检索结果-内蒙古大学图书馆

2021 International Conference on Green Energy, Computing and Sustainable Technology, GECOST 2021

作者： Daengsi, Therdpong Muttisan, Bundit Wuttidittachotti, Pongpisit Sirawongphatsara, Patsita Rmutp Sustainable Industrial Management Engineering Bangkok Thailand Kmutnb Data Communication and Networking Bangkok Thailand Rmutto Department of Computer Science Thailand

ISBN: (纸本)9781665438650

This paper presents the development of an air mattress to prevent pressure ulcers in patients who have limited movement. The major part of this mattress is a set of re-used dialysis bags that are a kind of waste from hospitals. This mattress prototype has been developed using Arduino Nano boards, force sensitive resistor (FSR) sensors and diaphragm air compressors. After completion, the first version of the air mattress prototype was evaluated by experienced nursing workers as acceptable with a score of 3.24±0.75, based on 5-point scale, which means further improvements for the next version are required. © 2021 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Wireless Sensor Networks Optimization using Deep Q-Networks for Smart Energy Applications

Energy-Efficient Wireless Sensor Networks Optimization using...

引用

Trends in Material science and Inventive Materials (ICTMIM), International Conference on

作者： Satyanarayana Nimmala Nukala Sujata Gupta P Vasanth Sena K Koteswara Chari Md Aleem Pasha Bandi Rambabu Department of CSE (Data Science) CVR College of Engineering Hyderabad India Department of Computer Engineering Technology Chaitanya Bharati Institute of Technology (CBIT) Hyderabad India Department of CSE G. Narayanamma Institute of Technology and Science Hyderabad India Department of CSE Teegala Krishna Reddy Engineering College Hyderabad India Department of Mechanical Engineering Chaitanya Bharati Institute of Technology (CBIT) Hyderabad India Department of CSE CVR College of Engineering Hyderabad India

ISBN: (数字)9798331501488

ISBN: (纸本)9798331501495

Energy efficiency poses a significant difficulty in Wireless Sensor Networks (WSNs), especially within smart energy applications like smart grids, energy monitoring, and predictive maintenance. This study presents an adaptive optimization approach based on reinforcement learning utilizing Deep Q-Networks (DQN) to improve energy efficiency in Wireless Sensor Networks (WSNs) through the dynamic adjustment of transmission power and routing algorithms. The suggested model is trained and assessed utilizing the LEACH (Low-Energy Adaptive Clustering Hierarchy) dataset within a simulated NS-3 and MATLAB environment. The simulation configuration comprises 100 to 500 sensor nodes distributed inside a 100m x 100m region, each with differing energy limitations, utilizing the IEEE 802.15.4(Zigbee) communication protocol. The performance evaluation is carried out under varying traffic loads and network density, contrasting the proposed DQN-based optimization with classic LEACH, GA-based clustering, and Q-learning models. The results indicate a 27.5% enhancement in network longevity relative to LEACH, a 21.8% decrease in energy consumption per node, an 18.3% advancement in packet delivery ratio, and a 16.7% reduction in end-to-end latency, hence providing dependable data transfer. The findings underscore the efficacy of reinforcement learning in prolonging the lifespan of wireless sensor networks and enhancing energy efficiency, rendering it exceptionally appropriate for practical smart energy applications, including power grid monitoring, industrial IoT, and renewable energy management. The proposed DQN-based optimization dynamically adjusts transmission power and routing strategies, resulting in significant energy savings and improved network performance

关键词： Wireless sensor networks Adaptive systems Heuristic algorithms Telecommunication traffic Routing Energy efficiency Mathematical models Smart grids Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

Audio-Visual Target Speaker Extraction with Reverse Selective Auditory Attention

arXiv

引用

arXiv 2024年

作者： Tao, Ruijie Qian, Xinyuan Jiang, Yidi Li, Junjie Wang, Jiadong Li, Haizhou Department of Electrical and Computer Engineering National University of Singapore Singapore Department of Computer Science and Technology University of Science and Technology Beijing Beijing100083 China Chinese University of Hong Kong Shenzhen518172 China Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big data Shenzhen518172 China Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore University of Bremen 28359 Germany

Audio-visual target speaker extraction (AV-TSE) aims to extract the specific person’s speech from the audio mixture given auxiliary visual cues. Previous methods usually search for the target voice through speech-lip synchronization. However, this strategy mainly focuses on the existence of target speech, while ignoring the variations of the noise characteristics, i.e., interference speaker and the background noise. That may result in extracting noisy signals from the incorrect sound source in challenging acoustic situations. To this end, we propose a novel selective auditory attention mechanism, which can suppress interference speakers and non-speech signals to avoid incorrect speaker extraction. By estimating and utilizing the undesired noisy signal through this mechanism, we design an AV-TSE framework named Subtraction-and-ExtrAction network (SEANet) to suppress the noisy signals. We conduct abundant experiments by re-implementing three popular AV-TSE methods as the baselines and involving nine metrics for evaluation. The experimental results show that our proposed SEANet achieves state-of-the-art results and performs well for all five datasets. The code can be found in: https://***/TaoRuijie/*** © 2024, CC BY.

