检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 698-708页

作者： Dutta, H Pallab Jyoti Bhuyan, M.K. Neog, Debanga Raj Macdorman, Karl F. Laskar, R.H. Department of Electronics and Electrical Engineering Indian Institute of Technology Assam Guwahati781039 India Department of Electronics and Electrical Engineering and Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Assam Guwahati781039 India Mehta Family School of Data Science and Artificial Intelligence Indian Institute ofTechnology Assam Guwahati781039 India School of Informatics and Computing Indiana University IN46202 United States Department of Electronics and Communication Engineering National Institute of Technology Assam Silchar788010 India

In this article, we propose a hand gesture-operated system as an AI application to relieve discomfort and restore function in hand and arm movements caused by injuries and nerve and muscle complications. The system trains patients with hand exercises, such as performing hand gestures accurately, traversing within specified bounds, and operating a hand gesture calculator. However, the system requires accurate hand gesture detection, which is impeded by background clutter and variations in illumination and in the hand's size and angle. To address this, we developed a robust hand detection module that uses a single-stage transformer deep network. The transformer network encodes global information and uses bipartite matching to reduce the frequency of spurious detections. It drives a regression head and a classification head to localize the hand gesture in a bounding box and assign it a class label. Hand keypoints are also detected to support drawing, path traversal, and calculator use. The approach is evaluated on two benchmark datasets: 1) OUHANDS and 2) NUS. The method yields 89.6% accuracy for OUHANDS and 100% for NUS. These results indicate that precise hand detection can support a robust system for rehabilitation through hand exercises. Our experiments confirm that the users' hand function progressively improved. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Exploration of Real-Time 3-D View Reconstruction Methods

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 5915-5927页

作者： Agrawal, Arya Sharma, Teena Verma, Nishchal K. Vellore Institute of Technology School of Computer Science and Engineering Vellore632014 India Indian Institute of Technology Mehta Family School of Data Science and Artificial Intelligence Guwahati781039 India Indian Institute of Technology Kanpur Department of Electrical Engineering 208016 India

Real-time 3-D view reconstruction in an unfamiliar environment poses complexity for various applications due to varying conditions such as occlusion, latency, precision, etc. This article thoroughly examines and tests contemporary methodologies addressing challenges in 3-D view reconstruction. The methods being explored in this article are categorized into volumetric and mesh, generative adversarial network based, and open source library based methods. The exploration of these methods undergoes detailed discussions, encompassing methods, advantages, limitations, and empirical results. The real-time testing of each method is done on benchmarked datasets, including ShapeNet, Pascal 3D+, Pix3D, etc. The narrative highlights the crucial role of 3-D view reconstruction in domains such as robotics, virtual and augmented reality, medical imaging, cultural heritage preservation, etc. The article also anticipates future scopes by exploring generative models, unsupervised learning, and advanced sensor fusion to increase the robustness of the algorithms. © 2020 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Kullback-Leibler Divergence-Based Regularized Normalization for Low-Resource Tasks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2638-2650页

作者： Kumar, Neeraj Narang, Ankur Lall, Brejesh Indian Institute of Technology Delhi Bharti School of Telecommunication Technology & Management New Delhi110016 India Indian Institute of Technology Delhi Department of Electrical Engineering New Delhi110016 India

Large pretrained models, like BERT, GPT, and Wav2Vec, have demonstrated their ability to learn transferable representations for various downstream tasks. However, obtaining a substantial amount of supervised data remains a challenge due to resource and time limitations. As a solution, researchers have turned their attention to using large pretrained datasets via techniques like fine tuning, linear probing, or prompt tuning in low-resource settings. Normalization techniques play a crucial role in speeding up training, style transfer, object detection, recurrent neural networks, and improving the generalization of deep neural networks. Despite their success in various domains, their effectiveness in low-resource NLP and speech tasks has been limited. A notable reason for this limitation is the difficulty in capturing expressiveness using affine parameters of normalization. To address this issue, we propose a novel approach called Kullback-Leibler (KL) regularized normalization or KL-Norm. The main objective of KL-Norm is to ensure that normalized data are well-behaved and to improve generalization by reducing overfitting by including a regularization loss function in the training process. It achieves this by promoting good performance on out-of-domain distributions and effectively filtering relevant features while eliminating superficial features or biases present in the dataset or pretrained model. Remarkably, KL-Norm accomplishes these objectives with minimal increase in model parameters and memory overheads. Through extensive experimental analysis, we showcase the improved accuracy and performance of KL-Norm in comparison to other normalization techniques on low-resource downstream NLP tasks. These tasks encompass a wide range of applications, including sentiment classification, semantic relationship characterization, semantic textual similarity, textual entailment, and paraphrase detection. Additionally, KL-Norm exhibits superior results in downstream speech tasks

