检索结果-内蒙古大学图书馆

Energy Aware Metaheuristic Optimization with Location Aided Routing Protocol for MANET

computers, Materials & Continua 2022年第4期71卷 1567-1580页

作者： E.Ahila Devi K.C.Ramya K.Sathesh Kumar Sultan Ahmad Seifedine Kadry Hyung Ju Park Byeong-Gwon Kang Department of Instrumentation and Control Engineering St.Joseph’s College of EngineeringChennai600119India Department of Electrical and Electronics Engineering Sri Krishna College of Engineering and TechnologyCoimbatore641008India School of Computing Kalasalingam Academy of Research and EducationKrishnankoil626128India Department of Computer Science College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAlkharj11942Saudi Arabia Department of Applied Data Science Noroff University CollegeKristiansand4612Norway Department of ICT Convergence Soonchunhyang UniversityAsan31538Korea

A mobile ad hoc network(MANET)involves a group of wireless mobile nodes which create an impermanent network with no central authority and *** nodes in the MANET are highly mobile and it results in adequate network topology,link loss,and increase the re-initialization of the route discovery *** planning in MANET is a multi-hop communication process due to the restricted transmission range of the *** aided routing(LAR)is one of the effective routing protocols in MANET which suffers from the issue of high energy *** few research works have focused on resolving energy consumption problem in LAR,energy efficiency still remains a major design *** this aspect,this study introduces an energy aware metaheuristic optimization with LAR(EAMO-LAR)protocol for *** EAMO-LAR protocol makes use of manta ray foraging optimization algorithm(MRFO)to help the searching process for the individual solution to be passed to the LAR *** fitness value of the created solutions is determined next to pass the solutions to the objective *** MRFO algorithm is incorporated into the LAR protocol in the EAMO-LAR protocol to reduce the desired energy *** ensure the improved routing efficiency of the proposed EAMO-LAR protocol,a series of simulations take *** resultant experimental values pointed out the supreme outcome of the EAMO-LAR protocol over the recently compared *** resultant values demonstrated that the EAMO-LAR protocol has accomplished effectual results over the other existing techniques.

关键词： MANET routing lar protocol energy efficiency mrfo algorithm metaheuristics

来源：评论

学校读者我要写书评

暂无评论

Extreme Learning Machine for Breast Cancer Diagnosis using cloud computing

Extreme Learning Machine for Breast Cancer Diagnosis using c...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Muller, Priya Shirley Prasad, Mudarakola Lakshmi Sikrant, Poornima A Reddy, Pundru Chandra Shaker Sharma, Swati Sharma, Nipun Sathyabama Institute of Science and Technology Department of Mathematics Chennai India Institute of Aeronautical Engineering Computer Science and Engineering Telangana Dundigal India Sri Ramachandra Institute of Higher Education and Research Sri Ramachandra Faculty of Management Sciences Tamilnadu Chennai India Sr University School of Computer Science and Artificial Intelligence Telangana Warangal506371 India Presidency University Bangalore School of Computer Science Engineering and Information Science Karnataka India

ISBN: (纸本)9798350309140

Worldwide, breast cancer ranks high among women's leading causes of mortality. The likelihood of mortality from breast cancer can be decreased with early detection and rapid treatment. Among those residing in rural regions with limited access to healthcare, machine learning on the cloud is currently playing a crucial role in illness diagnosis. Machine learning-based diagnostic systems can supplement radiologists' work as secondary readers to ensure accurate illness diagnosis, while cloud-based systems can facilitate remote diagnostics and telehealth services. The potential of artificial neural networks (ANN)-based techniques for illness diagnosis has piqued the interest of numerous academics. Among the many ANN versions, extreme learning machine (ELM) stands out as a promising candidate for tackling a wide range of classification issues. Three distinct areas of study are brought together in the suggested framework of this work: The first area where ELM is used is in the detection of breast-cancer. Next, the gain-ratio feature selection strategy is utilized to remove features that are not significant. Finally, this research offers an ELM-based CC-approach for remote breast-cancer diagnostics. Several cutting-edge technologies for illness diagnosis are contrasted with the cloud-based ELM's performance. The outcomes obtained on the Wisconsin-Diagnostic-Breast-Cancer(WBCD) dataset demonstrate that the ELM technique hosted in the cloud surpasses alternative approaches. When comparing ELM's performance in both the standalone and cloud contexts, the former proved to be superior. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Human Activity Recognition Based on Smartwatch Sensors Using Branch Convolutional Neural Networks 1

