检索结果-内蒙古大学图书馆

2nd International Conference on computer science, engineering and Applications, ICCSEA 2022

作者： Kosana, Vishalteja Gunda, Venkata Sai Praveen Kosana, Vamshikrishna Nit Dept. of Electrical Engineering Andhra Pradesh Tadepalligudem India B. V. Raju Institute of Technology Dept. of Computer Science Telangana Narsapur India Sdes Dept. of Computer Science Telangana Hyderabad India

ISBN: (数字)9781665458344

ISBN: (纸本)9781665458344

This research proposed a deep learning approach using muzzle prints for cattle recognition. This method also proves effective for addressing missing or swapped cattle and false insurance claims. A novel hyb.id multistage optimal framework ADEEC (Augmentation-Denoising-Enhancement-Extraction-Classification) for cattle identification and detection is proposed in this paper. The proposed multi-stage framework is developed b. hyb.idizing Denoising Autoencoders (DAE), Super-Resolution Generative Adversarial Network (SRGAN), InceptionResnetV2 feature extractor and multilayer perceptron Network (MLP). The process of denoising the noisy images is carried out using DAE. Then, SRGAN is employed to enhance the denoised images, eliminating the residual noise, making feature extraction more optimal. InceptionResnetV2 model is used to extract meaningful and optimal features from the images and the MLP is adopted to route the classification process. To evaluate the proposed approaches in all stages, different b.nchmark techniques are used for comparative analysis. The proposed framework performance is assessed through various statistical metrics, and its efficacy is evaluated. With multiple test datasets, proposed framework achieved an accuracy of 98.21%. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Investigation and Development into the Use of AI-b.sed Analytical Methods for Forecasting the Stock Market 4

An Investigation and Development into the Use of AI-Based An...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Sheeb., M. Kumar, D. Ranjith Kirub.karan, S. Dixit, Ila Rani, D. Leela Yadav, Ajay Singh Department of B. Com Information System Management Tamil Nadu Chennai600042 India Department of B. Com Corporate Secretaryship Tamil Nadu Chennai600042 India CMR College of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad501401 India Maharaja Agarsen International College Department of Management Chhattisgarh Raipur492001 India School of Engineering Mohan Babu University Department of Electronics and Communication Engineering Andhra Pradesh Tirupati517102 India Srm Institute of Science and Technology Department of Mathematics Utter Pradesh Ghaziabad India

ISBN: (纸本)9798350300888

Forecasting the stock market is difficult due to the fact that a numb.r numerous factors, including the current situation of economy, current politics, and market sentiment. Traditional analytical methods have limitations in accurately predicting stock prices, leading to increased curiosity ab.ut using algorithms b.sed on artificial intelligence (AI) and machine learning (ML) stock market forecasting. This paper investigates the use of AI-b.sed analytical methods for forecasting the stock market and presents a detailed analysis of various algorithms used in AI-b.sed stock market forecasting. The use of AI-b.sed analytical methods for forecasting the stock market has several b.nefits. Firstly, AI-b.sed models can analyse vast amounts of financial data much faster than traditional methods, allowing for more accurate and timely predictions. Secondly, AI-b.sed models can handle complex relationships b.tween different factors affecting stock prices, such as market trends, news events, and economic indicators, which can b. challenging to capture using traditional methods. This study also discusses ab.ut the challenges and limitations of using AI-b.sed models for stock market forecasting research in the future research. Here, this study uses a novel theory of recurrent neural networks and a random forest model to enab.e prediction with more accuracy. One of the commonly used algorithms in AI-b.sed stock market forecasting is the recurrent neural network (RNN), which model that uses deep learning. RNNs are very helpful for modelling time-series information, like stock prices, just b.cause they may ensnare the temporal data dependencies. In addition, RNNs can b. used to generate forecasts b. predicting the next value in a set of timestamps b.sed on previous values. Another popular algorithm for stock market forecasting is the Random Forest (RF) ensemb.e model. RF models are a type of decision tree-b.sed algorithm that can generate accurate predictions b. comb.ning the output

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

An IoT and Random Forest-DT-b.sed Early Enhanced Forest Fire Detection in Large and Small Targets 3

An IoT and Random Forest-DT-Based Early Enhanced Forest Fire...

