob-IMWTC offers a lightweight yet effective solution for image captioning,making it suitable for deployment on resource-constrained devices.
基金National Natural Science Foundation of China(Grant No.62103434)National Science Fund for Distinguished Young Scholars(Grant No.62176263).
文摘With network attack technology continuing to develop,traditional anomaly traffic detection methods that rely on feature engineering are increasingly insufficient in efficiency and accuracy.Graph Neural Network(GNN),a promising Deep Learning(DL)approach,has proven to be highly effective in identifying intricate patterns in graph⁃structured data and has already found wide applications in the field of network security.In this paper,we propose a hybrid Graph Convolutional Network(GCN)⁃GraphSAGE model for Anomaly Traffic Detection,namely HGS⁃ATD,which aims to improve the accuracy of anomaly traffic detection by leveraging edge feature learning to better capture the relationships between network entities.We validate the HGS⁃ATD model on four publicly available datasets,including NF⁃UNSW⁃NB15⁃v2.The experimental results show that the enhanced hybrid model is 5.71%to 10.25%higher than the baseline model in terms of accuracy,and the F1⁃score is 5.53%to 11.63%higher than the baseline model,proving that the model can effectively distinguish normal traffic from attack traffic and accurately classify various types of attacks.
基金supported by the Science and Technology Innovation Key R&D Program of Chongqing(CSTB2025TIAD-STX0032)National Key Research and Development Program of China(2024YFF0908200)+1 种基金the Chongqing Technology Innovation and Application Development Special Key Project(CSTB2024TIAD-KPX0018)the Southwest University Graduate Student Research Innovation(SWUB24051)。
文摘Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices.
基金funded by the Ministry of Higher Education(MoHE)Malaysia through the Fundamental Research Grant Scheme—Early Career Researcher(FRGS-EC),grant number FRGSEC/1/2024/ICT02/UNIMAP/02/8.
文摘critical for guiding treatment and improving patient outcomes.Traditional molecular subtyping via immuno-histochemistry(IHC)test is invasive,time-consuming,and may not fully represent tumor heterogeneity.This study proposes a non-invasive approach using digital mammography images and deep learning algorithm for classifying breast cancer molecular subtypes.Four pretrained models,including two Convolutional Neural Networks(MobileNet_V3_Large and VGG-16)and two Vision Transformers(ViT_B_16 and ViT_Base_Patch16_Clip_224)were fine-tuned to classify images into HER2-enriched,Luminal,Normal-like,and Triple Negative subtypes.Hyperparameter tuning,including learning rate adjustment and layer freezing strategies,was applied to optimize performance.Among the evaluated models,ViT_Base_Patch16_Clip_224 achieved the highest test accuracy(94.44%),with equally high precision,recall,and F1-score of 0.94,demonstrating excellent generalization.MobileNet_V3_Large achieved the same accuracy but showed less training stability.In contrast,VGG-16 recorded the lowest performance,indicating a limitation in its generalizability for this classification task.The study also highlighted the superior performance of the Vision Transformer models over CNNs,particularly due to their ability to capture global contextual features and the benefit of CLIP-based pretraining in ViT_Base_Patch16_Clip_224.To enhance clinical applicability,a graphical user interface(GUI)named“BCMS Dx”was developed for streamlined subtype prediction.Deep learning applied to mammography has proven effective for accurate and non-invasive molecular subtyping.The proposed Vision Transformer-based model and supporting GUI offer a promising direction for augmenting diagnostic workflows,minimizing the need for invasive procedures,and advancing personalized breast cancer management.
