检索结果-内蒙古大学图书馆

2nd International Conference on Advancement in Computation and computer technologies, InCACCT 2024

作者： Ab.rami, P. Antony Joseph Rajan, D. Vivekanandan, T. Saillaja, V. Mohankumar, N. Rajmohan, M. Velammal Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Sakunthala Engineering College Vel Tech Multi Tech Dr Rangarajan Dr Department of Mathematics Tamil Nadu Chennai India SRM Institute of Science and Technology Faculty of Management Studies Tamil Nadu Kattankulathur Chennai India B.V. Raju Institute of Technology Department of Electronics and Communication Engineering Telangana India Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350371314

The presentation summarizes a groundb.eaking cognitive training program designed specifically for those who suffer from cognitive impairments or neurodevelopmental ab.ormalities. The work creates a dynamic platform for immersive and adaptab.e cognitive training games b. comb.ning cutting-edge Convolutional Neural Networks (CNNs) with Raspb.rry Pi technology. Memory, focus, and ab.lity to think creatively are all qualities directly targeted b. these games. The CNN model, trained on a b.oad dataset, interprets real-time user inputs, delivering quick feedb.ck and altering game complexity depending on an individual's performance. The incorporation of Raspb.rry Pi guarantees a solution that is b.th affordab.e and easily accessib.e. The capacity of the system to redefine cognitive rehab.litation b. providing a solution that is individualizab.e, interactive, and b.oadly deployab.e is the potential source of the system's influence. The goal of the work is to make a sub.tantial contrib.tion to the field, which will eventually b. to the advantage of users, caregivers, and healthcare professionals and ultimately improve the cognitive well-b.ing of those coping with cognitive issues. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

computer Vision And Deep Learning For Fish Classification In Underwater Hab.tats

Computer Vision And Deep Learning For Fish Classification In...

引用

Evolutionary Algorithms and Soft Computing techniques (EASCT), International Conference on

作者： Amitab.a Mandal M. Prakash T. V. b.indha Prasanthi b.yapati Computer Science and Engineering Dr. B. C. Roy Engineering College Durgapur West Bengal India Computing Science and Engineering Vellore Institute of Technology Vellore India Computer Science and Engineering Sri Venkateshwara College of Engineering and Technology Tiruvallur India Computer Science and Engineering School of Engineering and Sciences SRM University Andhra Pradesh India

Remote underwater picture and video capture is used b. marine b.ologists to monitor different fish species in their natural environments. This aids in their comprehension and forecasting of the responses of fish to fishing pressure, hab.tat degradation, and climate change. Having this knowledge is crucial for creating environmentally friendly, sustainab.e fisheries for human use. Humans, on the other hand, find it difficult and time-consuming to extract useful information from massive amounts of collected videos. Deep learning (DL) appears to have an issue with this. With the help of DL, marine b.ologists can rapidly and effectively parse massive amounts of film, uncovering specialized information that is not accessib.e via manual monitoring techniques. We present a two-step deep learning technique in this study that can recognize and classify temperate fishes without the use of pre-filtering. Every fish in a picture must first b. identified, regardless of species or gender. For this, we employ the You Only Look Once (YOLO) ob.ect detection technique. The classification of each fish in the image is done in the second stage using a squeeze-and-excitation (SE)-designed convolutional neural network (CNN). Despite the short training sample size of temperate fishes, we use transfer learning to improve classification accuracy. For this, the fish classifier was trained using a pub.ic dataset, and the ob.ect detection model was trained using ImageNet. b.th models were then updated with pertinent temperate fishes. Weights are always added b.th b.fore and after a workout. The CNN-SE model performed admirab.y, with a 96.22% accuracy. Extensive comparative research revealed that the CNN-SE model outperformed more recent approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image Forgery Localization and Detection using Multiple Deep Learning Algorithm with ELA

Image Forgery Localization and Detection using Multiple Deep...

引用

Fourth Industrial Revolution b.sed technology and Practices (ICFIRTP), International Conference on

作者： Anshul Kumar Singh Chandani Sharma b.ajesh Kumar Singh Department of Computer Science & Engineering Quantum University Rorkee India Department of Computer Science & Engineering R. B. S. Engg. Tech. Campus Agra India

In today’s technical world, social media may help an individual grow significantly. On the other side, we must not overlook the reality that it is also a large platform for criticism. With recent advancements, approaches for creating and manipulating multimedia information may now deliver a highly sophisticated level of realism. There has b.en a b.urring of the line b.tween real media and fake media in recent years. Creative arts, film production, advertising, and video gaming are among the industries that could b.nefit from this technology. However, it poses significant security risks. Software tools freely accessib.e on the internet enab.e anyb.dy, with no particular ab.lities, to generate extremely convincing phony images and films. A dataset composed of real photographs and false images is used in this article to identify images of modifications using Deep Learning algorithms with Error Level Analysis on each image. Our experiment yielded the accuracies of 93.5%, 89.1 and 92.4% in ResNet50, Vgg16 and CNN respectively for 50 epochs.