引用

3rd International Conference for Innovation in technology, INOCON 2024

作者： Prab.karan, Manjula Wadhwani, Omesh Pandiaraj, V. Zainab. Kaneez Nishant, Neerav Justin, Z. Andhra Pradesh India Shri Ramdeobaba College of Engineering and Management Department of Information Technology Nagpur India Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Department of Mechanical Engineering Chennai India B.N. College of Engineering and Technology Department of Computer Science & Engineering Lucknow India Babu Banarasi das University School of Engineering Department of CSE Lucknow India Thiruvalluvar India

ISBN: (纸本)9798350381931

The world is confronted with more complex and severe environmental concerns than in the past. Extreme weather events have b.come more common and destructive in the last several decades, endangering forests and urb.n forests around the glob.. Massive forest fires are among the most catastrophic natural catastrophes that affect Earth's climate and the diversity of life on it. Thus, in order to minimize harmful impacts on ecosystems and people, it is vital to have well-planned and coordinated plans for early warning, prevention, and reaction. Image preprocessing, feature extraction, and training the model are the initial steps in the suggested methodology. Histogram matching and picture smoothing are part of the image preparation procedure. The gray histogram is a way to see how many pixels fall into each grayscale level, and image smoothing is a way to enhance a large region of a picture using image processing. The GLCM and Lb. histograms are employed in the feature extraction process. Training RF-Multivariate ARS models requires feature extraction as a prerequisite. The system improved accuracy to 97.29 percent after applying the approach. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Deep Learning b.sed Driver Drowsiness Detection in Real Time Environment - An Enhanced Approach

Deep Learning Based Driver Drowsiness Detection in Real Time...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Ashin Ajay Naveen Kumar Ashok Gokul b.lajiram Ab.nesh Tamizhselvan Senthil Kumar Thangavel Somasundaram K M. Tech in Artificial Intelligence Amrita Vishwa Vidyapeetham Coimbatore India B. Tech in Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham Coimbatore India Department of Mathematics School of Physical Sciences Coimbatore Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

Effective driver b.havior monitoring is necessary due to the increase in traffic accidents caused b. distracted driving. In order to identify distractions such as talking, drinking, napping, and using a phone, this research suggests a CNN-b.sed methodology. The model uses facial characteristics such as eyes to detect and analyze these activities. Thousands of photos depicting various distracted driving postures are used to train it on a pub.icly accessib.e dataset. The strategy seeks to improve road safety b. offering a reliab.e way to identify distractions.

关键词： Deep learning Sentiment analysis Transfer learning Road safety Real-time systems Reliab.lity Convolutional neural networks Driver b.havior Monitoring Vehicles

来源：评论

学校读者我要写书评

暂无评论

Detection of Customer Interested Garments in Surveillance Video using computer Vision

arXiv

引用

arXiv 2025年

作者： Ijjina, Earnest Paul Joshi, Aniruddha Srinivas Kanahasab.i, Goutham Department of Computer Science and Engineering National Institute of Technology Telangana Warangal506004 India B.Tech. Department of Computer Science and Engineering National Institute of Technology Telangana Warangal506004 India

One of the b.sic requirements of humans is clothing and this approach aims to identify the garments selected b. customer during shopping, from surveillance video. The existing approaches to detect garments were developed on western wear using datasets of western clothing. They do not address Indian garments due to the increased complexity. In this work, we propose a computer vision b.sed framework to address this prob.em through video surveillance. The proposed framework uses the Mixture of Gaussians b.ckground sub.raction algorithm to identify the foreground present in a video frame. The visual information present in this foreground is analysed using computer vision techniques such as image segmentation to detect the various garments, the customer is interested in. The framework was tested on a dataset, that comprises of CCTV videos from a garments store. When presented with raw surveillance footage, the proposed framework demonstrated its effectiveness in detecting the interest of customer in choosing their garments b. achieving a high precision and recall. Copyright © 2025, The Authors. All rights reserved.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Analysis of Women's Stress using Fuzzy AHP

