检索结果-内蒙古大学图书馆

5th IEEE Global Conference for Advancement in technology, GCAT 2024

作者： Pradhan, Patrali Chattopadhyay, Samiran Chowdhury, Subrata Rout, Suchismita Mishra, Manoj Ranjan Patra, Sudhansu Shekhar Haldia Institute of Technology Dept. of Computer Science and Engineering Haldia India Techno India University Kolkata India Sreenivasa Institute of Tech. and Management Studies Dept. of Computer Science and Engineering Andhra Pradesh Chittoor India Kiit Deemed to be University School of Computer Engineering Bhubaneswar India Kiit Deemed to be University School of Computer Applications Bhubaneswar India

ISBN: (纸本)9798350376685

This paper presents a framework for a Safety recommender system that offers Safety-as-a-Service (Safe-aaS) to on-road vehicles in IoT-based transportation systems. The proposed safety recommendation system integrates several phases, including preparing sensed data, self-supervised learning from the data, and predicting personalized safety plans. The customized safety plans, generated by analyzing on-road decision parameters such as dynamic road conditions, weather patterns, and driving assistance parameters, are suggested to registered users in real time through the Safe-aaS platform tailored to their specific *** a Safe-aaS enabled road transportation system, sensor nodes produce large volumes of data in a dynamic environment. Efficient analysis and storage of sensed data in edge devices poses a major challenge for service providers. Conversely, generating safety-related decisions with lower processing time ensures driver safety. The Safe-aaS-based recommender system provides safety-related decisions with low latency and processing delay. In the proposed recommendation system, a safety score is computed from the pre-processed sensed data across various parameters, followed by a user-specific similarity score and a corresponding risk score. We apply a fuzzy rule-based learning technique to predict optimized safety plans. To showcase the real-time scenario of our framework, we develop a user-friendly application interface at the primary stage. Extensive analysis shows that our system effectively detects on-road risks and adapts safety recommendations in dynamic weather and road conditions. © 2024 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Clear Text Visibility: A CNN-LSTM Approach for Frame of Interest Identification in Book Flipping Videos

Clear Text Visibility: A CNN-LSTM Approach for Frame of Inte...

引用

2024 IEEE International Conference on Modeling, Simulation and Intelligent Computing, MoSICom 2024

作者： Buddhawar, Gaurav Dave, Dharin Jariwala, Krupa Chattopadhyay, Chiranjoy Sardar Vallabhbhai National Institute of Technology Dept. of Computer Science and Engineering Surat India Pune India Flame University School of Computing and Data Sciences Pune India

ISBN: (纸本)9798331533311

Book flipping videos present a distinctive challenge for information extraction, requiring the identification of frames with clear text visibility during dynamic page turns. This paper introduces a novel approach to frame classification in book flipping videos, leveraging the combined effect of Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs). In particular, a CNN-LSTM model is employed, where a pre-trained CNN captures spatial features, and LSTMs extend the model's capability to distinguish temporal dependencies critical for page turn detection. Unlike conventional methods, this approach processes entire video sequences, enabling the model to learn intricate Frame of Interest (FoI) detection features indicative of page turns and text visibility. The proposed model offers improved interpretability, effectively classifying frames without compromising transparency. The research opens avenues for automated book digitization, digital library creation, and educational technology applications, enhancing information extraction and reliability from book flipping videos. © 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

Predicting Lung Cancer with Artificial Neural Network: Analyzing Performance and Feature Importance

Predicting Lung Cancer with Artificial Neural Network: Analy...

引用

Cognitive Computing in Engineering, Communications, sciences and Biomedical Health Informatics (IC3ECSBHI), International Conference on

作者： Vatsal Mehta Varun M Ashwini Kodipalli Roshan Joy Martis Shridhar B. Devamane Ushasree. A Dept. of AI & Data Science Global Academy of Technology Bangalore Karnataka India Dept. of Electronics & Communication Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science School of Computing Mysuru Dept. of Computer Science & Engineering Gokaraju Lailavathi Engineering College Hyderabad India

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

Lung cancer is the primary cause of cancer-related deaths globally. This cancer is majorly observed in smokers, increasing air pollution has also begun to affect non-smokers. Research indicates that exposure to polluted air significantly raises the risk of developing lung cancer, posing a major threat to public health. Despite advancements in medical technology, the mortality rate from lung cancer remains high, highlighting the importance of early diagnosis. Machine learning and deep learning offer promising solutions for early and accurate prediction through advanced data analysis. In our study, we utilized a dataset with 26 attributes for discern lung cancer, categorizing cases into three risk levels: high, medium, and low. We applied various algorithms and develop an Artificial Neural Network (ANN), comparing the overall performance with various machine-learning and deep-learning models. Our results show that the ANN achieved a high accuracy of 94.9% using the Adam optimizer, making it an effective model for lung cancer prediction.

