Recent advancements in autonomous vehicle technologies are transforming intelligent transportation systems.Artificial intelligence enables real-time sensing,decision-making,and control on embedded platforms with impro...Recent advancements in autonomous vehicle technologies are transforming intelligent transportation systems.Artificial intelligence enables real-time sensing,decision-making,and control on embedded platforms with improved efficiency.This study presents the design and implementation of an autonomous radio-controlled(RC)vehicle prototype capable of lane line detection,obstacle avoidance,and navigation through dynamic path planning.The system integrates image processing and ultrasonic sensing,utilizing Raspberry Pi for vision-based tasks and ArduinoNano for real-time control.Lane line detection is achieved through conventional image processing techniques,providing the basis for local path generation,while traffic sign classification employs a You Only Look Once(YOLO)model optimized with TensorFlow Lite to support navigation decisions.Images captured by the onboard camera are processed on the Raspberry Pi to extract lane geometry and calculate steering angles,enabling the vehicle to follow the planned path.In addition,ultrasonic sensors placed in three directions at the front of the vehicle detect obstacles and allow real-time path adjustment for safe navigation.Experimental results demonstrate stable performance under controlled conditions,highlighting the system’s potential for scalable autonomous driving applications.This work confirms that deep learning methods can be efficiently deployed on low-power embedded systems,offering a practical framework for navigation,path planning,and intelligent transportation research.展开更多
The modern world remains vulnerable to natural disasters,including floods,earthquakes,wildfires,and others.These events remain unpredictable and inevitable,and recovering quickly and effectively requires significant e...The modern world remains vulnerable to natural disasters,including floods,earthquakes,wildfires,and others.These events remain unpredictable and inevitable,and recovering quickly and effectively requires significant effort and expense.Monitoring is becoming more efficient thanks to technologies such as Unmanned Aerial Vehicles(UAVs),which can access hard-to-reach areas and provide real-time data.However,in disaster-affected areas,these monitoring systems may encounter many obstacles when communicating with servers or transmitting monitored data.This paper proposes an adaptive communication model to overcome the challenges faced in disaster-affected areas.A base station is responsible for collecting data(such as images and videos)captured by UAVs performing surveillance within its communication range.This station is typically a tower providing fixed cellular network service.However,in the absence of such a tower,a selected UAV may serve as the station,depending on the situation.If surveillance needs to be performed outside the coverage area,it can continue to communicate via nearby UAVs through cooperative communication.UAVs with internet support,known as the Internet of Flying Things(IoFT),will also be utilized to enhance communication capacity and efficiency.The proposed communication model is validated through experiments,showing superior data transmission performance and higher throughput.Analysis indicates it outperforms traditional systems,even in rural areas,with or without internet access.展开更多
Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)t...Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist.展开更多
The initial noise present in the depth images obtained with RGB-D sensors is a combination of hardware limitations in addition to the environmental factors,due to the limited capabilities of sensors,which also produce...The initial noise present in the depth images obtained with RGB-D sensors is a combination of hardware limitations in addition to the environmental factors,due to the limited capabilities of sensors,which also produce poor computer vision results.The common image denoising techniques tend to remove significant image details and also remove noise,provided they are based on space and frequency filtering.The updated framework presented in this paper is a novel denoising model that makes use of Boruta-driven feature selection using a Long Short-Term Memory Autoencoder(LSTMAE).The Boruta algorithm identifies the most useful depth features that are used to maximize the spatial structure integrity and reduce redundancy.An LSTMAE is then used to process these selected features and model depth pixel sequences to generate robust,noise-resistant representations.The system uses the encoder to encode the input data into a latent space that has been compressed before it is decoded to retrieve the clean image.Experiments on a benchmark data set show that the suggested technique attains a PSNR of 45 dB and an SSIM of 0.90,which is 10 dB higher than the performance of conventional convolutional autoencoders and 15 times higher than that of the wavelet-based models.Moreover,the feature selection step will decrease the input dimensionality by 40%,resulting in a 37.5%reduction in training time and a real-time inference rate of 200 FPS.Boruta-LSTMAE framework,therefore,offers a highly efficient and scalable system for depth image denoising,with a high potential to be applied to close-range 3D systems,such as robotic manipulation and gesture-based interfaces.展开更多
Generative Adversarial Networks(GANs)have become valuable tools in medical imaging,enabling realistic image synthesis for enhancement,augmentation,and restoration.However,their integration into clinical workflows rais...Generative Adversarial Networks(GANs)have become valuable tools in medical imaging,enabling realistic image synthesis for enhancement,augmentation,and restoration.However,their integration into clinical workflows raises concerns,particularly the risk of subtle distortions or hallucinations that may undermine diagnostic accuracy and weaken trust in AI-assisted decision-making.To address this challenge,we propose a hybrid deep learning framework designed to detect GAN-induced artifacts in medical images,thereby reinforcing the reliability of AI-driven diagnostics.The framework integrates low-level statistical descriptors,including high-frequency residuals and Gray-Level Co-occurrence Matrix(GLCM)texture features,with high-level semantic representations extracted from a pre-trained ResNet18.This dual-stream approach enables detection of both pixel-level anomalies and structural inconsistencies introduced by GAN-based manipulation.We validated the framework on a curated dataset of 10,000 medical images,evenly split between authentic and GAN-generated samples across four modalities:MRI,CT,X-ray,and fundus photography.To improve generalizability to real-world clinical settings,we incorporated domain adaptation strategies such as adversarial training and style transfer,reducing domain shift by 15%.Experimental results demonstrate robust performance,achieving 92.6%accuracy and an F1-score of 0.91 on synthetic test data,and maintaining strong performance on real-world GAN-modified images with 87.3%accuracy and an F1-score of 0.85.Additionally,the model attained an AUC of 0.96 and an average precision of 0.92,outperforming conventional GAN detection pipelines and baseline Convolutional Neural Network(CNN)architectures.These findings establish the proposed framework as an effective and reliable solution for detecting GAN-induced hallucinations in medical imaging,representing an important step toward building trustworthy and clinically deployable AI systems.展开更多
