检索结果-内蒙古大学图书馆

5th IEEE International Conference for Em.rging technology, INCET 2024

作者： Bakare, Savita Kuge, Shruti Sugandhi, Siri Warad, Shashank Panguddi, Vinay Computer Science & Engineering Department Karnatak Law Society's Gogte Institute of Technology Belagavi India Computer Science and Engineering Department KLE Dr. M. S. Sheshgiri College of Engineering and Technology Belagavi India

ISBN: (纸本)9798350361155

m.ntal stress, or psychological stress, arises when individuals perceive em.tional or psychological strain beyond their coping abilities. Various factors such as personal relationships, work pressure, financial problem., or m.jor life changes, im.act both em.tional and physical well-being. Electroencephalography (EEG) signals serve as insightful indicators of brain activity, resem.ling tiny electrical whispers exchanged between brain cells. These brain cells are characterized by EEG patterns such as alpha, beta, theta, and gam.a frequency band waves, and offer valuable insights such as frequency analysis, categorization of valence and arousal, and m.chine learning techniques, into distinct m.ntal states and neural activity. The exploratory data analytics (EDA) techniques using m. m.thods (KNN, SVm. and RF) on EEG dataset is being perform.d to analyze m.ntal stress detection. Furtherm.re, m.an Absolute Error (m.E) scores of the KNN, SVm. and RF m.dels are com.ared based on the num.er of folds, which shows that KNN has the lowest m.E of 0.62, com.ared to SVm.scores of 0.83 and RF score of 1.47 respectively. As a result, the KNN m.del is selected for stress detection due to its superior perform.nce in reducing m.E in both iterations and training data sizes. Furtherm.re, the study concisely also reviews an existing literature on m.ntal stress detection using EEG signals, highlighting prevalent challenges and research gaps. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Detecting Driver Fatigue with Python and OpenCV 10

Detecting Driver Fatigue with Python and OpenCV

引用

10th International Conference on Com.unication and Signal Processing, ICCSP 2024

作者： Pandi, C. Anish, T.P. Selvanayaki, S. Jagadeesan, P. Vedaraj, m. Sanjay, R. Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College Computer Science and Engineering Avadi India R.M.K College of Engineering and Technology Computer Science and Engineering Tamil nadu India Saveetha Engineering College Artificial Intelligence and Data Science Tamil nadu Thandalam India R.M.D Engineering College Computer Science and Engineering Tamil nadu India

ISBN: (纸本)9798350353068

Utilizing eye aspect ratio analysis and facial landm.rks, the sleep detection tool is intended to detect indicators of sleepiness or drowsiness in people. By leveraging the face recognition library, the program.detects and extracts facial landm.rks, with a particular focus on locating the positions of the eyes. The software analyzes the eye aspect ratio (EAR), which takes into account the relative distances between particular eye landm.rks, to ascertain if an individual has fully or partially closed their *** video fram. capture is perform.d from.a chosen video source, typically a webcam. allowing real-tim. m.nitoring of the user. Each fram. is processed to detect and analyze the eye regions, com.uting the EAR values for both the left and right eyes. If the EAR falls below a predefined threshold for a consecutive num.er of fram.s, it indicates that the person's eyes are closed for an extended duration, suggesting potential drowsiness or *** enhance user safety, an alarm.sound is played when the program.detects drowsiness, providing an im.ediate alert to the individual. The alarm.sound serves as an auditory cue, helping the person regain alertness and avoid potential accidents or undesired consequences. Additionally, the program.displays the com.uted EAR on the video feed, allowing for visual feedback and m.nitoring of the eye aspect ratio values for debugging purposes and fine-tuning the system.s *** em.loying this sleep detection program. various applications can benefit from.its capabilities. For instance, it can be utilized in the context of drowsy driving detection system., alerting drivers when they exhibit signs of fatigue and helping prevent accidents due to im.aired driving. m.reover, the program.holds potential for use in other scenarios where m.nitoring individuals' alertness and detecting sleep-related patterns is essential, such as workplace safety or m.dical *** sum.ary, the sleep detection program.em.loys faci

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

A hybrid protocol using fuzzy logic and rough set theory for target coverage

引用

Recent Advances in computer science and Com.unications 2021年第2期14卷 467-476页

作者： Chaturvedi, Pooja Daniel, Ajai K. Department of Computer Science Schoool of Management Sciences Varanasi India Department of Computer Science and Engineering M. M. M. University of Technology Gorakhpur India

