检索结果-内蒙古大学图书馆

Computational Intelligence, Communication technology and Networking (CICTN), International Conference on

作者： Aditya Pai H Chandrappa S Guru Prasad M S Atul Thakare Sharon Christa Pratik Kumar MIT School of Computing MIT Art Design and Technology University Pune India School of Computer Science and Engineering JAIN Deemed to be University Bengaluru India Dept. of Computer Science and Engineering Graphic Era (Deemed to be University) Dehradun India Department of Computer Application Graphic Era (Deemed-to-be University) Dehradun India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

Software reuse improves productivity and ensures that there is less time delivered to the market by enabling the proper usage of reusable code from the software repositories. The study provides the collaboration between the AI techniques, which includes Convolution Neural Networks (CNN), Random Forest (RF), and Support Vector Machines (SVM), to predict software components' reusability. The comparative analysis shows the effectiveness of different AI- driven algorithms, where CNN has shown the highest accuracy of 92%, thus reducing the human effort in finding the reusable modules. The Case studies in e-commerce and health care show the benefit of using AI-driven reuse of software; this means that the development time is reduced by 25%, and the maintenance cost is decreased by 20%. The paper highlights how different AI algorithm integration with software engineering has some limitations. The findings show that AI has greatly revolutionized software reuse. Thus bringing innovation and efficiency in software engineering.

关键词： Support vector machines Computational modeling Medical services Software Data models Convolutional neural networks Artificial intelligence Software reusability Random forests Software engineering

来源：评论

学校读者我要写书评

暂无评论

QoS provisioning based cost-effective routing in WSN based IoT network using fuzzy IDA∗ technique 8

QoS provisioning based cost-effective routing in WSN based I...

引用

8th International Conference on Computing for Sustainable Global Development, INDIACom 2021

作者： Lenka, Stitapragyan Nanda, Arabinda Pradhan, Sateesh Kumar Utkal University P. G. Dept. of Comp. Sc. and Application Bhubaneswar Odisha India Eastern Academy of Science and Technology Dept. of Computer Science and Engineering Bhubaneswar Odisha India

ISBN: (纸本)9789380544434

Wireless Sensor Network(WSN) is an integral part of Internet of Things (IoT) application network. Cost-effective WSN routing will help IoT applications to offer faster services in an efficient way. Routing in WSN is one of the challenging task due to node mobility and need on small battery to ruins active in the network. Flat routing shows poor performance for WSN if number of node increase. Cluster based routing is the alternative that is scalable and shows better utilization of network resources. The data transmission cost will be more, if the sender nodes send data directly to sink node due to large distance of data transmission and the node battery power dry very soon. To overcome this problem data packets send from sender node to sink node via cluster head node. The member nodes of a cluster send data packets to its header node, then the header node send the data packets to sink node. In our proposed method, the fuzzy inference system uses three Quality of Service (QoS) parameters distance, energy and angle to select the chance of a node becomes cluster head. Iterative Deepening A*(IDA*) search used to discover the shortest route that send data packets from supply node to the sink node. The fuzzy system is used to select the cluster head and IDA∗ search algorithm used to select the minimal cost path. The proposed method - Cost Effective Routing in WSN Using Fuzzy IDA*(CERWFI) is used to find an optimal route from starting node to ending node (sink). The research concludes by stating that space complexity of Dijkstra's and A∗ algorithm can be improved by IDA∗ algorithm. © 2021 Bharati Vidyapeeth, New Delhi. Copy Right in Bulk will be transferred to IEEE by Bharati Vidyapeeth.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

LSTM-Based Top N Recommendation System using Cognitive Data

LSTM-Based Top N Recommendation System using Cognitive Data

引用

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： Avick Kumar Dey Vineet Kumar Chauhan Pradeep Kumar Singh Prasenijit Choudhury Dept. of Computer Science & Engg. National Institute of Technology Durgapur India Dept. of Computer Science & Engg. Teerthankar Mahaveer University Moradabad India Dept. of Computer Engg.and Application GLA University Mathura India