基金Supported by Anhui Provincial Engineering Research Center for Sports and Health Information Monitoring Technology(KF2023012)。
文摘WiFi-based human activity recognition(HAR)provides a non-intrusive approach for ubiquitous monitoring;however,achieving both high accuracy and robustness simultaneously remains a significant challenge.This paper proposes a Convolutional Neural Network with Enhanced Convolutional Block Attention Module(CNN-ECBAM)framework.The approach systematically converts raw Channel State Information(CSI)into pseudo-color images,effectively preserving essential signal characteristics for deep neural network processing.The core innovation is an Enhanced Convolutional Block Attention Module(ECBAM),tailored to CSI data characteristics,which integrates Efficient Channel Attention(ECA)and Multi-Scale Spatial Attention(MSSA).By employing learnable adaptive fusion weights,it achieves dynamic synergy between channel and spatial features,enabling the network to capture highly discriminative spatiotemporal patterns.The ECBAM module is integrated into a unified Convolutional Neural Network(CNN)to form the overall CNN-ECBAM model.Experimental results on the UT-HAR and NTU-Fi_HAR datasets demonstrate that CNN-ECBAM achieves competitive performance in recognition accuracy and outperforms mainstream baseline models.Specifically,it attains 99.20%accuracy on UT-HAR(surpassing ResNet-18 at 98.60%)and achieves 100%accuracy on NTU-Fi_HAR(exceeding GAF-CNN at 99.62%).These results validate the effectiveness of the proposed method for high-precision and reliable WiFi-based HAR.
基金Supported by the National Key Research and Development Program of China(No.2023YFC3008202)the National Natural Science Foundation of China(No.42406019)the Scientific Research Fund of Zhejiang Provincial Education Department(No.Y202353066)。
文摘The prediction of sea surface partial pressure of carbon dioxide(pCO_(2))in the South China Sea is crucial for understanding the region’s contribution to the global carbon budget and its interactions with climate change.We applied the Spatiotemporal Convolutional Long Short-Term Memory(STConvLSTM)model,integrating key environmental factors including sea surface temperature(SST),sea surface salinity(SSS),and chlorophyll a(Chl a),to predict and analyze sea surface pCO_(2)in the South China Sea.The model demonstrated high accuracy in short-term predictions(1 month),with a mean absolute error(MAE)of 0.394,a root mean square error(RMSE)of 0.659,and a coefficient of determination(R^(2))of 0.998.For long-term predictions(12 months),the model maintained its predictive capability,with an MAE of 0.667,RMSE of 1.255,and R^(2)of 0.994.Feature importance analysis revealed that sea surface pCO_(2)and SST were the main drivers of the model’s predictions,whereas Chl a and SSS had relatively minor impacts.The model’s generalization ability was further validated in the northwest Pacific Ocean and tropical Pacific Ocean,where it successfully captured the spatiotemporal variation in pCO_(2)with small prediction errors.The ST-ConvLSTM model provides an efficient and accurate tool for forecasting and analyzing sea surface pCO_(2)in the South China Sea,offering new insights into global carbon cycling and climate change.This study demonstrates the potential of deep learning in marine science and provides a significant technical support for global changes and marine ecosystem research.
基金supported by the Intelligent System Research Group(ISysRG)supported by Universitas Sriwijaya funded by the Competitive Research 2024.
文摘Handling missing data accurately is critical in clinical research, where data quality directly impacts decision-making and patient outcomes. While deep learning (DL) techniques for data imputation have gained attention, challenges remain, especially when dealing with diverse data types. In this study, we introduce a novel data imputation method based on a modified convolutional neural network, specifically, a Deep Residual-Convolutional Neural Network (DRes-CNN) architecture designed to handle missing values across various datasets. Our approach demonstrates substantial improvements over existing imputation techniques by leveraging residual connections and optimized convolutional layers to capture complex data patterns. We evaluated the model on publicly available datasets, including Medical Information Mart for Intensive Care (MIMIC-III and MIMIC-IV), which contain critical care patient data, and the Beijing Multi-Site Air Quality dataset, which measures environmental air quality. The proposed DRes-CNN method achieved a root mean square error (RMSE) of 0.00006, highlighting its high accuracy and robustness. We also compared with Low Light-Convolutional Neural Network (LL-CNN) and U-Net methods, which had RMSE values of 0.00075 and 0.00073, respectively. This represented an improvement of approximately 92% over LL-CNN and 91% over U-Net. The results showed that this DRes-CNN-based imputation method outperforms current state-of-the-art models. These results established DRes-CNN as a reliable solution for addressing missing data.
