检索结果-内蒙古大学图书馆

28th International Symposium on VLSI Design and Test, VDAT 2024

作者： Paul, Suraj Indian Institute of Engineering Science and Technology Dept. of Information Technology West Bengal India

ISBN: (纸本)9798350380101

Workloads on multicore platforms are increasingly becoming dynamic. Resource assignment decisions of applications impact their timing response and system performance, especially for Network-on-Chip (NoC) based multicore systems hosting real-time applications. Such systems offer better scope for parallel application execution. Design-time solutions for task allocation may not be suitable for dynamic workloads. In such scenarios, dynamic task allocation techniques give improvement in system resource utilization and lends adaptivity to changing application workload. This work presents an efficient and scalable adaptive technique for joint allocation and scheduling of tasks of mixed critical applications at runtime. Potential allocation solutions are explored at design-time by focusing on timing characteristics of applications and their communication energy consumption while considering a set of multitasking processors. These design-points are reconfigured dynamically at runtime for adapting the resource allocation decisions of multiple applications depending on platform resources and application requirements. Simulation results demonstrate that the proposed strategy achieves 20.4% and 33.5% improvement in communication energy consumption and timing satisfaction of tasks of allocated applications, respectively. Also, the run-time overhead of online reconfiguration reduces by 27.8% with respect to the existing dynamic resource allocation approaches. © 2024 IEEE.

关键词： Multitasking

来源：评论

学校读者我要写书评

暂无评论

Appearance and motion-based unusual crowd events detection using multiple moving objects

引用

Multimedia Tools and Applications 2024年第42期83卷 90177-90189页

作者： Babu, K. Atlas, L. Godlin Sreeji, S. Arjun, K.P. Rasmi, A. Senthilvel, P. Gururama Computational Intelligence SRM Institute of Science & Technology Chengalpet Kattankulathur603203 India Department of Computer Science and Engineering Bharath Institute of Higher Education and Research Chennai India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computer Science and Engineering Gitam University Karnataka Bengaluru India Information Science and Engineering RRIT Bangalore India Saveetha University Chennai602 105 India

Unusual crowd analysis is an important problem in surveillance video due to their features cannot be extracted efficiently on the crowd scenes. To overcome this challenge, this paper introduced the appearance and motion based unusual events detection method by using multiple moving objects. This method includes appearance and motion based computation, and moving objects trajectory analysis. By using these all techniques, the unusual crowds and their activities can be obtained by analyzing moving objects size and the distance among multiple moving objects. Two benchmark datasets such as PETS 2009 and UMN are used for the experimental results. Also, several existing algorithms are compared with the proposed method to evaluate the effectiveness of the proposed work. The comparative analysis results proved that the proposed method achieved best accuracy for unusual crowd events. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： And trajectory analysis Appearance based analysis Distance based analysis Unusual crowd events detection

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Stable Strategy-Enabled Resource Allocation in 6G: A Strategy Integration-Based Game Theoretic Approach 1

Evolutionary Stable Strategy-Enabled Resource Allocation in ...

引用

1st Asian Conference on Communication and Networks, ASIANComNet 2024

作者： Pathak, Vivek Rathore, Muktesh Singh Sharma, Aryan Pandya, Rahul Jashvantbhai Indian Institute of Technology Department of EECE Dharwad India Indian Institute of Technology Department of Engineering Physics Dharwad India Indian Institute of Technology Department of Computer Science and Engineering Dharwad India