ISBN: (纸本)9781665487351

With the rapid increase in Social Web applications, a significant amount of research has been dedicated to the analysis and development of personalized recommendations using artificial intelligence. Different machine learning and neural networks are applied widely to recommend relevant research books or research articles to online learners. However, conventional machine learning algorithms require additional training models to train recommendation models for processing large-scale data. Hence they are considered to be inappropriate for generating personalized recommendations in learning systems. This research presents an LSTM-based approach for generating appropriate learning recommendations. The proposed approach analyses the behavior of online learners and predicts their interests. The performance of the proposed approach will be validated by determining different performance metrics such as accuracy, precision, recall, and F1 score.

关键词： Measurement Training Matched filters Simulation Neural networks Feature extraction Market research

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based model for Loan Amount Prediction and Distribution

Machine Learning based model for Loan Amount Prediction and ...

引用

2022 Workshop on Advances in Computational Intelligence, its Concepts and applications, ACI 2022

作者： Sharma, Hitesh K. Choudhury, Tanupriya Ahlawat, Prashant Mohanty, Sachi N. Jain, Sarika Dehradun248007 India Dept. of Computer Science Chandigarh University Punjab 140413 India Department of Computer Science Singidunum University Serbia and and School of Computer Science & Engineering VIT-AP University Andhra Pradesh Amaravati India Dept. of Computer Application National Institute of Technology Haryana Kurukshetra136119 India

With the enhancement of the technology, expand of businesses and thoughts more and more people are applying for the loans. Both for their personal use and for business use. But due to the limited amount of assets the bank cannot grant loans to each and every person. Finding out those right people is a typical and time-consuming process. Banks desire to deliver the loan to an individual who can be recompensate the loan on time and can afford maximum profit to the bank. So there is a need of a system which could do this analysis and save the banks time and resources. This can be done using Machine Learning. The objective of this paper is to create a more accurate loan prediction model using machine learning to reduce the risk behind selecting of appropriate people for the loan. For this we'll mine the previous records of the people to whom the bank has granted loan. Using these records variables and bank loan rules we will train a machine learning model which will predict that a person is eligible for loan or not. We will use sklearn for our model and train_test_split for splitting the data set into train dataset and test dataset. Here we are going to use various models like Logistic Regression, Decision Tree(DT) and Random Forest(RF) so as to fetch more accurate results as the given problem is a supervised classification problem. © 2020 Copyright for this paper by its authors.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Mathematical Models of Heterogeneous Machine Learning Techniques for Ransomware Protection in Cyber-Physical Systems

Mathematical Models of Heterogeneous Machine Learning Techni...

引用

Communication, Computing and Signal Processing (IICCCS), IEEE International Conference on

作者： Subir Gupta Sudipta Hazra Simanta Hazra Sourav Gayen Sayanti Mukherjee Anwesa Naskar Dept. of CSE (AIML) Haldia Institute Of Technology Haldia WB India Dept. of C.S.E. Asansol Engineering College Asansol WB India Dept. of C.S.E. NSHM Knowledge Campus Durgapur WB India Dept. of Computer Application Asansol Engineering College Asansol WB India Dept. of I.T. College of Engineering and Management Kolaghat Kolaghat WB India

ISBN: (数字)9798350390759

ISBN: (纸本)9798350390766

Ransomware attacks are a growing threat to cyber-physical systems (CPS), capable of causing financial losses, downtime, and even physical harm. Using machine learning to detect and prevent these attacks is a promising approach. A study compared four machine learning techniques—support vector machines (SVM), decision trees, random forests, and neural networks—to detect ransomware attacks on CPS. The models were trained and evaluated using a dataset of real ransomware incidents. Results showed that all four techniques effectively detected ransomware attacks. Neural networks achieved the highest F1 score, while SVMs excelled in precision, recall, and accuracy. However, the differences in performance among the methods were not significant. The models detected ransomware outbreaks within an average of 12 hours, allowing businesses to mitigate the attack's effects promptly. The study concluded that machine learning could effectively detect and prevent ransomware attacks on CPS. However, it is important to note that the study used a limited dataset, highlighting the need for further research with larger datasets to confirm these findings.

