Lightweight deep learning models are increasingly required in resource-constrained environments such as mobile devices and the Internet of Medical Things(IoMT).Multi-head convolution with channel attention can facilit...Lightweight deep learning models are increasingly required in resource-constrained environments such as mobile devices and the Internet of Medical Things(IoMT).Multi-head convolution with channel attention can facilitate learning activations relevant to different kernel sizes within a multi-head convolutional layer.Therefore,this study investigates the capability of novel lightweight models incorporating residual multi-head convolution with channel attention(ResMHCNN)blocks to classify medical images.We introduced three novel lightweight deep learning models(BT-Net,LCC-Net,and BC-Net)utilizing the ResMHCNN block as their backbone.These models were crossvalidated and tested on three publicly available medical image datasets:a brain tumor dataset from Figshare consisting of T1-weighted magnetic resonance imaging slices of meningioma,glioma,and pituitary tumors;the LC25000 dataset,which includes microscopic images of lung and colon cancers;and the BreaKHis dataset,containing benign and malignant breast microscopic images.The lightweight models achieved accuracies of 96.9%for 3-class brain tumor classification using BT-Net,and 99.7%for 5-class lung and colon cancer classification using LCC-Net.For 2-class breast cancer classification,BC-Net achieved an accuracy of 96.7%.The parameter counts for the proposed lightweight models—LCC-Net,BC-Net,and BT-Net—are 0.528,0.226,and 1.154 million,respectively.The presented lightweight models,featuring ResMHCNN blocks,may be effectively employed for accurate medical image classification.In the future,these models might be tested for viability in resource-constrained systems such as mobile devices and IoMT platforms.展开更多
Several popular time-frequency techniques,including the Wigner-Ville distribution,smoothed pseudo-Wigner-Ville distribution,wavelet transform,synchrosqueezing transform,Hilbert-Huang transform,and Gabor-Wigner transfo...Several popular time-frequency techniques,including the Wigner-Ville distribution,smoothed pseudo-Wigner-Ville distribution,wavelet transform,synchrosqueezing transform,Hilbert-Huang transform,and Gabor-Wigner transform,are investigated to determine how well they can identify damage to structures.In this work,a synchroextracting transform(SET)based on the short-time Fourier transform is proposed for estimating post-earthquake structural damage.The performance of SET for artificially generated signals and actual earthquake signals is examined with existing methods.Amongst other tested techniques,SET improves frequency resolution to a great extent by lowering the influence of smearing along the time-frequency plane.Hence,interpretation and readability with the proposed method are improved,and small changes in the time-varying frequency characteristics of the damaged buildings are easily detected through the SET method.展开更多
A hybrid time-frequency method known as Gabor-Wigner transform (GWT) is introduced in this paper for examining the time-frequency patterns of earthquake damaged buildings. GWT is developed by combining the Gabor trans...A hybrid time-frequency method known as Gabor-Wigner transform (GWT) is introduced in this paper for examining the time-frequency patterns of earthquake damaged buildings. GWT is developed by combining the Gabor transform (GT) and Wigner-Ville distribution (WVD). GT and WVD have been used separately on synthetic and recorded earthquake data to identify frequency shifting due to earthquake damages, but GT is prone to windowing effect and WVD involves ambiguity function. Hence to obtain better clarity and to remove the cross terms (frequency interference), GT and WVD are judiciously combined and the resultant GWT used to identify frequency shifting. Synthetic seismic response of an instrumented building and real-time earthquake data recorded on the building were investigated using GWT. It is found that GWT offers good accuracy for even slow variations in frequency, good time-frequency resolution, and localized response. Presented results confirm the efficacy of GWT when compared with GT and WVD used separately. Simulation results were quantified by the Renyi entropy measures and GWT shown to be an adequate technique in identifying localized response for structural damage detection.展开更多
This paper presents an evaluation of time-frequency methods for the analysis of seismic signals.Background of the present work is to describe,how the frequency content of the signal is changing in time.The theoretical...This paper presents an evaluation of time-frequency methods for the analysis of seismic signals.Background of the present work is to describe,how the frequency content of the signal is changing in time.The theoretical basis of short time Fourier transform,Gabor transform,wavelet transform,S-transform,Wigner distribution,Wigner-Ville distribution,Pseudo Wigner-Ville distribution,Smoothed Pseudo Wigner-Ville distribution,Choi-William distribution,Born-Jordan Distribution and cone shape distribution are presented.The strengths and weaknesses of each technique are verified by applying them to a particular synthetic seismic signal and recorded real time earthquake data.展开更多
