检索结果-内蒙古大学图书馆

Automation and Computation (AUTOCOM), International Conference on

作者： Nikesh Kumar Suresh Kumar Department of Computer Science Engineering Netaji Subhas University of Technology Delhi India Department of Computer Science & Engineering East Campus Netaji Subhas University of Technology Delhi India

This study introduces a novel approach to abstractive text summarisation, by harnessing the power of sequence-to-sequence (Seq2Seq) models along with word sense disambiguation (WSD) techniques. We utilised TensorFlow and NLTK libraries, employing the CNN/Daily Mail dataset to train the model. We integrated word sense disambiguation [17] in the preprocessing phase. With the help of WordNet we identified and utilised most common senses of word within texts. This step played a crucial role in improving the model’s *** created a Seq2Seq model equipped with LSTM units, embedding layers, and Time Distributed Dense layers, while focusing on optimising the vocabulary size, embedding dimensions, and LSTM units to achieve efficient summarisation. The model is trained on the preprocessed dataset, undergoing numerous epochs to refine its summarisation *** approach shows a significant improvement in capturing the context and nuances of the input texts, resulting in more coherent and accurate summaries. The results indicate promising advances in the field of abstractive text summarisation, opening ways for context-aware and semantically rich summarisation tools. This study not only contributes to the academic discussions in natural language processing but also offers practical implications for summarisation applications in various domains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Dual-Hop NOMA based Communication System with Practical Constraints: Imperfect CSI, HWI and ISIC 9

Asymmetric Dual-Hop NOMA based Communication System with Pra...

引用

9th International Conference on Signal Processing and Communication, ICSC 2023

作者： Khirwar, Isha Gupta, Akash Verma, Bharat Garg, Parul ECE Department The LNM Institute of Information Technology Jaipur India Division of Electronics and Communication Engineering Netaji Subhas University of Technology New Delhi India

ISBN: (纸本)9798350383201

In this paper, we present an asymmetric dual-hop decode-and-forward relay-based Non-Orthogonal Multiple Access (NOMA) based communication system. The source-to-relay link is characterized by η − µ distribution, while the relay to end users is characterized by Rayleigh distribution. Further, we have incorporated hardware impairments (HWI), and channel state information (CSI) errors due to imperfect successive interference cancellation (SIC), at the relay and end users. The mathematical framework for outage probability (OP) is being derived, and the analytical results are verified using Monte Carlo simulation results. © 2023 IEEE.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Evolution of Fuzzy Set Theory under Monotonic Constraints

Evolution of Fuzzy Set Theory under Monotonic Constraints

引用

2023 International Conference on Advancement in Computation and computer Technologies, InCACCT 2023

作者： Gupta, Kavya Tayal, Devendra Kumar Jain, Aarti Indira Gandhi Delhi Technical University for Women Department of Computer Science and Engineering Delhi India Netaji Subhas University of Technology Department of Electronics and Communication Engineering Delhi India

ISBN: (纸本)9798350396485

Fuzzy Set Theory (FST) has proved advantageous in various areas of research ever since it was proposed by Prof. Lotfi A Zadeh in 1965. The work on FST has grown manifolds since then resulting in many extensions of FST, one of them being the development of FST under Monotonic Constraints (MC). The notion of Monotonic Fuzzy Set Theory (M-FST) was first presented in 2000 by P Lindskog and L Ljung. It has since seen various augmentations of its own with expansions over various extensions of FST. The applications of M-FST include classification, regression, and prediction. In this paper, the evolution of FST under MC has been studied. First, the evolution of FST has been presented which is then extended to FST under MC. The benefits, challenges, and applications along with the future scopes of FST under MC have also been studied and presented. © 2023 IEEE.

关键词： Fuzzy set theory

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Algorithms for Traffic Flow Prediction in Intelligent Transportation Systems

Comparative Analysis of Machine Learning Algorithms for Traf...