This paper studies the performance of Traffic Engineering (TE) signal protocols used for load balancing in Multi-Protocol Label Switching (MPLS) networks, namely;Constraint Based Routed Label Distribution Protocol LDP...This paper studies the performance of Traffic Engineering (TE) signal protocols used for load balancing in Multi-Protocol Label Switching (MPLS) networks, namely;Constraint Based Routed Label Distribution Protocol LDP (CR-LDP) and Resource Reservation Protocol (RSVP). Furthermore, the performance of an MPLS network uses these TE signal protocols is compared to that of a conventional Internet Protocol (IP) network. Different applications including voice, video, File Transfer Protocol (FTP) and Hyperlink Text Transfer Protocol (HTTP) are used for the performance evaluation. Simulation results show superior performance of the MPLS network with CR-LDP TE signal protocol in all tested applications.展开更多
We study the effect of strain on band structure and valley-dependent transport properties of graphene heterojunctions.It is found that valley-dependent separation of electrons can be achieved by utilizing strain and o...We study the effect of strain on band structure and valley-dependent transport properties of graphene heterojunctions.It is found that valley-dependent separation of electrons can be achieved by utilizing strain and on-site energies.In the presence of strain,the values of transmission can be effectively adjusted by changing the strengths of the strain,while the transport angle basically keeps unchanged.When an extra on-site energy is simultaneously applied to the central scattering region,not only are the electrons of valleys K and K'separated into two distinct transmission lobes in opposite transverse directions,but the transport angles of two valleys can be significantly changed.Therefore,one can realize an effective modulation of valley-dependent transport by changing the strength and stretch angle of the strain and on-site energies,which can be exploited for graphene-based valleytronics devices.展开更多
Because of increased need to tissue and organ transplantation, tissue engineering (TE) researches have significantly increased in recent years in Iran. The present study explored briefly the advances in the TE approac...Because of increased need to tissue and organ transplantation, tissue engineering (TE) researches have significantly increased in recent years in Iran. The present study explored briefly the advances in the TE approaches in Iran. Through comprehensive search, we explored main TE components researches include cell, scaffold, growth factor and bioreactor conducted in Iran. The field of TE and regenerative medicine in Iran dates back to the early part of the 1990 decade and the advent of stem cell researches. During past two decades, Iran was one of leader in stem cell research in Middle East. The next major step in TE was application and fabrication of scaffolds for TE in the early 2000s with focused on engineering bone and nerve tissue. Iranian researchers extensively used natural scaffolds in their studies and hybridized natural polymers and inorganic scaffolds. There are many universities and government research institutes are conducting active research on tissue-engineering technologies. Limitations to TE in Iran include property design and validation of bioreactors. In conclusion, in the last few years, fields of tissue engineering and regenerative medicine such as stem cell technology and scaffolds have progressed in Iran, but one of the biggest challenges for TE is bioreactors researches.展开更多
The concept of emissivity has been with the scientific and engineering world since Planck formulated his blackbody radiation law more than a century ago.Nevertheless,emissivity is an elusive concept even for ex⁃perts....The concept of emissivity has been with the scientific and engineering world since Planck formulated his blackbody radiation law more than a century ago.Nevertheless,emissivity is an elusive concept even for ex⁃perts.It is a vague and fuzzy concept for the wider community of engineers.The importance of remote sensing of temperature by measuring IR radiation has been recognized in a wide range of industrial,medical,and environ⁃mental uses.One of the major sources of errors in IR radiometry is the emissivity of the surface being measured.In real experiments,emissivity may be influenced by many factors:surface texture,spectral properties,oxida⁃tion,and aging of surfaces.While commercial blackbodies are prevalent,the much-needed grey bodies with a known emissivity,are unavailable.This study describes how to achieve a calibrated and stable emissivity with a blackbody,a perforated screen,and a reliable and linear novel IR thermal sensor,18 dubbed TMOS.The Digital TMOS is now a low-cost commercial product,it requires low power,and it has a small form factor.The method⁃ology is based on two-color measurements,with two different optical filters,with selected wavelengths conform⁃ing to the grey body definition of the use case under study.With a photochemically etched perforated screen,the effective emissivity of the screen is simply the hole density area of the surface area that emits according to the blackbody temperature radiation.The concept is illustrated with ray tracing simulations,which demonstrate the approach.Measured results are reported.展开更多