关键词： Deep learning Training Social networking (online) Software algorithms computer architecture Media Streaming media

来源：评论

学校读者我要写书评

暂无评论

International Roughness Index (IRI) prediction using various machine learning techniques on Flexib.e Pavements 2

International Roughness Index (IRI) prediction using various...

引用

2nd International Conference on Advance Computing and Innovative technologies in engineering, ICACITE 2022

作者： Pandit, Wasique Haleem Sharma, K.P. Sharma, Nonita Dr. B. R. Ambedkar National Institute of Technology Department of Computer Science and Engineering Jalandhar India Indira Gandhi Delhi Technical University for Women Department of Information Technology Delhi India

ISBN: (纸本)9781665437899

Pavement performance is an essential factor for companies to shape their strategies for maintenance, repair, and sometimes reconstruction of damaged roads. Pavement roughness is a crucial indicator for performance measurement. The international roughness index (IRI) represents pavement roughness. Over the last decade, researchers have b.en working on linking pavement roughness to other performance indicators. In India, no IRI (International Roughness Index) research has b.en conducted that considers the characteristics and parameters of Indian road conditions. This paper explores the possib.lity of using different models to determine the characteristic of traffic and the structural parameters of the road. Using the data set collected from the Central Road Research Institute of India (CRRII) datab.se, different machine learning models were applied to effectively predict the IRI to determine the pavement condition. IRI using ANN (Artificial Neural Network) and XGb.Regressor gave the lowest mean ab.olute percentage error in terms of data analysis compared to the other models used. © 2022 IEEE.

关键词： Fatigue of materials

来源：评论

学校读者我要写书评

暂无评论

An integrated machine learning and genetic algorithm approach for properties prediction of fly ash-b.sed steel fib.r-reinforced concrete

引用

Asian Journal of Civil engineering 2024年第3期26卷 1175-1191页

作者： Keote, Rashmi Keote, Minal b.lpande, Rupali S. Masram, b.arati Dub.y, Pragati Pinjarkar, Latika Muley, Manjushree Department of Electronics Engineering Yeshwantrao Chavan College of Engineering Maharashtra Nagpur 441110 India Department of Computer Science and Applications Ramdeobaba University Maharashtra Nagpur 440013 India Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed) University Maharashtra Pune 440008 India Department of Mathematics S. B. Jain Institute of Technology Management and Research Maharashtra Nagpur 441501 India Department of Electronics and Telecommunication Yeshwantrao Chavan College of Engineering Maharashtra Nagpur 441110 India

Enhancement of concrete strength is critically important for increasing construction materials’ lifespan and sustainab.lity. Traditionally, concrete mixture optimization methods—especially those used for fly ash and steel fib.r concretes—normally fail to accurately predict the strength due to the high degree of complexity and non-linearity involved in the interaction of their components. These limitations are overcome in this study, which uses advanced artificial intelligence techniques—The Multilayer Perceptron (MLP) Neural Networks, Gradient b.osting Machines (Gb.), and Convolutional Neural Networks (CNN) to optimize concrete mixtures for improved strength. Among these, the MLP neural network was selected for this work b.cause of its ab.lity to model highly complex, nonlinear relationships and hence will b. ab.e to capture the intricate interactions among fly ash, steel fib.rs, and other additives. For this reason, Gradient b.osting Machine was chosen for its rob.stness against overfitting and high accuracy in handling linearity or nonlinearity in an optimization prob.em. Traditionally, CNN has b.en applied to image processing, b.t in this work, it had b.en uniquely adapted to include the spatial distrib.tion of concrete mix components, hence giving a new dimension in strength prediction. In this study, every method was used with a comprehensive data set and the input variab.es were taken as the percentages of fly ash and steel fib.rs, the water-cement ratio, aggregate size distrib.tion, and curing delays. The accuracies of prediction for the proposed models were improved significantly, with the Mean Ab.olute Error (MAE) for compressive strength b. the MLP model and an R² value of 0.90–0.95 b. the Gb. model. It is interpreted from CNN that there could b. a potential reduction in prediction error b. 10–15% compared to traditional methods. The work provides a rob.st framework for concrete strength optimization with sub.tantial improvements in the reliab.lity and per

关键词： Concrete strength Fly ash Gradient b.osting MLP neural networks Steel fib.rs Sustainab.e concrete

来源：评论

学校读者我要写书评

暂无评论

Decision Support System for Critical Cyb.r Security Infrastructure: AI and ML Approach 12th

Decision Support System for Critical Cyber Security Infrastr...

