检索结果-内蒙古大学图书馆

3rd International Conference on Electronics and Sustainable Communication Systems, ICESC 2022

作者： Jayakarthik, R. Srinivasan, Aravindan Goswami, Sohan Shivaranjini Mahaveerakannan, R. Vels Institute of Science Technology and Advanced Studies School of Computing Sciences Dept of Comp Science India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering AP Vaddeswaram India Technique Polytechnic Institute West Bengal 712102 India Viswam Degree College Department of Computer Science Madanapalle India Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (数字)9781665479714

ISBN: (纸本)9781665479714

Elderly individuals worldwide have a significant risk of injury or death due to falls. An aged person's mobility, independence, and quality of life can be significantly impacted if he or she falls and does not receive timely assistance. This paper proposes the creation of a low-power network, smart devices, and cloud computing-based fall detection system for senior individuals in indoor spaces as part of this study. 10 volunteers volunteered to have their fall and non-fall movement data collected using a wireless telemetry surface electromyography capture system. Generative Adversarial Network (GAN) models use the effective signal segments as input. Notifications are automatically sent to caregivers of the elderly if a fall is detected, and an alert is triggered. As the final step, the system offers cloud-based services. There is a service that allows healthcare professionals to obtain the fall data for further examination from a medical standpoint. In experiments, fall detection has been found to be highly accurate, precise, and recallable. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

S2RNN: Self-Supervised Reconfigurable Neural Network Hardware Accelerator for Machine Learning Applications

TechRxiv

引用

TechRxiv 2023年

作者： Khalil, Kasem Dey, Bappaditya Bayoumi, Magdy Department of Electrical and Computer Engineering University of Mississippi Mississippi United States Kapeldreef 75 Leuven3001 Belgium Department of Electrical Engineering Assiut University Egypt The Center for Advanced Computer Studies University of Louisiana LafayetteLA United States Department of Electrical and Computer Engineering University of Louisiana LafayetteLA United States

Neural networks have been commonly used in different domains. Hardware implementation of the neural networks is challenging to fit different applications’ requirements. This often necessitates realizing different neural network FPGA configurations from the very scratch specific to a given application. This paper proposes a flexible method that can be reconfigured in a self-supervised way to fit several applications’ requirements, by providing only maximum available computational nodes a prior. The proposed method is based on reconfiguring the required number of hidden layers and hidden nodes of that layer based on a given application. Reconfigurability also allows to decide and update the number of active nodes, at layer (l+1), which receives computational results of lth layer nodes. A configuration block is used to send a signal to the control block which follows each node output. The control block decides which following nodes receive the output according to the corresponding signal value from the configuration block. Each node receives a signal to be enabled or disabled from the configuration block. Therefore, the number of inputs of each node and nodes in each layer is determined according to the desired performance. The goal here is to automatically propose the optimal NN configuration through reconfigurability to fit different applications, to achieve the maximum accuracy possible. The optimality can be demonstrated in terms of minimum average power, average delay, and area overhead as well as maximum throughput and accuracy. The main advantage of the proposed approach is the reusability of the optimized architecture (which is self-learned online) for the very first application/dataset, as the initial configuration for any new/next dataset/application rather than starting from scratch. We have demonstrated with experimental results, the proposed approach helps primarily to significantly reduce optimized architecture search cost (the number of online training i

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Enhancing Stock Price Prediction Through Integration of Astrological and Astronomical Data using XGBoost

Enhancing Stock Price Prediction Through Integration of Astr...