引用

Technological Advancements in Computational Sciences (ICTACS), International Conference on

作者： Mahima Yadav Bijendra Kumar Department of Computer Science and Engineering Netaji Subhas University of Technology Delhi India

ISBN: (数字)9798350387490

ISBN: (纸本)9798350387506

As human society advances, the limitations of current transportation systems become more apparent, prompting a growing desire to leverage advanced technology for intelligent transportation solutions. However, low identification rates and complicated processing plague many of the vehicle detection techniques used in video analytics today. This paper gives a comparative analysis of multiple machine learning algorithms for traffic flow prediction in order to improve Intelligent Transportation Systems (ITS). Using an extensive dataset of historical traffic flow and environmental variables, we evaluate the performance of several methods: Linear Regression (LR), Support Vector Machine (SVM), Decision Trees, Random Forests (RF) and deep Neural Networks (DNN). Numerous Variables are taken into account in the evaluation, including scalability, computing efficiency, and forecast accuracy. The findings show that while algorithms like RF and SVM give good performance with less computational overhead, DNN obtain the maximum accuracy. The work offers valuable information on the disadvantages of various machine learning (ML) techniques, which may be used to select suitable models for the prediction of traffic movement in real-world ITS.

关键词： Support vector machines Training Accuracy Machine learning algorithms Computational modeling Scalability Transportation Predictive models Prediction algorithms Real-time systems

来源：评论

学校读者我要写书评

暂无评论

AI Enabled- Information Retrival Engine (AI-IRE) in Legal Services: An Expert-Annotated NLP for Legal Judgements 2

AI Enabled- Information Retrival Engine (AI-IRE) in Legal Se...

引用

2nd International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2023

作者： Kanhaiya, Kishan Naveen Sharma, Arpit Kumar Gautam, Kamlesh Rathore, Pramod Singh Netaji Subhas University of Technology Delhi India National Institute of Technology Kurukshetra India Manipal University Department of Computer and Communcation Engineering Jaipur India Poornima College of Engineering Department of Advance Computing Rajasthan Jaipur India

ISBN: (纸本)9798350325799

The relationships between the law and fact, and the use of the facts to support a legal conclusion requires practice. This study introduces a technique called the "legal analysis of data extraction"which helps students/law practitioners to quickly assess a law article on the basis of the extracted attributes, and then apply their understanding in order to support a legal conclusion. To ease the processing of the law text data and retrieval of important information (entities) like names of Judges, appellants, respondents, judgment dates, etc. by utilizing NLP processes and ML techniques. This study demonstrates a novel approach of advanced information retrieval in the law articles leveraging natural language processing and machine learning techniques which are productized and used on live data as well. In this custom NER, aggregate accuracy of 95% is achieved using text classification followed by a regex fallback and flagging mechanism. This study consists of the following sections- a) Introduction b) Related Work c) About Dataset d) Methodology and approach e) Fallback mechanisms f) Results and Evaluations g) Conclusions & Future Scope with h) References. © 2023 IEEE.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

Demystifying Cyber terrorism: Causes, Costs & its impact on individuals' psyche and public confidence

Demystifying Cyber terrorism: Causes, Costs & its impact on ...

引用

2023 International Conference on Recent Advances in Electrical, Electronics and Digital Healthcare Technologies, REEDCON 2023

作者： Zahra, Syed Rameem Saleem, Tausifa Jan Sonia Netaji Subhas University of Technology Department of Computer Science and Engineering Delhi India Indian Institute of Technology Delhi Department of Electrical Engineering Delhi India Shoolini University Yogananda School of Ai Computer and Data Science H.P Solan India