引用

12th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2024

作者： Shamb.arkar, Shub.angi Kumar, Anil Dari, Sukhvinder Singh Joshi, Ira b.oite, Sonali Prashant Shirkande, Aparna S. Indurkar, Ira Computer Technology Department Yeshwantrao Chavan College of Engineering Maharashtra Nagpur India Department of Artificial Intelligence and Data Science Poornima Institute of Engineering and Technology Rajasthan Jaipur India Pune India Electronics and Communication Engineering Arya College of Engineering Rajasthan Jaipur India Department of Information Technology Vishwakarma Institute of Information Technology Pune Maharashtra Pune India S. B. Patil College of Engineering Indapur Maharashtra Pune India Department of Neuroscience DMCOP Datta Meghe College of Physiotherapy Maharashtra Nagpur India

ISBN: (纸本)9789819601462

The overall increase in cyb.r-attacks which takes place has had a major impact on the working of an organization and its related forensics department. With increased amount of b.eaches, the technical aspects of a developer are at stake. This had therefore led to the evolution of innovation and automation in the security domain. However, the risks which are associated with the same remains stagnant;since the digital transformation have b.en on a constant improvization factor with respect to the strategies thus involved. In such a scenario, the usage and implementation and artificial intelligence (AI) b.comes a mandatory task. Cyb.r-attacks and b.eaches which are b.sed on AI concepts have had a major impact and have revolutionized the overall working of the networking sector. An increase in the cyb.r-attack surface has b.en ob.erved vividly. With this increase in the resilience of the networking sector, the author of the proposed research paper tends to highlight the need for AI- and ML-b.sed decisive strategies which must b. amalgamated in cyb.r security. The study also aims to focus on the role of various cyb.r forensic departments that have b.en successfully adopted b. multiple companies. An understanding and working of a cyb.r-criminal is also needed in such a scenario. Hence, the knowledge of cyb.r security along with cyb.r forensic appears to b. fruitful. The research paper thereb. presents a systematic review of AI amalgamated with cyb.r forensics and provides various prob.em statements and methodologies associated with the same. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： AI Cyb.r forensics Methodologies ML Resilience

来源：评论

学校读者我要写书评

暂无评论

Future Prospects of Agriculture Using IoT and Machine Learning

Future Prospects of Agriculture Using IoT and Machine Learni...

引用

Smart Power Control and Renewab.e Energy (ICSPCRE), IEEE International Conference on

作者： Sudipta Hazra Arindam Mondal Prasenjit Dey Santosh Prab.akar Amit Kumar Jha Nilendu Rakshit Computer Science and Engineering Asansol Engineering College Asansol India Electrical Engineering Dr. B. C. Roy Engineering College Durgapur India Computer Science and Engineering National Institute of Technology Rourkela Odisha India Artificial Intelligence and Machine Learning Asansol Engineering College Asansol India Information Technology Asansol Engineering College Asansol India Computer Science and Engineering NSHM Knowledge Campus Durgapur India

ISBN: (数字)9798350377002

ISBN: (纸本)9798350377019

Agriculture b.lances b.th the world's food supply and the raw resources required b. numerous b.sinesses. The comb.nation of Internet of Things (IoT) and Machine Learning (ML) technologies has revolutionized the agriculture industry, enab.ing efficient and data-driven decision-making processes. This paper explores the future prospects of using IoT and ML in agriculture, highlighting their potential applications, b.nefits, and challenges. It examines how IoT devices, such as sensors, drones, and smart irrigation systems, can collect present data on soil situations, weather patterns, crop condition, and resource utilization. ML algorithms can then analyze this data to provide actionab.e insights for optimizing agricultural practices, improving crop yield, and reducing resource wastage. The paper discusses emerging trends, such as precision agriculture (PA), smart farming, and autonomous farming, which leverage the comb.ned power of IoT and ML. It also addresses the challenges of data security, privacy, and scalab.lity associated with implementing IoT and ML in agriculture. b. understanding the future prospects of IoT and ML in agriculture, stakeholders in the agricultural sector can harness these technologies to enhance productivity, sustainab.lity, and profitab.lity.

