检索结果-内蒙古大学图书馆

3rd International Symposium on Sensor Technology and Control, ISSTC 2024

作者： Feng, Haoen National University of Singapore College of Design and Engineering Department of Electrical and Computer Engineering Singapore

ISBN: (纸本)9798331541637

Against the backdrop of highly developed smart sensor technology, machine learning, and multimodal data analysis, hand gesture recognition (HGR) has become an important field in promoting human-computer interaction, health monitoring, and rehabilitation medicine. This paper proposes a smart sensor system based on machine learning enhancement, which combines hardware devices such as Flex sensor, JY901S, camera and smart gloves, as well as machine learning models such as support vector machine (SVM) and long short-term memory network (LSTM), using For processing and analysis of gesture data. By using multi-modal data in static and dynamic gesture classification tasks, experimental results show that collaborative inference of multi-modal data significantly improves the model's classification accuracy compared to single or bi-modal data. © 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

LEU3: An Attention Augmented-Based Model for Acute Lymphoblastic Leukemia Classification

引用

IEEE Access 2025年 13卷 31630-31642页

作者： Dutta, Monoronjon Uddin Mojumdar, Mayen Alamgir Kabir, Md Ranjan Chakraborty, Narayan Md Tanvir Siddiquee, Shah Abdullah, Saad Laboratory Department of Computer Science and Engineering Dhaka1207 Bangladesh Mälardalen University School of Innovation Design and Engineering Västerås721 23 Sweden

Acute Lymphoblastic Leukemia (ALL), a cancer affecting the blood and bone marrow, requires precise classification for accurate diagnosis, personalized treatment plans, and improved predictive assessments to enhance patient survival and quality of life. This study presents LEU3, a novel classification model designed to improve the accuracy of leukemia detection from peripheral blood smear (PBS) images. LEU3 leverages an attention-based convolutional neural network (CNN) architecture, incorporating pooling layers, a global average pooling layer, and dense layers with dropout for regularization. The model is trained with an Adam optimizer comprising with four classes: Benign, early malignant pre-B, malignant pre-B, and malignant pro-B. Data augmentation techniques were employed to increase training set diversity. Additionally, Shapley Additive Explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) are used to enhance interpretability and transparency in the model's decision-making process. LEU3 achieved a test accuracy of 99% and a validation accuracy of 99% on 484 PBS images, demonstrating a 3% improvement over the baseline model. These results underline the potential of LEU3 in supporting medical professionals by reducing diagnostic workload and improving the accuracy of leukemia classification. © 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

A Comparative Analysis of Diabetes Prediction System Using Regressor Methods

A Comparative Analysis of Diabetes Prediction System Using R...

引用

2024 IEEE International Conference on Intelligent Computing and Emerging Communication Technologies, ICEC 2024

作者： Sharma, Mansi Kumar, Praveen Puri, Chetan Department of Computer Science and Design Wardha India Department of Computer Science and Medical Engineering Wardha India

ISBN: (纸本)9798331508432

Hyperglycaemia may be a trademark of diabetes mellitus, a chronic metabolic disease that has picked up universal consideration. The administration of diabetes and its related complications depends intensely on early recognizable proof and prevention. Routine approaches to diabetes conclusion can involve intrusive examinations and drawn-out methods. The objective of this development is to utilize machine learning procedures to make a solid and successful diabetes prediction system. A dataset comprising a few patient features, such as age, gender, BMI, affront and glucose levels, pregnancy history, and other related data, is utilized by the recommended framework. In arrange to suit lost values and standardize the information, certain characteristics are pre-processed. Predictive models are at that point prepared utilizing machine learning strategies with logistic regression, support vector machines, random forest, and gradient boosting. Metrics like as accuracy, precision, recall, F1-score, and zone beneath the bend (AUC) are utilized to assess the execution of the show. These measures are utilized to decide which show performs the finest and how well it generalizes to unused information. The system's user-friendly interface makes it simple to enter quiet data and get a anticipated diabetes determination. The ponder progresses the determination of diabetes by giving a non-invasive strategy which will be more exact. Way better early detection might lead to provoke mediation and made strides ailment administration in case the proposed approach is actualized. Additionally, it can reduce the toll that diabetes has on healthcare frameworks and offer assistance therapeutic professionals make well-informed choices. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Predicting Heart Disease: A Machine Learning Approach to Cardiac Health 2

Predicting Heart Disease: A Machine Learning Approach to Car...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Sharma, Mansi Kumar, Praveen Department of Computer Science and Design Wardha India Department of Computer Science and Medical Engineering Wardha India