关键词： Background noise

来源：评论

学校读者我要写书评

暂无评论

Real-Time Signal Processing using AI Integrated Framework for Color and Drawing in Gesture Recognition 5

Real-Time Signal Processing using AI Integrated Framework fo...

引用

5th International Conference on Contemporary Computing and Informatics, IC3I 2022

作者： Lavania, Geerija Arya, Vivek Sharma, Neha Rashid, Mamoon Akram, Shaik Vaseem JECRC Artificial Intelligence & Data Science Department Rajasthan Jaipur India Dept of Electronics and Communication Engineering Haridwar India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India Vishwakarma University Department of Computer Engineering Pune India Uttaranchal Institute of Technology Uttaranchal University Dehradun India

ISBN: (纸本)9798350398267

In the realm of image processing and pattern recognition, writing with gestures in the air has grown in popularity and difficulty over the past few years. It contributes significantly to the creation of automation processes and can improve human-machine communication in a range of systems. Many studies focus on cutting-edge methods and techniques that will expedite processing while preserving a high level of identification accuracy. Internally, the area of computer vision considers object tracking to be crucial. Object tracking techniques are credited to modern computers, easy access to good-looking, affordable video cameras, and automated video analytics requirements. The video analysis technique generally consists of three fundamental steps: first, recognizing the object, second, tracking its movement from frame to frame, and third, assessing the behavior of that object. Each of the four takes into account a separate issue: choosing the best item representation, choosing the tracking function, purchasing the item, and tracking the item. Numerous real-world applications, such as autonomous monitoring, video identification, and vehicle navigation, depend heavily on object-tracking algorithms. This area is utilized by the research, which focuses on it to create a prospective text-to-text converter transition. This Research occasionally works as a freelance journalist. Your fingerprint will be tracked by a computer. The created text can be copied and used for a variety of things, including emails and SMS. For the deaf, it will be a potent means to establish this connection. By removing the need for writing, an efficient communication system decreases the use of the phone and laptop. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

AFDGCF: Adaptive Feature De-correlation Graph Collaborative Filtering for Recommendations

arXiv

引用

arXiv 2024年

作者： Wu, Wei Wang, Chao Shen, Dazhong Qin, Chuan Chen, Liyi Xiong, Hui School of Data Science University of Science and Technology of China Hefei China Guangzhou HKUST Fok Ying Tung Research Institute Guangzhou China School of Computer Science and Technology University of Science and Technology of China Hefei China Shanghai Artificial Intelligence Laboratory Shanghai China Career Science Lab BOSS Zhipin Beijing China PBC School of Finance Tsinghua University Beijing China Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Collaborative filtering methods based on graph neural networks (GNNs) have witnessed significant success in recommender systems (RS), capitalizing on their ability to capture collaborative signals within intricate user-item relationships via message-passing mechanisms. However, these GNN-based RS inadvertently introduce excess linear correlation between user and item embeddings, contradicting the goal of providing personalized recommendations. While existing research predominantly ascribes this flaw to the over-smoothing problem, this paper underscores the critical, often overlooked role of the over-correlation issue in diminishing the effectiveness of GNN representations and subsequent recommendation performance. Up to now, the over-correlation issue remains unexplored in RS. Meanwhile, how to mitigate the impact of over-correlation while preserving collaborative filtering signals is a significant challenge. To this end, this paper aims to address the aforementioned gap by undertaking a comprehensive study of the over-correlation issue in graph collaborative filtering models. Firstly, we present empirical evidence to demonstrate the widespread prevalence of over-correlation in these models. Subsequently, we dive into a theoretical analysis which establishes a pivotal connection between the over-correlation and over-smoothing issues. Leveraging these insights, we introduce the Adaptive Feature De-correlation Graph Collaborative Filtering (AFDGCF) framework, which dynamically applies correlation penalties to the feature dimensions of the representation matrix, effectively alleviating both over-correlation and over-smoothing issues. The efficacy of the proposed framework is corroborated through extensive experiments conducted with four representative graph collaborative filtering models across four publicly available datasets. Our results show the superiority of AFDGCF in enhancing the performance landscape of graph collaborative filtering models. The code is availabl