引用

3rd International Conference on Machine Learning and Data engineering, ICMLDE 2024

作者： Nair, Rekha R Babu, Tina Kishore, S. Vishal, S. Mahapatra, Sheila Department of Computer Science and Engineering Alliance School of Advanced Computing Alliance University Bengaluru India Department of Computer Applications Nitte Deemed to Be University Nitte Institute of Professional Education Karnataka Mangalore India Department of Computer Applications School of Engineering Dayananda Sagar University Bengaluru India Department of Electrical and Electronics Engineering Alliance University Bangalore India

Predicting stock prices continues to be a significant challenge in the financial industry, prompting researchers to investigate various methods to improve accuracy. Hence proposed a novel approach by incorporating astrological and astronomical data into XGBoost models for stock price classification and prediction, utilizing deep neural networks (DNN). The dataset is collected from NASA JPL Horizons and Jaganath Hora software. The raw data is preprocessed with feature engineering, data cleaning, []and normalization to obtain a better forecasting stock prices and classification results. The proposed data executed with machine learning models, such as logistic regression, decision trees, random forest, SVM, XGB Classifier, LSTM, RNN, and CNN other than XGB Regressor for the forcasting. The proposed research is evaluated for classification with accuracy, precision, recall, F1 score, and forecasting with RMSE, MAE, R2, AIC, and BIC. The XGBoost classifier achieved 99% accuracy in predicting stock market movements, surpassing other models in determining whether the next day's stock price would be higher or lower than the previous day's price, while the DNN performed the best among all algorithms for overall stock price prediction. This approach could influence investment strategies, potentially affecting wealth distribution and financial market stability. © 2025 The Authors. Published by Elsevier B.V.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Energetic and Smart Design of Battery Management Scheme to Improve the Lifetime of Electric Vehicles

Energetic and Smart Design of Battery Management Scheme to I...

引用

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Varatharaju, V.M. Chidambaranathan, C.M. Karthik, Mamidala Vijay Sathi, G. Pandi, V. Samuthira Shobana, D. University of Technology and Applied Science Electrical Section Engineering Department Ibra Oman Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu India Cmr Engineering College Department of Electrical & Electronics Engineering Telangana Hyderabad India Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechanical Engineering Tamil Nadu Chennai India Chennai Institute of Technology Centre for Advanced Wireless Integrated Technology Tamil Nadu Chennai India Rajalakshmi Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350313987

In order to maximize efficiency, electric vehicles use Battery Management Systems (BMS) to manage their rechargeable batteries. The battery's safety and dependability are ensured by the battery management system, and the battery's age is extended without being damaged. Various monitoring methods are used to keep track of the battery pack's charging capacity, voltage-levels, current-ratings and ecological pressure ratio. A variety of analogue and digital sensors are employed with microcontrollers for this purpose. Several powerful batteries have been developed as a result of the tremendous advances in the field of batteries over the past ten years. High-power batteries with suitable battery management systems are essential for the safe and reliable operation of Electric Vehicles (EVs). This paper will address the power sources utilized by electric automobiles and the primary problems of battery control systems, as well as compare both the lithium ion battery as well as the metal based nickel-hydride batteries in regards to growing older along with the impact caused by climate through the use of the State-of-Charge (SOC) and closed device electricity. This study's goal is to compare and contrast different intelligence techniques along with the control methods used in electric vehicle battery management platforms. The study assesses the characteristics, structure, configuration, accuracy, benefits, and downsides of intelligent algorithms for estimating the condition of a battery. Focusing on parts, characteristics, aims, outcomes, advantages, and restrictions, this research analyses the various controllers used for warming, cooling, balancing, and protecting batteries. © 2023 IEEE.

关键词： Battery Management Systems BMS Electric Vehicles EVs SOC State-of-Charge

来源：评论

学校读者我要写书评

暂无评论

Rural Road Pavement Panel Detection with Unmanned Aerial Vehicles

Rural Road Pavement Panel Detection with Unmanned Aerial Veh...