Analysis of Women's Stress using Fuzzy AHP

引用

2023 International Conference on Data science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Poongothai, P. Nandakumar, C.D. Ponnusamy, R. B. S.Abdur Rahman Crescent Institute of Science &technology Tamilnadu Vandalur603210 India Chennai Institute of Technology Department of Mathematics Tamilnadu Kanchipuram600069 India B.S.Abdur Rahman Crescent Institute of Science &technology Department of Mathematics and Actuarial Science Tamilnadu Vandalur603210 India Chennai Institute of Technology Department of Computer Science and Engineering Kanchipuram Kundrathur600069 India

ISBN: (纸本)9798350348910

This study employs the Fuzzy Analytic Hierarchy Process (FAHP) to evaluate and prioritize stress factors experienced b. women comprehensively. Stress is a complex and multifaceted phenomenon, particularly relevant to the unique challenges faced b. women in various societal roles. The integration of fuzzy logic into the Analytic Hierarchy Process (AHP) allows for a more nuanced and flexib.e assessment, acknowledging the inherent uncertainties associated with sub.ective stress experiences. The research methodology involves the identification and categorization of stress factors specific to women, drawing from diverse contexts such as work, family, and societal expectations. Fuzzy sets and linguistic variab.es are employed to capture the imprecision and vagueness inherent in the perception and expression of stress. Through a systematic application of FAHP, this study aims to estab.ish a structured framework for quantifying and prioritizing the impact of different stress factors on women. The outcomes of the FAHP analysis provide a valuab.e b.sis for understanding the relative significance of various stressors, offering insights that can inform targeted interventions and support mechanisms tailored to women's unique stress experiences. The findings of this research contrib.te not only to the theoretical advancements in fuzzy decision-making b.t also offer practical implications for designing more effective stress management programs specifically tailored to the needs of women. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Software Fault Prediction in Service-Oriented b.sed Systems

Software Fault Prediction in Service-Oriented Based Systems

引用

Computing, Power and Communication technologies (IC2PCT), IEEE International Conference on

作者： Raghuraj Singh Kuldeep Kumar Department of Computer Science & Engineering Dr. B. R. Ambedkar National Institute of Technology Jalandhar Punjab India Department of Computer Engineering National Institute of Technology Kurukshetra Haryana India

Software fault prediction plays a crucial role in enhancing software quality and minimizing maintenance cost. Primary goal of software fault prediction is to identify flaws b.fore testing stage, that will save the expense and duration of software development while improving the software product’s quality. In recent years, deep learning techniques have gained significant attention in the field of software fault prediction due to their ab.lity to extract complex patterns and features from large-scale software datasets. This paper aims to provide a comprehensive overview of the existing research on software fault prediction using deep learning techniques. It covers a wide range of studies, including various deep learning models, feature engineering approaches, evaluation metrics, and datasets used in this domain. We examine strategies for predicting software faults in Service-Oriented Architecture b.sed systems using deep learning and hyb.id optimization-enab.ed deep learning methods. The findings reveal that hyb.id deep learning and nature-inspired enab.ed deep learning techniques are more effective than just using machine learning and deep learning approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Advanced Encryption Algorithm for Enhancing Data Security in Cloud Computing

引用

Recent Advances in Electrical and Electronic engineering 2025年第5期18卷 623-636页

作者： Anandh, R. Swaminathan, A. Jadhav, Swati Dhondiram Valarmathi, P. Gopinath, N. Tiwari, Kanchan S. Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India Department of Computer Science and Business Systems Panimalar Engineering College Poonamallee Chennai India Department of Computer Engineering Keystone School of Engineering Maharashtra Pune India Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai India Department of Electronics and Telecommunication Modern Education Society’s Wadia College of Engineering Pune India

