检索结果-南通市图书馆

Efficient Feature Selection and Machine Learning Based ADHD Detection Using EEG Signal

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第9期72卷 5179-5195页

作者： md.Maniruzzaman Jungpil Shin md.al Mehedi Hasan Akira Yasumura School of Computer Science and Engineering The University of AizuAizuwakamatsuFukushima965-8580Japan Faculty of Humanities and Social Science Kumamoto UniversityChuo-kuKumamotoJapan

Attention deficit hyperactivity disorder(ADHD)is one of the most common psychiatric and neurobehavioral disorders in children,affecting 11%of children *** study aimed to propose a machine learning(ML)-based algorithm for discriminating ADHD from healthy children using their electroencephalography(EEG)*** study included 61 children with ADHD and 60 healthy children aged 7–12 *** morphological and time-domain features were extracted from EEG *** t-test(p-valueal features of children with ADHD and enhance the classification *** selected potential features were used in four ML-based algorithms,including support vector machine(SVM),k-nearest neighbors,multilayer perceptron(MLP),and logistic regression,to classify ADHD and healthy *** overall prevalence of boys and girls with ADHD was 48.9%and 56.5%,*** average age of children with ADHD was 9.6±1.8 *** results illustrated that the combination of LASSO with SVM classifier achieved the highest accuracy of 94.2%,sensitivity of 93.3%,F1-score of 91.9%,and AUC of *** results also illustrated that MLP was the second-best ML-based classifier,which gave 93.4%accuracy,91.7%sensitivity,91.1%F1-score,and 0.960 *** findings indicated that the combination of the LASSO-based feature selection method and SVM classifier can be a useful tool for selecting reliable/potential features and classifying ADHD and healthy *** proposed ML-based algorithms could be useful for the early diagnosis of children with ADHD.

关键词： ADHD feature extraction feature selection classification machine learning

Regeneration mechanisms and therapeutic strategies for neuromuscular junctions in aging and diseases

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第1期20卷 193-194页

作者： Masashi Fujitani Abu md Mamun Tarif Yoshinori Otani Department of Anatomy and Neuroscience Faculty of MedicineShimane UniversityShimaneJapan

The neuromuscular junction(NMJ)is an essential synaptic structure composed of motor neurons,skeletal muscles,and glial cells that orchestrate the critical process of muscle contraction(Li et al.,2018).The typical NMJ structure is classically described as having a“pretzel-like”shape in mice(Figure 1),whereas human NMJs have a smaller,fragmented structure throughout *** NMJs exhibit smaller or fragmented endplates,partial denervation,reduced numbers of synaptic vesicles,abnormal presynaptic mitochondria,and dysfunctional perisynaptic Schwann cells(alhindi et al.,2022).

关键词： aging structure Figure

维普期刊数据库

Steel Surface Defect Detection Using Learnable Memory Vision Transformer

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 499-520页

作者： Syed Tasnimul Karim Ayon Farhan md.Siraj Jia Uddin Department of Computer Science and Engineering BRAC UniversityDhaka1212Bangladesh Department of AI and Big Data Endicott CollegeWoosong UniversityDaejeon34606Republic of Korea

This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as other transformer-based models including Token to Token ViT,ViT withoutmemory,and Parallel *** awidely-used steel surface defect dataset,the research applies data augmentation and t-distributed stochastic neighbor embedding(t-SNE)to enhance feature extraction and *** techniques mitigated overfitting,stabilized training,and improved generalization *** LMViT model achieved a test accuracy of 97.22%,significantly outperforming ResNet18(88.89%)and ResNet50(88.90%),aswell as the Token to TokenViT(88.46%),ViT without memory(87.18),and Parallel ViT(91.03%).Furthermore,LMViT exhibited superior training and validation performance,attaining a validation accuracy of 98.2%compared to 91.0%for ResNet 18,96.0%for ResNet50,and 89.12%,87.51%,and 91.21%for Token to Token ViT,ViT without memory,and Parallel ViT,*** findings highlight the LMViT’s ability to capture long-range dependencies in images,an areawhere CNNs struggle due to their reliance on local receptive fields and hierarchical feature *** additional transformer-based models also demonstrate improved performance in capturing complex features over CNNs,with LMViT excelling particularly at detecting subtle and complex defects,which is critical for maintaining product quality and operational efficiency in industrial *** instance,the LMViT model successfully identified fine scratches and minor surface irregularities that CNNs often *** study not only demonstrates LMViT’s potential for real-world defect detection but also underscores the promise of other transformer-based architectures like Token to Token ViT,ViT without memory,and Parallel ViT in industrial scenarios where complex spatial relationships are *** research m

关键词： Learnable Memory Vision Transformer(LMViT) Convolutional Neural Networks(CNN) metal surface defect detection deep learning,computer vision image classification learnable memory gradient clipping label smoothing t-SNE visualization

Rotation,Translation and Scale Invariant Sign Word Recognition Using Deep Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第3期44卷 2521-2536页