引用

International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM)

作者： Melody Mae O. Maluya Earl Ryan M. Aleluya Francis Jann A. Alagon Steve E. Clar Carl John O. Salaan Joel G. Opon Maria Fe P. Bahinting Department of Computer Applications College of Computer Studies Department of Computer Engineering and Mechatronics College of Engineering Department of Electrical Engineering College of Engineering Graduate School of Engineering Department of Civil Engineering College of Engineering Mindanao State University-Iligan Institute of Technology Iligan City Philippines

ISBN: (数字)9798350381177

ISBN: (纸本)9798350381184

Since they connect major population and economic hubs across borders, roads and transportation play a crucial role in a nation's economy. Crash and accident rates are a direct result of poor and substandard road conditions. Road inspectors can better plan repair and assessment tasks with the help of the Pavement Maintenance System (PMS). Distress detection surveys are still carried out manually in developing nations. However, manual road inspection techniques carried out on the ground are dangerous, time-consuming, and labor-intensive. Unmanned aerial vehicles (UAVs) offer the flexibility and manoeuvrability to swiftly visually inspect the damaged area and gather the required data without endangering human safety. Surveyors would therefore be better able to assess the state of road pavement in rural areas if pavement panel detection using unmanned aerial vehicles (UAVs) was implemented. In this study, the precision, recall, and latency of the YOLOv7 and YOLOv8 instance segmentation models for pavement panel detectors were examined. This paper also introduced a new dataset of UAV images from complex and unstructured road environments within the highway areas in the Philippines. The findings indicate that YOLOv8 performed better, with a latency of 84.65 ms, a precision of 97.36% ±0.002, and a recall of 98.71 %±0.004. Road users and managers may benefit from an accelerated pavement assessment process in rural areas thanks to the suggested pavement panel detection model.

关键词： Instance segmentation YOLO Surveys Roads Biological system modeling Transportation Inspection

来源：评论

学校读者我要写书评

暂无评论

A Unified Approach for Binary-Class and Multi-Class Data Augmented Generation

A Unified Approach for Binary-Class and Multi-Class Data Aug...

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Frederic Rizk Rodrigue Rizk Dominick Rizk Patrick Rizk Chee-Hung Henry Chu The Center for Advanced Computer Studies University of Louisiana at Lafayette Lafayette LA U.S.A. Department of Computer Science University of South Dakota Vermillion SD U.S.A. Department of Electrical Engineering and Computer Science The Catholic University of America Washington DC U.S.A. Department of Mechanical Engineering University of Quebec at Trois-Rivières Drummondville QC Canada The Center for Advanced Computer Studies Informatics Research Institute University of Louisiana at Lafayette Lafayette LA U.S.A.

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

Deep neural networks excel in a wide range of tasks but require diverse datasets to prevent overfitting. Overfitting occurs when a network fits training data too precisely, leading to poor generalization. Data Augmentation is often used to mitigate overfitting aiming at enlarging and improving the quality of training datasets, facilitating the construction of superior deep learning models. MAGAN algorithm emerges as an innovative approach that functions as a Meta-Analysis of Generative Adversarial Networks (GANs). MAGAN harnesses the latent space capabilities of GANs to confront the challenges presented by binary-class, multi-class, grayscale, and RGB images, effectively covering a wide spectrum of scenarios. In this paper, we propose the use of MAGAN algorithm for binary-class and multi-class data augmented generation. We also undertake an in-depth experimental analysis, evaluating the performance of the proposed MAGAN-based approach in comparison to two alternative baseline scenarios: one without any augmentation and another utilizing a conventional augmentation method. To gauge the effectiveness of the proposed technique, we employed diverse classification metrics, including accuracy, loss, precision, recall, F1-score, and the confusion matrix. Our results demonstrate that the proposed approach surpasses the other two scenarios achieving improvements in terms of accuracy by a factor of x1.15 and x1.03, respectively. This underscores the significant advantages of harnessing MAGAN, a meta-analysis of GANs, for data augmentation across a range of image types and classification tasks.