A hybrid control strategy integrating proportional derivative(PD)and the H-infinity control methodology is proposed for a serial two-link robotic manipulator with the goal of improving the tracking performance of the ...A hybrid control strategy integrating proportional derivative(PD)and the H-infinity control methodology is proposed for a serial two-link robotic manipulator with the goal of improving the tracking performance of the robot arm.The H-infinity controller has the ability to achieve a high performance and robustness in the presence of disturbances and uncertainties,while the PD controller is effective in stabilizing the manipulator.Simulation results using Matlab and Simulink show that the proposed hybrid controller,which integrates the advantages of both PD and H-infinity controllers,has the lowest rise time for the second link,the lowest settling time for the two links,the lowest peak time for both links,and the fastest decay of the error response.In addition,the hybrid control scheme also has the lowest mean square error value,with a 53.3%improvement over the H-infinity controller and a 91.8%improvement over the PD controller,indicating an improved trajectory tracking performance when compared with pure PD and pure H-infinity controllers,respectively.It was also found that the hybrid controller has the lowest integral absolute error,integral square error,integral time absolute error,and integral time square error for the second link,while the error values for the first link are satisfactory,showing a superior performance of the hybrid controller above the PD and H-infinity controllers,respectively.展开更多
This paper proposes a zero-shot based spatial recognition AI algorithm by fusing and developing multidimensional vision identification technology adapted to the situation in large indoor and underground spaces.With th...This paper proposes a zero-shot based spatial recognition AI algorithm by fusing and developing multidimensional vision identification technology adapted to the situation in large indoor and underground spaces.With the expansion of large shopping malls and underground urban spaces(UUS),there is an increasing need for new technologies that can quickly identify complex indoor structures and changes such as relocation,remodeling,and construction for the safety and management of citizens through the provision of the up-to-date indoor 3D site maps.The proposed algorithm utilizes data collected by an unmanned robot to create a 3D site map of the up-to-date indoor site and recognizes complex indoor spaces based on zero-shot learning.This research specifically addresses two major challenges:the difficulty of detecting walls and floors due to complex patterns and the difficulty of spatial perception due to unknown obstacles.The proposed algorithm addresses the limitations of the existing foundation model,detects floors and obstacles without expensive sensors,and improves the accuracy of spatial recognition by combining floor detection,vanishing point detection,and fusion obstacle detection algorithms.The experimental results show that the algorithm effectively detects the floor and obstacles in various indoor environments,with F1 scores of 0.96 and 0.93 in the floor detection and obstacle detection experiments,respectively.展开更多
This paper introduces a novel lightweight colour image encryption algorithm,specifically designed for resource-constrained environments such as Internet of Things(IoT)devices.As IoT systems become increasingly prevale...This paper introduces a novel lightweight colour image encryption algorithm,specifically designed for resource-constrained environments such as Internet of Things(IoT)devices.As IoT systems become increasingly prevalent,secure and efficient data transmission becomes crucial.The proposed algorithm addresses this need by offering a robust yet resource-efficient solution for image encryption.Traditional image encryption relies on confusion and diffusion steps.These stages are generally implemented linearly,but this work introduces a new RSP(Random Strip Peeling)algorithm for the confusion step,which disrupts linearity in the lightweight category by using two different sequences generated by the 1D Tent Map with varying initial conditions.The diffusion stage then employs an XOR matrix generated by the Logistic Map.Different evaluation metrics,such as entropy analysis,key sensitivity,statistical and differential attacks resistance,and robustness analysis demonstrate the proposed algorithm's lightweight,robust,and efficient.The proposed encryption scheme achieved average metric values of 99.6056 for NPCR,33.4397 for UACI,and 7.9914 for information entropy in the SIPI image dataset.It also exhibits a time complexity of O(2×M×N)for an image of size M×N.展开更多
The Internet of MedicalThings(IoMT)connects healthcare devices and sensors to the Internet,driving transformative advancements in healthcare delivery.However,expanding IoMT infrastructures face growing security threat...The Internet of MedicalThings(IoMT)connects healthcare devices and sensors to the Internet,driving transformative advancements in healthcare delivery.However,expanding IoMT infrastructures face growing security threats,necessitating robust IntrusionDetection Systems(IDS).Maintaining the confidentiality of patient data is critical in AI-driven healthcare systems,especially when securing interconnected medical devices.This paper introduces SNN-IoMT(Stacked Neural Network Ensemble for IoMT Security),an AI-driven IDS framework designed to secure dynamic IoMT environments.Leveraging a stacked deep learning architecture combining Multi-Layer Perceptron(MLP),Convolutional Neural Networks(CNN),and Long Short-Term Memory(LSTM),the model optimizes data management and integration while ensuring system scalability and interoperability.Trained on the WUSTL-EHMS-2020 and IoT-Healthcare-Security datasets,SNN-IoMT surpasses existing IDS frameworks in accuracy,precision,and detecting novel threats.By addressing the primary challenges in AI-driven healthcare systems,including privacy,reliability,and ethical data management,our approach exemplifies the importance of AI to enhance security and trust in IoMT-enabled healthcare.展开更多
In this paper, a bearing-based three-dimensional self-localization and distributed circumnavigation with connectivity preservation and collision avoidance are investigated for a group of quadrotor-type unmanned aerial...In this paper, a bearing-based three-dimensional self-localization and distributed circumnavigation with connectivity preservation and collision avoidance are investigated for a group of quadrotor-type unmanned aerial vehicles (UAVs). A leader–follower structure is adopted, wherein the leader moves with reference dynamics (a target). Different from the existing approaches that necessitate full knowledge of the time-varying reference trajectory, in this paper, it is assumed that only some vehicles (at least one) have access to the bearing relative to the target, and all other vehicles are equipped with sensors capable of measuring the bearings relative to neighboring vehicles. In this paper, a consensus estimator is proposed to estimate the global position for each vehicle using relative bearing measurements and an estimate of neighboring vehicles received from a direct communication network. Then, a continuous robust integral of the sign of the error (RISE) control approach is effectively integrated with the distributed vector field approach to ensure UAV formation orbiting around the moving target while avoiding obstacles and maintaining network links within available communication ranges. In contrast to the classical RISE control rule, a \(\tanh (\cdot )\) function is used instead of the \(\text {sgn}(\cdot )\) function to further decrease the high-gain feedback and to obtain a smoother control signal. Furthermore, by using the localized radial basis function (RBF) neural networks (NNs) in a cooperative way, deterministic learning theory is employed to accurately identify/learn model uncertainties resulting from the attitude dynamics. The convergence of the entire closed-loop system is illustrated using the Lyapunov theory and is shown to be uniformly ultimately bounded. Finally, numerical simulations show the effectiveness of the proposed approach.展开更多