ISBN: (纸本)9798350367003

In the rapidly advancing era of 6 G networks, an efficient resource allocation (RA) is necessitated. Consequently, our paper reveals a sophisticated mathematical model based on evolutionary game theory and replicator dynamics designed to optimize and stabilize resource distribution. The model delineates how evolutionary stable strategies (ESS) can be systematically identified and employed to enhance network efficiency and fairness significantly. Further, strategic interaction analysis and dynamic modeling integration demonstrate that ESS respond adeptly to changing network conditions and robustly guards against inefficiencies caused by signal degradation and user demand variability. Furthermore, we proposed a few algorithms, such as ESS sustainability and stabilization criteria for ESS, to depict the change in strategy population, which turns into the strategy fitness change and convergence of strategic population, respectively. Lastly, our empirical simulations validate the model's effectiveness in fostering resilient and equitable RA, setting a foundation for future 6G network designs prioritizing adaptability and sustainability. In conclusion, our paper aims to highlight the innovative approach succinctly, as well as the theoretical foundation and practical outcomes of our research, focusing on engaging and addressing a more expansive audience effectively in the upcoming era of next-generation communication technologies. © 2024 IEEE.

关键词： 6G Evolutionary Game Theory Evolutionary Stable Strategies Resource Allocation

来源：评论

学校读者我要写书评

暂无评论

An Effective Biomedical Named Entity Recognition by Handling Imbalanced Data Sets Using Deep Learning and Rule-Based Methods

引用

SN computer science 2023年第5期4卷 1-11页

作者： Archana, S.M. Prakash, Jay Singh, Pramod Kumar Ahmed, Waquar Computer Science and Engineering National Institute of Technology Kerala Calicut India Computer Science and Engineering ABV-Indian Institute of Information Technology and Management Madhya Pradesh Gwalior India Electronics and Communication Engineering National Institute of Technology Kerala Calicut India

Biomedical named entity recognition (Bio-NER) is an important and fundamental task for biomedical text mining. Bio-NER has various applications, especially in Natural Language Processing, and its performance heavily impacts dependent tasks. However, the class imbalance problem is the major issue for an effective Bio-NER. Over the past few years, rule-based methods and deep learning-based methods have been widely used. However, they are not able to effectively handle class imbalance issues. Therefore, we proposed a hybrid method by taking advantage of both methods for Bio-NER, which is named Hybrid Bio-NER (HBio-NER). Furthermore, we propose a training data format called ‘single_entity-O’, which reduces the class imbalance problem. Data preprocessing and ‘single_entity-O’ data representation format improve the class balance, further improving the HBio-NER system performance. HBio-NER identifies the named entities using the Bidirectional Long Short-Term Memory (Bi-LSTM) model and named entity boundaries (begin, inside of entity mentions) using rules. The effectiveness of the proposed method is tested on two data sets (NCBI disease and CHEMDNER chemical data sets) with different word representation models (GloVe, Word2Vec and FastText). The comparative analysis indicates that significant performance gain is achieved by the proposed method especially for disease named entity recognition. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Biomedical named entity recognition Biomedical text mining Deep learning Imbalanced data handling Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Droplet Routing in Digital Microfluidic Biochip using Agglomerative Hierarchical Clustering 6

Droplet Routing in Digital Microfluidic Biochip using Agglom...

引用

6th Doctoral Symposium on Intelligence Enabled Research, DoSIER 2024

作者： Das, Jayanti Pan, Indrajit Rahaman, Hafizur RCC Institute of Information Technology Kolkata700015 India Indian Institute of Engineering Science and Technology Shibpur711103 India

Digital microfluidic biochip (DMFB) has established its potential in different applications like lab-on-chip device to perform pathological analysis and sample testing, air contamination detection, drug discovery and many others related to this. Droplet routing in DMFB is an essential operation. Optimization of different droplet routing aspects are fine tuned to enhance the performance of DMFB. Existing researches have used different traditional optimization techniques to optimize the performance of droplet routing. Use of machine learning mechanism is very less. Early-stage research indicates a wide scope for applying machine learning mechanism in DMFB domain. A clustering-based droplet routing mechanism based on the approach of agglomerative hierarchical clustering (AHC) has been used in this work which finds cluster of electrodes to form a path between source to target. Experimental studies on different test benches show a potential result for the approach in compare to existing research reports. © 2025 Copyright for this paper by its authors.