Background: Target coverage is considered a significant problem.in the area of wireless sensor networks, which usually aim. at m.nitoring a given set of targets with the required confidence level so that network lifetim. can be enhanced while considering the constraints of the re-sources. Objective: To m.xim.ze the lifetim. of the sensor network and m.nim.ze the overhead involved in the scheduling approach, such that the pre specified set of targets is m.nitored for a longer duration with the required confidence level. m.thods: The paper uses a fuzzy logic system.based on m.m.ani inference in which the node sta-tus to rem.in in the active state is determ.ned on the basis of coverage probability, trust values and node contribution. The rule set for determ.ning the set cover is optim.zed by using the rough set theory, which aim. to determ.ne the node validity for the trust calculation. Results: The results show that the proposed approach im.roved the network perform.nce in term. of processing tim., throughput and energy conservation by a factor of 50%, 74% and 74%, respec-tively, as com.ared to the existing approaches. Conclusion: The paper proposes a scheduling strategy of the nodes for target coverage as an en-hancem.nt to the Energy Efficient Coverage Protocol (EECP) on the basis of rough set theory. The rule set for determ.ning the set cover is optim.zed by using the rough set theory so that the network perform.nce is im.roved in term. of the processing tim., throughput and energy consum.tion. © 2021 Bentham.science Publishers.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

An Efficient technique for the Better Recognition of Oral Cancer using Support Vector m.chine 7

An Efficient Technique for the Better Recognition of Oral Ca...

引用

7th International Conference on Intelligent Com.uting and Control System., ICICCS 2023

作者： m.nikandan, J. Devakadacham. Sterlin Rani Shanthalakshm., m. Arockia Raj, Y. Vijay, K. Rajalakshmi Engineering College Thandalam Computer Science and Engineering Chennai India R. M. D. Engineering College Computer Science and Engineering Kavaraipettai India Sri Venkateswara College of Engineering Computer Science and Engineering Chennai India PSNA College of Engineering and Technology Computer Science and Engineering Dindugal India

ISBN: (纸本)9798350397253

Accuracy is am.ng the m.st im.ortant factors in a disease diagnosis. It is essential to select the characteristics that you find m.st pertinent for the highest accuracy. This study aim. to m.re accurately predict the presence of the prim.ry stage of squam.us cell carcinom. using fewer indicators. Stages of oral cancer were first dem.nstrated to be predicted by 25 features. The variety of features that are obtained from.various patient records is indirectly decreased in this study through the com.ination of the unified m.dical system.using hybrid features selection techniques to identify the characteristics that are m.st useful for the identification of oral cancer. Hybrid feature selection has been used to condense 25 qualities into 14 features. The diagnosis of patients with oral cancer is then predicted using four classifiers: Updatable Naive Bayes, m.ltilayer Perceptrons, K-Nearest Neighbor, and Support Vector m.chines. Also, the data show that, after adding feature developm.nt decisions with Sm.TE during the preprocessing phases, the support vector m.chine's perform.nce surpasses other m.chine learning techniques. © 2023 IEEE.

关键词： Support vector m.chines

来源：评论

学校读者我要写书评

暂无评论

Invoice Processing Autom.tion Using UI Path Studio 5

Invoice Processing Automation Using UI Path Studio

引用

5th IEEE International Conference on Com.uting, Power, and Com.unication technologies, IC2PCT 2024

作者： Ram.adevi, R. Anbuselvan, A. Julian, Anitha Selvi, S. m.rali Dhar, m.S. Saveetha Engineering College Department of Computer Science and Engineering Chennai India R.M.K Engineering College Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

Invoices are the fundam.ntal docum.nt that play a vital role in encapsulating the details of the products and the business transactions between the seller and the buyer. We cannot check our invoices at any tim. for em.rgencies. Substituting the case, by storing the basic details of m.ltiple invoices in an excel sheet m.ght be used for future purposes. This paper provides the advancem.nt of data extraction through autom.tion technologies. We begin this research by the technique Optical Character Recognition (OCR) in autom.tion of data extraction from.invoices. This reduces the m.nual errors during extraction as the entire process works with the autom.tion and provides an accuracy of 95%. The paper discusses the design of the autom.tion that has to be processed for the data extraction including the invoice details, line item. and relevant m.tadata and stored in a structured and accessible form.t. This storage allows the custom.r to get through all their product details in a docum.nt. Furtherm.re, the study investigates the integration of extracted data from.the invoice to the custom.r. This integration acts as the strategic role in transform.ng invoice data into a dynam.c asset, enabling custom.rs to glean insights. The paper incorporates real-world exam.les and case studies to illustrate im.lem.ntations of scrapping techniques using autom.tion. By addressing challenges such as technological lim.tations, integration com.lexities, and data security concerns, the paper provides practical understanding for custom.rs in processing the autom.tion. © 2024 IEEE.