The rapid growth and increasing complexity of Internet of Things(IoT)devices have made network intrusion detection a critical challenge,especially in edge computing environments where data privacy is a primary concern...The rapid growth and increasing complexity of Internet of Things(IoT)devices have made network intrusion detection a critical challenge,especially in edge computing environments where data privacy is a primary concern.Machine learning-based intrusion detection techniques enhance IoT network security but often require centralized network data,posing significant risks to data privacy and security.Although federated learning(FL)-based network intrusion detection methods have emerged in recent years to address privacy concerns,they have not fully leveraged the advantages of graph neural networks(GNNs)for intrusion detection.To address this issue,we propose a federated spatiotemporal graph convolutional network(FedSTGCN)model,which integrates the capabilities of spatiotemporal GNNs(STGNNs)and federated learning.This framework enables collaborative model training across distributed IoT devices without requiring the sharing of raw data,thereby improving network intrusion detection accuracy while preserving data privacy.Extensive experiments are conducted on two widely used IoT intrusion detection datasets to evaluate the effectiveness of the proposed approach.The results demonstrate that FedSTGCN outperforms other methods in both binary and multiclass classification tasks,achieving over 97%accuracy in binary classification tasks and over 92%weighted F1-score in multiclass classification tasks.展开更多
This study aims to highlight the need for Industry 4.0 in a manufacturing system and explore the importance of the barriers to adopting Industry 4.0 technologies in Indian SMEs.Many barriers to implementing Industry 4...This study aims to highlight the need for Industry 4.0 in a manufacturing system and explore the importance of the barriers to adopting Industry 4.0 technologies in Indian SMEs.Many barriers to implementing Industry 4.0 were explored through a literature review.These barriers are prioritized using the Best-Worst Method(BWM).The framework has illustrated the approach to exploring the barriers and ranking these barriers based on feedback from industry experts.Some of the barriers such as lack of infrastructure,lack of financial resources,lack of government initiatives,high complexity,and cyber security and data ownership issues are observed to be very influential in SMEs to adopting Industry 4.0.The proposed framework can also be used in other industries for implementing Industry 4.0 technologies.Prioritizing and overcoming the barriers step-by-step may help the manager to digitalize the systems.展开更多
In the present study we attempted a parente-child trio,whole exome sequencing(WES)approach to study Apert’s syndrome.Clinical characteristics of the child were noted down and WES was carried out using Ion Torrent Sys...In the present study we attempted a parente-child trio,whole exome sequencing(WES)approach to study Apert’s syndrome.Clinical characteristics of the child were noted down and WES was carried out using Ion Torrent System that revealed the presence of previously reported P253R mutation in FGFR2 gene.Presence of two SNPs rs1047057 and rs554851880 in FGFR2 gene with an allelic frequency of 0.5113 and 0.001176 respectively and 161 complete damaging mutations were found.This study is the first reported case of exome sequencing approach on an Apert’s syndrome patient aimed at providing better genetic counselling in a non-consanguineous relationship.展开更多
Electrodeposition in electrochemical cells is one of the leading causes of its performance deterioration. The prediction of electrodeposition growth demands a good understanding of the complex physics involved, which ...Electrodeposition in electrochemical cells is one of the leading causes of its performance deterioration. The prediction of electrodeposition growth demands a good understanding of the complex physics involved, which can lead to the fabrication of a probabilistic mathematical model. As an alternative, a convolutional Long shortterm memory architecture-based image analysis approach is presented herein. This technique can predict the electrodeposition growth of the electrolytes, without prior detailed knowledge of the system. The captured images of the electrodeposition from the experiments are used to train and test the model. A comparison between the expected output image and predicted image on a pixel level, percentage mean squared error, absolute percentage error, and pattern density of the electrodeposit are investigated to assess the model accuracy. The randomness of the electrodeposition growth is outlined by investigating the fractal dimension and the interfacial length of the electrodeposits. The trained model predictions show a significant promise between all the experimentally obtained relevant parameters with the predicted one. It is expected that this deep learning-based approach for predicting random electrodeposition growth will be of immense help for designing and optimizing the relevant experimental scheme in near future without performing multiple experiments.展开更多
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-2023-00259678)by INHA UNIVERSITY Research Grant.