This research investigates the influence of indoor and outdoor factors on photovoltaic(PV)power generation at Utrecht University to accurately predict PV system performance by identifying critical impact factors and i...This research investigates the influence of indoor and outdoor factors on photovoltaic(PV)power generation at Utrecht University to accurately predict PV system performance by identifying critical impact factors and improving renewable energy efficiency.To predict plant efficiency,nineteen variables are analyzed,consisting of nine indoor photovoltaic panel characteristics(Open Circuit Voltage(Voc),Short Circuit Current(Isc),Maximum Power(Pmpp),Maximum Voltage(Umpp),Maximum Current(Impp),Filling Factor(FF),Parallel Resistance(Rp),Series Resistance(Rs),Module Temperature)and ten environmental factors(Air Temperature,Air Humidity,Dew Point,Air Pressure,Irradiation,Irradiation Propagation,Wind Speed,Wind Speed Propagation,Wind Direction,Wind Direction Propagation).This study provides a new perspective not previously addressed in the literature.In this study,different machine learning methods such as Multilayer Perceptron(MLP),Multivariate Adaptive Regression Spline(MARS),Multiple Linear Regression(MLR),and Random Forest(RF)models are used to predict power values using data from installed PVpanels.Panel values obtained under real field conditions were used to train the models,and the results were compared.The Multilayer Perceptron(MLP)model was achieved with the highest classification accuracy of 0.990%.The machine learning models used for solar energy forecasting show high performance and produce results close to actual values.Models like Multi-Layer Perceptron(MLP)and Random Forest(RF)can be used in diverse locations based on load demand.展开更多
The proliferation of distributed and renewable energy resources introduces additional operational challenges to power distribution systems.Transactive energy management,which allows networked neighborhood communities ...The proliferation of distributed and renewable energy resources introduces additional operational challenges to power distribution systems.Transactive energy management,which allows networked neighborhood communities and houses to trade energy,is expected to be developed as an effective method for accommodating additional uncertainties and security mandates pertaining to distributed energy resources.This paper proposes and analyzes a two-layer transactive energy market in which houses in networked neighborhood community microgrids will trade energy in respective market layers.This paper studies the blockchain applications to satisfy socioeconomic and technological concerns of secure transactive energy management in a two-level power distribution system.The numerical results for practical networked microgrids located at IllinoisTech−Bronzeville in Chicago illustrate the validity of the proposed blockchain-based transactive energy management for devising a distributed,scalable,efficient,and cybersecured power grid operation.The conclusion of the paper summarizes the prospects for blockchain applications to transactive energy management in power distribution systems.展开更多
Existing Internet of Things(IoT)systems that rely on Amazon Web Services(AWS)often encounter inefficiencies in data retrieval and high operational costs,especially when using DynamoDB for large-scale sensor data.These...Existing Internet of Things(IoT)systems that rely on Amazon Web Services(AWS)often encounter inefficiencies in data retrieval and high operational costs,especially when using DynamoDB for large-scale sensor data.These limitations hinder the scalability and responsiveness of applications such as remote energy monitoring systems.This research focuses on designing and developing an Arduino-based IoT system aimed at optimizing data transmission costs by concentrating on these services.The proposed method employs AWS Lambda functions with Amazon Relational Database Service(RDS)to facilitate the transmission of data collected from temperature and humidity sensors to the RDS database.In contrast,the conventional method utilizes AmazonDynamoDB for storing the same sensor data.Data were collected from 01 April 2022,to 26 August 2022,in Tokyo,Japan,focusing on temperature and relative humiditywitha resolutionof oneminute.The efficiency of the twomethods—conventional andproposed—was assessed in terms of both time and cost metrics,with a particular focus on data retrieval.The conventional method exhibited linear time complexity,leading to longer data retrieval times as the dataset grew,mainly due to DynamoDB’s pagination requirements and the parsing of payload data during the reading process.In contrast,the proposed method significantly reduced retrieval times for larger datasets by parsing payload data before writing it to the RDS database.Cost analysis revealed a savings of$1.56 per month with the adoption of the proposed approach for a 20-gigabyte database.展开更多
Multispectral imaging,which simultaneously captures the spatial and spectral information of a scene,is widely used across diverse fields,including remote sensing,biomedical imaging,and agricultural monitoring.We intro...Multispectral imaging,which simultaneously captures the spatial and spectral information of a scene,is widely used across diverse fields,including remote sensing,biomedical imaging,and agricultural monitoring.We introduce a snapshot multispectral imaging approach employing a standard monochrome image sensor with no additional spectral filters or customized components.Our system leverages the inherent chromatic aberration of wavelength-dependent defocusing as a natural source of physical encoding of multispectral information;this encoded image information is rapidly decoded via a deep learning-based multispectral Fourier imager network(mFIN).We experimentally tested our method with six illumination bands and demonstrated an overall accuracy of 98.25%for predicting the illumination channels at the input and achieved a robust multispectral image reconstruction on various test objects.This deep learning-powered framework achieves high-quality multispectral image reconstruction using snapshot image acquisition with a monochrome image sensor and could be useful for applications in biomedicine,industrial quality control,and agriculture,among others.展开更多