关键词： Hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Improving LSTM forecasting through ensemble learning: a comparative analysis of various models

引用

International Journal of information technology (Singapore) 2024年第8期16卷 5113-5131页

作者： Ahmad, Zishan Shanmugasundaram, Vengadeswaran Biju Khan, Rashid Department of Computer Science and Engineering Indian Institute of Information Technology Kerala Kottayam 686635 India LANOVIZ Security Solutions Kerala Ernakulam 682011 India

Supply chain management involves managing the entire manufacturing process, from purchasing supplies to delivering the final product. Demand forecasting helps businesses predict future customer demand by analyzing historical data and market patterns. While various papers discuss optimizing models, this research compares several machine learning models, such as ARIMA, SARIMA, and deep learning models like RNN, LSTM, GRU, and BLSTM. It also extends to approaches like ensemble learning with the LSTM model, discussing how ensemble learning can further improve the LSTM model. This paper explores ensemble learning in two ways: a) without model pruning, averaging all generated models, and b) with model pruning, removing underperforming models and averaging top performers. Experiments conducted on a public dataset from the University of Chicago achieved a very low RMSE loss of 9.26 on the LSTM model improved via ensemble learning with model pruning. This ensemble approach with model pruning improved accuracy in predicting future customer demand, and a complete pipeline integrating visualization and a notification system was developed. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： ARIMA BLSTM Ensemble learning GRU LSTM RNN SARIMA

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of EEG Feature Fusion Techniques for Emotion Classification 15

Comparative Evaluation of EEG Feature Fusion Techniques for ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Ameta, Durgesh Gupta, Ashish Singh, Harshil Deep Uzir, Didrikhya Kothari, Rhythm Bose, Rapolu Subhash Chandra Singh, Harjot Behera, Laxmidhar Iksmha Center Indian Institute of Technology Mandi Mandi India Indian Institute of Technology Kanpur Department of Electrical Engineering Kanpur India Indian Institute of Information Technology Department of Computer Science HP Una India Cair Indian Institute of Technology Mandi Mandi India Indian Institute of Information Technology Department of Electronics HP Una India Indian Institute of Technology Mandi Mandi India

ISBN: (纸本)9798350370249

Brain-computer interface (BCI) system-based emotion classification is an intriguing topic for research. Feature extraction is an essential step in these systems, usually carried out by a deep neural network or hand-crafted features. Studies in this area frequently highlight the significance of a small set of features;a precise comparison of different proposed features is still necessary. To classify emotions from EEG data, we attempt an exploratory evaluation of a number of EEG features, including those in the time domain, frequency domain, auto-encoded, and deep features, using the DENS dataset. Baseline techniques like Random Forest (RF), XgBoost (XGB), and KNN are used to compare feature performance. The results of this study shed light on the possibility of using these EEG features to identify emotional states. Compared to the previous results on the same dataset, our results show accuracies of 82.10% and 81.33% for valence and arousal, an increase of 29.63% and 18.82%, respectively. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Human Activity Recognition System for Assisted Living Environments

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2342-2357页

作者： Jain, Ankit Akerkar, Rajendra Srivastava, Abhishek Indian Institute of Technology Indore Department of Computer Science and Engineering Madhya Pradesh Indore453552 India Western Norway Research Institute Sogndal6856 Norway

Automatic human activity recognition has numerous applications, especially in elderly support and healthcare. Several approaches for human activity recognition (HAR) using a variety of sensors are available in literature. While such frameworks are effective, each has limitations related to privacy, convenience, cost, and performance. In this article, a robust framework for automatic human activity recognition is proposed that uses depth sensors that preserve privacy and are cost-effective. The depth sensors provide two data modalities, namely, depth maps and skeleton sequences, used together for activity recognition. Two novel descriptors, joint position descriptor based on the position of joints;and bone angle descriptor based on bone inclination, are generated from the skeleton sequence data. The descriptors convey both spatial and temporal information and are scale and view-point invariant. Depth video clips are used along with the descriptors to deal with the issue of noisy and missing skeleton sequences. The data modalities and descriptors are fused using a two-level fusion strategy for a multichannel convolutional neural network (CNN) framework. The proposed system is validated and shown to be superior to the existing state of the art through comparisons over four widely used public datasets. A computational complexity analysis of the system confirms its efficacy in real time. A prototypical implementation of the proposed system further validates its practicability. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Modelling a Learning-Based Dynamic Tree Routing Model for Wireless Mesh Access Networks