基金supported by the Chinese Academy of Science"Light of West China"Program(2022-XBQNXZ-015)the National Natural Science Foundation of China(11903071)the Operation,Maintenance and Upgrading Fund for Astronomical Telescopes and Facility Instruments,budgeted from the Ministry of Finance of China and administered by the Chinese Academy of Sciences。
文摘This paper addresses the performance degradation issue in a fast radio burst search pipeline based on deep learning.This issue is caused by the class imbalance of the radio frequency interference samples in the training dataset,and one solution is applied to improve the distribution of the training data by augmenting minority class samples using a deep convolutional generative adversarial network.Experi.mental results demonstrate that retraining the deep learning model with the newly generated dataset leads to a new fast radio burst classifier,which effectively reduces false positives caused by periodic wide-band impulsive radio frequency interference,thereby enhancing the performance of the search pipeline.
基金Supported by Open Funds for Shaanxi Provincial Key Laboratory of Infection and Immune Diseases,No.2023-KFMS-1.
文摘Gastrointestinal(GI)diseases,including gastric and colorectal cancers,signi-ficantly impact global health,necessitating accurate and efficient diagnostic me-thods.Endoscopic examination is the primary diagnostic tool;however,its accu-racy is limited by operator dependency and interobserver variability.Advance-ments in deep learning,particularly convolutional neural networks(CNNs),show great potential for enhancing GI disease detection and classification.This review explores the application of CNNs in endoscopic imaging,focusing on polyp and tumor detection,disease classification,endoscopic ultrasound,and capsule endo-scopy analysis.We discuss the performance of CNN models with traditional dia-gnostic methods,highlighting their advantages in accuracy and real-time decision support.Despite promising results,challenges remain,including data availability,model interpretability,and clinical integration.Future directions include impro-ving model generalization,enhancing explainability,and conducting large-scale clinical trials.With continued advancements,CNN-powered artificial intelligence systems could revolutionize GI endoscopy by enhancing early disease detection,reducing diagnostic errors,and improving patient outcomes.
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Supported by the College of Medicine Research Centre,Deanship of Scientific Research,King Saud University,Riyadh,Saudi Arabia
文摘BACKGROUND Artificial intelligence,such as convolutional neural networks(CNNs),has been used in the interpretation of images and the diagnosis of hepatocellular cancer(HCC)and liver masses.CNN,a machine-learning algorithm similar to deep learning,has demonstrated its capability to recognise specific features that can detect pathological lesions.AIM To assess the use of CNNs in examining HCC and liver masses images in the diagnosis of cancer and evaluating the accuracy level of CNNs and their performance.METHODS The databases PubMed,EMBASE,and the Web of Science and research books were systematically searched using related keywords.Studies analysing pathological anatomy,cellular,and radiological images on HCC or liver masses using CNNs were identified according to the study protocol to detect cancer,differentiating cancer from other lesions,or staging the lesion.The data were extracted as per a predefined extraction.The accuracy level and performance of the CNNs in detecting cancer or early stages of cancer were analysed.The primary outcomes of the study were analysing the type of cancer or liver mass and identifying the type of images that showed optimum accuracy in cancer detection.RESULTS A total of 11 studies that met the selection criteria and were consistent with the aims of the study were identified.The studies demonstrated the ability to differentiate liver masses or differentiate HCC from other lesions(n=6),HCC from cirrhosis or development of new tumours(n=3),and HCC nuclei grading or segmentation(n=2).The CNNs showed satisfactory levels of accuracy.The studies aimed at detecting lesions(n=4),classification(n=5),and segmentation(n=2).Several methods were used to assess the accuracy of CNN models used.CONCLUSION The role of CNNs in analysing images and as tools in early detection of HCC or liver masses has been demonstrated in these studies.While a few limitations have been identified in these studies,overall there was an optimal level of accuracy of the CNNs used in segmentation and classification of liver cancers images.