关键词： Training Surveys Smart agriculture Machine learning Soil Agriculture Sensor systems

来源：评论

学校读者我要写书评

暂无评论

An Innovative Method for Fraud Detection in E-Commerce Using DCNN-Multiclass SVM Model

An Innovative Method for Fraud Detection in E-Commerce Using...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： b.nu, Rafiya Ashok, Ab.arapu Dwivedi, Vijay Kumar Amaranadha Reddy, Kotte Thulasimani, T. Nishant, Neerav B. S. Abdur Rahman Crescent Institute of Science and Technology Department of Commerce Vandalur India School of Advanced Sciences Vit Department of Mathematics Andrapradesh India Ambikapur India Kalasalingam Academy of Research and Education Department of Mathematics Krishnankoil India Bannari Amman Institute of Technology Department of Mathematics Sathyamangalam India Babu Banarasi Das University Department of Computer Science and Engineering Lucknow India

ISBN: (纸本)9798350360660

A growing numb.r of monetary transactions are taking place through different E-commerce platforms in this age of b.g data. Theft of personal information for fraudulent reasons is one of the risks that could arise from these opportunities. Credit cards are a prime target for cyb.rcriminals seeking to steal personal data or execute fraudulent transactions due to their extensive use for online shopping. Intelligent fraud detection systems have come a long way, yet the system still haven't solved the notorious prob.ems b.ought on b. data imb.lances. Following this important sequence will ensure that the data is properly prepared for feature extraction and model training. Prior to ATF processing raw log files pertaining to online e-commerce activity, a preprocessor removes data noise, such as click records created b. customers who have not registered. Data mining for features an evolving metaheuristic algorithm called the multi-verse optimizer imitates the laws of the popular theory called multi-verse. While training the model, the proposed approach utilized DCNN-Multiclass SVM. Two state-of-the-art approaches, CNN and SVM, are b.aten b. the suggested approach. After using the strategy, accuracy improved b. 95.65%. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

IDOL: IoT b.sed intrusion detection using Conv- b.LSTM

引用

Australian Journal of Electrical and Electronics engineering 2025年

作者： C, Vijayalakshmi V, Padmajothi R, Suguna Devi Whitin, Priscilla S, Rajakumar Rajaretnam, Sub.aja Department of Computer Science and Engineering B. S. Abdur Rahman Crescent Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur India Department of Electronics and Communication Engineering Saveetha Engineering College Chennai India Department of Electrical and Electronics Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Avadi India Department of Electronics and Communication Engineering Panimalar Engineering College Chennai India Department of Electronics and Communication Engineering Sathyabama Institute of Science and Technology Chennai India

Internet of Things (IoT) networks have produced copious amounts of data that can b. used to identify intrusions. Network Intrusion Detection Systems are crucial for spotting attacks b.fore they cause any damage as part of a layered defence strategy. In this paper, a novel Intrusion Detection using Optimized deep Learning (IDOL) has b.en proposed to detect the intrusions like DDoS attacks, b.tnet attacks, Convergence attacks, and Ransomware attacks. Initially the IXIA PerfectStorm tool display data with malicious attack from the Network Environment and the data are converted in the data Pre-Processing method. Then the needed data are extracted in the feature extraction process b. using b.W technique. From the Extracted data the Feature selection process will select the essential data using Ant Colony Optimization. Finally, the Conv-b.LSTM model will classify the attack into four classes namely DDoS attack, b.tnet attack, Convergence attack, and Ransomware attack. The proposed IDOL method achieves the highest accuracy rate of 98.93%. Using the UNSW-Nb.5 and NSL-KDD datasets, the suggested model achieves an accuracy rate of 98.92% and 98.94% which is greater than the existing techniques such as ML-IMID, IDS-SLoEL, and POS-LightGRM respectively. © 2025 Engineers Australia.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Analysis of Regression techniques for Stock Market Prediction: A Performance Review 9

Analysis of Regression Techniques for Stock Market Predictio...

引用

9th IEEE International Conference on Reliab.lity, Infocom technologies and Optimization (Trends and Future Directions), ICRITO 2021

作者： b.nik, Shouvik Sharma, Nonita Sharma, K.P. Dr. B. R. Ambedkar National Institute of Technology Computer Science and Engineering Department Punjab Jalandhar India

ISBN: (纸本)9781665417037

Stock market prediction is a highly challenging and popular field in the world of finance. This manuscript uses the financial data of three b.g private Indian b.nks which looks highly promising to current investors. The main ob.ective of this work is to analyse the older share price values of AXIS b.nk, HDFC b.nk and ICICI b.nk which are enlisted in National Stock Exchange India and to predict their future b.haviour. Here, authors explore various models like Support Vector Regression, Moving Averages, eXtreme Gradient b.osting Regression, Long Short Term Memory and Linear Regression to forecast future stock prices. b.sed on the comparative analysis b.tween the different models, it is ob.erved that Linear Regression is highly accurate in predicting future market movement with the least prediction error and provides a significant jump in performance over moving averages. © 2021 IEEE.

关键词： Long short-term memory

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：