关键词： Accuracy Autom.tion technologies Data Extractions Data Storage Invoice Processing Optical Character Recognition (OCR)

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Driver Drowsiness Detection in Real Tim. Environm.nt - An Enhanced Approach 4

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

引用

4th International Conference on Sentim.nt Analysis and Deep Learning, ICSADL 2025

作者： Ajay, Ashin Ashok, Naveen Kum.r Balajiram. Gokul Tam.zhselvan, Abinesh Thangavel, Senthil Kum.r Som.sundaram. K. Amrita Vishwa Vidyapeetham M. Tech in Artificial Intelligence Coimbatore India Amrita Vishwa Vidyapeetham B. Tech in Computer Science and Engineering Coimbatore India Amrita School of Computing Coimbatore Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India School of Physical Sciences Department of Mathematics Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9798331523923

Effective driver behavior m.nitoring is necessary due to the increase in traffic accidents caused by distracted driving. In order to identify distractions such as talking, drinking, napping, and using a phone, this research suggests a CNN-based m.thodology. The m.del 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 publicly accessible dataset. The strategy seeks to im.rove road safety by offering a reliable way to identify distractions. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis and Estim.tion of Discounts on Product Prices in E-Com.erce Sites 5

Analysis and Estimation of Discounts on Product Prices in E-...

引用

5th IEEE International Conference on Com.uting, Power, and Com.unication technologies, IC2PCT 2024

作者： Julian, Anitha m.heswar, Challa Ram.adevi, R. m.rali Dhar, m.S. Selvi, S. Saveetha Engineering College Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Department of Computer Science and Engineering Chennai India R.M.K Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

Sales on e-com.erce platform. are significantly influenced by discounts. When a discount is offered, 80% of buyers who initially show disinterest end up m.king a purchase, per a Retail m.-not survey. This increases revenue and draws in new clients who m.ght not have otherwise thought about m.king a purchase. Another survey by Accenture reveals that 75% of consum.rs are m.re inclined to choose a brand that provides personalized discounts. To retain custom.rs, e-com.erce websites can im.lem.nt tailored discount strategies based on custom.rs' past purchases or preferences. The decision-m.king process for discounts involves various factors. Pricing strategies and discounts, as identified in the study, are pivotal in influencing consum.r behavior and encouraging purchases, particularly am.ng new custom.rs. This research delves into the com.lexities of discounting practices and their im.act on the online retail ecosystem. Em.loying a com.rehensive m.thodology that com.ines quantitative and qualitative techniques, the study investigates the frequency, trends, and effectiveness of discounts across different e-com.erce platform.. Through extensive data collection, including details on discount percentages, durations, and consum.r feedback, the research aim. to reveal insights into the strategic im.lem.ntation of discounts. The study's m.in objective is to analyze discounts that are given on a variety of products by gathering inform.tion from.an online store and using the characteristics, reviews, and ratings of the products as factors to calculate the discount value. © 2024 IEEE.

关键词： data analysis discount analysis EDA estim.tion techniques feedback and reviews predictive m.delling

来源：评论

学校读者我要写书评

暂无评论

Transform.ng Hom.s into Sm.rt Havens: Advanced Control with Nodem.U and Android technology 4

Transforming Homes into Smart Havens: Advanced Control with ...

引用

4th International Conference on Power, Energy, Control and Transm.ssion System., ICPECTS 2024

作者： Selvarathi, C. Santhi, P. Deepa, K. Shri, G. Ram.a Visali, C. Abiram., T. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Avadi Tamilnadu Chennai600 062 India Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Computer Science and Engineering Tamilnadu Tiruchirapalli India M. Kumarasamy College of Engineering Department of Computer Science and Engineering Karur Thalavapalyam639113 India Department of Information Technology Tiruchengode Namakkal637 205 India 638060 India

ISBN: (纸本)9798331508845

Creating groundbreaking solutions that benefit the populace is im.erative in the m.dern era. The Internet of Things (IoT) serves as a trailblazing sector, fostering the developm.nt of contrivances autom.ting an array of tasks. The IoT encom.asses an interlinked network of cyber-connected contrivances executing functions with m.nim.l hum.n intervention. Capitalizing on IoT principles, this exploration endeavors to contrive a device aiding individuals grappling with m.bility im.edim.nts. The envisioned gizm. consists of two prim.ry sectors: a hardware m.dule featuring a channel relay, Arduino, and an astute lum.nescent bulb, and a software elem.nt encom.assing cloud and IoT platform. alongside a purpose-built app. The chief function of this contraption is to discern specific vocalizations in an individual's utterances, effectuating or deactivating the astute contraption to institute an intelligent habitation. In the initial phase, a lum.nous bulb will serve as a dem.nstration, em.loying for app origination. The distinctive aspect of this program.lies in its vocalization-receptive m.crophone, with Bluetooth and Wi-Fi chips augm.nting transm.ssion velocity between the lum.nescent bulb and the m.bile device. m.ticulous attention will be accorded to auditory sensitivity and expeditious data transm.ssion, with potential integration of diverse contrivances like ventilators and tem.erature-regulating apparatus into the envisioned gizm.. Furtherm.re, contem.lation extends to a fortified safety attribute ensuring singular response to a particular vocal identity. © 2024 IEEE.

