检索结果-内蒙古大学图书馆

KDTL: knowledge-distilled transfer learning framework for diagnosing mental disorders using EEG spectrograms

Neural Computing and Applications 2024年第30期36卷 18919-18934页

作者： Singh, Shreyash Jadli, Harshit Padma Priya, R. Surya Prasath, V.B. Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Vellore India Division of Biomedical Informatics Cincinnati Children’s Hospital Medical Center CincinnatiOH45229 United States Department of Pediatrics University of Cincinnati College of Medicine CincinnatiOH45257 United States Department of Biomedical Informatics College of Medicine University of Cincinnati CincinnatiOH45267 United States Department of Computer Science University of Cincinnati CincinnatiOH45221 United States

Electroencephalography (EEG) is a well-known modality in neuroscience and is widely used in identifying and classifying neurological disorders. This paper investigates how EEG data can be used along with knowledge distillation-based deep learning models to detect mental disorders like epilepsy and sleep disorders. The EEG signals are converted into time–frequency plots using short-time Fourier transforms. Further, we propose a novel methodology for using knowledge distillation-based transfer learning (KDTL). Knowledge distillation is becoming quite prevalent in the machine learning field and is associated with various applications in our work;we propose its use in the detection of mental disorders from EEG spectrograms. We convert the EEGs using short-term Fourier transform to obtain time–frequency representation and apply teacher-student by first training a large teacher model and use knowledge distillation to train a student model. In our experiments, we found that ConvNext teacher and MobileNet student combination obtained better results. Our proposed KDTL approach is tested on two datasets with multiple cases, namely the Bonn and ISRUC datasets and obtain 98% and 95% accuracies, respectively. Further experimental results show that the overall KDTL methodology can obtain high classification accuracy across both datasets in binary and multiclass classifications and proves to be better than multiple prior works. Further, our KDTL approach provides a way to train lightweight models which have a smaller number of trainable parameters and thereby constitute lower training time overall. Our proposed KDTL-based approach obtained accurate results in diagnosing mental disorders from EEG spectrograms. Compared to other related methods, KDTL outperformed across tasks with obtained good results in both binary and multiclass classifications. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Protein Secondary Structure Prediction

Deep Learning Approaches for Protein Secondary Structure Pre...

引用

International Conference on Computer and Information technology (ICCIT)

作者： Umme Israt Afroz Shreshthajit Das Nazmul Siddique Department of Computer Science and Engineering Khulna University of Engineering & Technology(KUET) Khulna Bangladesh Department of Software Engineering Shahjalal University of Science & Technology(SUST) Sylhet Bangladesh School of Computing Engineering and Intelligent Systems Ulster University Londonderry UK

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

This paper presents a novel hybrid model comprising Evolutionary Scale Modeling (ESM), Convolution Neural Network (CNN) and Long Short Term Memory (LSTM) network for prediction of protein secondary structures from coil (C), helix (H), and sheet (E)—from amino acid sequences using deep learning techniques. Each architecture leverages unique strengths, with LSTMs capturing long-range dependencies, CNNs extracting local spatial patterns, and ESM enhancing contextual understanding of sequences. The hybrid model was trained and tested using two key datasets: the UniProt dataset and the pdb-intersect-pisces dataset, which provide a rich source of protein sequences and structural information. The proposed model achieved an accuracy of 89.22%, demonstrating robust performance in protein secondary structure prediction.

关键词： Proteins Deep learning Accuracy Computational modeling Neural networks Computer architecture Predictive models Transformers Information technology Long short term memory

来源：评论

学校读者我要写书评

暂无评论

A Review on IoT Botnet 2021

A Review on IoT Botnet

引用

2nd International Conference on Computing and Data Science, CONF-CDS 2021

作者： Zhao, Hao Shu, Hui Xing, Ying State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China Software College Zhongyuan University of Technology Zhengzhou China

ISBN: (纸本)9781450389570

The rapid development of the Internet of Things (IoT) also generates security threats that cannot be ignored. This paper lists the development history of botnets, introduces representative IoT botnets, and reveals their new characteristics. The botnet mechanism and characteristics of IoT botnets are analyzed in depth from three aspects: composition structure, life cycle, and attack behavior, and are compared with traditional botnets. Networks for comparison. The analysis discusses the details of IoT botnet technologies such as scanning discovery, covert communication and survival residency. Summarizes the research status of IoT botnet detection technologies and gives future directions. Finally, the importance of preventing IoT botnets and solving IoT security problems is discussed. © 2021 ACM.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Automated Surface Classification System Using Vibration Patterns - A Case Study With Wheelchairs

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第4期4卷 884-895页

作者： Yu, Haoxiang Raychoudhury, Vaskar Saha, Snehanshu Edinger, Janick Smith, Roger O. Gani, Md Osman The University of Texas at Austin Department of Electrical and Computer Engineering AustinTX78712 United States Miami University Department of Computer Science & Software Engineering OxfordOH45056 United States Bits Pilani K.K. Birla Goa Campus Department of Computer Science & Information Systems Appcair Zuarinagar403726 India University of Hamburg Department of Informatics & Distributed Operating Systems Hamburg20146 Germany University of Wisconsin-Milwaukee Department of Rehabilitation Sciences & Technology MilwaukeeWI53706 United States University of Maryland Baltimore County Department of Information Systems BaltimoreMD21250 United States

