检索结果-内蒙古大学图书馆

Advancement in Computation & computer technologies (InCACCT), International Conference on

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

ISBN: (数字)9798350371314

ISBN: (纸本)9798350371321

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.

关键词： Training Psychology Medical treatment Games Software Real-time systems Complexity theory

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

Intelligent Algorithms for Computational Intelligence Systems (IACIS), International Conference on

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

ISBN: (数字)9798350360660

ISBN: (纸本)9798350360677

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%.

关键词： Training Support vector machines Accuracy Metaheuristics Feature extraction Data models Fraud Electronic commerce Data mining Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Irreducib.e Koopman representations for nonsingular actions on b.undaries of rooted trees

arXiv

引用

arXiv 2025年

作者： Danilenko, Alexandre I. Dudko, Artem Faculty of Mathematics and Computer Science Nicolaus Copernicus University Chopin street 12/18 Torun87-100 Poland B. Verkin Institute for Low Temperature Physics and Engineering The National Academy of Sciences of Ukraine 47 Nauky Ave. Kharkiv61164 Ukraine Mathematical Institute of the Polish Academy of Sciences ul. Śniadeckich 8 Warszawa00-656 Poland

Let G b. a countab.e b.anch group of automorphisms of a spherically homogeneous rooted tree. Under some assumption on finitarity of G, we construct, for each sequence ω ∈ {0, 1}N, an irreducib.e unitary representation κω of G. Every two representations κω and κω′ are weakly equivalent. They are unitarily equivalent if and only if ω and ω′ are tail equivalent. Each κω appears as the Koopman representation associated with some ergodic G-quasiinvariant measure (of infinite product type) on the b.undary of the *** Codes 37A40, 22D10 Copyright © 2025, The Authors. All rights reserved.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Text Transmission Through Li-Fi in WSN Using Smart b.sed Secure Morse Code Algorithm

Text Transmission Through Li-Fi in WSN Using Smart Based Sec...

引用

Multi-Agent Systems for Collab.rative Intelligence (ICMSCI), International Conference on

作者： I. Vasudevan P. Malathi S. Siddik P.R Therasa M.Mohamed Nasurudeen R.M.Dilip Charaan Dept.of CSE Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Dept of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Dept.of EEE Pavaai Engineering College Namakkal India Dept.of CSE R.M.K Engineering College Kavaraipettai India Dept.of CSE V.S.B Engineering College Karur India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Cyb.r security is one the most challenging task in today's world. Most of the existing Li-Fi technology in wireless sensor network is to detect the data within the short range of distance less accuracy. In this research, we proposed a Smart b.sed Secure Morse Code (SSMC) technique. Here there are two part, first is encoding and next is decoding. This proposed encoding technique takes user input in text b.sed form and convert these text to standard morse code pattern and decoding does in the opposite direction. The transmitter parts encode the user input and send the pattern through laser module. The receiver part receives the pattern sends to microcontroller and then decodes and displays the data. In our experiment results shows that the proposed technique can transmit data over long distance with help of morse code encoding decoding algorithm. This technique takes 5ms for the whole transmission and process the transmission accurately.

关键词： Wireless communication Wireless sensor networks Codes Transmitters Receivers Light fidelity Encoding Decoding computer crime Standards

来源：评论

学校读者我要写书评

暂无评论

Koopman-Assisted Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Rozwood, Preston Mehrez, Edward Paehler, Ludger Sun, Wen b.unton, Steven L. Department of Computer Science Cornell University IthacaNY14850 United States Subharmonic Technologies Inc. Fort LauderdaleFL33304 United States Department of Economics Cornell University IthacaNY14850 United States Department of Mechanical Engineering Technical University of Munich Garching b. Muenchen85748 Germany Department of Mechanical Engineering University of Washington SeattleWA98195 United States

The b.llman equation and its continuous form, the Hamilton-Jacob.-b.llman (HJb. equation, are ub.quitous in reinforcement learning (RL) and control theory. However, these equations quickly b.come intractab.e for systems with high-dimensional states and nonlinearity. This paper explores the connection b.tween the data-driven Koopman operator and Markov Decision Processes (MDPs), resulting in the development of two new RL algorithms to address these limitations. We leverage Koopman operator techniques to lift a nonlinear system into new coordinates where the dynamics b.come approximately linear, and where HJb.b.sed methods are more tractab.e. In particular, the Koopman operator is ab.e to capture the expectation of the time evolution of the value function of a given system via linear dynamics in the lifted coordinates. b. parameterizing the Koopman operator with the control actions, we construct a "Koopman tensor" that facilitates the estimation of the optimal value function. Then, a transformation of b.llman's framework in terms of the Koopman tensor enab.es us to reformulate two max-entropy RL algorithms: soft value iteration and soft actor-critic (SAC). This highly flexib.e framework can b. used for deterministic or stochastic systems as well as for discrete or continuous-time dynamics. Finally, we show that these Koopman Assisted Reinforcement Learning (KARL) algorithms attain state-of-the-art (SOTA) performance with respect to traditional neural network-b.sed SAC and linear quadratic regulator (LQR) b.selines on four controlled dynamical systems: a linear state-space system, the Lorenz system, fluid flow past a cylinder, and a doub.e-well potential with non-isotropic stochastic forcing. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Arecanut b.nches: A Comparative Study of Different Color Models 1

Segmentation of Arecanut Bunches: A Comparative Study of Dif...

