检索结果-内蒙古大学图书馆

Sustainable computing and Smart Systems (ICSCSS), International Conference on

作者： R. Santhana Krishnan D. Kirubha V. Bibin Christopher J. Relin Francis Raj S. Gopikumar P. Alice Rani Department of Electronics and Communication Engineering SCAD College of Engineering and Technology Cheranmahadevi India Department of Computer Science and Engineering RajaRajeswari College of Engineering Bengaluru India Department of Computing Technologies Faculty of Engineering and Technology School of Computing College of Engineering and Technology SRM Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Civil Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Department of Tamil Sarah Tucker College Tirunelveli India

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

The modernization of airport facilities and services has become increasingly focused on enhancing passenger experiences. Among these experiences, personalized airport lobby experiences stand out as a key area for improvement. By tailoring services and amenities to individual preferences, airports can create more engaging and satisfying experiences for travelers. To achieve this level of personalization, it is imperative to accurately predict passenger preferences during their time in airport lobbies. In this research work, we present a novel AI-driven framework, named HybridGNN, designed for predicting passenger preferences to enhance personalized airport lobby experiences. The proposed framework integrates a hybrid recommender system with graph neural networks (GNNs), leveraging the strengths of both approaches to provide accurate and personalized recommendations. Through comprehensive simulation analysis, HybridGNN is evaluated against existing algorithms using simulation metrics such as accuracy, mean squared error (MSE), training time, and precision. Results indicate that HybridGNN consistently outperforms existing algorithms across all metrics, demonstrating its effectiveness in predicting passenger preferences. This research contributes to the advancement of personalized airport experiences and underscores the potential of AI-driven frameworks in enhancing passenger satisfaction and engagement.

关键词： Training Measurement Technological innovation Schedules Accuracy Social networking (online) Soft sensors

来源：评论

学校读者我要写书评

暂无评论

A new approach for solving global optimization and engineering problems based on modified Sea Horse Optimizer

arXiv

引用

arXiv 2024年

作者： Hashim, Fatma A. Mostafa, Reham R. Khurma, Ruba Abu Qaddoura, Raneem Castillo, P.A. Faculty of Engineering Helwan University Egypt University of Sharjah Sharjah27272 United Arab Emirates Department of Information System Faculty of Computers and Information Sciences Mansoura University Mansoura35516 Egypt MEU Research Unit Faculty of Information Technology Middle East University Amman11831 Jordan School of Computing and Informatics Al Hussein Technical University Amman Jordan Department of Computer Engineering Automatics and Robotics University of Granada Granada Spain

Sea Horse Optimizer (SHO) is a noteworthy metaheuristic algorithm that emulates various intelligent behaviors exhibited by sea horses, encompassing feeding patterns, male reproductive strategies, and intricate movement patterns. To mimic the nuanced locomotion of sea horses, SHO integrates the logarithmic helical equation and Levy flight, effectively incorporating both random movements with substantial step sizes and refined local exploitation. Additionally, the utilization of Brownian motion facilitates a more comprehensive exploration of the search space. This study introduces a robust and high-performance variant of the SHO algorithm named mSHO. The enhancement primarily focuses on bolstering SHO’s exploitation capabilities by replacing its original method with an innovative local search strategy encompassing three distinct steps: a neighborhood-based local search, a global non-neighbor-based search, and a method involving circumnavigation of the existing search region. These techniques improve mSHO algorithm’s search capabilities, allowing it to navigate the search space and converge toward optimal solutions efficiently. To evaluate the efficacy of the mSHO algorithm, comprehensive assessments are conducted across both the CEC2020 benchmark functions and nine distinct engineering problems. A meticulous comparison is drawn against nine metaheuristic algorithms to validate the achieved outcomes. Statistical tests, including Wilcoxon’s rank-sum and Friedman’s tests, are aptly applied to discern noteworthy differences among the compared algorithms. Empirical findings consistently underscore the exceptional performance of mSHO across diverse benchmark functions, reinforcing its prowess in solving complex optimization problems. Furthermore, the robustness of mSHO endures even as the dimensions of optimization challenges expand, signifying its unwavering efficacy in navigating complex search spaces. The comprehensive results distinctly establish the supremacy and effic

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Galvanic Skin Response based Stress Detection System using Machine Learning and IoT

Galvanic Skin Response based Stress Detection System using M...

