检索结果-内蒙古大学图书馆

SADAK: Simple, and Automatic Detection of Accidents on roads using Kolmogorov-Arnold Networks

International Journal of Information Technology (Singapore) 2025年 1-8页

作者： Dutta, Anurag Kumar, Pijush Kanti Lakshmanan, K. Ghosh, Soubhik Department of Computer Science Government College of Engineering & Textile Technology Calcutta Serampore India Department of Information Technology Government College of Engineering & Textile Technology Calcutta Serampore India Department of Mathematics Kuwait American School of Education Hawalli Salmiya Kuwait Department of Computer Science Bengal College of Engineering and Technology Calcutta Durgapur India

Road accidents are one of the major contributors to mortality in India with nearly 1.68 lakh deaths in 2023 accounting for nearly 19 deaths per hour. While road accidents aren’t always “fatal”, delayed detection leads to the loss of many lives. Deep Learning deliberately showed terrific results for a lot of tasks, but for a long time, the Deep Learning models utilized the standard Multi-Layered Perceptron (MLP) architecture as its’ skeleton. Recently, a state-of-the-art architecture—Kolmogorov Arnold Network (KAN) showed up, with variable activation functions in each edge of the graphical representation of the network. Several works have inherited the KAN architecture and have shown better results in many instances. This research proposes a class of accident detection models, SADAK (Simple, and Automatic Detection of Accidents on roads using Kolmogorov–Arnold Networks) for detection of road accidents inheriting KAN architecture. To benchmark its efficiency, several well-known MLP based architectures have been considered, alongside some state-of-the-art models, which result in accuracies as high as 89% using the MLP (Vision Transformer), and 97% using the KAN architecture (KAN-Convolutional-MLP). © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Deep learning Kolmogorov Arnold network Multi-layered perceptron Road accidents

来源：评论

学校读者我要写书评

暂无评论

A Reduced State-Space Generation Method for Concurrent Systems Based on CPN-PR Model

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年第6期44卷 2328-2342页

作者： Zhong, Wenjie Sun, Tao Zhou, Jian-Tao Wang, Zhuowei Song, Xiaoyu Inner Mongolia University College of Computer Science the Engineering Research Center of Ecological Big Data Ministry of Education the Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software the Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot010000 China Guangdong University of Technology School of Computer Science and Technology Guangzhou510006 China Portland State University Department of Electrical and Computer Engineering PortlandOR97207 United States

Colored Petri nets (CPNs) provide descriptions of the concurrent behaviors for software and hardware. Model checking based on CPNs is an effective method to simulate and verify the concurrent behavior in system design. However, the model-checking method traverses the full state space, which suffers from the state-space explosion problem. A reduced state-space generation method related to the property of concurrent systems is proposed. Specifically, we extend CPNs to define a property-related model (CPN-PR) and give a property-related analysis method whose results can be used to generate the CPN-PR model. A reduced state-space generation method is developed based on enabled binding element filtering rules. The stutter trace equivalence between the state spaces of CPN and CPN-PR has been proven by showing that the reduced state space may not change the model-checking result. A comparison experiment is conducted to demonstrate the effectiveness of our method. © 1982-2012 IEEE.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

An efficient ACO-inspired multi-path routing for source location privacy with dynamic phantom node selection scheme in IoT environments

引用

Soft Computing 2024年第23期28卷 13149-13166页

作者： Arpitha, T. Chouhan, Dharamendra Shreyas, J. Department of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore University Karnataka Bengaluru560001 India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal India

The rapid growth in the smart era of Internet of Things (IoT) relies on the various applications that lead to the design wide range of routing protocols utilizing Machine learning techniques. Third party interference in the open network to perform malicious activities by using location information of the node is high. Many researchers have designed a wide range of protocols to improve security and energy efficiency but the dynamic nature of the Internet of Things suppressed the performance of those algorithms. This may lead to data drop, node death, delay, less network lifetime, and increased third party malicious activities. In this paper, a novel routing mechanism is developed to preserve source location privacy and prevent adversaries from doing backtracking attacks and traffic analysis for energy preservation. The proposed model consists of two key functions Node/Network Condition based Dynamic Phantom Node selection (NCDPNS) and Ant colony optimization Algorithm Aided Multi-Path based Routing (ACOMPR). Here, NCDPNS selects the phantom node based on the node/network conditions like node availability, link availability, node energy level, distance from other nodes in the network, and number of neighboring hops to preserve the location privacy. ACOMPR selects the path based on the ant colony optimization algorithm to choose more than one path for data transmission with very less common resources shared among multiple paths between the source and destination for energy efficient data transmission. The proposed mechanism is achieving the source location privacy at the first stage and energy efficient routing at the second stage. The proposed mechanism is implemented using a Network Simulator-2 (NS2) simulator with predefined network parameters. The results depict that it achieves high throughput, less delay, increased network lifetime, and low energy dissipation for data transmission by preserving the location of the node. The dynamic nature of the IoT is considered