关键词： Deep learning Measurement Accuracy Training data Artificial neural networks Gray-scale Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Emotion and Gesture Recognition System for Humans and Animals Using computer Vision and Deep Learning

Multi-Modal Emotion and Gesture Recognition System for Human...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： Rekha R Nair Tina Babu Kishore S Smitha Shivaswamy Aruna S Manchikalapudi Bhargavi Department of Computer Science and Engineering Alliance School of Advanced Computing Alliance University Bengaluru India Department of Computer Application Nitte Institute of Professional Education Nitte(Deemed to be University) Mangaluru Karnataka India Department of Computer Applications Acharya Institute of Technology Bengaluru India School of Science and Computer studies CMR University Bangalore India Department of Computer Science and Engineering(AIML) Malla Reddy College of Engineering and Technology Hyderabad India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Emotion recognition through facial expressions and gesture analysis has emerged as a key area of research in computer vision and human-computer interaction. The ability to automatically detect and classify human emotions has wide-ranging applications, from enhancing user experiences to improving mental health monitoring and surveillance systems. This project builds on this background to develop a comprehensive system for recognizing emotions and gestures in both humans and animals. The system integrates facial emotion recognition, hand gesture interpretation, and animal emotion detection into a single platform. Using advanced deep learning models and computer vision libraries, the system classifies facial expressions into categories such as happiness, sadness, anger, fear, surprise, and neutral. The gesture recognition component interprets hand signals to convey messages like “need help” or “need water.” An innovative aspect of this work is the extension of emotion recognition to animals, particularly focusing on species like dogs and monkeys. Implemented primarily in Python, the system leverages libraries such as OpenCV and DeepFace. By combining these different modalities of nonverbal communication analysis, the project presents a versatile solution with potential applications in human-computer interaction, mental health monitoring, security, and animal welfare.

关键词： Hands Human computer interaction Emotion recognition computer vision Accuracy Animals Face recognition Computational modeling Gesture recognition Mental health

来源：评论

学校读者我要写书评

暂无评论

Stimulating creativity and grit of high school students with creative STEM activities: an RCT with noncompliance

引用

Quality and Quantity 2024年第1期59卷 605-634页

作者： Ballerini, Veronica Dominici, Alice Ferracane, Martina Francesca Menchetti, Fiammetta Noirjean, Silvia Department of Statistics Computer Science Applications “G. Parenti” University of Florence Florence Italy Department of Economics European University Institute Fiesole Italy Dondena Centre for Research on Social Dynamics and Public Policy Bocconi University Milan Italy School of Computing Engineering & amp Digital Technologies Teesside University Middlesbrough United Kingdom Robert Schuman Centre for Advanced Studies European University Institute Fiesole Italy

Creativity and grit are widely recognized as vital components for the success and prosperity of individuals, even more so for younger people who will have to deal with the complex challenges connected to the digital era. Yet, whether these skills can be learnt or are innate traits is still subject to debate, which is further complicated by the difficulty of defining and, in turn, assessing these concepts. In this study, we challenge the idea that creativity and grit cannot be learnt and show that creative pedagogy activities, such as those offered by FabLabs, are powerful tools to enhance these non-cognitive skills. We conduct a randomized controlled trial in which 710 students from five Italian high schools are randomly assigned to creative STEM courses. The courses are delivered by FabLabs, small-scale workshops that offer access to tools for digital fabrication and employ a hands-on pedagogical approach expected to impact students’ creativity and grit positively. Assignment to the courses is at the class level: only students in classes randomly selected to join the Fablab activities can participate, and they may decide whether to enrol or not on a voluntary basis. We address noncompliance by adopting an instrumental variable approach. We use two modalities to measure creativity: a self-assessment through the Short Scale of Creative Self and an assessment made by an independent expert using an index of creativity developed by the authors. While the effect on self-assessed creativity is not significant, results show that the external, independent assessment of students’ creativity can capture a significant effect of Fablabs’ courses. It also emerges that FabLab activities have a positive significant effect on students’ grit, measured through the Duckworth scale. The encouraging results obtained for a relatively small sample of students should prompt a replication of the experiment on a broader scale. © The Author(s) 2024.