引用

Augmented Intelligence and Sustainable Systems (ICAISS), International Conference on

作者： Ayalapogu Ratna Raju R. Ramadevi Padamata Ramesh Babu Vetriselvi D Department of Computer Science and Engineering Mahatma Gandhi Institute of Technology Hyderabad Telangana India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical And Technical Sciences Chennai Tamil Nadu India Department of Computer Science and Engineering Koneru Lakshmaiah Educational Foundation Guntur Andhra Pradesh India Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai Tamil Nadu India

The primary objective of this study is to construct an Internet of Things (IoT)-based stress detection system that uses Galvanic Skin Response (GSR) and pulse sensors. In today's contemporary world, stress has developed into a widespread problem and early recognition of the condition is necessary for efficient intervention and treatment. The suggested system utilizes GSR and pulse sensors in conjunction with the IoT technologies to continuously monitor and analyze an individual's stress levels. The GSR sensor analyzes changes in the electrical conductance of the skin, which is known to occur during times of stress; in contrast, the pulse sensor identifies patterns in heart rate related to stress. Signal processing methods are used to process the newly collected sensor data, after which useful characteristics are retrieved. After the data has been analyzed, it is wirelessly sent to a cloud platform so that machine learning algorithms may be used for further analysis and categorization. The system displays the current amount of stress in real-time and can send warnings if the current stress level reaches a certain threshold. To guarantee that the system conforms to the rules, the system has established privacy and data security precautions. Our goal is to contribute, via this study, to the creation of an accurate and reliable stress detection system that may aid people in efficiently controlling the amounts of stress that they are experiencing in their lives.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Domain-Specific Assistant-Instruction on Psychotherapy Chatbot

SSRN

引用

SSRN 2023年

作者： Kang, Cheng Cheng, Yuqing Urbanova, Katerina Hu, Lihong Zhang, Yudong Hu, Yong Novak, Daniel Department of Cybernetics Czech Technical University Faculty of Mechanical Engineering Department of Energy Engineering in Prague Czech Republic Li Ka Shing Faculty of Medicine The University of Hong Kong Hong Kong Shenzhen Mental Health Centre Shenzhen China National Institute of Mental Health Prague Czech Republic School of Computing and Mathematical Sciences United Kingdom

Large language models (LLMs) have demonstrated impressive generalization capabilities throughfine-tuning on specific tasks with human-written instruction data. However, the limited quantity,diversity, and professional expertise of such instruction data raise concerns about the performanceof LLMs in psychotherapy tasks when provided with domain-specific instructions. To addressthis, we propose Domain-Specific Assistant Instructions based on AlexanderStreet therapy andcounseling data and fine-tune pre-trained LLMs on this dataset. Through quantitative evaluation oflinguistic quality using automatic and human evaluation, we observe that pre-trained LLMs finetunedon Psychotherapy Assistant Instructions outperform state-of-the-art LLMs response *** Assistant-Instruction approach offers a half-annotation method to align pre-trained LLMs withinstructions. We also release our large synthetic dataset, facilitating future studies on professionalinstruction tuning. © 2023, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Multi-method analysis of emotional and affective states

Multi-method analysis of emotional and affective states

引用

Progress in Applied Electrical engineering (PAEE)

作者： Adrian Luckiewicz Bogdan Ruszczak Mariusz Pelc Dariusz Mikołajewski Adam Sudoł Barbara Grochowicz Edward J. Gorzelanczyk Patryk Mendon Aleksandra Kawala-Sterniu Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Opole Poland Institute of Computer Science University of Opole Opole Poland School of Computing and Mathematical Sciences University of Greenwich London UK Institute of Computer Science Kazimierz Wielki University Bydgoszcz Poland Neuropsychological Research Unit 2nd Clinic of the Psychiatry and Psychiatric Rehabilitation Medical University in Lublin Lublin Poland Faculty of Natural and Technical Sciences University of Opole Opole Poland Institute of Philosophy Kazimierz Wielki University Bydgoszcz Poland

ISBN: (数字)9798331527563

ISBN: (纸本)9798331527570

This study explores the neurological basis of emotions using a multi-method approach, analysing functional near-infrared spectroscopy (fNIRS) data obtained from a 26-channel device. Author’s primary objective was to examine the brain’s response to tasks that provoke emotional, imagery and affective reactions through the observation of hemodynamic changes in data. By applying data processing methods and techniques, cerebral activations corresponding to different emotional states were shown. This research enriches comprehension of how emotion and imagery tasks are processed by the brain and offers insights into aspects of brain activity during emotionally charged engagements.