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Constraints Separation Based Evolutionary Multitasking for Constrained Multi-Objective Optimization Problems

引用

IEEE/CAA Journal of Automatica Sinica 2024年第8期11卷 1819-1835页

作者： Kangjia Qiao Jing Liang Kunjie Yu Xuanxuan Ban Caitong Yue Boyang Qu Ponnuthurai Nagaratnam Suganthan School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou 450001China School of Electrical Engineering and Automation Henan Institute of TechnologyXinxiang 453003China School of Electronic and Information Zhongyuan University of TechnologyZhengzhou 450007China KINDI Center for Computing Research College of EngineeringQatar UniversityDoha 999043Qatar

Constrained multi-objective optimization problems(CMOPs)generally contain multiple constraints,which not only form multiple discrete feasible regions but also reduce the size of optimal feasible regions,thus they propose serious challenges for *** all constraints,some constraints are highly correlated with optimal feasible regions;thus they can provide effective help to find feasible Pareto ***,most of the existing constrained multi-objective evolutionary algorithms tackle constraints by regarding all constraints as a whole or directly ignoring all constraints,and do not consider judging the relations among constraints and do not utilize the information from promising single ***,this paper attempts to identify promising single constraints and utilize them to help solve *** be specific,a CMOP is transformed into a multitasking optimization problem,where multiple auxiliary tasks are created to search for the Pareto fronts that only consider a single constraint ***,an auxiliary task priority method is designed to identify and retain some high-related auxiliary tasks according to the information of relative positions and dominance ***,an improved tentative method is designed to find and transfer useful knowledge among *** results on three benchmark test suites and 11 realworld problems with different numbers of constraints show better or competitive performance of the proposed method when compared with eight state-of-the-art peer methods.

关键词： Constrained multi-objective optimization(CMOPs) evolutionary multitasking knowledge transfer single constraint.

来源：评论

学校读者我要写书评

暂无评论

Towards reliability analysis of IEEE 802.11p MAC for platooning in a heterogeneous traffic setup 10

Towards reliability analysis of IEEE 802.11p MAC for platoon...

引用

10th International Conference on Wireless Networks and Mobile Communications, WINCOM 2023

作者： Gayathree, M.S. Manjunath, Sreelakshmi Indian Institute of Technology Mandi School of Computing and Electrical Engineering Himachal Pradesh India

ISBN: (纸本)9798350329674

We study the performance of the IEEE 802.11p medium access protocol for platooning of connected vehicles in the presence of interruptions from human-driven Motorised Two Wheelers (MTWs). We invoke specific mobility models for the movement of the vehicles - car-following models for connected vehicle platoons and gap-acceptance model to capture the interruptions by the MTWs - and use them to configure (i) the traffic setup and (ii) the rate at which data packets related to safety-critical messages are generated. A control-theoretic analysis of the car-following models yields a bound on the admissible communication delay to ensure non-oscillatory convergence of the platoon headway. We then use suitable Markov chain models to derive the distribution of the MAC access delay experienced by packets pertaining to safety-critical events as well as routine safety messages. Using the delay distribution and the bound on the admissible delay we compute the reliability of the 802.11p MAC protocol in terms of traffic and protocol parameters. It is seen that the MAC protocol may not always ensure timely delivery of packets for safe platooning. Our study highlights the need for redesign of MAC protocols for vehicular communications in heterogeneous conditions. © 2023 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Novel Metamaterial Inspired SSP-WGM Resonator Based Highly Sensitive EM Biosensor for Noninvasive Measurement of Blood Glucose Using Aqueous Glucose Solution and Saliva

Novel Metamaterial Inspired SSP-WGM Resonator Based Highly S...