作者： Abu Saleh Musa Miah Jungpil Shin md.al Mehedi Hasan md Abdur Rahim Yuichi Okuyama School of Computer Science and Engineering The University of AizuAizuwakamatsuFukushima965-8580Japan Department of Computer Science and Engineering Pabna University of Science and TechnologyPabnaBangladesh

Communication between people with disabilities and people who do not understand sign language is a growing social need and can be a tedious *** of the main functions of sign language is to communicate with each other through hand *** of hand gestures has become an important challenge for the recognition of sign *** are many existing models that can produce a good accuracy,but if the model test with rotated or translated images,they may face some difficulties to make good performance *** resolve these challenges of hand gesture recognition,we proposed a Rotation,Translation and Scale-invariant sign word recognition system using a convolu-tional neural network(CNN).We have followed three steps in our work:rotated,translated and scaled(RTS)version dataset generation,gesture segmentation,and sign word ***,we have enlarged a benchmark dataset of 20 sign words by making different amounts of Rotation,Translation and Scale of the ori-ginal images to create the RTS version *** we have applied the gesture segmentation *** segmentation consists of three levels,i)Otsu Thresholding with YCbCr,ii)Morphological analysis:dilation through opening morphology and iii)Watershed ***,our designed CNN model has been trained to classify the hand gesture as well as the sign *** model has been evaluated using the twenty sign word dataset,five sign word dataset and the RTS version of these *** achieved 99.30%accuracy from the twenty sign word dataset evaluation,99.10%accuracy from the RTS version of the twenty sign word evolution,100%accuracy from thefive sign word dataset evaluation,and 98.00%accuracy from the RTS versionfive sign word dataset ***,the influence of our model exists in competitive results with state-of-the-art methods in sign word recognition.

关键词： Sign word recognition convolution neural network(cnn) rotation translation and scaling(rts) otsu segmentation

Japanese Sign Language Recognition by Combining Joint Skeleton-Based Handcrafted and Pixel-Based Deep Learning Features with Machine Learning Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第6期139卷 2605-2625页

作者： Jungpil Shin md.al Mehedi Hasan Abu Saleh Musa Miah Kota Suzuki Koki Hirooka School of Computer Science and Engineering The University of AizuAizuwakamatsu965-8580Japan Department of Computer Science&Engineering Rajshahi University of Engineering&TechnologyRajshahi6204Bangladesh

Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing *** Japan,approximately 360,000 individualswith hearing and speech disabilities rely on Japanese Sign Language(JSL)for ***,existing JSL recognition systems have faced significant performance limitations due to inherent *** response to these challenges,we present a novel JSL recognition system that employs a strategic fusion approach,combining joint skeleton-based handcrafted features and pixel-based deep learning *** system incorporates two distinct streams:the first stream extracts crucial handcrafted features,emphasizing the capture of hand and body movements within JSL ***,a deep learning-based transfer learning stream captures hierarchical representations of JSL gestures in the second ***,we concatenated the critical information of the first stream and the hierarchy of the second stream features to produce the multiple levels of the fusion features,aiming to create a comprehensive representation of the JSL *** reducing the dimensionality of the feature,a feature selection approach and a kernel-based support vector machine(SVM)were used for the *** assess the effectiveness of our approach,we conducted extensive experiments on our Lab JSL dataset and a publicly available Arabic sign language(ArSL)*** results unequivocally demonstrate that our fusion approach significantly enhances JSL recognition accuracy and robustness compared to individual feature sets or traditional recognition methods.

关键词： Japanese Sign Language(JSL) hand gesture recognition geometric feature distance feature angle feature GoogleNet

Ru/NiMnB spherical cluster pillar for highly proficient green hydrogen electrocatalyst at high current density

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2025年第1期100卷 397-408页

作者： md Ahasan Habib Shusen Lin Mehedi Hasan Joni Sumiya Akter Dristy Rutuja Mandavkar Jae-Hun Jeong Jihoon Lee Department of Electronic Engineering College of Electronics and Information Kwangwoon University

Advanced OER/HER electrocatalytic alternatives are crucial for the wide adaptation of green hydrogen ***,Ru/NiMnB spherical cluster pillar （SCP）,denoted as Ru/NiMnB,is synthesized using a combination of electro-deposition and hydrothermal *** investigation of Ru doping in the NiMnB matrix revealed significant improvements in electrocatalytic *** Ru/NiMnB SCPs demonstrate superior OER/HER activity with low overpotentials of 150 and 103 mV at 50mA/cm2in 1 M KOH,making them highly competitive with state-of-the-art ***,the Ru/NiMnB SCPs exhibit a low 2-E cell voltage of 2.80 V at ultra-high current density of 2,000 m A/cm2in 1 M KOH,outperforming the standard benchmark electrodes of RuO2||Pt/C,thereby positioning Ru/NiMnB as one of the best bifunctional *** SCPs exhibit exceptional high-current characteristics,stability and corrosion resistance,as evidenced by continuous operation at 1,000 mA/cm2high-current density for over 150 h in 6 M KOH at elevated temperatures under harsh industrial *** a small amount of Ru incorporation significantly enhances the electrocatalytic performances of NiMnB,attributed to increased active sites and improved intrinsic properties such as conductivity,adsorption/desorption capability and reaction ***,Ru/NiMnB SCPs present a promising bi-functional electrode concept for efficient green H2production.