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Heart Disease Prediction Using Machine Learning 9

Heart Disease Prediction Using Machine Learning

引用

9th International Conference on Science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Swathisree, M. Gayathri, E. Manivannan, R. KoneruLakshmaiah Education Foundation University Department of Computer Science And Engineering Telangana Hyderabad522502 India Stanley College of Engineering And Technology For Women Department of Computer Science And Engineering Telangana Hyderabad500001 India

ISBN: (纸本)9798350365092

A critical health condition that continues to be encyclopedically significant is heart disease, which poses a challenge to reliable prophetic models for early opinion and intervention. The purpose of this investigation is to determine whether or not machine learning algorithms are effective in predicting cardiac-related complaints. A comprehensive dataset that included a variety of clinical characteristics, such as age, cholesterol levels, blood pressure, and life circumstances, was implemented. The development of prophetic models was accomplished through the utilization of a number of machine literacy techniques, such as logistic retrogression, decision trees, and arbitrary timbers. It was necessary to implement point selection and cross-validation methods in order to improve the generalizability and delicateness of the model. There is a promising performance in heart complaint vaticination, with certain algorithms displaying higher prophetic potential, as demonstrated by the results. The findings highlight the potential for machine literacy to assist healthcare interpreters in relating individuals who are at risk of experiencing heart complaints. This would allow for the development of innovative intervention measures and improved patient concerns. Additional research is necessary to validate these models in a variety of clinical contexts and populations. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Construction of Cascaded Deep Neural Network with Optimization-Based Feature Selection in CT Images for Detecting Laryngeal Cancer 5th

Construction of Cascaded Deep Neural Network with Optimizati...

引用

5th International Conference on Innovative Product Design and Intelligent Manufacturing Systems, ICIPDIMS 2023

作者： Naga Padmavathi, P. Sree Devi, M. Maheswara Rao, V.V.R. Gopala Gupta, Amara S. A. L. G. Department of Computer Science and Engineering Amrita Sai Institute of Science and Technology AP Paritala India Department of Computer Science and Engineering Shri Vishnu Engineering College for Women AP Bhimavaram India Department of Computer Science and Engineering KoneruLakshmaiah Education Foundation AP Vaddeswaram India

ISBN: (纸本)9789819767311

A sin laryngeal carcinoma is the most common kind of head and neck cancer to damage the soft tissues of the larynx. To prevent further medical difficulties and to provide better patient care, early stage laryngeal cancer identification is essential. The primary objective of this research is to provide computer-aided cancer diagnosis driven by deep learning. In order to do this, we create a brand-new Optimization-Based Cascaded Deep Neural Network (OCDNN) that distinguishes between good and unhealthy/cancerous tissues. Additionally, we also provide cascaded patch-based CNN (CP-CNN) picture segmentation. The models are assessed using accepted measures that are unique to the biomedical field. When compared to other models, the performance of our suggested OCDNN architecture was exceptional. Additionally, it fared better than other cutting-edge CNN models applied to medical domain challenges. The findings suggest that the suggested method is quite successful in identifying early indications of laryngeal cancer. The results demonstrate that the suggested strategy may help doctors identify laryngeal carcinoma early and precisely. The suggested OCDNN is discovered to attain 98.4% accuracy, 94% precision, 97.5% recall, and 98% *** paragraph of about 100 words to give a brief introduction to your work. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Hybrid Binary Dragonfly Algorithm with Grey Wolf Optimization for Feature Selection 6th

Hybrid Binary Dragonfly Algorithm with Grey Wolf Optimizatio...