引用

2023 IEEE Microwaves, Antennas, and Propagation Conference, MAPCON 2023

作者： Dutta, Debarati Anand, Ravi Shah, Prashant Mendiratta, Namrata Sarkar, Anirban Indian Institute of Technology School of Computing and Electrical Engineering Himachal Pradesh Mandi India

ISBN: (纸本)9798350328264

This paper introduces a novel spoof surface plasmon polariton (SSPP) based metamaterial-inspired electromagnetic (EM) biosensor for non-invasive diabetes analysis. The sensor design incorporates a spoof surface whispering gallery mode (SS-WGM) resonator, which effectively localizes the electric field within a specific region due to its slow-wave propagation. To achieve optimal sensitivity, a PDMS microfluidic channel is utilized to hold the sample (SUT) precisely on the region of maximum EM field concentration. Two different non-invasive samples, aqua solution mimicking blood, and human saliva, are used for evaluation. The comprehensive analysis reveals that this proposed microwave sensor holds great potential in advancing the development of modern lab-on-chip systems based on microwave technology. © 2023 IEEE.

关键词： Localized Surface Plasmon (LPS) microfluidic channel PDMS component Spoof Localized Surface Plasmon (SLSP) Spoof Surface Plasmon (SSP) Spoof Surface Plasmonic Whispering Gallery Mode (SSP-WGM)

来源：评论

学校读者我要写书评

暂无评论

Optimized Charging Method for Fast Charging of EV Batteries 49

Optimized Charging Method for Fast Charging of EV Batteries

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Kumar, Devesh Das, Moumita School of Computing and Electrical Engineering Indian Institute of Technology Himachal Pradesh Mandi India

ISBN: (纸本)9798350331820

Nowadays, energy storage plays a crucial role in electric vehicles. The existing constant current constant voltage charging methods can accelerate damage inside the battery by causing a loss of lithium ions, if a high current (more than 1C) is injected. Hence, a new optimized charging algorithm is proposed in this paper. In this charging method, four charging algorithms are combined, which are pulse current charging (0% to 20% SOC), pulse and burp current charging (20% to 80% SOC), and constant current constant voltage charging (above 80% SOC). This proposed hybrid charging algorithm reduces the charging time to less than an hour. One of the important features of this charging algorithm is that it charges the battery in pulse charging and pulse and burp charging modes at low frequency (2.5 Hz). Additionally, the negative current pulse in pulse and burp charging mode helps to mitigate the issue of lithium plating on the surface of the negative electrode during the charging process. Hence, the proposed method optimizes the performance of the battery to improve the battery life. The proposed algorithm is implemented in a bidirectional DC-DC power converter to verify the operation. The simulation and experimental results of the proposed charging method are included in this paper which shows, improvement of the battery life. The experimental results are also included in this paper. © 2023 IEEE.

关键词： DC-DC converters

来源：评论

学校读者我要写书评

暂无评论

A New Method to Detect the Dissimilarity in the Blood Flow of Both Carotid Arteries Using Photoplethysmography 3rd

A New Method to Detect the Dissimilarity in the Blood Flow o...

引用

The 3rd International Conference on Frontiers in computing and Systems (COMSYS 2022)

作者： Shakya, Kshitij Chowdhury, Shubhajit Roy School of Computing and Electrical Engineering Indian Institute of Technology Mandi Mandi175005 India