关键词： Causal inference Creative pedagogy FabLabs Instrumental variables Noncompliance

来源：评论

学校读者我要写书评

暂无评论

A Music Recommender System to Identify the Emotional State of a Person Using Machine Learning Algorithms

A Music Recommender System to Identify the Emotional State o...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Muruganantham A C. Malarvizhi Divya Vahini. S D. Saranya A. Uthiramoorthy Department of Computer Science (PG) Kristu Jayanti College Bengaluru Karnataka India Department of Computer Science PSG Institute of Advanced Studies Coimbatore India Department of Computer Applications Dr.Mahalingam College of Engineering and Technology Pollachi Tamil Nadu India Department of Information Technology Sri Eshwar College of Engineering Coimbatore Department of Computer Science Rathinam College of Arts and Science

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

In today's digital world, customized recommendation algorithms can improve user experiences in many different areas. Within the sphere of intelligent human-technology interaction, this paper specifically examines a music recommender system driven by machine learning algorithms. It figures out what mood users are in and can provide an appropriate response in real time. The system being propounded in this essay uses advanced technology in facial expression recognition. With the help of a webcam, it aims to accurately detect user emotions, including joy, sadness, and anger. Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN) and Support Vector Machines (SVM) have been employed to effectively classify people's mood and recommend an appropriate song. Our extensive tests and examinations show that CNN, RNN, and SVM models are all very good at guessing users' moods--with high precision, recall, F1-score, and accuracy percentages. Furthermore, in-depth analyses like confusion matrixes illuminate how well each model serves as an emotion recognizer. This study's findings are representative of future prospects in affective computing around the globe with major implications for intelligent recommendation systems to which it's important that the models are sensitive. In conclusion, the suggested Music Recommender System is something new for taking a more personal view: We can be as deeply entertained as the web allows us to be--make tailored entertainment paths in the digital era.

关键词： Support vector machines Emotion recognition Recurrent neural networks Machine learning algorithms Accuracy Mood Face recognition Computational modeling Convolutional neural networks Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Wireless Information and Energy Transfer in the Era of 6G Communications

arXiv

引用

arXiv 2024年

作者： Psomas, Constantinos Ntougias, Konstantinos Shanin, Nikita Xu, Dongfang Mayer, Kenneth Tran, Nguyen Minh Cottatellucci, Laura Choi, Kae Won Kim, Dong In Schober, Robert Krikidis, Ioannis The Department of Electrical and Computer Engineering University of Cyprus Nicosia Cyprus The Institute for Digital Communications Department of Electrical Engineering Friedrich-Alexander Universität Erlangen-Nürnberg Germany The Academy of Interdisciplinary Studies The Hong Kong University of Science and Technology Hong Kong The Department of Electrical and Computer Engineering School of Information and Communication Engineering Sungkyunkwan University Suwon Korea Republic of The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of

Wireless information and energy transfer (WIET) represents an emerging paradigm which employs controllable transmission of radio-frequency signals for the dual purpose of data communication and wireless charging. As such, WIET is widely regarded as an enabler of envisioned 6G use cases that rely on energy-sustainable Internet-of-Things (IoT) networks, such as smart cities and smart grids. Meeting the quality-of-service demands of WIET, in terms of both data transfer and power delivery, requires effective co-design of the information and energy signals. In this article, we present the main principles and design aspects of WIET, focusing on its integration in 6G networks. First, we discuss how conventional communication notions such as resource allocation and waveform design need to be revisited in the context of WIET. Next, we consider various candidate 6G technologies that can boost WIET efficiency, namely, holographic multiple-input multiple-output, near-field beamforming, terahertz communication, intelligent reflecting surfaces (IRSs), and reconfigurable (fluid) antenna arrays. We introduce respective WIET design methods, analyze the promising performance gains of these WIET systems, and discuss challenges, open issues, and future research directions. Finally, a near-field energy beamforming scheme and a power-based IRS beamforming algorithm are experimentally validated using a wireless energy transfer testbed. The vision of WIET in communication systems has been gaining momentum in recent years, with constant progress with respect to theoretical but also practical aspects. The comprehensive overview of the state of the art of WIET presented in this paper highlights the potentials of WIET systems as well as their overall benefits in 6G networks. Copyright © 2024, The Authors. All rights reserved.

关键词： Energy transfer

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：