引用

computer Systems science & engineering 2023年第2期44卷 1531-1549页

作者： N.Krishnammal C.Kalaiarasan A.Bharathi Department of Computer Science and Engineering Sri Shakthi Institute of Engineering and TechnologyCoimbatoreIndia School of Engineering Presidency UniversityBengaluruIndia Department of Information Technology Bannari Amman Institute of TechnologySathyamangalamIndia

Link asymmetry in wireless mesh access networks(WMAN)of Mobile ad-hoc Networks(MANETs)is due mesh routers’transmission *** is depicted as signiﬁcant research challenges that pose during the design of network protocol in wireless *** on the extensive review,it is noted that the substantial link percentage is symmetric,i.e.,many links are *** is identiﬁed that the synchronous acknowledgement reliability is higher than the asynchronous ***,the process of establishing bidirectional link quality through asynchronous beacons underrates the link reliability of asym-metric *** paves the way to exploit an investigation on asymmetric links to enhance network functions through link ***,a novel Learning-based Dynamic Tree routing(LDTR)model is proposed to improve network performance and *** the evaluation of delay measures,asymmetric link,interference,probability of transmission failure is *** proportion of energy consumed is used for monitoring energy conditions based on the total energy *** learning model is a productive way for resolving the routing issues over the network model during *** asymmetric path is chosen to achieve exploitation and exploration *** learning-based Dynamic Tree routing model is utilized to resolve the multi-objective routing ***,the simulation is done with MATLAB 2020a simulation environment and path with energy-efﬁciency and lesser E2E delay is evaluated and compared with existing approaches like the Dyna-Q-network model(DQN),asymmetric MAC model(AMAC),and cooperative asymmetric MAC model(CAMAC)*** simulation outcomes demonstrate that the anticipated LDTR model attains superior network performance compared to *** average energy consump-tion is 250 J,packet energy consumption is 6.5 J,PRR is 50 bits/sec,95%PDR,average delay percentage is 20%.

关键词： Wireless mesh access networks mobile ad-hoc network reinforcement learning multi-objective constraint asymmetric link

来源：评论

学校读者我要写书评

暂无评论

Workload Pattern Learning-Based Cloud Resource Management Models: Concepts and Meta-Analysis

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2025年第3期10卷 418-438页

作者： Saxena, Deepika Singh, Ashutosh Kumar University of Aizu Department of Computer Science and Engineering Aizuwakamatsu965-0006 Japan Indian Institute of Information Technology Madhya Pradesh Bhopal462003 India University of Economics and Human Sciences Warsaw01-043 Poland

Workload pattern learning-based resource management is crucial for cloud computing environments for achieving higher performance, sustainability, fault-tolerance, and quality of service. The existing literature lacks a comprehensive discussion and meta-analysis of workload pattern learning centered cloud resource management. In this context, this paper presents a first comprehensive study about five pattern learning and analysis-driven techniques applied for achieving higher efficiency and performance during multi-constrained cloud resource management. The paper manifests utility and significance of workload pattern learning-based resource management as compared with traditional resource management. The five principle techniques are thoroughly discussed with coherent depiction of intended concept alongwith numerical illustration. The most prominent state-of-the-art models belonging to each technique are further distinguished based on distinct objectives conferring an extensive survey and comparison. Besides, conceptual and theoretical analysis, the leading models underlying the major resource management techniques are implemented on a common platform and thoroughly examined using real-world Google Cluster workload traces. Based on the all-inclusive study and performance evaluation, trade-off discussion among these techniques are capsuled to put forward imperative concluding remarks with concrete open issues and insightful future research directions. © 2016 IEEE.

关键词： Quality of service

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：