关键词： Deep learning Accuracy Computational modeling Biological system modeling Lung cancer Mortality Artificial neural networks Predictive models Prediction algorithms Public healthcare

来源：评论

学校读者我要写书评

暂无评论

Leveraging UAV technology for Enhanced Disaster Management: Innovations and applications

Leveraging UAV Technology for Enhanced Disaster Management: ...

引用

2024 IEEE International Conference on Signal Processing and Advance Research in Computing, SPARC 2024

作者： Upadhyay, Govind Murari Vats, Prashant Shanker, Surabhi Bhushan, Saloni Mittal, Sonu Mandot, Manju Manipal University Jaipur Dept. of Computer Application Rajasthan Jaipur India Manipal University Jaipur School of CSE Dept. of CSE Rajasthan Jaipur India K.R. Mangalam University School of Engineering & Technology Dept. of CSE Sohna Road Haryana Gurugram India Chhatrapati Shivaji Maharaj University Dept. of Computer Science/IT Maharashtra Panvel India Amity Institute of Information Technology Amity University Noida Dept. of CSE Uttar Pradesh India J. R. N. Rajasthan Vidyapeeth University Dept. of Computer Science/IT Rajasthan Udaipur India

ISBN: (纸本)9798350385199

Unmanned Aerial Vehicles (UAVs) have substantially advanced the sector by providing improved real-time monitoring, data collecting, and situational awareness capabilities when integrated into disaster management techniques. This study examines the creative uses of unmanned aerial vehicles (UAVs) in disaster relief, emphasising how they may speed up reaction times and increase operational effectiveness in emergency situations. With an emphasis on their usefulness in human detection, damage assessment, and coordination efforts, we propose a thorough framework that describes the design, deployment, and evaluation of UAV systems customised for catastrophe situations. The study shows how UAVs may be used to enhance processes of decision-making and enable more efficient recovery and catastrophe response through instances and quantitative evaluation. The results demonstrate how UAV technology may revolutionise conventional disaster management procedures and provide insightful information for future studies and real-world applications in the field. © 2024 IEEE.

关键词： Disaster prevention

来源：评论

学校读者我要写书评

暂无评论

A System to Track Fabricated Content in Social media using Machine Learning Approach

A System to Track Fabricated Content in Social media using M...

引用

2024 IEEE International Conference on Recent Advances in science and Engineering technology, ICRASET 2024

作者： Hegde, Ramakrishna Soumyasri, S.M. Shivashankara, S. Kavyashree, M.K. Pemula, Rambabu Harshitha, M. Vidyavardhaka College of Engineering Affiliated to Visvesvaraya Technological University Dept. of Computer Science and Engineering Mysuru India Vidya Vikas Institute of Engineering and Technology Affiliated to Visvesvaraya Technological University Dept. of Computer Applications Mysuru India Kr Pete Krishna Govt. Engg. College Dept. of Computer Science and Engineering Krishnarajapet Mandya India Sjce Jssstu Mysore India Vidya Jyothi Institute of Technology Dept. of Artificial Intelligence Hyderabad India Vidya Vikas Institute of Engineering and Technology Dept.of Information Science and Engg. Mysore India

ISBN: (纸本)9798350388602

In today's society, when the internet is pervasive, everyone gets their news from a variety of online sources. Information can swiftly reach millions of users in a short amount of time due to the growing usage of social media sites like Facebook, Twitter, and others. Fake news has far-reaching effects, ranging from swaying election outcomes in favor of particular politicians to fostering prejudiced viewpoints. The primary platforms for disseminating fake news are Instagram, WhatsApp, and numerous other social media platforms. By presenting a machine learning-based fake news detection algorithm, this work provides a remedy. This model needs fictitious data that was gathered from multiple information sources. data is extracted using web analytics, which is mostly used to build datasets. Real data sets and fake data sets are the two primary categories into which the data is separated. Random forest, logistic regression, decision trees, KNN, and gradient boosting are the classifiers used to classify the data. The data is categorized as true or false data based on the version that was received. The user will be able to determine whether or not the information on the website is fraudulent based on this. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Resting-State Network Transitions in Temporal Lobe Epilepsy: Insights from MEG Based Dynamic Functional Connectivity