Finding a barrier-free accessible path through the built environment is necessary for wheelchair users. Researchers have identified the effect of surface vibration on the health of wheelchair users and proposed various solutions to identify and annotate mobility barriers. However, the effects of surface-induced vibration on accessibility are yet to be investigated. In order to address this problem, we present the WheelShare system, which uses machine learning to identify surfaces and curbs from vibration captured by accelerometer and gyroscope sensors (both smartphone and wearable device). WheelShare allows users to share their collected data via crowdsourcing. Based on this surface-specific vibration, we recognize 32 different surfaces found across the built environment (in Austria, China, France, Germany, India, and the USA for 32 human subjects) with an accuracy of 97.5%. The recognized surfaces are then grouped into different categories based on their characteristics. Our novel contributions in this article include the following. 1) We have developed a machine-learning-enabled surface recognition system that uses sensor data to capture surface-induced vibration patterns. 2) We have tested the robustness of the system for devices with only accelerometer data (such as low-end smartphones) and achieved an accuracy of 91.6%. 3) We have deployed our prototype WheelShare system for real-time surface classification in new sites that are unseen in training and testing and successfully recognized the surface characteristics. © 2020 IEEE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Geometric Latent Diffusion Model for Graph Generation 41

Hyperbolic Geometric Latent Diffusion Model for Graph Genera...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Fu, Xingcheng Gao, Yisen Wei, Yuecen Sun, Qingyun Peng, Hao Li, Jianxin Li, Xianxian Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies. Copyright 2024 by the author(s)

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Posture Detection with Hybrid Deep VGG16 and Attention Mechanism Network

引用

Procedia Computer Science 2025年 258卷 1209-1218页

作者： Ogundokun Roseline Oluwaseun Rytis Maskeliūnas Federick Oscar Oluwakayode A. Oki Department of Software Engineering Kaunas University of Technology Kaunas 44249 Lithuania Department of Computer Science Landmark University Omu-Aran Nigeria Department of Computer Systems Engineering Tshwane University of Technology (TUT) Pretoria South Africa Adioo Technology Abuja Nigeria Department of Information Technology East London Walter Sisulu University South Africa

Human Posture Detection (HPD) and classification are the initial steps toward various computer vision applications related to security, advertisement, and healthcare. Even though more than three decades have passed, most methods have been focused only on detecting standing people. However, in real applications, human postures may be significantly different, such as standing, sitting, lying, and crouching, and the shapes of a human are varied with viewpoints, thus making detection and classification difficult. Moreover, the gradual transition from one posture to another further complicates the determination of the number of postures to be classified. This paper uses a pre-trained model to determine the number of unique human postures in activities. We approached PC as a multiclass detection problem using the very deep VGG 16 Convolutional Neural Network (CNN) empowered by an attention mechanism. Extract frames from video data recorded, followed by the derivation of features through a convolutional neural network. Classify different postures—bending, exercise, lying, sitting, and standing—with VGG 16 and attention mechanism. It is trained on the ETRI-Activity3D-LivingLab Dataset. Our proposed (VEACT-CNN) framework has shown stability in HPD with an overall accuracy of 95% and an F-measure of 98% while generating a very low level of false alarms rate (FAR) of 0.02 (2%). For comparison purposes, the accuracy obtained by other models on the same dataset is VGG 16.

关键词： Vision-based human detection Posture classification VGG 16 Deep learning Pre-trained model Human posture detection

来源：评论

学校读者我要写书评

暂无评论

RAT: A Refactoring-Aware Traceability Model for Bug Localization

RAT: A Refactoring-Aware Traceability Model for Bug Localiza...

引用

International Conference on software engineering (ICSE)

作者： Feifei Niu Wesley K. G. Assunção LiGuo Huang Christoph Mayr-Dorn Jidong Ge Bin Luo Alexander Egyed State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Institute for Software Systems Engineering Johannes Kepler University Linz Austria Department of Computer Science and Engineering Southern Methodist University Dallas Texas USA

A large number of bug reports are created during the evolution of a software system. Locating the source code files that need to be changed in order to fix these bugs is a challenging task. Information retrieval-based bug localization techniques do so by correlating bug reports with historical information about the source code (e.g., previously resolved bug reports, commit logs). These techniques have shown to be efficient and easy to use. However, one flaw that is nearly omnipresent in all these techniques is that they ignore code refactorings. Code refactorings are common during software system evolution, but from the perspective of typical version control systems, they break the code history. For example, a class when renamed then appears as two separate classes with separate histories. Obviously, this is a problem that affects any technique that leverages code history. This paper proposes a refactoring-aware traceability model to keep track of the code evolution history. With this model, we reconstruct the code history by analyzing the impact of code refactorings to correctly stitch together what would otherwise be a fragmented history. To demonstrate that a refactoring aware history is indeed beneficial, we investigated three widely adopted bug localization techniques that make use of code history, which are important components in existing approaches. Our evaluation on 11 open source projects shows that taking code refactorings into account significantly improves the results of these bug localization techniques without significant changes to the techniques themselves. The more refactorings are used in a project, the stronger the benefit we observed. Based on our findings, we believe that much of the state of the art leveraging code history should benefit from our work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