ISBN: (纸本)9789819926794

This paper describes a method for detecting the change in blood flow profile in the left and right common carotid artery to detect any hindrance, possibly a plaque in the blood flow. A device was made which extracts the PPG signals from the carotid arteries over the neck skin and compares the results between the two. For the case where the growth of plaque is assumed to be different for both carotid arteries, which is generally the case, this method suits best. The least complex and portability of the device made allows users to perform this method easily and inexperienced persons can easily be trained to do so. An all-purpose PPG device was designed to extract PPG signals from various sites on the body with this one device. Two such identical devices were made to be used to get reference and target signals from their respective sites to draw some promising outcomes from it. The modes of application of device have been described in the later part of the paper. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Novel Darknet traffic data synthesis using Generative Adversarial Networks enhanced with oscillatory Growing Cosine Unit activated convolution layers

引用

International Journal of Cognitive computing in engineering 2024年第1期5卷 58-65页

作者： Pradeep C, Antony Amali D, Geraldine Bessie Noel, Mathew Mithra Ghalib, Muhammad Rukunuddin Subramaniam, Prabhakar Rontala Venugopal, Chitra School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Electrical Engineering Vellore Institute of Technology Vellore India School of Computing De Montfort University Dubai United Arab Emirates Information Systems and Technology Westville South Africa Electrical Engineering & Renewable Energy Oregon Institute of Technology United States

The Darknet is an anonymous, encrypted collection of websites, with a passive listening nature - accepting incoming packets, while not supporting outgoing packets. Thus, it can potentially host criminal or malicious activity and software, becoming a cyber security threat. Network Detection Systems are effective in identifying dark net traffic and mitigating its ill effects. However, capturing and extracting data from raw network traffic for training these systems can be time-intensive and costly. Using the CIC-Darknet 2020 dataset, this paper proposes using a Novel Generative Adversarial Networks (GAN) Architecture generating the required training and testing data for these systems. This uses a combination of Growing Cosine Unit (GCU) activated convolution layers and Dense layers for the Generator. Feature selection with statistical correlation methods is used to select the most relevant features. An independently trained Evaluator network is used to evaluate the generated data. The proposed system is compared to other established Tabular data GANs like Conditional Tabular GAN (CTGAN) and Copula GAN with similar parameters and on the same data. The Proposed GAN architecture outperforms CTGAN and CopulaGAN by 20 % and 10 % in ters of accuracy while also taking 90 % and 30 % less time to train respectively. Results from measuring similarity of data using the Inverted Kolmogorov - Smirnov D statistic also show significantly better results for the Proposed GAN Architecture. This shows significant promise in using Generative models to reduce the time and effort costs associated with collecting and formatting data to use in research and for training detection systems. © 2024

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An Optimized Hybrid Deep Learning Model for Appliance Energy Prediction in Smart Homes

引用

Journal of engineering Science and technology Review 2024年第3期17卷 151-158页

作者： Vidhya, S. Balaji, M. Kamaraj, V. Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India Department of Electrical and Electronics Engineering Sri Sivasubramaniya Nadar College of Engineering Chennai India

The increased energy consumption due to industrial machines and household appliances affectenergy sustainability as well as economic stability. To meet the energy demand various practices are followed worldwide. Research on sustainable energy production is at peak meanwhile research towards reducing the cost of energy generation is gaining more interest in recent times. one of the key points considered to reduce the power generation cost is energy consumption prediction. Future demands can be predicted, and necessary power can be generated or delivered to meet the demand. Specifically, prediction model is essentially required for smart homes as they utilize multiple devices for smart connectivity. Machine learning algorithms are widely used for energy prediction applications. However, the performance of machine learning models needs manual selection of features and is still complex in data analysis and decision-making process. Recently deep learning (DL) techniques are used in various classification and prediction applications. DL superior performance is incorporated for energy prediction for smart home appliances. This research work presents a hybrid optimized DL model using Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) network. Additionally, to improve the prediction performances, the parameters of the hybrid DL model is fine-tuned using canonical particle swarm optimization algorithm. Experiments of the proposed model utilizes UCI Household power consumption dataset to evaluate the performances in terms of RMSE, MAPE, MAE and R2-score. The proposed model attained RMSE of 26.2154W, MAPE of 2.965%, MAE of 18.65W and R2-Score of 0.9989 which is much better than existing linear regression, extreme learning machine and diverse LSTM models. © 2024 school of Science, DUTH. All rights reserved

关键词： Domestic appliances

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：