关键词： Support vector machines Neural networks Machine learning Organizations Cyber-physical systems Data models Ransomware Decision trees Protection Random forests

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Healthcare Record Management: Secure Documentation Storage and Access through Advanced Blockchain Solutions

arXiv

引用

arXiv 2025年

作者： Brijwani, Geeta N. Ajmire, Prafulla E. Junaid, Mohammad Atique Mohammad Charasia, Suhashini Awadhesh Bhende, Deepali O. Computer Science Dept. Sant Gadge Baba Amravati University Amravati India Department of Computer Science Faculty of Engineering & Technology Sant Gadge Baba Amravati University India Department of Computer Science Rashtrasant Tukadoji Maharaj Nagpur University Nagpur India Department of Master of Computer Application Rashtrasant Tukadoji Maharaj Nagpur University Nagpur India

Integrating blockchain technology into healthcare systems presents a transformative approach to documenting, storing, and accessing electronic health records (EHRs). This research introduces a novel blockchain-based EHR system designed to significantly enhance security, scalability, and accessibility compared to existing solutions. Current systems primarily utilize SHA-256 for security and either IPFS or centralized storage, which, while effective, have limitations in providing comprehensive data integrity and security. The proposed system leverages a hybrid security algorithm combining Argon2 and AES and integrates a hybrid storage and consensus mechanism utilizing IPFS and PBFT. This multifaceted approach ensures robust encryption, efficient consensus, and high fault tolerance. Furthermore, the system incorporates Multi-Factor Authentication (MFA) to safeguard against unauthorized access. It utilizes advanced blockchain tools like MetaMask, Ganache, and Truffle to facilitate seamless interaction with the decentralized network. Simulation results demonstrate that this system offers superior protection against data breaches and enhances operational efficiency. Specifically, the proposed hybrid model substantially improves data integrity, consensus efficiency, fault tolerance, data availability, latency, bandwidth utilization, throughput, memory usage, and CPU usage across various healthcare applications. To validate the performance and security of the proposed system, comprehensive analyses were conducted using real-world healthcare scenarios. The findings highlight the significant advantages of the blockchain-based EHR system, emphasizing its potential to revolutionize healthcare data management by ensuring secure, reliable, and efficient handling of sensitive medical information. © 2025, CC0.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Narrow Down Forecast Range: Using Knowledge of Past Operations and Attribute-Dependent Thresholding in Good Fishing Ground Prediction

Narrow Down Forecast Range: Using Knowledge of Past Operatio...

引用

OCEANS

作者： Haruki Konii Teppei Nakano Yasumasa Miyazawa Tetsuji Ogawa Dept. of Communications and Computer Engineering Waseda University Tokyo Japan Intelligent Framework Laboratory Tokyo Japan Application Laboratory Japan Agency for Marine-Earth Science and Technology Yokohama Japan

In this study, an attempt has been made to highly narrow down the results of predicting good fishing grounds. In the automatic prediction of good fishing grounds using meteorological and oceanographic information, there is a trade-off between reducing the number of missed detections of good fishing grounds and narrowing down the forecast range. For example, the forecast range will inevitably widen if good fishing grounds are tried to be detected perfectly, which has a negative impact on fishers’ operational decision-making. This study, therefore, attempts to introduce techniques to narrow down the forecast range, such as the use of past operational information and stricter thresholding for judgment, to the convolutional autoencoder-based good fishing ground prediction. Experimental comparisons conducted using actual catch information in bullet tuna trolling demonstrated the effectiveness of the proposed method; it succeeded in narrowing down the forecast range of good fishing grounds without increasing the number of good fishing grounds missed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image-Based Attendance System using Facial Recognition

Image-Based Attendance System using Facial Recognition

引用

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： Vineet Kumar Chauhan Trilok Singh Abhishek Dixit Raushan Kumar Singh Pradeep Kumar Singh Juginder Pal Singh Dept. of Computer Science & Engg TMU University Moradabad India Dept. of Computer Science & Engg. Invertis University Bareilly India Dept. of Information Technology Vardhaman College of Engineering Hyderabad India Dept. of Computer Engg. and Application GLA University Mathura India

