检索结果-内蒙古大学图书馆

3rd International Conference on Electrical, Electronics, information and Communication Technologies, ICEEICT 2024

作者： Parthasarathy, R. Kiruthiga Devi, M. Karthick, V. Kumar, P. Mahendran, Rakesh Kumar Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Chennai India Dr. Mgr Educational and Research Institute Department of Information Technology Chennai India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350369083

Evaluating the candidate answers during online examination by a human examiner is wearisome task. Along with that, security concerns also associated in the E-Learning environment in terms of false data injection and modification attacks respectively. The state of the art work, either focus on designing intelligent and robust question answering model using Machine Learning (ML)/Deep Learning (DL) algorithm, or designing a secure framework for E-Learning environment using blockchain. To neutralize that issue, we design a secure and intelligent model for E-Learning environment using Deep Reinforcement Learning (DRL) and blockchain methodology respectively named EvauleBlock. The EvauleBlock composed of four major processes such as data assortment, data pre-processing, intelligent answer evaluation, and blockchain storage. In data assortment stage, the training of the proposed DRL algorithm named Multi Agent Deep Deterministic Policy Gradient (MADDPG) is taken place by crawling the related question answering data from the various websites. Followed by, we have performed pre-processing for the candidate written answers using adequate pre-processing steps. Once the answers are pre-processed, it is then provided to the MADDPG algorithm which employs four agents for validating the candidate answers by checking the semantic, syntactic, keyword, and context similarity scoring respectively. At last, the overall scores are securely stored in the blockchain using Proof of Work (PoW) consensus algorithm. The implementation of this work is carried out using python 3.11.0 tool and performance of the proposed model are validated and compared with adequate performance metrics. The results are promising when compared to the conventional models. © 2024 IEEE.

关键词： Answer Evaluation Blockchain Deep Reinforcement Learning E-Learning Question Answering system

来源：评论

学校读者我要写书评

暂无评论

Distributed Energy and Reserve Scheduling in Local Energy Communities Using L-BFGS Optimization

引用

CSEE Journal of Power and Energy Systems 2024年第3期10卷 942-952页

作者： Mohammad Dolatabadi Alireza Zakariazadeh Alberto Borghetti Pierluigi Siano Department of Management&Innovation Systems University of SalernoSalernoItaly Department of Electrical Electronicand Information EngineeringUniversity of BolognaBolognaItaly University of Science and Technology of Mazandaran BehshahrIran Department of Power Systems National University of Science and Technology POLITEHNICA BucharestBucharestRomania IEEE

Encouraging citizens to invest in small-scale renewable resources is crucial for transitioning towards a sustainable and clean energy *** energy communities(LECs)are expected to play a vital role in this ***,energy scheduling in LECs presents various challenges,including the preservation of customer privacy,adherence to distribution network constraints,and the management of computational *** paper introduces a novel approach for energy scheduling in renewable-based LECs using a decentralized optimization *** proposed approach uses the Limitedmemory Broyden–Fletcher–Goldfarb–Shanno(L-BFGS)method,significantly reducing the computational effort required for solving the mixed integer programming(MIP)*** incorporates network constraints,evaluates energy losses,and enables community participants to provide ancillary services like a regulation reserve to the grid *** assess its robustness and efficiency,the proposed approach is tested on an 84-bus radial distribution *** indicate that the proposed distributed approach not only matches the accuracy of the corresponding centralized model but also exhibits scalability and preserves participant privacy.