文摘Lightweight deep learning models are increasingly required in resource-constrained environments such as mobile devices and the Internet of Medical Things(IoMT).Multi-head convolution with channel attention can facilitate learning activations relevant to different kernel sizes within a multi-head convolutional layer.Therefore,this study investigates the capability of novel lightweight models incorporating residual multi-head convolution with channel attention(ResMHCNN)blocks to classify medical images.We introduced three novel lightweight deep learning models(BT-Net,LCC-Net,and BC-Net)utilizing the ResMHCNN block as their backbone.These models were crossvalidated and tested on three publicly available medical image datasets:a brain tumor dataset from Figshare consisting of T1-weighted magnetic resonance imaging slices of meningioma,glioma,and pituitary tumors;the LC25000 dataset,which includes microscopic images of lung and colon cancers;and the BreaKHis dataset,containing benign and malignant breast microscopic images.The lightweight models achieved accuracies of 96.9%for 3-class brain tumor classification using BT-Net,and 99.7%for 5-class lung and colon cancer classification using LCC-Net.For 2-class breast cancer classification,BC-Net achieved an accuracy of 96.7%.The parameter counts for the proposed lightweight models—LCC-Net,BC-Net,and BT-Net—are 0.528,0.226,and 1.154 million,respectively.The presented lightweight models,featuring ResMHCNN blocks,may be effectively employed for accurate medical image classification.In the future,these models might be tested for viability in resource-constrained systems such as mobile devices and IoMT platforms.
文摘Several popular time-frequency techniques,including the Wigner-Ville distribution,smoothed pseudo-Wigner-Ville distribution,wavelet transform,synchrosqueezing transform,Hilbert-Huang transform,and Gabor-Wigner transform,are investigated to determine how well they can identify damage to structures.In this work,a synchroextracting transform(SET)based on the short-time Fourier transform is proposed for estimating post-earthquake structural damage.The performance of SET for artificially generated signals and actual earthquake signals is examined with existing methods.Amongst other tested techniques,SET improves frequency resolution to a great extent by lowering the influence of smearing along the time-frequency plane.Hence,interpretation and readability with the proposed method are improved,and small changes in the time-varying frequency characteristics of the damaged buildings are easily detected through the SET method.
文摘A hybrid time-frequency method known as Gabor-Wigner transform (GWT) is introduced in this paper for examining the time-frequency patterns of earthquake damaged buildings. GWT is developed by combining the Gabor transform (GT) and Wigner-Ville distribution (WVD). GT and WVD have been used separately on synthetic and recorded earthquake data to identify frequency shifting due to earthquake damages, but GT is prone to windowing effect and WVD involves ambiguity function. Hence to obtain better clarity and to remove the cross terms (frequency interference), GT and WVD are judiciously combined and the resultant GWT used to identify frequency shifting. Synthetic seismic response of an instrumented building and real-time earthquake data recorded on the building were investigated using GWT. It is found that GWT offers good accuracy for even slow variations in frequency, good time-frequency resolution, and localized response. Presented results confirm the efficacy of GWT when compared with GT and WVD used separately. Simulation results were quantified by the Renyi entropy measures and GWT shown to be an adequate technique in identifying localized response for structural damage detection.
