检索结果-内蒙古大学图书馆

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Suneela, M. Sahithi, Mandadi Vamsi, Nuthalapati Naik, Nunsavathu Balaji Chowdary, Narra Sujitha Vignan's Lara Institute of Technology & Science College Dept. of Computer Science & Engineering Guntur India

ISBN: (纸本)9798350370249

The project 'Enhancing Dietary Monitoring Using Deep Learning:Food Recognition And Calorie Estimation' introduces an innovative method aimed at improving dietary tracking and fostering healthier eating habits. By employing cutting-edge deep learning techniques, its core objective is to precisely identify various food items and rapidly estimate their caloric content, offering users advanced and personalized monitoring capabilities. Utilizing the Python programming language alongside the MobileNet architecture model, the project underwent rigorous training and evaluation using the expansive Food 101 dataset, comprising 37,046 food images distributed across 101 distinct classes. Notably, the model demonstrated exceptional performance, achieving a training accuracy of 97.02% and a validation accuracy of 98.17%, highlighting the efficacy of this approach in accurately categorizing a wide array of food items. This system provides users with several crucial functionalities. Furthermore, it furnishes users with essential insights by estimating the caloric content of recognized foods, facilitating effective monitoring of dietary intake. The intelligent diet monitoring capabilities enabled by Food Recognition and Calorie Estimation empower users to make informed choices regarding their dietary preferences. Through the continuous tracking and analysis of their daily food consumption, users can glean valuable insights into their nutritional habits, set personalized goals, and make necessary adjustments to achieve a well-balanced and healthy diet. Enhancing Dietary Monitoring Using Deep Learning:Food Recognition And Calorie Estimation stands as a prominent illustration of successful implementation of deep learning techniques, particularly with the utilization of the MobileNet architecture, for food recognition and calorie estimation. With its remarkable accuracy, real-time processing capabilities, and intelligent monitoring features, this project has the potential to revolutioni

关键词： Convolutional Neural Network (CNN) algorithm datasets MobileNet architecture Web application

来源：评论

学校读者我要写书评

暂无评论

Oracle-Efficient Reinforcement Learning for Max Value Ensembles 38

Oracle-Efficient Reinforcement Learning for Max Value Ensemb...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hussing, Marcel Kearns, Michael Roth, Aaron Sengupta, Sikata Bela Sorrell, Jessica Dept. of Computer and Information Science University of Pennsylvania PhiladelphiaPA19104 United States Dept. of Computer Science Johns Hopkins University BaltimoreMD21218 United States

Reinforcement learning (RL) in large or infinite state spaces is notoriously challenging, both theoretically (where worst-case sample and computational complexities must scale with state space cardinality) and experimentally (where function approximation and policy gradient techniques often scale poorly and suffer from instability and high variance). One line of research attempting to address these difficulties makes the natural assumption that we are given a collection of base or constituent policies (possibly heuristic) upon which we would like to improve in a scalable manner. In this work we aim to compete with the max-following policy, which at each state follows the action of whichever constituent policy has the highest value. The max-following policy is always at least as good as the best constituent policy, and may be considerably better. Our main result is an efficient algorithm that learns to compete with the max-following policy, given only access to the constituent policies (but not their value functions). In contrast to prior work in similar settings, our theoretical results require only the minimal assumption of an ERM oracle for value function approximation for the constituent policies (and not the global optimal policy or the max-following policy itself) on samplable distributions. We illustrate our algorithm's experimental effectiveness and behavior on several robotic simulation testbeds. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction of Chronic Liver Disease Using Machine Learning Algorithms and Interpretation with SHAP Kernels

Prediction of Chronic Liver Disease Using Machine Learning A...

引用

2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： Raj, Harini Niharika, G. Kodipalli, Ashwini Rao, Trupthi Global Academy of Technology Dept. Artificial Intelligence & Data Science Karnataka Bangalore India

ISBN: (纸本)9798350382693

The study below shows that we have mainly focused on predicting liver disease. The dataset used was obtained from Kaggle which contained 11 columns and 583 rows, amongst which there were 142 females and 441 males. The dataset contained various features which helped our model to do better predictions. We have used Machine Learning algorithms for the purpose which included classification algorithms like Random-Forest, Logistic-Regression, Decision-Tree, SVM, KNN. The results obtained from all these classifiers were then given to an ensemble model to arrive at exceptional results. In the paper below we obtained the highest accuracy using Random Forest classifier which gave us a result of 72%. We have then used LIME & SHAP kernels. SHAP kernels allowed us to explain the underlying decision-making-process in a better way, it also enhanced the interpretability and trustworthiness of the models. These findings highlight the effectiveness of the ML models and their contribution to the field of liver disease diagnoses and prediction. © 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

Enhancing Password Security: Fuzzy AHP and TOPSIS-based Vulnerability Assessment 9