QoS Prediction Model of Cloud Services Based on Deep Learning

引用

IEEE/CAA Journal of Automatica Sinica 2022年第3期9卷 564-566页

作者： WenJun Huang PeiYun Zhang YuTong Chen MengChu Zhou Yusuf Al-Turki Abdullah Abusorrah Nanjing University of Information Science&Technology School of Computer and SoftwareNanjingChina IEEE New Jersey Institute of Technology Helen and John C.Hartmann Department of Electrical and Computer EngineeringNewarkUSA Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer EngineeringFaculty of Engineeringand K.A.CARE Energy Research and Innovation CenterKing Abdulaziz UniversityJeddah 21589Saudi Arabia

Dear editor,This letter presents a deep learning-based prediction model for the quality-of-service(QoS)of cloud ***,to improve the QoS prediction accuracy of cloud services,a new QoS prediction model is proposed,which is based on multi-staged multi-metric feature fusion with individual *** multi-metric features include global,local,and individual *** results show that the proposed model can provide more accurate QoS prediction results of cloud services than several state-of-the-art methods.

关键词： services Services individual

来源：评论

学校读者我要写书评

暂无评论

The ABLoTS Approach for Bug Localization: is it replicable and generalizable?

The ABLoTS Approach for Bug Localization: is it replicable a...

引用

International Mining software Repositories, MSR

作者： Feifei Niu Christoph Mayr-Dorn Wesley K. G. Assunção LiGuo Huang Jidong Ge Bin Luo Alexander Egyed State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Institute for Software Systems Engineering Johannes Kepler University Linz Austria Department of Computer Science and Engineering Southern Methodist University Dallas Texas USA

Bug localization is the task of recommending source code locations (typically files) that probably contain the cause of a bug and hence need to be changed to fix the bug. Along these lines, information retrieval-based bug localization (IRBL) approaches have been adopted, which identify the most bug-prone files from the source code space. In current practice, a series of state-of-the-art IRBL techniques leverage the combination of different components, e.g., similar reports, version history, code structure, to achieve better performance. ABLoTS is a recently proposed approach with the core component, TraceScore, that utilizes requirements and traceability information between different issue reports, i.e., feature requests and bug reports, to identify buggy source code snippets with promising results. To evaluate the accuracy of these results and obtain additional insights into the practical applicability of ABLoTS, supporting of future more efficient and rapid replication and comparison, we conducted a replication study of this approach with the original data set and also on an extended data set. The extended data set includes 16 more projects comprising 25,893 bug reports and corresponding source code commits. While we find that the TraceScore component as the core of ABLoTS produces comparable results with the extended data set, we also find that the ABLoTS approach no longer achieves promising results, due to an overlooked side effect of incorrectly choosing a cut-off date that led to training data leaking into test data with significant effects on performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a Model for Discriminating Electroencephalograms of Patients with Mild Cognitive Impairment and Healthy Individuals Using a Support Vector Machine 13

Development of a Model for Discriminating Electroencephalogr...

引用

Joint 13th International Conference on Soft Computing and Intelligent systems and 25th International Symposium on advanced Intelligent systems, SCIS and ISIS 2024

作者： Tanabe, Akifumi Nakatani, Kyosuke Harachi, Kento Yamamoto, Yusuke Muramatsu, Ayumi Nagahara, Hajime Takemura, Noriko Shimojo, Shinji Furihata, Daisuke Mizuno-Matsumoto, Yuko Kamae-Shigenobu, Kazue Shinosaki, Kazuhiro Graduate School of Information Science University of Hyogo Kobe Japan School of Life Science and Technology Tokyo Institute of Technology Yokohama Japan Aino University Department of Medical Engineering Ibaraki Japan Institute for Datability Science Osaka University Suita Japan Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Aomori University Faculty of Software and Information Technology Aomori Japan Osaka University Cyber Media Center Suita Japan Asakayama General Hospital Sakai Japan

ISBN: (纸本)9798350373332

We performed machine learning using spectrum analysis and power spectra of electroencephalograms (EEGs) of patients with mild cognitive impairment (MCI). Spectrum analysis was performed on the EEGs of MCI patients and healthy individuals, and the power spectrum values of the two groups were calculated and compared. Based on the power spectrum values of the theta and alpha bands, models for discriminating MCI patients were created using a support vector machine (SVM), and their accuracies were compared. In the spectrum analysis, the theta band showed significantly higher power spectrum values in the MCI group. In the comparison of the accuracies of SVM models, the model using the theta band showed higher values in parameters, such as accuracy rate. These results suggested that the power spectrum values of the theta band are useful for discriminating MCI patients. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：