关键词： Distributed optimization flexibility services L-BFGS method local energy community renewables reserve

来源：评论

学校读者我要写书评

暂无评论

DevSched: an efficient bug-triaging model for allocating and balancing developer tasks

引用

Iran Journal of computer science 2024年第1期7卷 1-11页

作者： Uddin, K. M. Aslam Satu, Md. Shahriare Riyad, Md. Mahmudul Hasan Sakib, Kazi Institute of Information Technology University of Dhaka Dhaka Bangladesh Department of Information and Communication Engineering Noakhali Science and Technology University Noakhali Bangladesh Department of Management Information Systems Noakhali Science and Technology University Noakhali Bangladesh Department of Applied Mathematics Noakhali Science and Technology University Noakhali Bangladesh

Bug triage is a critical aspect of software development that involves classifying and prioritizing reported bugs. Effective bug triage ensures that resources are allocated and bug patterns are efficiently identified to address underlying issues. However, inappropriate bug distributions among different types of developers cause delays, errors, incapability, and lower job satisfaction. Many works were proposed to recommend developers for fixing bugs. However, previous works did not consider the proper workload distributions among developers. The objective of the work is to introduce a task allocation and load-balancing model called Developer Scheduler (DevSched) that properly distributes unassigned bugs among different types of developers more efficiently. DevSched creates multiple developer profiles from existing bug reports. Different new bug reports are converted bug into vectors, and developer profiles are transformed into a corpus of words. Then, different bugs are assigned into developers by comparing the highest cosine similarity between vectors of bugs and developers’ corpus. DevSched dynamically updates the developer’s workload, and their ratings are adjusted based on the performance. In this work, Eclipse, Mozilla, and NetBeans bug reports are utilized to investigate individual developers’ performance in bug-triaging process. DevSched assigns and balances bugs among different kinds of developers more efficiently. After applying the proposed load-balancing model, the standard deviations are rapidly decreased than normal bug distributions for different datasets. This process is repeated for each bug to ensure the efficient allocation of resources and the resolution of critical issues. Therefore, the lowest standard deviation is found to be 0.48 for the Eclipse dataset. By assigning bugs based on defined thresholds, skills, and workloads, DevSched improves its efficiency, reduces delays, and enhances job satisfaction among developers. © The Author(s), under exc

关键词： Developer DevSched Load balancing Standard deviation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Decentralized Federated Learning in LEO Satellite Networks 24

Adaptive Decentralized Federated Learning in LEO Satellite N...

引用

24th IEEE International Conference on Communication technology, ICCT 2024

作者： Li, Dong Yan, Zhigang Hao, Yuyu Niyato, Dusit Quek, Tony Q. S. Macau University of Science and Technology School of Computer Science and Engineering Macau China Nanyang Technological University School of Computer Science and Engineering Singapore Singapore University of Technology and Design Information Systems Technology and Design Pillar Singapore

ISBN: (纸本)9798350363760

In Federated Learning (FL) for the low Earth orbit (LEO) satellite networks with parameters aggregated by a ground station, the communication overhead is a substantial concern. To circumvent this limitation and alleviate the latency within the FL for the satellite-ground communication, Decentralized Federated Learning (DFL) has appeared as an effective solution. However, considering the heterogeneity of satellites, the problem on how to efficiently leverage the limited resources available to enhance the model performance of DFL has drawn little attention, which motivates this work. Specifically, the proposed solution involves optimizing the number of local training rounds across diverse satellites with varying resource budgets to enhance the DFL performance by utilizing the resource more efficiently. Simulation results show that, the proposed scheme achieves a much better performance than the conventional schemes with fixed rounds of local training. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

LibMTL: A Python Library for Deep Multi-Task Learning

引用

Journal of Machine Learning Research 2023年第1期24卷 1-7页

作者： Lin, Baijiong Zhang, Yu The Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering Southern University of Science and Technology Peng Cheng Laboratory China

This paper presents LibMTL, an open-source Python library built on PyTorch, which provides a unified, comprehensive, reproducible, and extensible implementation framework for Multi-Task Learning (MTL). LibMTL considers different settings and approaches in MTL, and it supports a large number of state-of-the-art MTL methods, including 13 optimization strategies and 8 architectures. Moreover, the modular design in LibMTL makes it easy to use and well extensible, thus users can easily and fast develop new MTL methods, compare with existing MTL methods fairly, or apply MTL algorithms to real-world applications with the support of LibMTL. The source code and detailed documentations of LibMTL are available at https://***/median-research-group/LibMTL and https://***, respectively. ©2023 Baijiong Lin and Yu Zhang.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Cardiac Arrest Prediction Model Using Ensemble Technique 4