文摘Liver tumors segmentation from computed tomography (CT) images is an essential task for diagnosis and treatments of liver cancer. However, it is difficult owing to the variability of appearances, fuzzy boundaries, heterogeneous densities, shapes and sizes of lesions. In this paper, an automatic method based on convolutional neural networks (CNNs) is presented to segment lesions from CT images. The CNNs is one of deep learning models with some convolutional filters which can learn hierarchical features from data. We compared the CNNs model to popular machine learning algorithms: AdaBoost, Random Forests (RF), and support vector machine (SVM). These classifiers were trained by handcrafted features containing mean, variance, and contextual features. Experimental evaluation was performed on 30 portal phase enhanced CT images using leave-one-out cross validation. The average Dice Similarity Coefficient (DSC), precision, and recall achieved of 80.06% ± 1.63%, 82.67% ± 1.43%, and 84.34% ± 1.61%, respectively. The results show that the CNNs method has better performance than other methods and is promising in liver tumor segmentation.
文摘Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly accomplish driving functions. Speaking of machine vision, deep learning techniques, and specifically convolutional neural networks, have been proven to be the state of the art technology in the field. As these networks typically involve millions of parameters and elements, designing an optimal architecture for deep learning structures is a difficult task which is globally under investigation by researchers. This study experimentally evaluates the impact of three major architectural properties of convolutional networks, including the number of layers, filters, and filter size on their performance. In this study, several models with different properties are developed,equally trained, and then applied to an autonomous car in a realistic simulation environment. A new ensemble approach is also proposed to calculate and update weights for the models regarding their mean squared error values. Based on design properties,performance results are reported and compared for further investigations. Surprisingly, the number of filters itself does not largely affect the performance efficiency. As a result, proper allocation of filters with different kernel sizes through the layers introduces a considerable improvement in the performance.Achievements of this study will provide the researchers with a clear clue and direction in designing optimal network architectures for deep learning purposes.
基金supported by the Fundamental Research Funds for the Central Universities of China(Grant No.2013SCU11006)the Key Laboratory of Digital Mapping and Land Information Application of National Administration of Surveying,Mapping and Geoinformation of China(Grant NO.DM2014SC02)the Key Laboratory of Geospecial Information Technology,Ministry of Land and Resources of China(Grant NO.KLGSIT201504)
文摘The development of precision agriculture demands high accuracy and efficiency of cultivated land information extraction. As a new means of monitoring the ground in recent years, unmanned aerial vehicle （UAV） low-height remote sensing technique, which is flexible, efficient with low cost and with high resolution, is widely applied to investing various resources. Based on this, a novel extraction method for cultivated land information based on Deep Convolutional Neural Network and Transfer Learning （DTCLE） was proposed. First, linear features （roads and ridges etc.） were excluded based on Deep Convolutional Neural Network （DCNN）. Next, feature extraction method learned from DCNN was used to cultivated land information extraction by introducing transfer learning mechanism. Last, cultivated land information extraction results were completed by the DTCLE and eCognifion for cultivated land information extraction （ECLE）. The location of the Pengzhou County and Guanghan County, Sichuan Province were selected for the experimental purpose. The experimental results showed that the overall precision for the experimental image 1, 2 and 3 （of extracting cultivated land） with the DTCLE method was 91.7%, 88.1% and 88.2% respectively, and the overall precision of ECLE is 9o.7%, 90.5% and 87.0%, respectively. Accuracy of DTCLE was equivalent to that of ECLE, and also outperformed ECLE in terms of integrity and continuity.
文摘Nowadays,the amount of wed data is increasing at a rapid speed,which presents a serious challenge to the web monitoring.Text sentiment analysis,an important research topic in the area of natural language processing,is a crucial task in the web monitoring area.The accuracy of traditional text sentiment analysis methods might be degraded in dealing with mass data.Deep learning is a hot research topic of the artificial intelligence in the recent years.By now,several research groups have studied the sentiment analysis of English texts using deep learning methods.In contrary,relatively few works have so far considered the Chinese text sentiment analysis toward this direction.In this paper,a method for analyzing the Chinese text sentiment is proposed based on the convolutional neural network(CNN)in deep learning in order to improve the analysis accuracy.The feature values of the CNN after the training process are nonuniformly distributed.In order to overcome this problem,a method for normalizing the feature values is proposed.Moreover,the dimensions of the text features are optimized through simulations.Finally,a method for updating the learning rate in the training process of the CNN is presented in order to achieve better performances.Experiment results on the typical datasets indicate that the accuracy of the proposed method can be improved compared with that of the traditional supervised machine learning methods,e.g.,the support vector machine method.