Network Intrusion Detection System(NIDS)detection of minority class attacks is always a difficult task when dealing with attacks in complex network environments.To improve the detection capability of minority-class at...Network Intrusion Detection System(NIDS)detection of minority class attacks is always a difficult task when dealing with attacks in complex network environments.To improve the detection capability of minority-class attacks,this study proposes an intrusion detection method based on a two-layer structure.The first layer employs a CNN-BiLSTM model incorporating an attention mechanism to classify network traffic into normal traffic,majority class attacks,and merged minority class attacks.The second layer further segments the minority class attacks through Stacking ensemble learning.The datasets are selected from the generic network dataset CIC-IDS2017,NSL-KDD,and the industrial network dataset Mississippi Gas Pipeline dataset to enhance the generalization and practical applicability of the model.Experimental results show that the proposed model achieves an overall detection accuracy of 99%,99%,and 95%on the CIC-IDS2017,NSL-KDD,and industrial network datasets,respectively.It also significantly outperforms traditional methods in terms of detection accuracy and recall rate for minority class attacks.Compared with the single-layer deep learning model,the two-layer structure effectively reduces the false alarm rate while improving the minority-class attack detection performance.The research in this paper not only improves the adaptability of NIDS to complex network environments but also provides a new solution for minority-class attack detection in industrial network security.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
文摘Recent advancements in autonomous vehicle technologies are transforming intelligent transportation systems.Artificial intelligence enables real-time sensing,decision-making,and control on embedded platforms with improved efficiency.This study presents the design and implementation of an autonomous radio-controlled(RC)vehicle prototype capable of lane line detection,obstacle avoidance,and navigation through dynamic path planning.The system integrates image processing and ultrasonic sensing,utilizing Raspberry Pi for vision-based tasks and ArduinoNano for real-time control.Lane line detection is achieved through conventional image processing techniques,providing the basis for local path generation,while traffic sign classification employs a You Only Look Once(YOLO)model optimized with TensorFlow Lite to support navigation decisions.Images captured by the onboard camera are processed on the Raspberry Pi to extract lane geometry and calculate steering angles,enabling the vehicle to follow the planned path.In addition,ultrasonic sensors placed in three directions at the front of the vehicle detect obstacles and allow real-time path adjustment for safe navigation.Experimental results demonstrate stable performance under controlled conditions,highlighting the system’s potential for scalable autonomous driving applications.This work confirms that deep learning methods can be efficiently deployed on low-power embedded systems,offering a practical framework for navigation,path planning,and intelligent transportation research.
文摘The modern world remains vulnerable to natural disasters,including floods,earthquakes,wildfires,and others.These events remain unpredictable and inevitable,and recovering quickly and effectively requires significant effort and expense.Monitoring is becoming more efficient thanks to technologies such as Unmanned Aerial Vehicles(UAVs),which can access hard-to-reach areas and provide real-time data.However,in disaster-affected areas,these monitoring systems may encounter many obstacles when communicating with servers or transmitting monitored data.This paper proposes an adaptive communication model to overcome the challenges faced in disaster-affected areas.A base station is responsible for collecting data(such as images and videos)captured by UAVs performing surveillance within its communication range.This station is typically a tower providing fixed cellular network service.However,in the absence of such a tower,a selected UAV may serve as the station,depending on the situation.If surveillance needs to be performed outside the coverage area,it can continue to communicate via nearby UAVs through cooperative communication.UAVs with internet support,known as the Internet of Flying Things(IoFT),will also be utilized to enhance communication capacity and efficiency.The proposed communication model is validated through experiments,showing superior data transmission performance and higher throughput.Analysis indicates it outperforms traditional systems,even in rural areas,with or without internet access.
文摘Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist.
文摘The initial noise present in the depth images obtained with RGB-D sensors is a combination of hardware limitations in addition to the environmental factors,due to the limited capabilities of sensors,which also produce poor computer vision results.The common image denoising techniques tend to remove significant image details and also remove noise,provided they are based on space and frequency filtering.The updated framework presented in this paper is a novel denoising model that makes use of Boruta-driven feature selection using a Long Short-Term Memory Autoencoder(LSTMAE).The Boruta algorithm identifies the most useful depth features that are used to maximize the spatial structure integrity and reduce redundancy.An LSTMAE is then used to process these selected features and model depth pixel sequences to generate robust,noise-resistant representations.The system uses the encoder to encode the input data into a latent space that has been compressed before it is decoded to retrieve the clean image.Experiments on a benchmark data set show that the suggested technique attains a PSNR of 45 dB and an SSIM of 0.90,which is 10 dB higher than the performance of conventional convolutional autoencoders and 15 times higher than that of the wavelet-based models.Moreover,the feature selection step will decrease the input dimensionality by 40%,resulting in a 37.5%reduction in training time and a real-time inference rate of 200 FPS.Boruta-LSTMAE framework,therefore,offers a highly efficient and scalable system for depth image denoising,with a high potential to be applied to close-range 3D systems,such as robotic manipulation and gesture-based interfaces.
基金supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2601).