Enhancing Password Security: Fuzzy AHP and TOPSIS-based Vuln...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Kumar, Ashwin Darshan Shankar, R. Kodipall, Ashwini Rao, Trupthi Soma, Bhavani Gargi, N. Global Academy of Technology Dept. of Artificial Intelligence & Data Science Karnataka Bangalore India

ISBN: (纸本)9798350394474

In the digital age, passwords are key to securing access to personal, financial and corporate assets. But the changing cyber threat landscape requires a stronger approach to password security. Password authentication has become an important part of network security strategy. It is very important to know how vulnerable is a given password. In this paper we have considered the different criteria's that affect the vulnerability and ranked them accordingly using Fuzzy Ahp method. Among the different alternatives the most vulnerable password is identified using Fuzzy topsis method hinge on the ranked criteria's from the above method. We have used the proposed methods to rank the passwords based on how vulnerable they are and the results are presented © 2024 IEEE.

关键词： Technology transfer

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised and personalized federated activity recognition based on active learning and label propagation

引用

Personal and Ubiquitous Computing 2022年第5期26卷 1281-1298页

作者： Presotto, Riccardo Civitarese, Gabriele Bettini, Claudio Dept. of Computer Science University of Milan Milan Italy

One of the major open problems in sensor-based Human Activity Recognition (HAR) is the scarcity of labeled data. Among the many solutions to address this challenge, semi-supervised learning approaches represent a promising direction. However, their centralized architecture incurs in the scalability and privacy problems that arise when the process involves a large number of users. Federated learning (FL) is a promising paradigm to address these problems. However, the FL methods that have been proposed for HAR assume that the participating users can always obtain labels to train their local models (i.e., they assume a fully supervised setting). In this work, we propose FedAR: a novel hybrid method for HAR that combines semi-supervised and federated learning to take advantage of the strengths of both approaches. FedAR combines active learning and label propagation to semi-automatically annotate the local streams of unlabeled sensor data, and it relies on FL to build a global activity model in a scalable and privacy-aware fashion. FedAR also includes a transfer learning strategy to fine-tune the global model on each user. We evaluated our method on two public datasets, showing that FedAR reaches recognition rates and personalization capabilities similar to state-of-the-art FL supervised approaches. As a major advantage, FedAR only requires a very limited number of annotated data to populate a pre-trained model and a small number of active learning questions that quickly decrease while using the system, leading to an effective and scalable solution for the data scarcity problem of HAR. © 2022, The Author(s).

关键词： Mobile computing

来源：评论

学校读者我要写书评

暂无评论

FUZZY AHP and TOPSIS Approach to Evaluate the Criteria of HVAC Control System

FUZZY AHP and TOPSIS Approach to Evaluate the Criteria of HV...

引用

2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： Gowda, S. Mayur Urf Hosamani, Manjunath Madar Kodipalli, Ashwini Rohini, B.R. Soma, Bhavani Gargi, N. Global Academy of Technology Dept. of Artificial Intelligence & Data Science Karnataka Bangalore India

ISBN: (纸本)9798350382693

Effective control of Heating, Ventilation, and Air Conditioning (HVAC) systems is necessary to optimize indoor comfort, energy efficiency, and environmental impact. This study presents a novel method that combines the Technique for Order of Preferences by Similar to Ideal Solution (TOPSIS) with the Fuzzy Analytic Hierarchy Process (AHP) to improve decision-making in HVAC control systems. Conventional HVAC control systems may not be well-suited to dynamic and uncertain situations since they frequently rely on deterministic algorithms and preset rules. On the other hand, the suggested method makes use of fuzzy logic to address the innate ambiguity and imprecision in HVAC control choices. reducing the impact on the environment and energy use. © 2024 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Test Suite Minimization Through PSO 11

Test Suite Minimization Through PSO

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Ahuja, Neeru Bhatia, Pradeep Kumar Guru Jambheshwar University of Science and Technology Dept. of Computer Science and Engineering Haryana Hisar125001 India

ISBN: (纸本)9798350350357

Regression testing is a critical stage that ensures the software changes are not affecting existing functionality. Ideally, conducting regression tests after each software change is essential. However, the exhaustive repetition of full tests for every alteration proves time-consuming, expensive, and demands significant resources. Test suite minimization serves as a solution by eliminating redundant test cases. This research presents an advanced approach to eliminate redundant test cases effectively. The proposed method focuses on identifying a concise yet effective set of test cases that align with requirements and efficiently uncover faults. This streamlined approach not only reduces testing expenses but also contributes to a more efficient testing process. The study demonstrates its effectiveness in minimizing the test suite by employing the Particle Swarm Optimization (PSO) algorithm with varied inertia weight strategies. Results from simulations indicate the success of this approach in reducing the test suite size while maintaining or even improving code coverage. Comparative analysis against Genetic Algorithms (GA) and Artificial Bee Colony (ABC) methods underscores the superior performance of PSO, specifically with tailored inertia weight strategies. This research significantly contributes to optimizing software testing methodologies, ultimately enhancing fault detection efficiency in software development. © 2024 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Sentimental Analysis of Various TV Serials in Society 15

