检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Garg, Shail Gayatri, Yerukola Surya Kausthub, A. Rajagopal, Shinu M. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

The study investigates how quantum cryptography can be employed to improve security in smart grid communication networks. Attempting to use the BB84 QKD protocol, it allows secure creation and management of those cryptographic keys that cannot be broken with the help of quantum and traditional hacking techniques. It depends on symmetric encryption mechanisms like AES to provide high data confidentiality during transmission. Regarding the key management, the system provides a key management server that distributes keys to the grid nodes and performs key updating to ensure control with the managing authority. It also presents reliability under practical conditions through performance analogs such as Quantum Bit Error Rates (QBER), and system latency. This approach shows that quantum cryptography can provide a highly secure and efficient communication network for the next-generation smart grid. © 2025 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Big Data Application in Cancer Classification by Analysis of RNA-seq Gene Expression 3

Big Data Application in Cancer Classification by Analysis of...

引用

3rd IEEE International Conference on Intelligent Technologies, CONIT 2023

作者： Amruth, A. Ramanan, R. Paul, Rhea Vishal, S. Saravanan, S. Amrita School of Computing Dept. of Computer Science and Engineering Bengaluru India Amrita School of Computing Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350338607

computer Science domain has got massive developments in the past decade, especially in the field of Big Data and Artificial Intelligence. Many industries are adopting these technologies to improve their products and services. Healthcare is one such industry which comes across voluminous data. Big Data platform is used to process the data and subsequently AI models can be used for prediction or classification. This paper focuses on proposing a Spark based pipeline to reduce the time required to process the voluminous data. With the aid of this new pipeline, we classify the type of cancer through analysis of RNA-seq gene expression levels. The Spark-based pipeline is run on default standalone mode and on a cluster. The study recorded that the Spark-based pipeline run on cluster mode improved the performance approximately by 11 times (regarding processing costs) when compared to the performance of Python-based pipeline. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Path Planning for Autonomous Drones Using Proximal Policy Approximating Agent

Path Planning for Autonomous Drones Using Proximal Policy Ap...

引用

International Conference on Advances and Applications of Artificial Intelligence and Machine Learning, ICAAAIML 2023

作者： Varshini Devi, I. Pravine Mukesh, R. Paayas, P. Varsha, P. Supritha, R. PrasannaKumar, R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (纸本)9789819795062

The advent of autonomous drones promises transformative applications across many industries, necessitating the ability to plan long-range paths automatically. The purpose of this paper is to explore the synergistic effect of Markov Decision Processes (MDPs) and deep reinforcement learning (DRL) in the context of autonomous drone racing. A simulated racing track is used to demonstrate how autonomous drones can optimize path planning using the Proximal Policy Optimization algorithm (PPO). In our study, we present an agent that efficiently navigates strategic checkpoints, is adaptable, and generalizes its skills to similar situations. It demonstrates the potential of DRL and PPO to advance autonomous drone path planning, paving the way for practical implementation in a wide range of industries. With drones reshaping industries, this work contributes to the exciting future of autonomous systems. The agent covered an average distance of 19.6 m per episode, showcasing its ability to navigate the test environment effectively. In a notable feat, the agent exhibited the capability to pass through a maximum of 9 holes in the test environment without encountering any collisions. This indicates a high level of adaptability and strategic decision-making, even in the face of increased environmental complexity. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Feature Selection Model for Early Prediction of Metabolic Syndrome 4

A Hybrid Feature Selection Model for Early Prediction of Met...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Sreepadh, A.S. Sheshu, P. Reshiha, R.G. Kumar, T Vinay Jeyakumar, Gurusamy Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9798331523923

Metabolic Syndrome (MetS) is a medical condition that increases the risk of cardiovascular diseases, stroke, and type 2 diseases. Some of the symptoms of MetS are high blood pressure, elevated blood sugar, excess body fat, and abnormal cholesterol levels. All these symptoms are interconnected, which has made early diagnosis of MetS critical. In current medical strategies, there is no personalized medication which leads to unfavorable health outcomes and further increased risks. This paper aims to address these challenges by identifying optimal feature subsets required for the early prediction of MetS. To get the optimal features a hybrid model is proposed in this paper. The proposed model utilizes both the filter method and the wrapper method. Firstly, features are selected using the correlation coefficient (CC) method which is a filter method, and then the selected features are further refined using genetic algorithm (GA) which is a wrapper method. This hybrid model increases the prediction accuracy and reduces computational cost. The methodology of the proposed model, its experimental setup, the results obtained, and the inferences gained are presented in this paper. © 2025 IEEE.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Explaining Sentiments in Indian Legal Judgments with LIME and SHAP 8th

Explaining Sentiments in Indian Legal Judgments with LIME an...