引用

15th Multi-disciplinary International Conference on Artificial Intelligence, MIWAI 2022

作者： Hnoohom, Narit Maitrichit, Nagorn Mekruksavanich, Sakorn Jitpattanakul, Anuchit Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Mahidol University Nakorn Pathom Thailand Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9783031209925

ISBN: (纸本)9783031209918

Human activity recognition (HAR) has become a popular research topic in artificial intelligence thanks to the development of smart wearable devices. The main goal of human activity recognition is to efficiently recognize human behavior based on available data sources such as videos and images, including sensory data from wearable devices. Recently, HAR research has achieved promising results using learning-based approaches, especially deep learning methods. However, the need for high performance is still an open problem for researchers proposing new methods. In this work, we investigated the improvement of HAR by hierarchical classification based on smartwatch sensors using deep learning (DL) methods. To achieve the research goal, we introduced branch convolutional neural networks (B-CNNs) to accurately recognize human activities hierarchically and compared them with baseline models. To evaluate the deep learning models, we used a complex HAR benchmark dataset called WISDM-HARB dataset that collects smartwatch sensor data from 18 physical activities. The experimental results showed that the B-CNNs outperformed the baseline convolutional neural network (CNN) models when the hierarchical connection between classes was not considered. Moreover, the results confirmed that branch CNNs with class hierarchy improved the recognition performance with the highest accuracy of 95.84%. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Systematic Approach for the Prediction of Personality Based on Attention Enhanced GCNN and LSTM Approach 2

A Systematic Approach for the Prediction of Personality Base...

引用

2nd International Conference on Edge Computing and Applications, ICECAA 2023

作者： Sharma, Prashant Sagvekar, Vijaya Alone, Vinod N. Krishna, P. Vamsi Thulasimani, T. Sethumadhavan, R. Mandsaur University Faculty of Engineering Department of Computer Science and Engineering Madhya Pradesh Mandsaur India Pacific Academy of Higher Education and Research University Pacific Hills Computer Engineering India Vppcoe & Va Computer Engineering Department Sion Maharashtra Mumbai India School of Management Malla Reddy University Telangana Hyderabad India Bannari Amman Institute of Technology Department of Mathematics Erode Tamilnadu Sathyamangalam India Dayananda Sagar College of Engineering Department of Management Studies Karnataka Bangalore India

ISBN: (纸本)9798350347579

Individuals can be distinguished from one another in significant ways, and one such way is by one's personality. Predicting someone's character traits is a perennial topic of study. Personality prediction using social media data has great potential because it eliminates the need for users to fill out lengthy questionnaires, saving both time and improving the method's trustworthiness. As a result, understanding personality is a topic that piques the curiosity of scientists. There are many real-world uses for personality prediction. The popularity of social media platforms continues to grow. Every day, more and more pictures and text are uploaded on the internet. Most recent efforts have been concentrated on feature extraction, feature selection, and model training. The proposed method employs AGCNN-LSTM for measuring performance. The suggested model performs better than the CNN and LSTM models against which it is benchmarked. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Badminton Activity Recognition and Player Assessment based on Motion Signals using Deep Residual Network 13

Badminton Activity Recognition and Player Assessment based o...

引用

13th IEEE International Conference on Software engineering and Service Science, ICSESS 2022

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Hnoohom, Narit Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand Faculty of Engineering Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Nakhon Pathom Thailand Faculty of Applied Science King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Bangkok Thailand

ISBN: (数字)9781665410328

ISBN: (纸本)9781665410311

With the fast expansion of digital technologies and sporting events, interpreting sports data has become an immensely complicated endeavor. Internet-sourced sports big data exhibit a significant development trend. Big data in sports offer a wealth of information on sportspeople, coaching, athletics, swimming, and badminton. Today, various sports data are freely accessible, and incredible data analysis tools based on wearable sensors have been established, allowing us to investigate the usefulness of these data thoroughly. In this research, we investigate the detection of badminton action and player evaluation based on movement data captured by wearable sensors. Movement data captured by an accelerometer, gyroscope, and magnetometer are utilized for training and validating a classification model for badminton actions. In addition, the movement signals are used to train a player evaluation model employing a deep residual network. To assess our suggested technique, we utilized a publicly available benchmark dataset consisting of inertial measurement unit (IMU) sensors attached to every investigator's dominant wrist, palm, and both legs. The experimental findings indicate that the proposed deep residual network obtained good performance with a maximum accuracy of 98.00% for identifying badminton activities and 98.56% for evaluating badminton players. © 2022 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Design of Evolutionary Algorithm Based Unequal Clustering for Energy Aware Wireless Sensor Networks