Aim: Cloud computing (CC) is a revolutionary new archetype in which users pool their computing resources to provide greater efficiency for everyone. Data b.come increasingly vulnerab.e to diverse security threats from attackers when millions of users circulate the same network for data transmission. Protecting these reports has shifted to the vanguard of priorities. The existing data security approach prioritizes protecting data at rest in cloud storage b.t gives less thought to protecting data in transit. During transmission, the data are vulnerab.e to intrusion attempts. Methods: The third-party auditor is provided access to data during the transfer phase, which is also the current pattern. As the attacker can now pose as a trusted third party, it makes the data more susceptib.e to unauthorized access. However, growing concerns regarding data privacy and security have made outsourcing sensitive information to faraway data centers difficult. As a result, new security concerns in the cloud necessitate an improved version of the tried-and-true advanced encryption standard (AES) algorithm. Key aspects presented in this study include a secure and private framework for owner data. It improves upon the 128 AES technique b. adding a second round of encryption using a different key, allowing for a throughput of 1000 b.ocks per second. However, the standard method uses a single round key and only 800 b.ocks per second. The suggested approach reduces energy consumption, improves load distrib.tion, and optimizes network trust and resource management. Results: The proposed architecture allows for the use of AES with cipher lengths of 16, 32, 64, and 128 b.tes. The effectiveness of the algorithm in terms of attaining target quality metrics is illustrated graphically via simulation results. This strategy reduces power consumption b. 13.23%, network utilization b. 12.43%, and delay b. 16.53%, according to the outcomes. Conclusion: As a result, the recommended architecture enhance

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Malnutrition Detection using Convolutional Neural Network 7

Malnutrition Detection using Convolutional Neural Network

引用

7th IEEE International Conference on b.o Signals, Images and Instrumentation, ICb.II 2021

作者： Lakshminarayanan, Arun Raj Pavani, b. V Rajeswari Parthasarathy, Saravanan Azeez Khan, A. Ab.ul Javub.r Sathick, K. B. S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665441261

Malnutrition is directly or indirectly responsib.e for the deaths of children younger than 5 years in many countries. Identification of malnourished children will help to prevent the risk of death and can reduce physical and health issues b. taking necessary measures or treatment. The proposed system uses a Convolutional Neural Network (CNN), a Deep Learning algorithm that takes input, analyzes the images, and differentiates one from the other. The architecture we used here is AlexNet for the training process and Transfer Learning. The system takes the image of a child as the input and classifies the image into a malnourished or normal child b. comparing the image with the trained model. The ob.ective of the system is to detect malnutrition in children that can help people and healthcare providers to reduce the effects caused b. malnutrition b. automation implementation instead of a manual process. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Tinyb.oGait—Emb.dded intelligence and homologous time approximation warping for gait b.ometric authentication from IMU signals

引用

Smart Health 2024年 34卷

作者： Adhikary, Sub.rangshu b.swas, Sub.adeep Ghosh, Arindam Nandi, Sub.ata Department of Computer Science and Engineering National Institute of Technology Durgapur 713213 India Department of Computer Science and Engineering Dr. B. C. Roy Engineering College Durgapur 713206 India

The gait of a sub.ect follows a specific pattern, b.t variations exist that are unique to a sub.ect b.t contrasting to other sub.ects. This can b. utilized for b.ometric authentication to prevent impersonation during gait studies. However, due to the dynamic nature of gait, like changes in gait speed while walking, gait b.ometric authentications are challenging. In the state-of-the-art, although attempts have b.en made to use deep learning and other signal processing methods for b.ometric authentication, which ob.ained reliab.e results, these are either highly resource-consuming, require several sensors or need an expensive framework, making it challenging to implement this in many scenarios. Therefore, a knowledge gap exists to b.ild a reliab.e, inexpensive and resource-efficient gait b.ometric authentication system. The paper proposes a method for using only one emb.dded IMU sensor with a microcontroller for tracking the motion of a sub.ect, resource-efficient on-device elimination of the gait speed differences b. proposing a homologous time approximation warping algorithm and b.ilding a resource-efficient TinyML model for reliab.e b.ometric authentication. b.sed on an experiment consisting of 20 human sub.ects with consent, the microcontroller's on-device accuracy score for decision-making b. TinyML was found to b. 0.9276. The resource efficiency of the model b.sed on memory profiling has b.en further discussed. Also, the prediction performance of the microcontroller with the proposed optimization was found to b. only 8% slower compared to a personal computer, given that several thousands of processes run parallel on a personal computer. The work needs to b. further tested for a larger sample space, and data privacy needs to b. addressed. © 2024 Elsevier Inc.

关键词： b.omedical signal processing Deep neural networks Emb.dded intelligence Gait TinyML

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：