基金This work was supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(NRF-2018R1A2B6007333).
文摘Compressive strength of concrete is a significant factor to assess building structure health and safety.Therefore,various methods have been developed to evaluate the compressive strength of concrete structures.However,previous methods have several challenges in costly,time-consuming,and unsafety.To address these drawbacks,this paper proposed a digital vision based concrete compressive strength evaluating model using deep convolutional neural network(DCNN).The proposed model presented an alternative approach to evaluating the concrete strength and contributed to improving efficiency and accuracy.The model was developed with 4,000 digital images and 61,996 images extracted from video recordings collected from concrete samples.The experimental results indicated a root mean square error(RMSE)value of 3.56(MPa),demonstrating a strong feasibility that the proposed model can be utilized to predict the concrete strength with digital images of their surfaces and advantages to overcome the previous limitations.This experiment contributed to provide the basis that could be extended to future research with image analysis technique and artificial neural network in the diagnosis of concrete building structures.
基金co-supported by National Natural Science Foundation of China(No.U1933202)Natural Science Foundation of Civil Aviation University of China(No.U1733201)+1 种基金China Scholarship Council(CSC)(No.201906830043)Postgraduate Research&Practice Innovation Program of Jiangsu Province,China(Nos.KYCX18_0310 and KYCX18_0265)。
文摘Safety is one of the important topics in the field of civil aviation. Auxiliary Power Unit(APU) is one of important components in aircraft, which provides electrical power and compressed air for aircraft. The hazards in APU are prone to cause economic losses and even casualties. So,actively identifying the hazards in APU before an accident occurs is necessary. In this paper, a Hybrid Deep Neural Network(HDNN) based on multi-time window convolutional neural network-Bidirectional Long Short-Term Memory(CNN-Bi LSTM) neural network is proposed for active hazard identification of APU in civil aircraft. In order to identify the risks caused by different types of failures, the proposed HDNN simultaneously integrates three CNN-Bi LSTM basic models with different time window sizes in parallel by using a fully connected neural network. The CNN-Bi LSTM basic model can automatically extract features representing the system state from the input data and learn the time information of irregular trends in the time series data. Nine benchmark models are compared with the proposed HDNN. The comparison results show that the proposed HDNN has the highest identification accuracy. The HDNN has the most stable identification performance for data with imbalanced samples.
基金supported in part by the National Natural Science Foundation of China under Grant(62171045,62201090)in part by the National Key Research and Development Program of China under Grants(2020YFB1807602,2019YFB1804404).
文摘Automatic modulation classification(AMC)aims at identifying the modulation of the received signals,which is a significant approach to identifying the target in military and civil applications.In this paper,a novel data-driven framework named convolutional and transformer-based deep neural network(CTDNN)is proposed to improve the classification performance.CTDNN can be divided into four modules,i.e.,convolutional neural network(CNN)backbone,transition module,transformer module,and final classifier.In the CNN backbone,a wide and deep convolution structure is designed,which consists of 1×15 convolution kernels and intensive cross-layer connections instead of traditional 1×3 kernels and sequential connections.In the transition module,a 1×1 convolution layer is utilized to compress the channels of the previous multi-scale CNN features.In the transformer module,three self-attention layers are designed for extracting global features and generating the classification vector.In the classifier,the final decision is made based on the maximum a posterior probability.Extensive simulations are conducted,and the result shows that our proposed CTDNN can achieve superior classification performance than traditional deep models.
基金Science and Technology Support Plan Project of Tianjin Municipal Science and Technology Commission(No.15ZCZDNC00130)
文摘Image based individual dairy cattle recognition has gained much attention recently. In order to further improve the accuracy of individual dairy cattle recognition, an algorithm based on deep convolutional neural network( DCNN) is proposed in this paper,which enables automatic feature extraction and classification that outperforms traditional hand craft features. Through making multigroup comparison experiments including different network layers,different sizes of convolution kernel and different feature dimensions in full connection layer,we demonstrate that the proposed method is suitable for dairy cattle classification. The experimental results show that the accuracy is significantly higher compared to two traditional image processing algorithms: scale invariant feature transform( SIFT) algorithm and bag of feature( BOF) model.