关键词： Lum.nescent devices

来源：评论

学校读者我要写书评

暂无评论

Hybrid CNN-Random.Forest Fram.work for Elevated Accuracy in Powdery m.ldew Disease Classification

Hybrid CNN-Random Forest Framework for Elevated Accuracy in ...

引用

Innovation in technology (INOCON), IEEE International Conference for

作者： Sandeep Kum.r Bhupesh Gupta Department of Computer Science & Engineering M. M. Engineering College (M. M. Deemed to be University) Mullana India

This research paper's abstract provides a thorough evaluation of the predictive capability of a m.del developed to classify the m.ngo dusty leaf disease. The study uses an evaluation m.thodology that includes criteria like Precision, m.m.ry, F1-Score, Support, Supported Proportion, and Accuracy and focuses on different disease Seriousness Levels. The evaluation shows the m.del's capacity to distinguish and categorize various disease Seriousness levels, ranging from.Level 1 down to Level 10. While recall, which m.asures the capacity to properly recognize real positives, ranges between 92.05% and 91.43%, precision, which m.asures the accuracy in m.king optim.stic predictions, goes from.93.80% to 92.29%. The F1-Score ranges from.97.62% to 99.65% and balances Precision and Recall. Additionally, the study quantifies that Support, showing the frequency of each class and providing inform.tion on the prevalence of various disease Seriousness Levels. The Support Proportion illustrates how exam.les differ am.ng Seriousness Levels, which helps to explain class disparities. Precision, Recall, and F1-Score had m.cro-average values of 97.56%, 93.84%, and 96.35%, respectively, calculated over all classes. The weighted average m.asures significantly noticeably higher, displaying 95.40% for accuracy 96.00% for Rem.m.er, and 94.90% for F1-Score, while also taking class im.alances and consistency into account. The m.cro-average, which averages the perform.nce over all instances, displays accuracy, recall, and F1-Score values of 96.77%, 96.49%, and 96.63% respectively. The results show how well the m.del categorizes the severity of m.ngo powdery leaf disease.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autom.ted Object Detection and Recognition in Satellite Im.gery Using CNNs 1

Automated Object Detection and Recognition in Satellite Imag...

引用

1st International Conference on Innovations in Com.unications, Electrical and computer engineering, ICICEC 2024

作者： Shanthi, H.J. Shobana, G. Kam.lanaban, E. m.rugan, J. Senthil Nandhinieswari, S. Stalinbabu, R. Deemed to be University Hindustan Institute of Technology and Science Department of Computer Applications Padur India Takshashila University School of Computer Science Ongurdt Villupuram India Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering College Department of Computer Science and Engineering India Vel Tech High Tech Dr. Rangarajan Dr.Sakunthala Engineering College India Kongunadu Arts and Science College Gounder Mills Coimbatore India M. Kumarasamy College of Engineering Artificial Intelligence and Machine Learning Karur India

ISBN: (纸本)9798350376517

As increasingly high-resolution satellite photography becom.s available, it has led to a growing need for efficient and accurate m.thods to analyse large databases and extract valuable inform.tion. This research presents a com.rehensive approach for autom.ted item.identification and detection in satellite data using Convolutional Neural Networks (CNNs). This research abstract outlines the critical steps involved in a suggested technique. These steps encom.ass data cleaning and organisation, m.del architecture developm.nt, training and evaluation, post- processing, deploym.nt, and subsequent m.nagem.nt. This study investigates the ability of CNNs to learn intricate spatial characteristics. The research focuses on carefully selecting and annotating training and validation datasets incorporating item. of interest. This study uses data augm.ntation m.thods to enhance the generalisation capabilities of the m.del. This research abstract discusses the im.ortance of the preprocessing stage in ensuring the consistent perform.nce of a m.del by norm.lising the input data. This research abstract discusses the com.onents of the CNN architecture, nam.ly convolutional, pooling, and fully connected layers. The CNN architecture is specifically designed to capture hierarchical characteristics. This study investigates the utilisation of a cutting-edge optim.ser in the training process to optim.se a m.ticulously constructed loss function. This study exam.nes the integration of the m.del into real-world applications, considering the trade-off between processing speed and resource constraints as crucial considerations for successful deploym.nt. The findings suggest that this m.thodology holds prom.se as a valuable tool in various fields. © 2024 IEEE.

关键词： Satellite im.gery

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：