文摘Generative Adversarial Networks(GANs)have become valuable tools in medical imaging,enabling realistic image synthesis for enhancement,augmentation,and restoration.However,their integration into clinical workflows raises concerns,particularly the risk of subtle distortions or hallucinations that may undermine diagnostic accuracy and weaken trust in AI-assisted decision-making.To address this challenge,we propose a hybrid deep learning framework designed to detect GAN-induced artifacts in medical images,thereby reinforcing the reliability of AI-driven diagnostics.The framework integrates low-level statistical descriptors,including high-frequency residuals and Gray-Level Co-occurrence Matrix(GLCM)texture features,with high-level semantic representations extracted from a pre-trained ResNet18.This dual-stream approach enables detection of both pixel-level anomalies and structural inconsistencies introduced by GAN-based manipulation.We validated the framework on a curated dataset of 10,000 medical images,evenly split between authentic and GAN-generated samples across four modalities:MRI,CT,X-ray,and fundus photography.To improve generalizability to real-world clinical settings,we incorporated domain adaptation strategies such as adversarial training and style transfer,reducing domain shift by 15%.Experimental results demonstrate robust performance,achieving 92.6%accuracy and an F1-score of 0.91 on synthetic test data,and maintaining strong performance on real-world GAN-modified images with 87.3%accuracy and an F1-score of 0.85.Additionally,the model attained an AUC of 0.96 and an average precision of 0.92,outperforming conventional GAN detection pipelines and baseline Convolutional Neural Network(CNN)architectures.These findings establish the proposed framework as an effective and reliable solution for detecting GAN-induced hallucinations in medical imaging,representing an important step toward building trustworthy and clinically deployable AI systems.
文摘This paper studies the performance of Traffic Engineering (TE) signal protocols used for load balancing in Multi-Protocol Label Switching (MPLS) networks, namely;Constraint Based Routed Label Distribution Protocol LDP (CR-LDP) and Resource Reservation Protocol (RSVP). Furthermore, the performance of an MPLS network uses these TE signal protocols is compared to that of a conventional Internet Protocol (IP) network. Different applications including voice, video, File Transfer Protocol (FTP) and Hyperlink Text Transfer Protocol (HTTP) are used for the performance evaluation. Simulation results show superior performance of the MPLS network with CR-LDP TE signal protocol in all tested applications.
基金National Natural Science Foundation of China(Grant No.11574067)。
文摘We study the effect of strain on band structure and valley-dependent transport properties of graphene heterojunctions.It is found that valley-dependent separation of electrons can be achieved by utilizing strain and on-site energies.In the presence of strain,the values of transmission can be effectively adjusted by changing the strengths of the strain,while the transport angle basically keeps unchanged.When an extra on-site energy is simultaneously applied to the central scattering region,not only are the electrons of valleys K and K'separated into two distinct transmission lobes in opposite transverse directions,but the transport angles of two valleys can be significantly changed.Therefore,one can realize an effective modulation of valley-dependent transport by changing the strength and stretch angle of the strain and on-site energies,which can be exploited for graphene-based valleytronics devices.
文摘Because of increased need to tissue and organ transplantation, tissue engineering (TE) researches have significantly increased in recent years in Iran. The present study explored briefly the advances in the TE approaches in Iran. Through comprehensive search, we explored main TE components researches include cell, scaffold, growth factor and bioreactor conducted in Iran. The field of TE and regenerative medicine in Iran dates back to the early part of the 1990 decade and the advent of stem cell researches. During past two decades, Iran was one of leader in stem cell research in Middle East. The next major step in TE was application and fabrication of scaffolds for TE in the early 2000s with focused on engineering bone and nerve tissue. Iranian researchers extensively used natural scaffolds in their studies and hybridized natural polymers and inorganic scaffolds. There are many universities and government research institutes are conducting active research on tissue-engineering technologies. Limitations to TE in Iran include property design and validation of bioreactors. In conclusion, in the last few years, fields of tissue engineering and regenerative medicine such as stem cell technology and scaffolds have progressed in Iran, but one of the biggest challenges for TE is bioreactors researches.
文摘The concept of emissivity has been with the scientific and engineering world since Planck formulated his blackbody radiation law more than a century ago.Nevertheless,emissivity is an elusive concept even for ex⁃perts.It is a vague and fuzzy concept for the wider community of engineers.The importance of remote sensing of temperature by measuring IR radiation has been recognized in a wide range of industrial,medical,and environ⁃mental uses.One of the major sources of errors in IR radiometry is the emissivity of the surface being measured.In real experiments,emissivity may be influenced by many factors:surface texture,spectral properties,oxida⁃tion,and aging of surfaces.While commercial blackbodies are prevalent,the much-needed grey bodies with a known emissivity,are unavailable.This study describes how to achieve a calibrated and stable emissivity with a blackbody,a perforated screen,and a reliable and linear novel IR thermal sensor,18 dubbed TMOS.The Digital TMOS is now a low-cost commercial product,it requires low power,and it has a small form factor.The method⁃ology is based on two-color measurements,with two different optical filters,with selected wavelengths conform⁃ing to the grey body definition of the use case under study.With a photochemically etched perforated screen,the effective emissivity of the screen is simply the hole density area of the surface area that emits according to the blackbody temperature radiation.The concept is illustrated with ray tracing simulations,which demonstrate the approach.Measured results are reported.
文摘A hybrid control strategy integrating proportional derivative(PD)and the H-infinity control methodology is proposed for a serial two-link robotic manipulator with the goal of improving the tracking performance of the robot arm.The H-infinity controller has the ability to achieve a high performance and robustness in the presence of disturbances and uncertainties,while the PD controller is effective in stabilizing the manipulator.Simulation results using Matlab and Simulink show that the proposed hybrid controller,which integrates the advantages of both PD and H-infinity controllers,has the lowest rise time for the second link,the lowest settling time for the two links,the lowest peak time for both links,and the fastest decay of the error response.In addition,the hybrid control scheme also has the lowest mean square error value,with a 53.3%improvement over the H-infinity controller and a 91.8%improvement over the PD controller,indicating an improved trajectory tracking performance when compared with pure PD and pure H-infinity controllers,respectively.It was also found that the hybrid controller has the lowest integral absolute error,integral square error,integral time absolute error,and integral time square error for the second link,while the error values for the first link are satisfactory,showing a superior performance of the hybrid controller above the PD and H-infinity controllers,respectively.