引用

computer Systems Science & engineering 2023年第10期47卷 1283-1297页

作者： Mohammed Altaf Ahmed T.Satyanarayana Murthy Fayadh Alenezi E.Laxmi Lydia Seifedine Kadry Yena Kim Yunyoung Nam Department of Computer Engineering College of Computer Engineering&SciencesPrince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Chaitanya Bharathi Institute of Technology HyderabadTelanganaIndia Department of Electrical Engineering College of EngineeringJouf UniversitySakaka 72388Saudi Arabia Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Applied Data Science Noroff University CollegeKristiansandNorway Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjmanUnited Arab Emirates Department of ICT Convergence Soonchunhyang UniversityAsan 31538Korea

Wireless Sensor Networks(WSN)play a vital role in several real-time applications ranging from military to *** the benefits of WSN,energy efficiency becomes a major part of the challenging issue in WSN,which necessitate proper load balancing amongst the clusters and serves a wider monitoring *** clustering technique for WSN has several benefits:lower delay,higher energy efficiency,and collision *** clustering protocol has several *** a large-scale network,cluster-based protocols mainly adapt multi-hop routing to save energy,leading to hot spot problems.A hot spot problem becomes a problem where a cluster node nearer to the base station(BS)tends to drain the energy much quicker than other nodes because of the need to implement more *** article introduces a Jumping Spider Optimization Based Unequal Clustering Protocol for Mitigating Hotspot Problems(JSOUCP-MHP)in *** JSO algorithm is stimulated by the characteristics of spiders naturally and mathematically modelled the hunting mechanism such as search,persecution,and jumping skills to attack *** presented JSOUCPMHP technique mainly resolves the hot spot issue for maximizing the network *** JSOUCP-MHP technique elects a proper set of cluster heads(CHs)using average residual energy(RE)to attain *** addition,the JSOUCP-MHP technique determines the cluster sizes based on two measures,i.e.,RE and distance to BS(DBS),showing the novelty of the *** proposed JSOUCP-MHP technique is examined under several experiments to ensure its *** comparison study shows the significance of the JSOUCPMHP technique over other models.

关键词： Wireless sensor networks energy efficiency cluster heads unequal clustering hot spot issue lifetime enhancement

来源：评论

学校读者我要写书评

暂无评论

Multi-resolution CNN for Lower Limb Movement Recognition Based on Wearable Sensors 1

引用

15th Multi-disciplinary International Conference on Artificial Intelligence, MIWAI 2022

作者： Hnoohom, Narit Chotivatunyu, Pitchaya Mekruksavanich, Sakorn Jitpattanakul, Anuchit Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Mahidol University Nakorn Pathom Thailand Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9783031209925

ISBN: (纸本)9783031209918

Human activity recognition (HAR) remains a difficult challenge in human-computer interaction (HCI). The Internet of Healthcare Things (IoHT) and other technologies are expected to be used primarily in conjunction with HAR to support healthcare and elder care. In HAR research, lower limb movement recognition is a challenging research topic that can be applied to the daily care of the elderly, fragile, and disabled. Due to recent advances in deep learning, high-level autonomous feature extraction has become feasible, which is used to increase HAR efficiency. Deep learning approaches have also been used for sensor-based HAR in various domains. This study presents a novel method that uses convolutional neural networks (CNNs) with different kernel dimensions, referred to as multi-resolution CNNs, to detect high-level features at various resolutions. A publicly available benchmark dataset called HARTH was used to evaluate the recognition performance to collect acceleration data of the lower limb movements of 22 participants. The experimental results show that the proposed approach improves the F1 score and achieves a higher score of 94.76%. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Single-and Multiuser Virtual Reality Training for Forklift Driving 2

Single-and Multiuser Virtual Reality Training for Forklift D...