引用

8th IFIP TC 12 International Conference on computer, Communication and Signal Processing, ICCCSP 2024

作者： Babu, T. Hemanth Kiran, V. Gopi Bhat, Suhas S. Prabhakar, Priyanka Pati, Peeta Basa Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9783031736162

This paper presents a comparative study on sentiment analysis applied to legal texts, specifically legal opinions, and judgments. This paper uses embeddings such as T5, XLM Roberta and BERT, Roberta, and Legal BERT to convert the textual data into pre-trained language model word representation, to make it easier for ML algorithms to determine the sentiment (positive, negative, or neutral) of legal documents. The dataset was converted into embeddings, and various models, including KNN, ANN, SVM, random forest, XG boost, logistic regression, and decision tree, were employed for sentiment analysis. Each model was subjected to hyperparameter tuning using Grid Search CV, resulting in the highest accuracy of 66.66% with SVM on T5 embeddings. This research provides valuable insights into the emotional degrees within legal texts, demonstrating the effectiveness of our sentiment analysis approach. © IFIP International Federation for Information Processing 2025.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Design and Simulation of an Intelligent Traffic Management System Using Vehicular Networks 3

Design and Simulation of an Intelligent Traffic Management S...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Tapan Datta, P. Lalith Kumar, D. Tanoj, S. Rajagopal, Shinu M. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

In this study, the reasearch is focused on the simulation of vehicular communication networks, especially intelligent traffic systems, to enhance dependability, safety, and optimality in communication. The simulation is performed using the OMNeT++ simulator and is integrated with the Veins framework that uses the IEEE 802.11p protocol for V2V and V2I communications. Importing real-world traffic scenarios into the framework is obtained via the use of SUMO through TraCIScenarioManager. Other features of the framework include the definition of mobility models, dynamic obstacles, and detailed radio propagation modeling. TraCIDemo11p is used for mobility and communication by both RSUs and vehicles with applications in beaconing and channel switching. The whole framework analyzes smart traffic management solutions, providing as much insight into their performance based upon the communication reliability and overall efficiency in vehicular networks. © 2025 IEEE.

关键词： Highway administration

来源：评论

学校读者我要写书评

暂无评论

Keyframe Extraction Approaches for Intelligent Video Analysis 4

Keyframe Extraction Approaches for Intelligent Video Analysi...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Sabarivasan, N. Thangavel, Senthil Kumar Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9798331523923

Real-time violence detection is essential for protecting the safety and security of people, especially in college campuses that are dynamic and have crowds. Manual surveillance systems are popular but inefficient as they require human attention all the time and are not capable of quickly identifying and responding to violent *** the exsisting violence detection model takes quite a time for processing the entire video. The proposed model extracts features as keyframes from the video using MobileNet V3 and K-medoids clustering. The redundancy of video data can be avoided and significant violent activities identified by isolating and analyzing critical frames from video data. This enhances the efficiency and responsiveness of surveillance systems. This work primarily contributes a customized violent activities dataset and implementing keyframe extraction algorithm for optimizing the usage of computational resources, and incorporating lightweight algorithms for seamless deployment with existing CCTV networks. The experimental results clearly demonstrate the ability of this approach to detect keyframes, thereby offering a scalable and practical solution. © 2025 IEEE.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Detection of Acute Lymphoblastic Leukemia in Microscopic Blood Cell Images 12th

Efficient Detection of Acute Lymphoblastic Leukemia in Mic...