关键词： Electrical engineering Brain Data processing Hemodynamics Functional near-infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Driven Multi-Level Dynamical Fusion for Single-Cell Multi-Omics Cell Type Annotation

Multi-Task Driven Multi-Level Dynamical Fusion for Single-Ce...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jiawei Li Shizhan Chen Zongbo Han Wei Li Jijun Tang Fei Guo College of Intelligence and Computing Tianjin University Tianjin China College of Artificial Intelligence Nankai University Tianjin China Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen China School of Computer Science and Engineering Central South University Changsha China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The emergence of single-cell multi-omics sequencing technology has enabled the simultaneous profiling of diverse omics data within individual cells. It offers a more comprehensive perspective on cellular phenotypes and heterogeneity. However, single-cell multi-omics data are inherently high-dimensional and heterogeneous. Due to technical limitations and scarce starting materials, the data are often affected by noise and dropout effects. To address these challenges, we propose a novel multitask driven multi-level dynamical fusion algorithm for single-cell multi-omics cell type annotation, named scMMDyn. Our approach incorporates reconstruction and classification auxiliary tasks to guide the training of trustworthy modules at both the feature and modality levels. It executes dynamical fusion during these stages and finally achieves cross-modality fusion via an attention mechanism. This method effectively mitigates data quality issues through reconstruction tasks and feature-level dynamical fusion while providing interpretability at both feature and modality levels. Experimental results across diverse single-cell multi-omics datasets show that our method surpasses existing approaches in cell type annotation.

关键词： Training Sequential analysis Phenotypes Annotations Heuristic algorithms Data integrity Noise Multitasking Classification algorithms Reliability

来源：评论

学校读者我要写书评

暂无评论

ML-Powered Biomedical Signals Processing using Hybrid Filters

ML-Powered Biomedical Signals Processing using Hybrid Filter...

引用

Progress in Applied Electrical engineering (PAEE)

作者： Mariusz Pelc Dariusz Mikołajewski Patryk Mendoń Adrian Luckiewicz Adam Sudoł Edward Jacek Gorzelańczyk Aleksandra Kawala-Sterniuk Institute of Computer Science University of Opole Opole Poland School of Computing and Mathematical Sciences University of Greenwich London UK Institute of Computer Science Kazimierz Wielki University Bydgoszcz Poland Neuropsychological Research Unit 2nd Clinic of the Psychiatry and Psychiatric Rehabilitation Medical University in Lublin Lublin Poland Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Opole Poland Faculty of Natural and Technical Sciences University of Opole Opole Poland Institute of Philosophy Kazimierz Wielki University Bydgoszcz Poland

ISBN: (数字)9798331527563

ISBN: (纸本)9798331527570

This paper deals with the problem of signals filtering using hybrid filters. Such solutions may prove to be especially beneficial in the context of biomedical signals filtering where the signals’ amplitudes are typically not very high and they can be easily affected by different kinds of disturbances. Having a number of different types of filters tuned for some specific purposes we will show how the best filter choice is affected by selecting one ML model over another.

关键词： Electrical engineering Filters Biological system modeling Biomedical communication

来源：评论

学校读者我要写书评

暂无评论

Automated Pneumonia Classification Using DensePneumoNet in Chest CT Scans

Automated Pneumonia Classification Using DensePneumoNet in C...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： Ezhil E Nithila Bibin Christopher V J. Relin Francis Raj A Srinivasan N. Soundiraraj R. Santhana Krishnan Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Avadi Chennai India Department of Computing Technologies Faculty of Engineering and Technology School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Information Technology Velammal College of Engineering and Technology Madurai India Department of Electrical and Electronics Engineering PSNA College of Engineering and Technology Dindigul India Department of Electronics and Communication Engineering SCAD College of Engineering and Technology Cheranmahadevi India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