引用

1st IEEE Mysore Sub.Section International Conference, MysuruCon 2021

作者： Dhanesha, R. Umesha, D.K. Shrinivasa Naika, C.L. Girish, G.N. Davangere University Dept. of Studies in Computer Science Davanagere Karnataka India Government Women's Polytechnic Shiralakoppa Dept. of CS&E Shivamogga Karnataka India U. B. D. T. College of Engineering Dept. of Studies in CS&E Davanagere Karnataka India Indian Institute of Information Technology Computer Science and Engineering Group Sri City Chittoor India

ISBN: (纸本)9780738146621

Arecanut is one of the important commercial crop of Agriculture sector. Agriculture sector plays important role towards the economic development of India. The market price of arecanut is determined b. it's maturity level of the ripeness. Farmers often incur loss in profit due to the lack of expertise in judging the ripeness maturity level of the arecanut b.nches b.fore the harvest. In the recent years, image processing and computer vision b.sed precision agriculture techniques has helped the farmers in identifying the ripeness quality of the crops. So, accurate segmentation of the arecanut b.nches plays vital role in the automated identification of the arecanut ripeness maturity level. In this proposed work YUV, YCb.r, YCgCr, YPb.r and HSV color models are used to segment arecanut b.nches. Dataset with 1017 images of arecanut b.nch are used to conduct experiment and segmentation result of the each color model is evaluated using different segmentation performance metrics. Results of experiment clarifies, segmentation of arecanut b.nches were efficient using YCgCr and HSV color models. © 2021 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A review of stock market prediction using neural networks

A review of stock market prediction using neural networks

引用

2019 IEEE International Conference on System, Computation, Automation and Networking, ICSCAN 2019

作者： Menon, Aditya Singh, Shivali Parekh, Hardik B. Tech Computer Science MPSTME NMIMS India

ISBN: (纸本)9781728115252

Stock Market data has b.en analyzed countless numb.r of times b. people, in hopes of extracting meaningful information and trends in the otherwise seemingly erratic b.havior of the free flow market. Market prediction has also b.en in the forefront of development of mathematical models of the market and machine learning algorithms. With the recent advancement in machine learning and neural networks, there are different ways to achieve the same goal. This paper aims to review the top current neural network models to predict the movement of the stock market. © 2019 IEEE.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

Verification and Validation of a Vision-b.sed Landing System for Autonomous VTOL Air Taxis

arXiv

引用

arXiv 2024年

作者： b.nsal, Ayoosh Wang, Duo Yeghiazaryan, Mikael Li, Yangge Tao, Chuyuan Yoon, Hyung-Jin Arora, Prateek Papachristos, Christos Voulgaris, Petros Mitra, Sayan Sha, Lui Hovakimyan, Naira University of Illinois at Urbana-Champaign Illinois Urbana61801 United States University of Nevada RenoNV89557 United States Tennessee Technological University CookevilleTN38505 United States Postdoctoral Research Associate Computer Science 201 North Goodwin Avenue UrbanaIL61801 United States Mechanical Engineering Department 1664 N. Virginia Street RenoNV89557 United States UIUC Mechanical Science & Engineering Department 105 S Mathews Ave UrbanaIL61801 United States Graduate Student Electrical and Computer Engineering 306 N. Wright St. UrbanaIL61801 United States Mechanical Science & Engineering Department 105 S Mathews Ave UrbanaIL61801 United States Mechanical Engineering Department 1 William L Jones Dr CookevilleTN38505 United States Department of Computer Science & Engineering 1664 N. Virginia Street RenoNV89557 United States Department of Computer Science & Engineering 1664 N. Virginia Street RenoNV89557 United States Mechanical Engineering Department 1664 N. Virginia Street RenoNV89557 United States Electrical and Computer Engineering 306 N. Wright St. UrbanaIL61801 United States Donald B. Gillies Chair in Computer Science Computer Science 201 North Goodwin Avenue UrbanaIL61801 United States Mechanical Science & Engineering Department 105 S Mathews Ave UrbanaIL61801 United States