基金supported by Kyonggi University Research Grant 2024.
文摘This paper proposes a zero-shot based spatial recognition AI algorithm by fusing and developing multidimensional vision identification technology adapted to the situation in large indoor and underground spaces.With the expansion of large shopping malls and underground urban spaces(UUS),there is an increasing need for new technologies that can quickly identify complex indoor structures and changes such as relocation,remodeling,and construction for the safety and management of citizens through the provision of the up-to-date indoor 3D site maps.The proposed algorithm utilizes data collected by an unmanned robot to create a 3D site map of the up-to-date indoor site and recognizes complex indoor spaces based on zero-shot learning.This research specifically addresses two major challenges:the difficulty of detecting walls and floors due to complex patterns and the difficulty of spatial perception due to unknown obstacles.The proposed algorithm addresses the limitations of the existing foundation model,detects floors and obstacles without expensive sensors,and improves the accuracy of spatial recognition by combining floor detection,vanishing point detection,and fusion obstacle detection algorithms.The experimental results show that the algorithm effectively detects the floor and obstacles in various indoor environments,with F1 scores of 0.96 and 0.93 in the floor detection and obstacle detection experiments,respectively.
基金Türkiye Bilimsel ve Teknolojik Arastırma Kurumu。
文摘This paper introduces a novel lightweight colour image encryption algorithm,specifically designed for resource-constrained environments such as Internet of Things(IoT)devices.As IoT systems become increasingly prevalent,secure and efficient data transmission becomes crucial.The proposed algorithm addresses this need by offering a robust yet resource-efficient solution for image encryption.Traditional image encryption relies on confusion and diffusion steps.These stages are generally implemented linearly,but this work introduces a new RSP(Random Strip Peeling)algorithm for the confusion step,which disrupts linearity in the lightweight category by using two different sequences generated by the 1D Tent Map with varying initial conditions.The diffusion stage then employs an XOR matrix generated by the Logistic Map.Different evaluation metrics,such as entropy analysis,key sensitivity,statistical and differential attacks resistance,and robustness analysis demonstrate the proposed algorithm's lightweight,robust,and efficient.The proposed encryption scheme achieved average metric values of 99.6056 for NPCR,33.4397 for UACI,and 7.9914 for information entropy in the SIPI image dataset.It also exhibits a time complexity of O(2×M×N)for an image of size M×N.
文摘The Internet of MedicalThings(IoMT)connects healthcare devices and sensors to the Internet,driving transformative advancements in healthcare delivery.However,expanding IoMT infrastructures face growing security threats,necessitating robust IntrusionDetection Systems(IDS).Maintaining the confidentiality of patient data is critical in AI-driven healthcare systems,especially when securing interconnected medical devices.This paper introduces SNN-IoMT(Stacked Neural Network Ensemble for IoMT Security),an AI-driven IDS framework designed to secure dynamic IoMT environments.Leveraging a stacked deep learning architecture combining Multi-Layer Perceptron(MLP),Convolutional Neural Networks(CNN),and Long Short-Term Memory(LSTM),the model optimizes data management and integration while ensuring system scalability and interoperability.Trained on the WUSTL-EHMS-2020 and IoT-Healthcare-Security datasets,SNN-IoMT surpasses existing IDS frameworks in accuracy,precision,and detecting novel threats.By addressing the primary challenges in AI-driven healthcare systems,including privacy,reliability,and ethical data management,our approach exemplifies the importance of AI to enhance security and trust in IoMT-enabled healthcare.
文摘In this paper, a bearing-based three-dimensional self-localization and distributed circumnavigation with connectivity preservation and collision avoidance are investigated for a group of quadrotor-type unmanned aerial vehicles (UAVs). A leader–follower structure is adopted, wherein the leader moves with reference dynamics (a target). Different from the existing approaches that necessitate full knowledge of the time-varying reference trajectory, in this paper, it is assumed that only some vehicles (at least one) have access to the bearing relative to the target, and all other vehicles are equipped with sensors capable of measuring the bearings relative to neighboring vehicles. In this paper, a consensus estimator is proposed to estimate the global position for each vehicle using relative bearing measurements and an estimate of neighboring vehicles received from a direct communication network. Then, a continuous robust integral of the sign of the error (RISE) control approach is effectively integrated with the distributed vector field approach to ensure UAV formation orbiting around the moving target while avoiding obstacles and maintaining network links within available communication ranges. In contrast to the classical RISE control rule, a \(\tanh (\cdot )\) function is used instead of the \(\text {sgn}(\cdot )\) function to further decrease the high-gain feedback and to obtain a smoother control signal. Furthermore, by using the localized radial basis function (RBF) neural networks (NNs) in a cooperative way, deterministic learning theory is employed to accurately identify/learn model uncertainties resulting from the attitude dynamics. The convergence of the entire closed-loop system is illustrated using the Lyapunov theory and is shown to be uniformly ultimately bounded. Finally, numerical simulations show the effectiveness of the proposed approach.