引用

6th International Conference on Innovative Computing and Communication, ICICC 2023

作者： Moturi, Sireesha Vemuru, Srikanth Tirumala Rao, S.N. Mallipeddi, Sneha Ananya Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur India Department of Computer Science and Engineering Narasaraopeta Engineering College Guntur India

ISBN: (纸本)9789819933143

The curse of dimensionality produced by the fast proliferation of information science will have a detrimental impact on the machine learning model's performance. In the data mining process, feature selection is often thought of as a preprocessing technique for finding an optimal subset of features from a given collection of all features. Grey Wolf Optimizer (GWO) suffers with the problem of global optimal solution and Dragonfly Algorithm (DA) suffers from local optima. To combine the benefits of these two algorithms, an enhanced New Levy Updated Dragonfly Algorithm (NL-DA) and Grey Wolf Updated Dragonfly Algorithm (GWU-DA) are developed in this article as a wrapper-based strategy for finding the best subset of features. An improvement is made in the Levy Flight Mechanism (LFM), food and predator to improve the algorithm's randomisation, probabilistic behaviour and searching behaviour. The fitness function of NL-DA and GWU-DA is evaluated with a hybrid classifier, such as Support Vector Machine (SVM) and Deep Belief Network (DBN). The suggested NL-DA is compared to three existing algorithms and GWU-DA is compared to nine existing algorithms over eighteen datasets from the University of California, Irvine (UCI). Various evaluation metrics are utilised to assess how well the proposed algorithms perform. According to the results, enhanced NL-DA and GWU-DA are superior in terms of enhancing prediction accuracy and lowering the number of selected features. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey of Deep Learning Techniques in Malaria Diagnosi 6

A Comprehensive Survey of Deep Learning Techniques in Malari...

引用

6th International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMLA 2024

作者： Saha, Mainak Bhaumik, Rabin Ranganath, Abadhan Basu, Miriyala Trinath Pagadala, Pavan Kumar Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Telangana Hyderabad500075 India Techno College of Engineering Agartala Department of Computer Science and Engineering West Tripura Agartala799004 India

ISBN: (纸本)9798331505790

Malaria is a malignant disease, and it has a high mortality rate as compared to other disease. The survey of death cases in the past century reported the maximum due to malaria. Many times, it seems like a normal fever and body pain. So, many patients avoid proper medication and treatment. Many times, it is seen that the patients are unable to get cured from malaria due to inaccurate diagnosis and inproper medication. The clinical diagnosis and trials were followed in the early days, which took much time. The advancement of diagnostic techniques and processes such as rapid diagnosis technique (RDT) blood testing kit, Internet of Things (IoT) wearables with deep learning techniques, reverse transcriptase-Polymer chain reaction (RT-PCR) etc. Rapid and accurate identification of the protozoan Plasmodium parasites that cause human malaria is essential for improving the treatment and managing a lifethreatening disease. The most commonly used method for detecting Plasmodium in blood films is still microscopic analysis with Blood film staining. This article discusses the history of Plasmodium detection and evaluates the benefits and drawbacks of the current diagnostic techniques. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Effect of Catalyst in the Pyrolysis of Waste Polyethylene Terephthalate (PET) Plastics 6th

Effect of Catalyst in the Pyrolysis of Waste Polyethylene Te...

引用

6th International Conference in Mechanical engineering Research, ICMER 2021

作者： Loreniana, Emil Jean D. Sorongon, Justin Dhavee D. Genobiagon, Cresencio P. Chemical Engineering Program College of Engineering Education University of Mindanao Matina Campus New Matina Davao City8000 Philippines Mechanical Engineering Program College of Engineering Education University of Mindanao Matina Campus New Matina Davao City8000 Philippines

ISBN: (纸本)9789811914560

Pyrolysis is taken into account as the foremost promising thermochemical conversion technology for converting solid wastes into liquid fuels. The present work focused on producing liquid from PET plastic fuel with catalyst employment through the pyrolysis process. Moreover, it aims to differentiate quantitively and qualitatively the liquid yield's improvement concerning the catalyst employed in its benzoic acid content, high heating value, density, and fire and flashpoint. The product yields and compositions are also determined. The experiment takes place in a batch reactor with a heating range of 350–500 °C. The process that used Ca(OH)2 as a catalyst encompasses a maximum liquid yield of 70.6%. In terms of density, the oil produced from three catalysts’ employment has comparable value with the commercial light petroleum fuel in a range of 794–884 kg/m3. The pyrolysis with the Fe2O3 catalyst has the lowest flashpoint of 28.2 °C, while the zeolite and Ca(OH)2 catalytic process has the same flash point of 30 °C. Also, the Fe2O3 catalytic process has the highest fire point of 40.6 °C among the three catalysts. The pyrolysis with Ca(OH)2 catalyst had a maximum heating value of 9284.05 cal/g when Ca(OH)2 was used as a catalyst. The paper concludes with the addition of catalyst, namely zeolite, Ca(OH)2, and Fe2O3, into PET plastic in the pyrolysis process, increased oil yields, and improved its characteristics. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Catalysts