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

An Efficient Shortest Path Optimized Algorithm For Vehicle Adhoc Networks System

An Efficient Shortest Path Optimized Algorithm For Vehicle A...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： K. Shalini K. Harinath Reddy Kondalarao Punati Kavin K. S. P. Veena K. Pushpalatha Department of Artificial Intelligence and Data Science Vardhaman College of Engineering Shamshabad India Department of Electrical and Electronics Engineering Annamacharya Institute of Technology and Sciences Rajampet India Faculty of Electronics and Communication Engineering Hyderabad Institute of Technology and Management Hyderabad India Department of Electrical and Electronics Engineering Government College of Engineering Tirunelveli Tamilnadu India Department of Computer Engineering N. S. S. Polytechnic College Pandalam Pathanamthitta India Department of Computer Science and Engineering Coimbatore Institute of Engineering and Technology Coimbatore India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

VANET (Vehicular ad-hoc network) is a network of advanced automobiles designed to solve the problem of mobility and, as a result, reduce the number of accidents. Because VANET is a type of MANET (mobile ad hoc network) surrounded by human-driven nodes, the social concept can be used to explain VANET routing decisions. This motivates academics to look into the possibilities of using Social Network Analysis (SNA) to create routing strategies. The most critical problem in any system is parcel drop. Social characteristics-based architectures encounter comparable challenges, resulting in inefficient message delivery. In this research, the dragonfly method is used to the shortest path methodology for fixed line VANET with the purpose of reducing package drop and increasing network reliability. This is made achievable by sculpted system of values centralization analysis, which improves the decision via dragonfly optimization methodology. The behavior of the using nodes capability then be determined by the importance computation. In this study, the sustainability of the optimized shortest path system is measured in terms of End to End delay, Energy Consumption, Packet Loss, and Throughput. The dragonfly algorithm’s throughput evaluation is 650 kbps as compared to the traditional way.

关键词： Social networking (online) Vehicular ad hoc networks Transportation Routing Throughput Safety Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Advanced Deep Learning Method for Thyroid Nodule Detection and Evaluation in Ultrasound Images

Advanced Deep Learning Method for Thyroid Nodule Detection a...

引用

Intelligent data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Sesha Vidhya S Swagata Sarkar Rashmi B R Suseendra R Prakash Kumar P S Srimathi S Department of ECE RMK College of Engineering and Technology Department of Artificial intelligence and Data Science Sri Sairam Engineering College Sai Leo Nagar West Tambaram Chennai 44 Department of Computer Science and Engineering Raja Rajeswari College of Engineering Kumbalgodu Karnataka Department of Information Technology Panimalar Engineering College Department of Information Technology K S R Institute for Engineering and Technology Tiruchengode Namakkal Department of Bio Technology Saveetha School of Engineering SIMATS Chennai Tamilnadu India

Thyroid nodule detection in its earliest stages is a difficult endeavor. Thyroid nodule diagnosis requires a lot of time and effort if done manually. The original ultrasound imaging of thyroid nodules is very variable due to differences in equipment and technicians. The issue with nodules is determining whether or not they are cancerous. Thyroid nodule evaluation through ultrasonography is presently advised as the first line of treatment. Ultrasound imaging can be helpful in making a diagnosis; But this relies heavily on the proficiency of the radiologist. There is a great need for faster and more efficient automated techniques of screening ultrasound pictures. This research study presents a deep learning method to detect thyroid nodules quickly and accurately. Some image processing techniques are required for optimal utilization of ultrasound imaging data of thyroid nodules. In this study, authors used deep neural networks InceptionResnet V2 and image augmentation to create a system for autonomous thyroid nodule categorization. For testing, neural networks with four-layer network nodes and the Local Laplacian Filtering technique are used to improve the image quality. The proposed method's reliability is evaluated by using the Thyroid Digital Image database (TDID), a freely available dataset. The comparative findings demonstrate that the proposed method is superior to the current state of advancement in machine learning. Based on experiments, it is evident that the proposed technique has an Accuracy 0.99, Precision 0.98, Recall 0.96, Fl-Score 0.98, AVC-ROC 0.99.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting Breast Cancer: A Comparative Study of Various Machine Learning Models

Detecting Breast Cancer: A Comparative Study of Various Mach...