文摘This paper presents an evaluation of time-frequency methods for the analysis of seismic signals.Background of the present work is to describe,how the frequency content of the signal is changing in time.The theoretical basis of short time Fourier transform,Gabor transform,wavelet transform,S-transform,Wigner distribution,Wigner-Ville distribution,Pseudo Wigner-Ville distribution,Smoothed Pseudo Wigner-Ville distribution,Choi-William distribution,Born-Jordan Distribution and cone shape distribution are presented.The strengths and weaknesses of each technique are verified by applying them to a particular synthetic seismic signal and recorded real time earthquake data.
文摘The rapid growth and increasing complexity of Internet of Things(IoT)devices have made network intrusion detection a critical challenge,especially in edge computing environments where data privacy is a primary concern.Machine learning-based intrusion detection techniques enhance IoT network security but often require centralized network data,posing significant risks to data privacy and security.Although federated learning(FL)-based network intrusion detection methods have emerged in recent years to address privacy concerns,they have not fully leveraged the advantages of graph neural networks(GNNs)for intrusion detection.To address this issue,we propose a federated spatiotemporal graph convolutional network(FedSTGCN)model,which integrates the capabilities of spatiotemporal GNNs(STGNNs)and federated learning.This framework enables collaborative model training across distributed IoT devices without requiring the sharing of raw data,thereby improving network intrusion detection accuracy while preserving data privacy.Extensive experiments are conducted on two widely used IoT intrusion detection datasets to evaluate the effectiveness of the proposed approach.The results demonstrate that FedSTGCN outperforms other methods in both binary and multiclass classification tasks,achieving over 97%accuracy in binary classification tasks and over 92%weighted F1-score in multiclass classification tasks.
文摘This study aims to highlight the need for Industry 4.0 in a manufacturing system and explore the importance of the barriers to adopting Industry 4.0 technologies in Indian SMEs.Many barriers to implementing Industry 4.0 were explored through a literature review.These barriers are prioritized using the Best-Worst Method(BWM).The framework has illustrated the approach to exploring the barriers and ranking these barriers based on feedback from industry experts.Some of the barriers such as lack of infrastructure,lack of financial resources,lack of government initiatives,high complexity,and cyber security and data ownership issues are observed to be very influential in SMEs to adopting Industry 4.0.The proposed framework can also be used in other industries for implementing Industry 4.0 technologies.Prioritizing and overcoming the barriers step-by-step may help the manager to digitalize the systems.
文摘In the present study we attempted a parente-child trio,whole exome sequencing(WES)approach to study Apert’s syndrome.Clinical characteristics of the child were noted down and WES was carried out using Ion Torrent System that revealed the presence of previously reported P253R mutation in FGFR2 gene.Presence of two SNPs rs1047057 and rs554851880 in FGFR2 gene with an allelic frequency of 0.5113 and 0.001176 respectively and 161 complete damaging mutations were found.This study is the first reported case of exome sequencing approach on an Apert’s syndrome patient aimed at providing better genetic counselling in a non-consanguineous relationship.
文摘Electrodeposition in electrochemical cells is one of the leading causes of its performance deterioration. The prediction of electrodeposition growth demands a good understanding of the complex physics involved, which can lead to the fabrication of a probabilistic mathematical model. As an alternative, a convolutional Long shortterm memory architecture-based image analysis approach is presented herein. This technique can predict the electrodeposition growth of the electrolytes, without prior detailed knowledge of the system. The captured images of the electrodeposition from the experiments are used to train and test the model. A comparison between the expected output image and predicted image on a pixel level, percentage mean squared error, absolute percentage error, and pattern density of the electrodeposit are investigated to assess the model accuracy. The randomness of the electrodeposition growth is outlined by investigating the fractal dimension and the interfacial length of the electrodeposits. The trained model predictions show a significant promise between all the experimentally obtained relevant parameters with the predicted one. It is expected that this deep learning-based approach for predicting random electrodeposition growth will be of immense help for designing and optimizing the relevant experimental scheme in near future without performing multiple experiments.