Cardiac Arrest Prediction Model Using Ensemble Technique

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Sinha, Dibakar More, Sarla Jeyakrishnan, V. Mishra, Durgesh Manipal University Jaipur Department of Computer Science Engineering Rajasthan Jaipur India Symbiosis University of Applied Sciences School of Computer Science and Information Technology MP Indore India

ISBN: (纸本)9798331518981

The physician employs a diverse range of laboratory diagnostics, physical examinations, and on occasion, even invasive procedures to ascertain the presence of diseases. It is necessary to have a physician that possesses exceptional training, expertise and skill in the specific field, for detection of the disease in its initial phases. Despite the widespread use of ensemble techniques in disease prediction, here is a notable absence of comprehensive evaluation of regularly utilized ensemble algorithms for highly studied diseases. Consumers typically resort to seeking medical assistance from a doctor or other medical expert only after exhausting all other home remedies without finding relief for their ailments. This is probably a result of insufficient comprehension, as well as other factors related to behavior. This paper introduces a conventional ensemble LSTM model that incorporates data preparation and feature engineering. The model proposed in this research represents major gains in numerous statistical parameters like precision, f score, accuracy and ROC curve in comparison to the other models. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Adaptive iterated local search algorithm for dynamic patient admission scheduling problems

引用

Soft Computing 2025年第7期29卷 1-11页

作者： Turky, Ayad Sabar, Nasser R. Song, Andy Hussain, Abir Liatsis, Panos Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Computer Science and Information Technology La Trobe University MelbourneVIC3086 Australia School of Computing Technologies RMIT University Melbourne Australia Department of Electrical Engineering University of Sharjah Sharjah United Arab Emirates Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates

Healthcare resource management is essential for ensuring the quality of patient care. However, it can be a complex and costly task. This work addresses the patient admission scheduling (PAS) problem, a complex aspect of healthcare resource management. PAS aims to allocate patients to hospital beds within a planning horizon, subject to a variety of healthcare constraints. The goal is to maximize management efficiency and patient comfort to improve medical treatment. In this work, we consider a practical variant of PAS known as dynamic PAS (DPAS). DPAS considers several factors and constraints, such as the daily registration of new patients, urgent patients, uncertainties in stay lengths, operating theatre resources, and the surgery scheduling process. An effective and efficient adaptive iterated local search (AILS) algorithm is proposed to solve DPAS. To enable the search to explore the search space efficiently, the proposed AILS adaptively integrates a number of components. Two adaptive perturbation strategies are devised to locate unexplored areas in the search space. To exploit the newly discovered areas effectively, we propose an adaptive local search mechanism as an intensification strategy to find a high-quality solution. The proposed AILS algorithm is compared to benchmark problems used by existing algorithms. The experimental results demonstrate the effectiveness and efficiency of the proposed approach. Specifically, out of 30 tested instances, AILS obtains 17 of the best-known results using less computational time. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

DBNLP: detecting bias in natural language processing system for India-centric languages

引用

International Journal of information technology (Singapore) 2025年 1-16页

作者： T. G, Keerthan Kumar Mendke, Saish Parihar, Rohit Mayya, Samarth Venkatesh, Spoorthy Koolagudi, Shashidhar G. Department of Information Science and Engineering Siddaganga Institute of Technology Karnataka Tumkur 572102 India Department of Computer Science and Engineering National Institute of Technology Karnataka Surathkal Karnataka Mangalore 575025 India Department of Artificial Intelligence and Machine Learning CSPIT CHARUSAT Gujarat Anand 388421 India