“DensePneumoNct” is a specialized deep learning algorithm designed for accurate and efficient detection of pneumonia from CT chest images. Leveraging the DenseNet architecture within TensorFlow, this algorithm demonstrates superior performance across critical metrics including accuracy, recall, precision, and F1 score. The implementation utilizes the ImageNet dataset, preprocessed to ensure standardization and resizing, optimizing input uniformity for robust model training. The DenseNet model architecture features dense blocks and transition layers, fostering strong feature propagation and effective downsampling of feature maps. Hyperparameter tuning, including a learning rate of 0.001, a batch size of 64, and training over 100 epochs, enhances model convergence and performance refinement. Training enhancements such as early stopping and learning rate scheduling further stabilize model training and prevent overfitting. Evaluation on a validation set showcases “DensePneumoNet”'s capability to distinguish COVID-19 pneumonia, viral pneumonia, and healthy lung tissues with unparalleled accuracy. Comparative analysis against ResNet-50, Inception-v3, SqueezeNet, and LeNet confirms DensePneumoNet's superiority in all evaluated parameters, affirming its efficacy for critical medical imaging tasks. “DensePneumoNet” represents a significant advancement in pneumonia detection, poised to enhance diagnostic accuracy and clinical decision-making in medical settings.

关键词： Training Measurement COVID-19 Pneumonia Accuracy Computed tomography Lung Standardization Medical diagnostic imaging Tuning

来源：评论

学校读者我要写书评

暂无评论

Access controls and Privacy Measures for Electronic Health Records: Security Perspective

Access Controls and Privacy Measures for Electronic Health R...

引用

International Conference on Emerging Trends in Networks and Computer Communications (ETNCC)

作者： Abdullah Mahfuzul Huda Mohammed Ayad Alkhafaji Raaid Alubady Ghassan Ahmed Ali Rajan Verma University Institute of Computing Chandigarh University Punjab India College of Computing and Informatics Saudi Electronic University Riyadh KSA College of Technical Engineering National University of Science and Technology Dhi Qar Iraq Technical Engineering College Al-Ayen University Thi-Qar Iraq College of Information Networks University of Babylon Babylon Iraq Faculty of Islamic Technology Universiti Islam Sultan Sharif Ali Negara Brunei Darussalam Division of Research and Development Lovely Professional University Phagwara KKR and KSR institute of technology and sciences Guntur Andhra Pradesh

ISBN: (数字)9798350353266

ISBN: (纸本)9798350353273

One of the main applications of ubiquitous computing is in healthcare. Cloud-based health apps have supplanted popular health apps in recent years, allaying worries about computational cost and scalability. Data security and privacy become major concerns in a cloud-based, ubiquitous health care system. The primary contribution of this study is providing high privacy, data confidentiality, and availability against health data. This is accomplished by utilizing the suggested access control model, which grants access control to different system users based on a PR-based technique. For every user and piece of data, a Privacy Rating (PR) is calculated before access to any requested data is granted. The findings demonstrate that the suggested strategy offers a high degree of security and privacy for the data kept in the healthcare system.

关键词： Access control Data privacy Privacy Scalability Data security Medical services Ubiquitous computing Market research Electronic medical records Information systems

来源：评论

学校读者我要写书评

暂无评论

Arabic Sentiment Analysis of Food Delivery Services Reviews

Arabic Sentiment Analysis of Food Delivery Services Reviews

引用

International Symposium on Networks, Computers and Communications (ISNCC)

作者： Dheya Mustafa Safaa M. Khabour Ahmed S. Shatnawi Eyad Taqieddin Dept. of Computer Engineering Faculty of Engineering The Hashemite University Zarqa Jordan Dept. of Information Systems Faculty of Information Technology and Computer Sciences Yarmouk University Irbid Jordan Dept. of Software Engineering Jordan University of Science & Technology Irbid Jordan Dept. of Cyber Security School of Computing and Informatics Al-Hussein Technical University Amman Jordan

Customer reviews on online platforms have grown to become an important source of insight into a company's performance. Food delivery services (FDS) companies aim to effectively use customers' feedback to identify areas for improvement of customer satisfaction. Although Arabic is becoming one of the most widely used languages on the Internet, only a few studies have focused on Arabic sentiment analysis to date. The present study conducts an extensive emotion mining and sentiment analysis on FDS-related reviews in Arabic, exploiting natural language processing, and machine learning techniques to extract information that reflects customers' subjective viewpoints, recognize their feelings, and determine polarity in the FDS domain. This work begins with collecting the FDS dataset (Talabat), and then extracting and creating a dialects lexicon for Arabic dialects, followed by walking the reader through detailed steps of cleaning and pre-processing a manually annotated dataset. Finally, we examined classification algorithms including Decision Tree (DT), and Support Vector Machine (SVM). We achieved a maximum accuracy of about 82% using the SVM classifier.

关键词：

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：