来源：评论

学校读者我要写书评

暂无评论

Plant Leaf Disease Identification based on Machine and Deep Learning Methods 3

Plant Leaf Disease Identification based on Machine and Deep ...

引用

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

作者： Kalaiarasi, P. Ramalakshmi, R. Kannan, V. Bhuvanesh, A. Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Krishnankoil India Department of Agriculture Kalasalingam Academy of Research and Education Krishnankoil India Department of Electrical and Electronics Engineering PSN College of Engineering and Technology Tirunelveli India

ISBN: (纸本)9798331527549

The substantial effects of plant diseases on agriculture, which result in losses in production of crops, financial losses, and food insecurity, highlight the necessity for plant leaf disease detection and categorization. In order to effectively control illnesses, stop them from spreading to other plants, and develop tailored treatment plans, early and precise disease identification is essential. Various strategies are used for plant leaf disease diagnosis, such as manual symptom assessment, computer image processing, and visual examination by skilled professionals. Traditional methods rely on human expertise to visually identify disease symptoms based on characteristic patterns, discolorations, or lesions on plant leaves. These techniques, however, are labor-intensive, time-consuming, and sensitive to bias and mistakes. The development of automated and computer-based techniques for the identification of plant leaf disease through the use of ML (machine learning) algorithms and digital imaging technology has garnered increasing attention in recent years. There are still a number of issues with the DL (deep learning) and ML algorithms. In order to identify research gaps and address them in the future while developing a unique framework, this study presents an examination of ML and DL models. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligent based Cost Optimized Smart Energy Distribution and Management 2

Artificial Intelligent based Cost Optimized Smart Energy Dis...

引用

2nd IEEE International Conference on Emerging Research in Computational Science, ICERCS 2024

作者： Anitha, R. Siva Prasad, G. Senthil, M. Sarfaraz Ahmed, A. Raja, Laxmi Vijayakumar, S.D. Government Engineering College Department of Electronics and Communication Engineering Kerala India QIS College of Engineering and Technology Department of Computer Science and Engineering Andhra Pradesh India Sri Eshwar College of Engineering Department of Computer Science and Engineering Tamil Nadu Coimbatore India Karpagam Academy of Higher Education Department of Cyber Security Coimbatore India Builders Engineering College Department of Electronics and Communication Engineering Tamil Nadu India

ISBN: (纸本)9798331534950

The ever-increasing need for energy, along with the requirement to cut emissions of greenhouse gases and maximize efficiency in energy use, has been a driving force behind the development of cutting-edge technology in the field of intelligent energy distribution and management. This research article proposes an Artificial Intelligence (AI)-based cost-optimized smart energy distribution and management system. The purpose of this research is to present a new solution to addressing these difficulties. In order to intelligently manage the distribution and consumption of energy resources in a manner that is both cost-effective and efficient, the system that has been developed makes use of several artificial intelligence approaches, such as machine learning, optimization algorithms, and data analytics. The system's goal is to maximize energy utilization while keeping costs to a minimum and achieve the best possible optimization of energy distribution. In order to forecast energy demand and supply, the AI algorithms analyses data from the past as well as data that is being collected in real time. They also take into account aspects such as the current weather, the current time of day, and the preferences of individual users. The system makes real-time adjustments to the distribution of energy based on these projections, taking into account issues such as load balancing, the integration of renewable energy sources, and grid stability. Additionally, the system supports demand response capabilities, which enables users to actively participate in the management of energy by modifying their patterns of consumption based on real-time pricing signals. This allows users to actively participate in the management of energy. This demand-side management function not only promotes energy efficiency but also gives customers more agency in terms of the decisions they make regarding their energy consumption. © 2024 IEEE.

关键词： Artificial Intelligence Cost Optimization Demand Response Energy Distribution Energy Management Machine Learning Optimization Renewable Energy Smart Energy

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：