关键词： Potassium hydroxide

Comparative Analysis of Credit-Strength among Industries of Bangladesh:altman’s Z-score Measurement

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Sustainable Business and Economics 2023年第1期6卷 26-43页

作者： md.al Amin Department of Accounting Mawlana Bhashani Science and Technology UniversitySantoshTangail1902Bangladesh

The main motive of the study is to explore the financial position of prominent industries in Bangladesh to give direction to investors for sound investment *** altman Z-score model has been used to assess the financial soundness of the 23 companies of five prominent industries in *** data have been collected from the annual reports of the selected *** study found that 20%and 40%of the selected companies of the ceramic industry and tannery industry fall on the safe form respectively that means where investors can invest without any doubt as they are financially ***,28.57%,40%,and 25%of the selected companies of cement,ceramic,and paper and printing industries stand in the grey zone respectively which indicates the companies have a good chance of bankruptcy within two *** 71.43%,40%,75%,60%,and 100%of companies in the cement,ceramic,paper&printing,tannery,and jute industries’financial conditions are not satisfactory respectively as they fall in the distress *** only 20%of the selected industries fall in the safe *** means the overall financial soundness of the selected industries is not *** study will be an important source for further study in the field of credit strength *** actor of society those are involved in the business(investors,lenders,workers,suppliers,financial institutions as well as the economy itself)can be able to make adequate decisions by the findings of the study.

关键词： Credit-strength Z-score Financial ratios

Does the Accounting Information Systems(AIS)Influence the Economy?

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Business Administration Research 2021年第3期4卷 24-35页

作者： md.Abdul Halim md.al Amin Department of Business Administration Mawlana Bhashani Science and Technology UniversityTangailBangladesh Department of Accounting Mawlana Bhashani Science and Technology UniversityTangailBangladesh

The purpose of this study is to look at the impact of accounting information systems on the *** study has been directed based on the analytical and *** observed a total of 500 *** run the research and to get informative results,this paper used primary *** uses the Chi squire test,ANOVA tests,and Multinomial Logistic tests for analyzing the *** calculates the data with the help of IBM statistical packages for social science(SPSS).This paper assumes that AIS is beneficial for Bangladeshi organizations,which contributes to the economic development of ***,it finally shows that this system has a gap between what accounting information systems are&what should *** paper suggests that an organization may get potential benefits through the implementation of AIS in *** also will be benefited stakeholders from implying *** paper conducts based on the listed financial organizations of *** is the main limitation of this *** is the first work in Bangladesh based on my *** provides accurate information to all stakeholders that help them to the right *** will also help to improve the economic development of Bangladesh.

关键词： Application of AIS Benefits of AIS Chi-square ANOVA Developing economy

Analysing the relationship between drought and soil erosion using vegetation health index and RUSLE models in Godavari middle sub-basin,India

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Geoscience Frontiers 2022年第2期13卷 21-33页

作者： md Masroor Haroon Sajjad Sufia Rehman Roshani Singh md Hibjur Rahaman Mehebub Sahana raihan Ahmed Ram Avtar Department of Geography Faculty of Natural SciencesJamia Millia IslamiaNew DelhiIndia School of Environment Education and Development(SEED)University of ManchesterUnited Kingdom Graduate School of Environment Earth Science Hokkaido UniversityJapan

Drought is a natural phenomenon posing severe implications for soil,groundwater and agricultural *** has been recognized as one of the most pervasive global change drivers to affect the *** being a weakly renewable resource takes a long time to form,but it takes no time to ***,the response of soil to drought conditions as soil loss is not manifested in the existing ***,this study makes a concerted effort to analyze the relationship between drought conditions and soil erosion in the middle sub-basin of the Godavari River in *** remote sensing data was utilized for driving drought indices during ***,we constricted Temperature condition index(TCI)and Vegetation Condition Index(VCI)from Land Surface Temperature(LST)and Enhanced Vegetation Index(EVI)derived from MODIS *** and VCI were then integrated to determine the Vegetation Health Index(VHI).Revised Universal Soil Loss Equation(RUSLE)was utilized for estimating soil *** relationship between drought condition and vegetation was ascertained using the Pearson *** of the northern and southern watersheds experienced severe drought condition in the sub-basin *** mean frequency of the drought occurrence was 7.95 *** average soil erosion in the sub-basin was estimated to be 9.88 t ha^(-1)year^(-1).A positive relationship was observed between drought indices and soil erosion values(r value being 0.35).However,wide variations were observed in the distribution of spatial *** various factors,the slope length and steepness were found to be the main drivers of soil erosion in the ***,the study calls for policy measures to lessen the impact of drought and soil erosion.

关键词： Drought vulnerability Soil erosion RUSLE Vegetation Health Index(VHI) Godavari middle sub-basin

维普期刊数据库