ISBN: (纸本)9781665493826

Just like the game for Information technology (IT) security was turned topsy-turvy by the arrival of mobile devices a few decades ago, the Internet of Things (IoT) today is changing it again a big time. Data breaches, loss of productivity and profitability were quite a commonplace when mobile security became an issue. Today as IoT tries to connect everything to the internet, it intensifies the problem (more privacy violations, phishing/skimming attacks, security incidents) by creating a vast attack surface for the rogue players implying that important national (ports, airports, bridges, power-pants etc.) and cyber infrastructure could now be attacked. Moreover, if the network of your company has a weak point, it can easily be compromised to set off an attack. These Cyber terrorism attacks instigate identical responses from individuals as those for conventional terrorism attacks e.g. they heighten anxiety and stress, worsen feelings of vulnerability and harden the political attitudes of people. But this dimension is often overlooked by the policy makers. However, the increase in cyber terrorism cases has increased the research interest in the domain. Researchers are focusing on improving the security of internet and IoT devices. The field is still in its infancy. A lot needs to be done to mitigate these attacks. Motivated to demystify the repercussions of the cyber terrorism, this paper analyzes the distinctive characteristics of the most significant cyberattacks, investigates the expenditures incurred by the industries as a result of these cyber events, and then examines the impact of these attacks on the psychological health of the populace and the trust in public institutions. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Predicting Stress Using Time-Domain Feature engineering via Smartphone Soft-Typing Data

Predicting Stress Using Time-Domain Feature Engineering via ...

引用

Artificial Intelligence and Emerging technology (Global AI Summit), International Conference on

作者： Sakshi M.P.S Bhatia Pinaki Chakraborty Department of Computer Science and Engineering Netaji Subhas University of Technology Delhi India

ISBN: (数字)9798350379716

ISBN: (纸本)9798350379723

People with significant intellectual disabilities frequently struggle to articulate their stress, which makes timely carer reactions difficult. Stress, a frequent problem in modern life, is often overlooked, emphasising the importance of early detection. Smartphones, which are continually used, generate a variety of behavioural data, making them perfect for stress detection. This paper offers an autonomous real-time stress detection system that use wearable sensors to capture physiological signals and machine learning to detect stress-related changes. Our study uses data from smartphone sensors, including linear acceleration, gravity, gyroscope, and touchscreen sensors, to detect stress through soft keyboard typing behaviours. We capture nuances in phone interactions under stress by extracting statistical time domain features from raw sensor data, such as mean, variance, standard deviation, and energy. Using feature selection techniques, we reduced the dataset to the most significant features, minimizing model complexity and improving accuracy. We applied advanced machine learning methods like bagging, boosting, and stacking classifiers. The AdaBoost classifier achieved a 94.21% accuracy, a 5.58% improvement using the selected feature subset compared to the full feature set. The optimized model also significantly reduced the model-building time to 1.73 seconds, demonstrating the efficiency and practicality of our approach for real-time stress detection.

关键词： Accuracy Computational modeling Touch sensitive screens Feature extraction Boosting Real-time systems Time-domain analysis Stress Smart phones Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

An optimized classification of apps reviews for improving requirement engineering

引用

Recent Advances in computer Science and Communications 2021年第5期14卷 1390-1399页

作者： Bhatia, M.P.S. Kumar, Akshi Beniwal, Rohit Division of Computer Engineering Netaji Subhas Institute of Technology Delhi India Department of Computer Science & Engineering Delhi Technological University Delhi India

Background: The App Stores, for example, Google Play and Apple Play Store provide a platform that allows users to provide feedback on the apps in the form of reviews. An app review typically includes star rating followed by a comment. Recent studies have shown that these reviews possess a vital source of information that can be used by the app developers and the vendors for improving the future versions of an app. However, in most of the cases, these reviews are present in unstructured form and extracting useful information from them requires a great effort. Objective: This article provides an optimized classification approach that automatically classifies the reviews into a bug report, feature request, and shortcoming & improvement request relevant to Requirement engineering. Methods: Our methodology used supervised Machine Learning techniques (Multinomial Naive Bayes, Linear SVC, CART Decision Tree) that have been first evaluated based on t h e conven-tional Bag of Words (BOW) feature extraction model along with other auxiliary features such as review rating, review length, review tense, and review sentiment score to automatically classify app reviews into their relevant categories, and subsequently, a feature selection method is used to provide an optimized classification approach for improving classifier performance using Particle Swarm Optimization (PSO) nature-inspired algorithm. Results: Result shows that we achieved best results with precision of 62.0 % and recall of 47.3 % with Linear SVC Machine Learning technique, which we further optimized with PSO nature-inspired algorithm, i.e., with PSO + Linear SVC, thus, resulting in a precision of 63.6 % and recall of 55.0 %. Conclusion: This optimized automatic classification improves the Requirement engineering where developer straightforwardly knows what to improve further in the concerned app. © 2021, Bentham Science Publishers. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Optimization of environmental impact inclusive cost for sustainable distributed energy resources in distribution system