ISBN: (纸本)9798331528713

Heart disease continues to be a major worldwide health problem, taking many lives annually. Reducing death rates and moving forward persistent results depend heavily on early recognizable proof and anticipation. Conventional techniques for diagnosing cardiac disease can be time-consuming and can require intrusive strategies. Machine learning has ended up a practical strategy for handling these issues in later a long time. Machine learning calculations are able of distinguishing patterns and making exceptionally exact forecasts almost the possibility of cardiac infection by assessing enormous databases of persistent data. This study looks into how machine learning may be utilized to estimate the hazard of heart infection depending on distinctive quiet characteristics. A huge dataset was utilized, which included details approximately blood weight, cholesterol, age, gender, smoking status, and the presence of certain medical disorders. Through the utilize of cutting-edge machine learning strategies such as Random Forest, Support Vector Machine, and Neural Networks, our goal was to make models that may dependably distinguish individuals as either tall or low chance heart malady patients. The comes about of this think about illustrate how machine learning has the capacity to totally change the field of heart illness anticipation. Healthcare experts can act early with focused interventions, such as pharmaceutical, lifestyle changes, or more advanced demonstrative strategies, by accurately recognizing those who are at high risk. This individualized approach to treatment can lower the overall burden of heart illness and enormously upgrade understanding results. This study appears how well machine learning can anticipate the hazard of heart infection. In specific, the Random Forest demonstrate turned out to be a valuable asset for deciding which individuals would benefit from early mediation. We may expect the advancement of continuously more complex and precise models as ma

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach to Classify Skin Cancer

A Deep Learning Approach to Classify Skin Cancer

引用

2024 IEEE International Conference on Intelligent Computing and Emerging Communication Technologies, ICEC 2024

作者： Sharma, Mansi Kumar, Praveen Department of Computer Science and Design Wardha India Department of Computer Science and Medical Engineering Wardha India

ISBN: (纸本)9798331508432

A effective treatment for skin cancer depends on early discovery, which may be a major around the world health issue. This study offers a interesting strategy for dependably classifying skin injuries as benign or malignant by utilizing convolutional neural networks (CNNs). Convolutional Neural Networks (CNNs) are a promising strategy with incredible potential for skin cancer screening. CNNs are well-known for their capacity to observe complex designs from picture data and are able of accurately recognizing benign or malignant skin injuries. Analysts can make exceptionally valuable demonstrative devices by utilizing enormous datasets of skin injury photos to prepare CNN models. Methods like information augmentation, ensemble approaches, transfer learning, attention mechanisms, and generative ill-disposed systems can be utilized to make strides execution indeed encourage. Besides, making mobile and cloud-based apps and examining logical AI can progress the impact and openness of skin cancer diagnosis. CNNs are idealize for this reason because of their reputation for being able to extract complex patterns from visual information. Our approach involves employing a sizable dataset of photographs of skin injuries that have been meticulously labeled to prepare a CNN show. The demonstrate is planning to secure discriminative properties, such as asymmetry, uneven borders, color change, distance across, and creating characteristics, that distinguish benign from malignant tumors. The results of our tests appear how well our proposed CNN-based strategy works to distinguish skin cancer at high accuracy rates. The demonstrate ceaselessly beats out conventional machine learning approaches, illustrating the benefits of profound learning strategies in this field. This ponder progresses the field of dermatology's computer-aided conclusion, giving a possibly valuable instrument to assist therapeutic specialists distinguish and treat skin cancer early on. © 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

Study of the Efficiency of Using Ateb-Functions in Modeling Oscillatory Processes for Networks 18

Study of the Efficiency of Using Ateb-Functions in Modeling ...

引用

18th IEEE International Conference on computer Science and Information Technologies, CSIT 2023

作者： Rebot, Dariia Topilnytskyy, Volodymyr Shcherbovskykh, Serhiy Stefanovych, Tetyana Lviv Polytechnic National University Computer-Aided Design System Department Lviv Ukraine Lviv Polytechnic National University Design and Operation of Machines Department Lviv Ukraine

ISBN: (纸本)9798350360462

The paper examines the feasibility of utilizing Ateb-functions to analyze oscillatory processes. The transformation of Ateb-functions to ordinary trigonometric functions with changes in the nonlinearity parameter is presented. This allows for their application in novel sets of partial differential equations in the study of oscillatory processes and motion in computer networks. © 2023 IEEE.