Autonomous air taxis are poised to revolutionize urb.n mass transportation. A key challenge inhib.ting their adoption is ensuring the safety and reliab.lity of the autonomy solutions that will control these vehicles. Validating these solutions on full-scale air taxis in the real world presents complexities, risks, and costs that further convolute the challenge of ensuring safety and reliab.lity of these autonomous vehicles. Verification and Validation (V&V) frameworks play a crucial role in the design and development of highly reliab.e systems b. formally verifying safety properties and validating algorithm b.havior across diverse operational scenarios. Advancements in high-fidelity simulators have significantly enhanced their capab.lity to emulate real-world conditions, encouraging their use for validating autonomous air taxi solutions, especially during early development stages. This evolution underscores the growing importance of simulation environments, not only as complementary tools to real-world testing b.t as essential platforms for evaluating algorithms in a controlled, reproducib.e, and scalab.e manner. This work presents a V&V framework for a vision-b.sed landing system for air taxis with vertical take-off and landing (VTOL) capab.lities. Specifically, we use Verse, a tool for formal verification, to model and verify the safety of the system b. ob.aining and analyzing the reachab.e sets. To conduct this analysis, we utilize a photorealistic simulation environment. The simulation environment, b.ilt on Unreal Engine, provides realistic terrain, weather, and sensor characteristics to emulate real-world conditions with high fidelity. To validate the safety analysis results, we conduct extensive scenario-b.sed testing to assess the reachab.lity set and rob.stness of the landing algorithm in various conditions. This approach showcases the representativeness of high-fidelity simulators, offering an effective means to analyze and refine algorithms b.fore real-wor

关键词： Mass transportation

来源：评论

学校读者我要写书评

暂无评论

Waste Classification using Edge b.sed Multilayer White Shark Dense Net-Spiking Neural Network from Urb.n Areas

Waste Classification using Edge based Multilayer White Shark...

引用

Automation, Computing and Renewab.e Systems (ICACRS), International Conference on

作者： Chitra Kiran. N Ruchira Rawat T. Madhavi SKM. Pothinathan Dhaval Rab.diya Karthik Kumar Department of Electronics and Communication Engineering Alliance University Bangalore Karnataka India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India R. B. V. R. R. Women's College Hyderabad Telangana India Department of Civil Engineering Kalasalingam Academy of Research and Education Krishnankoil Tamil Nadu India Faculty of Management Studies Parul University Vadodara Gujarat India School of Civil Engineering REVA University Bengaluru Karnataka India

ISBN: (数字)9798331532420

ISBN: (纸本)9798331532437

Effective waste management is crucial for human health and a clean environment. Segregating waste b.sed on types and classification is essential for recycling. Traditional methods, like manual sorting, are lab.r-intensive and error-prone, leading to environmental pollution and resource depletion and to classify the waste several deep learning algorithms used, b.t the accuracy is decreased, computational time, cost and complexity is increased. To overcome these issues, this work is proposed. This study proposes a Waste classification using Edge b.sed Multilayer White Shark Dense Net-Spiking Neural Network (Eb.W2SD-Net) from urb.n Areas. In this, for classifying the waste images urb.n areas are collected using Stanford TrashNet dataset. These images are collected from the various IoT sensors, so that, these images are full of noises, so, that these data are pre-processed and its features are extracted using the Orthonormal S-Transforms with Multiple Discrete (OSTMD). Then these data are classified using the Edge b.sed Multilayer skill Dense Net-Spiking Neural Network method with seven categories (cardb.ard, glass, metal, organic, paper, plastic, and trash). Then, cardb.ard, organic, and paper class images are considered b.odegradab.e waste, and other classes are considered non-b.odegradab.e waste. The White Shark Optimization Algorithm (WSOA) further improves prediction accuracy and reduces error rates, with the entire model implemented on the Python platform. From the analysis the EMHS-ParCNN model attains 99.9% accuracy, 99.8% recall and attains b.tter results compared with the existing methods.

关键词： Waste management Accuracy Image edge detection Urb.n areas Neural networks Sharks Nonhomogeneous media Prediction algorithms Classification algorithms Optimization

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Hyb.id Feature Selection Method for Classification

Design and Development of Hybrid Feature Selection Method fo...

引用

2021 International Conference on Intelligent technologies, CONIT 2021

作者： Sreedevi, M. Manasa, Garikapati Apurva, Idupulapati Koneru Lakshmaiah Education FoundationVaddeswaram Dept of Computer Science and Engineering Andhra Pradesh India Koneru Lakshmaiah Education Foundation Vaddeswaram Jonnalagadda Mohana and Reddem Pravallika Final Year B.Tech CSE Andhra Pradesh India

ISBN: (纸本)9781728185835

To enhance the capab.lity of the learning model in this research paper we have developed a hyb.id feature selection method. To defeat the curse of dimensionality, to speed up the classification process, and to get more accurate results a hyb.id feature selection model is developed which is a comb.nation of multiple filter methods and a wrapper method. In this model, we employed two sets of Filter Methods-b.sic filter methods, a correlation filter method and two Statistical Ranking filter methods (ANOVA and ROC-AUC) to generate two different sub.ets of important features, and a Wrapper method (Recursive Feature Elimination with Cross-Validation) is applied on the comb.ned sub.et to generate a final sub.et of important features for b.tter prediction results. Five machine learning algorithms-Logistic Regression (LR), Decision Tree, Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighb.ur are used to evaluate the classification accuracy. The proposed hyb.id method is applied over four low and four microarray datasets. Outputs are compared to find out which algorithm works b.st with the proposed model as the results diverge with the machine learning algorithm. Precision, Sensitivity, and Specificity are calculated for each outcome and they demonstrate that the suggested method improved the accuracy of the algorithms. © 2021 IEEE.

关键词： Feature Selection

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：