引用

IEEE Transactions on Neural Systems and Rehabilitation Engineering 2025年 33卷 2286-2298页

作者： Suhas, M.V. Sinha, Sanjib Kotegar, Karunakar Ravindranadh Chowdary, M. Raghavendra, K. Asranna, Ajay Viswanathan, L.G. Mariyappa, N. Anitha, H. Manipal Academy of Higher Education Manipal Institute of Technology Department of Electronics and Communication Engineering Karnataka Manipal 576104 India National Institute of Mental Health and Neurosciences (NIMHANS) Department of Neurology Karnataka Bangalore 560029 India Manipal Academy of Higher Education Manipal Institute of Technology Department of Data Science and Computer Applications Karnataka Manipal 576104 India National Institute of Mental Health and Neurosciences (NIMHANS) MEG Research Centre Department of Neurology Karnataka Bangalore 560029 India Manipal Academy of Higher Education Manipal Institute of Technology Department of Computer Science and Engineering Karnataka Manipal 576104 India

Temporal Lobe Epilepsy (TLE), a common form of focal epilepsy, is associated with recurrent seizures originating in the temporal lobe, often leading to cognitive and psychological impairments. This study explores dynamic functional connectivity (dFC) patterns in TLE patients compared to Healthy Controls (HC) using resting-state Magnetoencephalography (MEG) data. dFC, which captures the temporal variability of brain networks, was analyzed across eight frequency bands (delta, theta, alpha, beta, low gamma, mid gamma, high gamma, and broadband) in 21 TLE patients and 21 HC. Nine dFC metrics, including state transitions, connectivity strength, network stability, and overall network movement, were derived using amplitude envelope correlations between 68 brain regions mapped to resting-state networks. Results reveal heightened variability in beta band transitions and increased entropy in delta band transitions, indicating unstable and diverse network configurations. TLE patients showed reduced dwell time in visual networks and increased dwell time in the dorsal attention network, suggesting compensatory mechanisms. Reduced connectivity in alpha and beta bands, coupled with increased variability in theta and low gamma bands, highlights widespread network instability. These findings emphasize dFC metrics as potential biomarkers for TLE, offering insights for targeted therapeutic interventions to stabilize brain dynamics. © 2001-2011 IEEE.

关键词： Dynamic functional connectivity magnetoencephalography resting state network temporal lobe epilepsy

来源：评论

学校读者我要写书评

暂无评论

Fingerprint definition for song recognition using Machine Learning Algorithm

Fingerprint definition for song recognition using Machine Le...

引用

2023 International Conference on Smart Systems for applications in Electrical sciences, ICSSES 2023

作者： Arunakumari, B.N. Shashidhar, R. Sahana, B. Jagadamba, G. Manjunath, A.S. Roopa, M. Bms Institute of Technology and Management Dept. of Computer Science and Engineering Bengaluru India Jss Science and Technology University Dept. of Electronics & Communication Engineering Mysuru India Rv College of Engineering Dept. of Electronics & Communication Engineering Bengaluru India Siddaganga Institte of Technology Dept. of Information Science and Engineering Tumkuru India Jss Science and Technology University Dept. of Master of Computer Applications Mysuru India Dayananda Sagar College of Engineering Dept. of Electronics & Communication Bengaluru India

ISBN: (纸本)9798350347296

A condensed content-based signature that summarises an audio recording is known as an audio fingerprint. Audio The capability to recognize music regardless of design and without the use of meta-data or watermark embedding has made fingerprinting technologies popular. In. tegrity checking, watermark support, and content-based aural retrieval are additional applications for fingerprinting. The various methods of fingerprinting have been discussed using various justifications and terminologies, such as pattern matching, multimedia information retrieval, or cryptography. It is a distinct and condensed digest created using perceptually important elements of a video. Audio material can be monitored using fingerprinting technologies without requiring embedding of metadata or watermarks. However, audio fingerprinting has extra applications The algorithm is trained using thousands of mini audio speech commands. In order to improve the training efficiency, audio features are extracted during a pre-processing. The accuracy of the developed model is 83.7%. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A Review Paper on Various Energy Saving Techniques in WSN