引用

12th International Conference on Big Data and Artificial Intelligence, BDA 2024

作者： Pavani, Bhupathi Vishva Thanmai, Gaddam Singh, Rimjhim Padam Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9783031818202

Acute Lymphoblastic Leukemia (ALL), a type of blood cell cancer, rapidly progresses until it affects the white blood cells, compromising the human body’s ability to fight infections. Untreated Acute Lymphoblastic Leukemia (ALL) can quickly infiltrate vital organs, leading to life-threatening situations and its early treatment is essential to prevent the destructive spread and improve the survival chances. Recent deep-learning techniques help in timely diagnosis of the fatal disease with Convolutional Neural Networks (CNN) detecting Acute Lymphoblastic Leukemia (ALL) in patients by automatically analyzing microscopic blood cell images. Hence, this paper proposes a novel CNN-based approach employing the fine-tuned EfficientNet-B0 model enhanced using an optimally placed self-attention layer with HardSwish activation function. Experimentational analysis has also been done by employing self-attention layers at different architectural positions and with recent activation functions to develop an efficient and optimal model architecture. Several other CNN models such as MobileNet, EfficientNetB0, DenseNet, NASNet, InceptionV3, and Xception have also been trained to classifying blood cell images into normal and ALL classes for comparison purposes. The proposed model outperformed all other techniques with a huge margin of 5% and had the highest accuracy of 86.85%, precision of 87%, recall of 87%, and F1-Score of 87%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Advanced Financial Sentiment Analysis using FinBERT to Explore Sentiment Dynamics 3

Advanced Financial Sentiment Analysis using FinBERT to Explo...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Baghavathi Priya, S. Kumar, Madhav Nitheesh Prakash, J.D. Krithika, N. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (纸本)9798331527549

This research investigates the incorporation of sophisticated Natural Language Processing (NLP) methods in the intricate field of finance. In particular, it utilizes FinBERT, a tailored language model created to understand the complex subtleties of financial text data, in conjunction with assessments of DistilBERT and Bidirectional Encoder Representations from Transformers (BERT). The main goal is to create a strong preprocessing framework that improves the interpretative ability of models for sentiment classification designed for financial uses while providing an in-depth evaluation of the comparative performance of the models. Through extensive empirical validation, our approach demonstrates that FinBERT outperforms the other models in accurately capturing subtle sentiment variations and financial terminology. The comparative study underlines the compromises between computational efficiency and precision, with DistilBERT providing a streamlined option. This research emphasizes FinBERT’s transformative capabilities in analyzing financial sentiment and simultaneously delivering essential insights into the comparative strengths and weaknesses of other approaches, presenting a comprehensive viewpoint to inform decision-making within the financial sector. Upon comprehensive analysis of the methods used in this paper, it is shown that FinBERT is best at capturing hidden features within the data and able to work well with unseen data also with an average accuracy of 89.6% over all the 3 classes that are present in the dataset. The suggested framework has the potential to greatly improve predictive analytics and risk management approaches, allowing for more informed, precise, and prompt financial decisions in intricate market conditions. © 2025 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

A survey on dynamic graph processing on GPUs: concepts, terminologies and systems

引用

Frontiers of computer Science 2024年第4期18卷 1-23页

作者： Hongru GAO Xiaofei LIAO Zhiyuan SHAO Kexin LI Jiajie CHEN Hai JIN National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Zhejiang Lab Hangzhou 311121China

Graphs that are used to model real-world entities with vertices and relationships among entities with edges,have proven to be a powerful tool for describing real-world problems in *** most real-world scenarios,entities and their relationships are subject to constant *** that record such changes are called dynamic *** recent years,the widespread application scenarios of dynamic graphs have stimulated extensive research on dynamic graph processing systems that continuously ingest graph updates and produce up-to-date graph analytics *** the scale of dynamic graphs becomes larger,higher performance requirements are demanded to dynamic graph processing *** the massive parallel processing power and high memory bandwidth,GPUs become mainstream vehicles to accelerate dynamic graph processing ***-based dynamic graph processing systems mainly address two challenges:maintaining the graph data when updates occur(i.e.,graph updating)and producing analytics results in time(i.e.,graph computing).In this paper,we survey GPU-based dynamic graph processing systems and review their methods on addressing both graph updating and graph *** comprehensively discuss existing dynamic graph processing systems on GPUs,we first introduce the terminologies of dynamic graph processing and then develop a taxonomy to describe the methods employed for graph updating and graph *** addition,we discuss the challenges and future research directions of dynamic graph processing on GPUs.

关键词： dynamic graphs graph processing graph algorithms GPUs

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：