ISBN: (纸本)9781665487351

In today's digital age, attendance systems utilizing facial recognition are essential in schools, universities, companies, etc. One feature of the human body that might help identify a person is the face. Using a camera, we initially built a database of various people's faces for this project, and the recognizer algorithm would use this information. The system will be prepared to take attendance on its own after the database has been established. A cross-check will be performed between the recently acquired face image and the database. The attendance will be recorded and the data immediately saved into the excel sheet if the same face's image is found in the database. This attendance-based system using Face Recognition will be developed using PCA (Principal Component Analysis) and CNN (Convolutional Neural Network).

关键词： Databases Face recognition Companies Wavelet analysis Market research Information age Linear discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer in Oral Cancer Detection

Vision Transformer in Oral Cancer Detection

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： Pinky Agarwal Naman Gupta Yashita Bharadwaj Anju Yadav Pratistha Mathur Computer Application Manipal University Jaipur Jaipur India Dept. name of organization (of Aff.) Manipal University Jaipur Jaipur India Information Technology Manipal University Jaipur Jaipur India

Oral cancer is a malignancy that can manifest in multiple areas of the mouth, including the tongue, lips, oral mucosa, gums, floor of the mouth, and other soft tissues. Despite the development of advanced diagnostic and therapeutic methods, the incidence and prevalence of oral cancer continue to be a cause for concern. This condition can have devastating effects on patients, including significant physical and emotional distress. Detecting oral cancer at an early stage can improve a patient's chances of survival and reduce the need for aggressive treatment. In recent years, machine learning techniques have demonstrated promising results in the detection of oral cancer. This research aims to explore the role of vision transformers in oral cancer classification as benign and malignant. The results obtained from the vision transformer are compared with Machine learning techniques like SVM, extreme Gradient Boosting (XGBoost), and Random Forest. Overall, the results show that ViT outperformed SVM, Random Forest, and XGBoost in oral cancer detection and stage classification with an accuracy of 96.7%. The accuracy, precision, recall, and F1-score of ViT are higher than other methods. The findings of the research show that all four machine learning methods examined can produce high precision rates in detecting oral cancer, with the Vision Transformer technique achieving superior results as vision transformers are designed to capture global context information in images. The proposed system has great potential to advance the precision and efficiency of oral cancer diagnosis, which can lead to more prompt and effective treatment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of Symptoms for Malaria using Soft Computing Method 1

Classification of Symptoms for Malaria using Soft Computing ...

引用

1st International Conference on Machine Learning, computer Systems and Security, MLCSS 2022

作者： Nayak, Subrata Kumar Pradhan, Sateesh Kumar Mishra, Sujogya Patra, Narayan Pradhan, Sipali GVHSS Sishu Ananda Mahavidyalaya Department of Computer Science Odisha Balipatna India Utkal University Department of Computer Science and Application Bhubaneswar India Odisha University of Technology and Research Department of Mathematics Odisha Bhubaneswar India Institute of Technical Education and Research SoA Deemed to Be University Department of Csit Bhubaneswar India Rbvrr Women's College Dept. of Computer Science Hyderabad India

ISBN: (纸本)9781665454933

Detection of Malaria Fever is a challenge for the doctors as symptoms of Malaria fever vary concerning places;for example, the types of malaria fever found in our country are not the same in South Africa, England, and other western countries. Malaria is not fatal if detected early, but due to its complex nature, it is difficult to side-line this fever with other fevers like Typhoid, Dengue, and other class of fevers. Our objective is to find the minimal attributes responsible for malaria by using Rough Set Theory (RST), a Soft Computing technique that is a useful tool to handle imprecise and vague datasets. Our objective is to find a set of attributes (symptoms) of malaria from the vague medical data set, which are helpful for the doctors for concrete diagnosis of malaria. We validate our claim by using statistical techniques. © 2022 IEEE.

关键词： Rough set theory

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：