A Review Paper on Various Energy Saving Techniques in WSN

引用

2022 International Conference on Electronics and Renewable Systems, ICEARS 2022

作者： Josephine V. L., Helen Rajan, Dhivya Rajalakshmi, K. Cmr Institute of Technology Dept. of Computer Applications Karanataka Bengaluru India Montfort College Dept. Of. Computer Science Karanataka Bengaluru India

ISBN: (纸本)9781665484251

WSN (Wireless Sensor Network) is a unique variety of temporary type of Local area networks that are highly distributed self-organized systems. There is a detailed collection of various sensor nodes which are vastly deployed throughout the environment. Sensor node is a very small electronic device that is attached to a sensor network. They have an uncomplicated working mechanism that collects the data from any physical movement of an event that occurs or event query that is time driven. The notable feature of the sensor network is data gathering. Each sensory node can gather data, analyse that information and make that information to move to the location that is a destination. Routing algorithms play a vital role in making routing decision that delivers the packet to the exact point through optimal route. Since there is an energy restriction in WSNs, the energy related economisation becomes the most avoidable objective of various routing protocols. routing protocols of various sensor networks is reviewed and presented in this paper which provides a clear classification of various categories and comparison of the various methods. © 2022 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of Teletherapy in Managing Voice Disorders: A Systematic Review

引用

Indian Journal of Otolaryngology and Head & Neck Surgery 2025年 1-17页

作者： Varma, Maya Nayak, Srikanth Rao, Rohini R. Devadas, Usha Department of Speech and Hearing Manipal College of Health Professions Manipal Academy of Higher Education Manipal India Department of Audiology and Speech-Language Pathology Yenepoya Medical College Yenepoya University (Deemed to be University) Mangalore India Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Manipal India

Telerehabilitation has developed as one of the important aspects of health care delivery in the current era. Hence the present study aimed to systematically review the literature and understand the effectiveness of teletherapy in the management of voice disorders. A comprehensive search was performed in the PUBMED, CINAHL, and Scopus databases using Boolean operators, adhering to the PRISMA. The methodological quality of the selected studies was assessed using the ROBINS-I tool. The review included 12 articles meeting the inclusion criteria, featuring various study designs. All studies reported positive outcomes from televoice therapy intervention across multiple voice outcome measures, irrespective of whether participants received direct or indirect or a combination of voice therapy techniques. Studies comparing teletherapy with face-to-face therapy indicated that teletherapy is as effective as in-person therapy. However, the overall risk of bias assessment for the included studies, using the ROBINS-I tool, ranged from moderate to serious. This systematic review revealed that teletherapy is a feasible alternative to in-person therapy for voice disorders. However, there is a need to understand the effectiveness of teletherapy in demonstrating different voice therapy techniques. Further studies are needed to understand the application of various/particular voice therapy techniques via telepractice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comparative Analysis of ensemble methods and their efficiency in the classification of ‘HIT AND RUN’ cases in an imbalanced dataset (Traffic Crashes) with and without using "Synthetic minority oversampling technique"

A comparative Analysis of ensemble methods and their efficie...

引用

International Conference on computer Theory and applications (ICCTA)

作者： Manjula Shenoy K R Srinivas Prabhu Information and Communication Technology Department Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Data Science and Computer Applications Department Manipal Institute of Technology Manipal Academy of Higher Education Manipal India

ISBN: (数字)9798350309584

ISBN: (纸本)9798350309591

In some cases of developing a predictive model for a classification problem, the distribution of classes is skewed, meaning a majority of the training samples belong to a single class and a very small number of samples belong to a minority class. If Machine Learning techniques are applied directly to such data sets, it may result in a model which either ignores the minority class as a whole or gives less importance to the samples belonging to the minority class. Such datasets are often called imbalanced datasets. There are multiple ways to deal with these problems some include Random Over Sampling, Random Under Sampling, Threshold value tuning, one class classification to find the outlier, etc. One such technique is called the "Synthetic minority oversampling technique (SMOTE)". In this paper we are going to analyze the efficiency of ensemble methods for the classification of imbalanced datasets with and without using SMOTE. The dataset used for this purpose is an open-source Traffic crashes dataset available on the Chicago data portal. The target variable for our study is the "HIT_AND_RUN_I" column available in the dataset. This is a dichotomous variable that has 2 valid values. "Y" for the cases that are of positive outcomes as in "HIT_AND_RUN_I" = yes. "N" for the cases that are of negative outcomes as in "HIT_AND_RUN_I" = No.

关键词： Training Predictive models computer crashes data models Ensemble learning Tuning Portals

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：