引用

Neural Computing and Applications 2024年 1-13页

作者： Firdous, Aaquib Tyagi, Arjun Tyagi, V.V. Kumar, Bhavnesh Centre for Energy & amp Environment Malaviya National Institute of Technology Rajasthan Jaipur302017 India Department of Electrical Engineering Faculty of Technology University of Delhi Delhi110007 India School of Energy Management Shri Mata Vaishno Devi University Jammu & Kashmir Katra182320 India Department of Instrumentation and Control Engineering Netaji Subhas University of Technology New Delhi110078 India

The proliferation of renewable energy (RE) and increasing electrical demand stress the existing generation and transmission systems. Moreover, due to environmental concerns, the proper utilization of small-scale renewable distributed energy resources (DERs) has become essential. DERs can play a pivotal role in evolving grids by reducing emissions and improving energy delivery by providing system services like voltage maintenance. Optimal sizing and sitting of these DERs into the distribution system promise various benefits and a viable solution to overcome the limitations of large transmission and conventional generation systems and provide better voltage maintenance. Besides, utilizing realistic data generation from working plants and varying load patterns allows for better insights into power system operations under growing RE. This work presents a profit-based optimal sizing and sitting of DERs into the distribution system while considering environmental costs. An improved Harmony Search algorithm has been applied to optimize the proposed cost-based objective function, which consists of various costs in generating distributed energy while simultaneously considering the environmental expenses incurred due to the release of different pollutant gasses. Also, the generation data of working solar and wind plants and realistic varying loads across seasons, weekdays, and weekend days have been considered to explore real operating scenarios. Efficacy has been verified from the optimization results that illustrate its capability to allocate DERs in conjunction with reduced costs and emissions, facilitating optimal system operations. The algorithm has been tested for two standard distribution systems focusing on reducing overall generation costs, social costs labelled due to emissions, improvement in voltage profile, and reduction in overall losses of the system. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Distributed energy

来源：评论

学校读者我要写书评

暂无评论

Hate Speech Detection in Hindi language using BERT and Convolution Neural Network 3

Hate Speech Detection in Hindi language using BERT and Convo...

引用

3rd IEEE International Conference on Computing, Communication, and Intelligent Systems, ICCCIS 2022

作者： Shukla, Shubham Nagpal, Sushama Sabharwal, Sangeeta Netaji Subhas University of Technology Department of Computer Science and Engineering Sector-3 Dwarka Delhi India

ISBN: (纸本)9781665462006

Social media has become crucial in our lives;it inculcates our opinions by providing untreated information. Whether we might be not participating actively but indirectly everyone became part of its coverage. Wide spread of information over the internet without any validation made it hard to analyze the impact of misleading information. Cyber hate, which is used as a tool to incite violence against a group of people based on ethnicity, nationality, language, sexual orientation, religious faiths, etc., poses a disgraceful utilization of social media. Previous apposite studies reported hate speech mainly in the English language. Less effort has been made for the resource-constraint language such as Hindi, Marathi, Kannada, etc. This work entitles hate speech detection in low-resource Hindi language using BERT and Deep Convolution Neural Network. The proposed Hindi Hate Speech BERT Convolution Neural Network model intends to detect hate speech in real-time so that any harmful incidence can be avoided as early as possible. This model presents a two-stage architecture: In the first stage, we have applied a pre-trained BERT encoder to generate encodings. In the second stage, a convolution neural network followed by a sigmoid layer is used to detect text as hatred or non-hatred. Our model achieved 0.84 & 0.77 f1-score for Hasoc 2020 and Hasoc 2021 dataset respectively. © 2022 IEEE.

关键词： Neural network models

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：