Natural language processing (NLP) is gaining widespread interest and seeing advancements rapidly due to its attractive and exhilarating applications. NLP models are being developed in search engines for real-world scenarios such as language translation, sentiment analysis, chat-bots such as ChatGPT, and auto-completion. These models are trained on a vast corpus of online data, exposing them to harmful biases and stereotypes towards various communities. The models learn these biases, making harmful and undesirable predictions about particular genders, religions, races, and professions. Biases in NLP systems can perpetuate societal biases and discrimination, leading to unfair and unequal treatment of individuals or groups. It is crucial to identify these biases, which will help mitigate them. Most of the literary works in this area have been primarily Western-centric, focusing on the English language, making it tough to use them for Indian models and languages. In this work, we propose a model called Detecting Bias in Natural Language Processing System for India-Centric Languages (DBNLP), which aims to identify the biases relevant to the Indian context present in the text-based language models, particularly for the English and Hindi languages. The DBNLP presents three techniques for bias identification based on (1) a Context Association Test (CAT), (2) a template-based perturbation technique for various co-domain associations, and (3) a co-occurrence count-based corpus analysis technique. Further, this work showcases how India-centric models such as IndicBERT, MuRIL, and datasets such as IndicCorp are biased toward various demographic categories. Detecting bias in natural language processing systems for India-centric languages is essential to creating fair, diverse, and inclusive models that benefit society. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Diverse and Inclusive models Harmful biases and stereotypes India-centric models Indian context Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Smart Garbage Management with Layered Control and Automated Reporting using IoT 11th

Smart Garbage Management with Layered Control and Automated ...

引用

11th International Conference on Intelligent Computing and Applications, ICRTC 2023

作者： Christy Jeba Malar, A. Deva Priya, M. Aru Maakadalamudhan, T. Gayathri Devi, C.J. Kanishka, R. Department of Information Technology Sri Krishna College of Technology Tamil Nadu Coimbatore India Department of Computer Science and Engineering Sri Eshwar College of Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9789819717231

Efficient management of municipal waste is essential for ensuring public health and a clean environment. In this paper, a novel method for automating smart garbage management using Internet of Things (IoT) technology is proposed. The system utilizes an IoT device to collect real-time data on garbage levels, air pollution and foul smells which are transmitted to the driver and municipal authorities through a cloud web application. The system also incorporates a layered control escalation and reporting mechanism to guarantee prompt action by authorities in the event of garbage collection delays or other emergencies. The system architecture, implementation details and evaluation results are presented, and the potential to improve the efficiency and effectiveness of municipal waste management is discussed. The proposed system offers a cost-effective and sustainable solution that can benefit both public and environment. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A parametric survey on polyphonic sound event detection and localization

引用

Multimedia Tools and Applications 2024年 1-38页

作者： Mohmmad, Sallauddin Sanampudi, Suresh Kumar JNTU Hyderabad India School of Computer Science and Artificial Intelligence SR University TS Warangal India Department of Information Technology JNTUH University College of Engineering Nachupally Kondagattu TS Jagtial India

With the rapid growth in technology, everything will become automatic. Automatic detection is needed in health, security, smart homes, smart cities, and various environments. Sound is an essential function of automatic detection, which can be created in different environmental situations. To handle this, various sound detection devices are incorporated that run alone or with a combination of video. This auditory detection system is becoming more emerging in research today. This study is a survey on sound event detection and localization-related models. This survey research included details about different datasets, feature extractions, and classification methods that are implemented in sound-related research. Distinct and typical environmental situations comprise multiple sound sources that generate different sounds and noise. Our research compares distinct algorithms to detect sound events and localization, such as HMM, CNN, SVM, Random Forest, NMF, CRNN, VGG16, etc. Sound-related feature extraction methods, such as MFCC, Mel-Spectrogram, Mel band elements, ZCR, and wavelet features, and their importance in sound classification are also explained with a comparative analysis approach. The sections end with challenges with the existing approaches in different environments and feature extraction combinations. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Support vector machines

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：