关键词： computer networks

来源：评论

学校读者我要写书评

暂无评论

Building a Smart Virtual Chatbot Assistant with HTML, CSS, and JavaScript 2

Building a Smart Virtual Chatbot Assistant with HTML, CSS, a...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Khonde, Tanvi Patle, Sneha Talvekar, Shreya Hajbe, Jahnavi Faculty of Engineering and Technology Department of Computer Science and Design Maharashtra Wardha442201 India

ISBN: (纸本)9798331505745

A virtual chatbot assistant is an interactive application designed to simulate human-like communication and respond to user inquiries promptly. It focuses on building an interesting user interface and putting simple conversational logic into practice;this article presents the development of a chatbot using HTML, CSS, and JavaScript. Developers can make these fundamental web technologies useful in the creation of accessible and user-friendly chatbot systems for any kind of application. The literature indicates that chatbot technology is under development, which includes the merging of AI and natural language processing to enhance the capabilities of conversations. This handbook is an invaluable tool in making useful chatbots by linking the needs of the users with contemporary online technology. © 2025 IEEE.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

Bitcoin Price Prediction Using Deep Learning Models 4

Bitcoin Price Prediction Using Deep Learning Models

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Hajare, Rasika Puri, Chetan Gote, Pradnyawant M. Faculty of Engineering and Technology Department of Computer Science and Design Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

Forecasting the price of bitcoins is significant in contemporary research, given the fact that the digital currency is relatively unpredictable and highly integrated in global securities markets. This paper compares the use of three deep learning models, namely recurrent neural networks (RNN), gated recurrent unit (GRU), and a convolutional neural network-long short-term memory (CNN-LSTM) for Bitcoin price prediction. Historical Bitcoin price data is used in the dataset, and every one of the models is trained and tested based on its performance to predict future prices based on past data. The proposed models include the RNN and GRU, which incorporate sequential dependency mappings to learn complex sequences, and the CNN-LSTM structures combine convolution layers for feature extraction and LSTM layers for sequencing. Different models' competency is discussed using the averaged Mean Squared Error (MSE) and graphs of the model's prediction against actual prices. The experimental results reveal that the proposed CNN-LSTM model has better prediction accuracy than RNN and GRU in time-series forecasting tasks, indicating that more complex architecture hybrid models might provide better forecasting performance. In analyzing and analyzing cryptocurrency price dynamics, this investigation gives information about the opportunities and challenges of these models to enhance future research. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Optimal Hyperparameters for Collaborative Filtering: A Comparative Study 2

Optimal Hyperparameters for Collaborative Filtering: A Compa...

引用

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Jose, Basil Bhatkande, Aditya Phadte, Siddharth Kerkar, Richa Muzavor, Adnan Agnel Institute of Technology and Design Department of Computer Engineering Goa Assagao India

ISBN: (纸本)9798350371314

In recommendation systems, collaborative filtering algorithms play a vital role in offering personalized recommendations based on user-item interactions. This paper conducts a detailed comparative study of three collaborative filtering algorithms, including Alternating Least Squares (ALS), Singular Value Decomposition (SVD), and Neural Collaborative Filtering (NCF). The paper's objective is to provide the optimal hyperparameter configurations for the three algorithms, which would boost their predictive power, using the Movie Lens 25M dataset. Initially the algorithms are evaluated with default parameters whose results shows that SVD performs better in Mean Absolute Error (MAE) while ALS performs better in RMSE. However, after the hyperparameter tuning with multiple parameters, such as epoch, rank, maxIter, learning rate, and batch size, the most optimal hyperparameter configuration for the algorithms was defined. The results tells that each of the algorithm have the capacity to handle sparsity. According to the RMSE and MAE, ALS and SVD have a slight advantage over NCF. These results are essential for choosing the appropriate hyperparameters enhancing the accuracy of the algorithms and the recommendation system as a whole. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection for Secure Optimal Routing Techniques in Wireless Sensor Networks 2

Intrusion Detection for Secure Optimal Routing Techniques in...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Karthick, V. Nirmalkumar, P. Parthasarathi, C. Sanjay, S.S. Department of Computer Science and Design Rajalakshmi Engineering College Tamilnadu Chennai India

ISBN: (纸本)9798350383867

There is a Wide variety of areas where WSNs are heavily relied upon, these network are referred to as radio frequency sensor networks, or simply WSNs. As far as the environment monitoring is concerned, WSNs are very imperative in that they facilitate the measurements of temperature, humidity, and air *** systems should be able to detect abnormal and suspicious movements like malware, denial of service attacks, and illegal access attempts. Our systems is also able to detect those attackers of WNS (Wireless Network System) attacks by using CHS(Cluster Head Selection) based optimal secure solution. We can do as well to build a secure wireless network that suits everyone, and protects all the data. Routing and security issues are tackled using AWNS and thereby, the availability of data becomes *** performs the task of anomaly detection and thereby the identification of extraordinary events and trends on the collected data is possible. These uncommon events are not just to be passed by and thrown up because of the fact that they might as well suggest a sensor failure, equipment failure, or even a possible hazard to the safety of the institution. © 2024 IEEE.

关键词： Air quality

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：