引用

2nd IEEE International Conference on Cognitive Aspects of Virtual Reality, CVR 2023

作者： Froland, Tord Hettervik Ravyse, Werner Luimula, Mika Heldal, Ilona Western Norway University of Applied Sciences Chemistry and Biomedical Laboratory Sciences Department of Safety Bergen Norway School of ICT: Futuristic Interactive Technologies Research Group Turku University of Applied Sciences Turku Finland Western Norway University of Applied Sciences Department of Computer Science Electrical Engineering and Mathematical Sciences Bergen Norway

ISBN: (纸本)9798350338638

Hands-on skills training is a constant requirement in a multitude of practical work settings and virtual reality (VR) is often found to be a valuable training opportunity to safely prepare students for their future work environments. One of the main benefits of utilizing VR-based training is providing high grades of presence and involvement. Although the user experiences of students are a key factor that impacts the use of a VR simulation, it becomes more challenging to decide whether single-or multi-user experiences should be planned and developed. This paper presents the results from a between-subjects case study comparing the user experiences of single-and multi-user VR training for forklift driving. Findings highlight the importance of considering various aspects of VR technology to design VR training environments for high user experiences, including the impact of age, group dynamics, and freedom of movement in the environment. The benefits and challenges of single-and multi-user VR training for high experiences and implications for utilizing serious games in VR-based training are discussed. © 2023 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Enhancing Oral Cancer Screening with Deep Learning Algorithms 1

Enhancing Oral Cancer Screening with Deep Learning Algorithm...

引用

1st International Conference on Computing, Sciences and Communications, ICCSC 2024

作者： Bhaskar, Attarde Viren Soujanya, A. Ramal, P. Janaki Santhana Lakshmi, S. Nithyakalyani, K. Kumar, Bharathi Ramesh Dr. D.Y. Patil Medical College Hospital & Research Centre Pimpri Department of Critical Care Medicine Pune India CVR College of Engineering Ibrahimpatnam Department of Computer Science and Engineering Telangana India Saveetha Engineering College Chennai Department of Computer Science Engineering Tamil Nadu India Mohamed Sathak A.J.college of Engineering Siruseri Department of Computer Science and Engineering Chennai India Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College Chennai Department of Biomedical Engineering Tamil Nadu India Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Avadi Department of Mathematics Chennai India

ISBN: (纸本)9798350353648

The majority of the conventional approaches used in current oral cancer screening methods, such as biopsy and visual inspection, result in late-stage detection, high false-positive/negative rates, and higher healthcare expenses. These techniques need specialized staff and are labor-intensive and subjective. To improve diagnostic speed and accuracy, the research offers a unique approach that makes use of deep learning methods, particularly Transformer models and Hybrid Neural Networks (HNNs). To enhance input quality, the system incorporates sophisticated image preparation methods such as data augmentation and normalization. While HNNs integrate Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for robust feature extraction and temporal analysis, Transformers use attention techniques to extract contextual information. Its potential for early and accurate oral cancer detection is highlighted by the results, which show a significant improvement in detection accuracy (94% vs. 80-85% in existing systems), sensitivity (90% vs. 70-78%), and specificity (92% vs. 75-82%), along with a reduction in processing time to just 2 minutes. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Networks for Eating and Drinking Recognition based on Smartwatch Sensors

Deep Learning Networks for Eating and Drinking Recognition b...

引用

2022 research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2022

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Hnoohom, Narit Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (数字)9781665473248

ISBN: (纸本)9781665473248

Smartwatches are becoming more popular for recognizing and monitoring human actions in everyday life. These wearable devices are equipped with various IMU sensors for ubiquitous data processing and recording of human physical activity data. Sensor-based human activity recognition (HAR) has risen to the top of the list of the most active research topic due to its widely real-life applications in various practical domains, such as healthcare monitoring, sports and exercise tracking, and misbehavior prevention. Many machine learning and deep learning approaches have been recently proposed to solve the problem of human activity recognition, focusing on activities of daily living. However, an exciting and challenging HAR topic deals with more complex human activities such as eating-related activities. This paper proposes a sensor-based HAR framework using data from eating-related activities recorded by a smartwatch sensor. In this framework, five d eep learning networks (CNN, LSTM, BiLSTM, Stacked LSTM, CNN-LSTM, and LSTM-CNN) are evaluated for their recognition of eating-related activities. To ensure the model's dependability, data from eating-related activities on the standard publicly available dataset WISDM-HARB are utilized to evaluate the proposed framework using state-of-the-art metrics: accuracy and confusion matrices. Experiment findings demonstrate that the S tacked LSTM model outperforms other deep learning models, achieving an accuracy of 97.37%. © 2022 IEEE.

关键词： Learning systems

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：