Sentimental Analysis of Various TV Serials in Society

引用

15th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2023

作者： Sarkar, Ripa Sarkar, Ratna R. BRAC University Dept. of Computer Science and Engineering Dhaka Bangladesh Jahangirnagar University Dept. of Computer Science and Engineering Savar Bangladesh

ISBN: (纸本)9798350324433

Sentiment analysis which involves identifying emotions in the text is a widely studied topic of natural language processing. Many researchers focus on social media content like posts, tweets and reviews for their studies. In this paper, a large number of data from comments about serials on social media and internet forums in Banglish is collected and analyzed. We use NLP techniques to do the sentiment analysis of the comments. This study explores how different kinds of serials have impacted society and concentrates on how they have influenced the creation of Banglish comments. This study aims to conduct a sentiment analysis of Banglish comments generated in response to different genres of serials and to analyze their potential societal implications. Along with Long Short-Term Memory (LSTM), we use several machine-learning algorithms such as Logistic Regression (LR), Multinomial Naive Bayes (MNB), Gaussian Naive Bayes, Decision Tree (DT), AdaBoost, Random Forest (RF) and Support Vector Machine (SVM) to create this model. The SVM gives the highest accuracy among all of the machine learning algorithms. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Automated Road Extraction in Urban and Rural Regions from Remote Sensing Imagery with U-Net and ResNet-Based Architectures 1

Automated Road Extraction in Urban and Rural Regions from Re...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Sharma, Palvi Kumar, Rakesh Gupta, Meenu Obaid, Ahmed J. Chandigarh University Dept. of Computer Science & Engineering Punjab India Chandigarh University Dept. of Computer Science & Engineering Punjab India University of Kufa Faculty of Computer Science and Mathematics Najaf Iraq National University of Science and Technology College of Technical Engineering Dhi Qar Iraq

ISBN: (纸本)9798350356816

Accurate road extraction from Remote Sensing Imagery (RSI) is crucial for various applications, including urban planning, navigation, and disaster response. This study investigates automated road extraction in rural, semi-urban and urban regions using deep learning architectures, specifically UNet and Deep Residual U-Net (ResNet) models. We leverage High-Resolution Satellite Imagery (HRSI) to train and validate our models, focusing on the distinct characteristics and challenges presented by urban and rural environments. Our methodology involves comprehensive data preprocessing and augmentation techniques to enhance model robustness. We evaluate the performance of both architectures using metrics and achieved an accuracy of 90.29%, recall of 80.95%, precision of 74.89%, and F1- score of 77.80% for the Deep Residual U-Net. Experimental results demonstrates that while both models perform well, the Deep Residual U-Net exhibits superior accuracy and generalization, particularly in complex urban landscapes. © 2024 IEEE.

关键词： Urban planning

来源：评论

学校读者我要写书评

暂无评论

FitTip: Merging Technology and Fitness for Posture Improvement 3

FitTip: Merging Technology and Fitness for Posture Improveme...

引用

3rd International Conference on Trends in Electrical, Electronics and computer Engineering, TEECCON 2024

作者： Tembhurnikar, Atharv Sarvankar, Girish Yadav, Gitanjali Vaidya, Rohan Shelar, Aditya Bhage, Kartik Vishwakarma Institute of Information Technology Dept. of Artificial Intelligence and Data Science Pune India

ISBN: (纸本)9798331505714

Poor form is a primary contributor to exercise-related accidents, which can result in permanent physical handicap and deter people from maintaining a regular fitness regimen. This study suggests FitTip, an intelligent posture identification and correction device that uses computer vision and machine learning, as a means of preventing these kinds of injuries. Using a proprietary dataset of yoga and gym routines, we developed a convolutional neural network (CNN) integrated with the Mediapipe framework to accurately categorize and correct workout positions in real time. Position analysis is used in FitTip' s design to provide real-time feedback and change recommendations. The algorithm was evaluated on a dataset of five workout poses, and the results indicated that it could get 98.73% training and validation accuracy. These findings show how well algorithm works to improve overall fitness results and workout safety. The suggested algorithm offers a framework that is scalable for enhancing posture during activity, and it may eventually be integrated with wearables and fitness applications. It includes a real-time camera feed for pose detection, a key-point detection module, and a feedback algorithm that suggests corrections based on the angles between body joints. This paper also addresses challenges such as limited dataset size and variability in user movements, proposing solutions through enhanced preprocessing and pose analysis techniques. FitTip algorithm makes training safer and more accessible for people of all fitness levels, which adds to the expanding field of fitness technology. © 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

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：