文摘This research investigates the influence of indoor and outdoor factors on photovoltaic(PV)power generation at Utrecht University to accurately predict PV system performance by identifying critical impact factors and improving renewable energy efficiency.To predict plant efficiency,nineteen variables are analyzed,consisting of nine indoor photovoltaic panel characteristics(Open Circuit Voltage(Voc),Short Circuit Current(Isc),Maximum Power(Pmpp),Maximum Voltage(Umpp),Maximum Current(Impp),Filling Factor(FF),Parallel Resistance(Rp),Series Resistance(Rs),Module Temperature)and ten environmental factors(Air Temperature,Air Humidity,Dew Point,Air Pressure,Irradiation,Irradiation Propagation,Wind Speed,Wind Speed Propagation,Wind Direction,Wind Direction Propagation).This study provides a new perspective not previously addressed in the literature.In this study,different machine learning methods such as Multilayer Perceptron(MLP),Multivariate Adaptive Regression Spline(MARS),Multiple Linear Regression(MLR),and Random Forest(RF)models are used to predict power values using data from installed PVpanels.Panel values obtained under real field conditions were used to train the models,and the results were compared.The Multilayer Perceptron(MLP)model was achieved with the highest classification accuracy of 0.990%.The machine learning models used for solar energy forecasting show high performance and produce results close to actual values.Models like Multi-Layer Perceptron(MLP)and Random Forest(RF)can be used in diverse locations based on load demand.
基金funded in part by Grant No.RG-15-135-43 from the Deanship of Scientific Research(DSR)at King Abdulaziz University in Saudi Arabia.
文摘The proliferation of distributed and renewable energy resources introduces additional operational challenges to power distribution systems.Transactive energy management,which allows networked neighborhood communities and houses to trade energy,is expected to be developed as an effective method for accommodating additional uncertainties and security mandates pertaining to distributed energy resources.This paper proposes and analyzes a two-layer transactive energy market in which houses in networked neighborhood community microgrids will trade energy in respective market layers.This paper studies the blockchain applications to satisfy socioeconomic and technological concerns of secure transactive energy management in a two-level power distribution system.The numerical results for practical networked microgrids located at IllinoisTech−Bronzeville in Chicago illustrate the validity of the proposed blockchain-based transactive energy management for devising a distributed,scalable,efficient,and cybersecured power grid operation.The conclusion of the paper summarizes the prospects for blockchain applications to transactive energy management in power distribution systems.
文摘Existing Internet of Things(IoT)systems that rely on Amazon Web Services(AWS)often encounter inefficiencies in data retrieval and high operational costs,especially when using DynamoDB for large-scale sensor data.These limitations hinder the scalability and responsiveness of applications such as remote energy monitoring systems.This research focuses on designing and developing an Arduino-based IoT system aimed at optimizing data transmission costs by concentrating on these services.The proposed method employs AWS Lambda functions with Amazon Relational Database Service(RDS)to facilitate the transmission of data collected from temperature and humidity sensors to the RDS database.In contrast,the conventional method utilizes AmazonDynamoDB for storing the same sensor data.Data were collected from 01 April 2022,to 26 August 2022,in Tokyo,Japan,focusing on temperature and relative humiditywitha resolutionof oneminute.The efficiency of the twomethods—conventional andproposed—was assessed in terms of both time and cost metrics,with a particular focus on data retrieval.The conventional method exhibited linear time complexity,leading to longer data retrieval times as the dataset grew,mainly due to DynamoDB’s pagination requirements and the parsing of payload data during the reading process.In contrast,the proposed method significantly reduced retrieval times for larger datasets by parsing payload data before writing it to the RDS database.Cost analysis revealed a savings of$1.56 per month with the adoption of the proposed approach for a 20-gigabyte database.
文摘Multispectral imaging,which simultaneously captures the spatial and spectral information of a scene,is widely used across diverse fields,including remote sensing,biomedical imaging,and agricultural monitoring.We introduce a snapshot multispectral imaging approach employing a standard monochrome image sensor with no additional spectral filters or customized components.Our system leverages the inherent chromatic aberration of wavelength-dependent defocusing as a natural source of physical encoding of multispectral information;this encoded image information is rapidly decoded via a deep learning-based multispectral Fourier imager network(mFIN).We experimentally tested our method with six illumination bands and demonstrated an overall accuracy of 98.25%for predicting the illumination channels at the input and achieved a robust multispectral image reconstruction on various test objects.This deep learning-powered framework achieves high-quality multispectral image reconstruction using snapshot image acquisition with a monochrome image sensor and could be useful for applications in biomedicine,industrial quality control,and agriculture,among others.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)—Innovative Human Resource Development for Local Intellectualization program grant funded by the Korea government(MSIT)(IITP-2025-RS-2022-00156334)in part by Liaoning Province Nature Fund Project(2024-BSLH-214).
文摘Network Intrusion Detection System(NIDS)detection of minority class attacks is always a difficult task when dealing with attacks in complex network environments.To improve the detection capability of minority-class attacks,this study proposes an intrusion detection method based on a two-layer structure.The first layer employs a CNN-BiLSTM model incorporating an attention mechanism to classify network traffic into normal traffic,majority class attacks,and merged minority class attacks.The second layer further segments the minority class attacks through Stacking ensemble learning.The datasets are selected from the generic network dataset CIC-IDS2017,NSL-KDD,and the industrial network dataset Mississippi Gas Pipeline dataset to enhance the generalization and practical applicability of the model.Experimental results show that the proposed model achieves an overall detection accuracy of 99%,99%,and 95%on the CIC-IDS2017,NSL-KDD,and industrial network datasets,respectively.It also significantly outperforms traditional methods in terms of detection accuracy and recall rate for minority class attacks.Compared with the single-layer deep learning model,the two-layer structure effectively reduces the false alarm rate while improving the minority-class attack detection performance.The research in this paper not only improves the adaptability of NIDS to complex network environments but also provides a new solution for minority-class attack detection in industrial network security.
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.