引用

engineering and Technology (PICET), Parul International Conference on

作者： Pawan Patil Bhushan Fulkar Mansi Sharma Rajendra Rewatkar Department of Artificial Intelligence and Data Science Datta Meghe institute of Higher Education and Research Wardha India Department of Computer Science and Design Datta Meghe institute of Higher Education and Research Wardha India Department of Biomedical Engineering Datta Meghe institute of Higher Education and Research Wardha India

ISBN: (数字)9798350369748

ISBN: (纸本)9798350369755

One of the deadliest illnesses in the world, cancer primarily affects women. Therefore, the primary goal of our research must be to cure cancer through scientific means. The secondary goal should be to detect cancer early on, as this can aid in the eventual removal of the cancer. After looking over 41 publications, we discovered that there are a number of methods for detecting cancer. In the medical field, detecting breast cancer is crucial since a correct diagnosis may greatly enhance patient outcomes. In order to assess how well different machine learning models identify breast cancer, we compare them all in this research. In particular, we contrast the Naive Bayes, Random Forest, Support Vector Machines (SVM), Logistic Regression, and Decision Tree methods. Our goal is to evaluate how well these algorithms classify cases of breast *** all the models studied, Random Forest performs better in terms of accuracy. Healthcare practitioners may find Random Forest to be a potential tool as it generates excellent accuracy rates in identifying breast cancer patients by utilizing its ensemble learning technique. Our comparative review provides useful details on the advantages and disadvantages of several machine learning methods for breast cancer. This research compares and contrasts several machine learning methods, including deep learning techniques, and finds that our suggested approach performs better than all of them.

关键词： Support vector machines Logistic regression Accuracy Machine learning Forestry Breast cancer Robustness Naive Bayes methods Ensemble learning Random forests

来源：评论

学校读者我要写书评

暂无评论

A New NVM Storage System with High Throughput Device Driver

A New NVM Storage System with High Throughput Device Driver

引用

IEEE International Conference on Big data and Cloud Computing (BdCloud)

作者： Tai Cai Jianfei Da Deiiao Niu Lei Li Jianchong Shi Ranzhuo Li School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China Department of Statistics and Data Science School of Science National University of Singapore Singapore Singapore

NVM device offers an effective way to solve the storage wall of the computer system, but its high read/write speed poses a significant challenge to the existing I/O software stack in Linux. This paper designs an effective BIO management strategy for NVM device driver and builds a high throughput NVM storage system to improve the concurrency and reduce BIO management overhead. First, a two-phase dynamic BIO management strategy module is proposed to separate BIO reception and execution, thereby improving the concurrency of BIO management in the NVM device driver. A lightweight BIO migration strategy is then designed to reduce the access number to NVM devices and improve the throughput of NVM device driver. Finally, based on Intel's open-source NVM device driver named PMEM, a high throughput NVM device driver named SVTNVM is implemented to build the new NVM storage system prototype. Some tests and analysis were carried out by using Filebench and Fio to simulate application workloads for evaluation. The results show that SVTNVM can improve IOPS by 29.3% and I/O bandwidth by 23.3% compared with current NVM storage system with PMEM.

关键词： Concurrent computing Linux Prototypes Full stack Bandwidth Throughput Device drivers

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Malware Detection in the Industrial Internet of Things: A Comprehensive Analysis

Deep Learning Approaches for Malware Detection in the Indust...

引用

Information Technology (ACIT)

作者： Ghassan Samara Mohammad Abu Fadda Abeer Al-Mohtaseb Raed Alazaidah Alrefai Mohamed N. Mahmoud Odeh Mohammad Aljaidi Mohammed Mahmod Shuaib Mohammad Kanan Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan Faculty of Information Technology Zarqa University Zarqa Jordan Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan Department of Mathematics Faculty of Science Zarqa University Zarqa Jordan Department of Industrial Engineering University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

This survey aims to identify hazards associated with the Internet of Things (IoT), focusing on malware that can infiltrate various devices, applications, and systems within the Industrial Internet of Things (IIoT). Such malware enables malicious actors to manipulate these systems. This research utilizes deep learning as a method for detecting malicious programs. Additionally, it provides hypotheses and background information on deep learning and the IIoT, along with an overview of the types of malware that can compromise IoT applications. Finally, the study presents findings related to the research hypotheses and relevant topics.

关键词： Deep learning Surveys Accuracy Focusing Malware Hazards Object recognition Information technology Industrial Internet of Things

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：