检索结果-内蒙古大学图书馆

3rd World Conference on Internet of Things: Applications and Future, ITAF 2023

作者： El-rashidy, Nora El-Ghamry, Amir ElSayed, Nesma E. Machine Learning and Information Retrieval Department Faculty of Artificial Intelligence Kafrelsheiksh University Kafrelsheiksh Egypt Faculty of Computers and Information Mansoura University Mansoura Egypt School of Engineering and Computer Science Hosted By Global Academic Foundation University of Hertfordshire Garden City Egypt Faculty of Computer Science and Engineering New Mansoura University Mansoura Egypt Delta Higher Institute for Management and Accounting Information Systems Mansoura Egypt

ISBN: (纸本)9789819947638

Blood transfusion is in constant demand, as it is required for several medical procedures and life-or-death operations. This study is motivated by the fact that the need for blood transfusions is steadily on the rise because of accidents, operations, diseases, etc. such that the ability to accurately predict the number of blood donors allows medical personnel to predict the future blood supply and plan accordingly to recruit enough volunteers to meet demand. We attempt to handle this supply–demand gap by using a predictive model that identifies potential donors. We model the probability of a person donating blood, depending on five specific features, using machine learning techniques. This paper implements a machine learning pipeline that includes data preprocessing and donor classification. Several ensemble models have been developed. The results show that the random forest model led to the best test set accuracy (96.3%), which beat other methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning for Uneven Data in Industrial IoT Using a Distributed Bias-Aware Adversarial Network 5

Deep Learning for Uneven Data in Industrial IoT Using a Dist...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Gupta, Raj Kumar Naveena, N. Rao, B. Srinivasa Rs, Rajasree Sarkar, Swagata Kumar, Kallakunta Ravi Sardar Vallabhbhai Patel College Veer Kunwar Singh University Physics Department Bihar Ara Bhabua India Kongu Engineering College Computer Technology-UG Perundurai India Gokaraju Rangaraju Institute of Engineering & Technology Department of Computer Science and Engineering Hyderabad500090 India New Horizon College of Engineering Artificial Intelligence and Machine Learning Bangalore India Sri Sairam Engineering College Department of Artificial Intelligence and Data Science Sai Leo Nagar Chennai44 India Koneru Lakshmaiah Education Foundation Department of Ece AP Vaddeswaram India

ISBN: (纸本)9798350321425

In minority class and noisy data situations, supervised learning performs more favorably for the majority class but cannot generalize testing data. Performance in the aforementioned use cases might be improved with the help of neural-based data augmentation approaches for generating new data and deep convolutional models for classification. GANs (generative adversarial networks) have recently demonstrated impressive advancements in picture generation. To address the restrictions imposed by the distribution bias problem between the produced data and the unique data, and to provide a more vigorous data augmentation, the presented distribution bias aware collaborative GAN (DGAN) model for unbalanced deep learning in industrial IoT. By including an auxiliary classifier in the foundational GAN model, a comprehensive data augmentation system may be built. In particular, a provisional source of energy with random labels is envisioned and trained combatively with the classification model to appropriately augment the amount of data specimens in minority classes, and a mass fraction system is newly envisioned between two distinct feature extraction, allowing the cooperative adversarial training among some of the power source, voltage divider, and classification algorithm. The next step is to develop an augmentation approach for smart anomaly detection in class imbalance, which, by adjusting for dispersion bias using the properly balanced data, might significantly improve classification precision. Experiment assessments using real-world unbalanced datasets show the superior recital of the suggested model in addressing the distribution biased issue for multi-class classification in class imbalance for commercial IoT applications, as compared to five baseline techniques. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Semantic Segmentation for Enhanced Football Analytics: A Pixel-level Approach

引用

Procedia Computer Science 2024年 235卷 2662-2673页

作者： Bharathi Malakreddy A Sadanand Venkataraman Mohammed Sinan Khan Nidhi Srinivas Padmanabhuni Santhi Natarajan Research & Consultancy Cell BMS Institute of Technology & Management Bengaluru India Department of Artificial Intelligence & Machine Learning BMS Institute of Technology & Management Bengaluru India Department of Computer Science and Engineering Research Shiv Nadar University Chennai India *** Benaluru India

Semantic Segmentation, a pivotal technique in image analysis, is adeptly leveraged in this research to bolster sports analytics, with a concentrated focus on football. A comprehensive pipeline is unveiled for an in-depth analysis of a select portion of the IAUFD 100k dataset, encompassing 2030 manually annotated football images. The methodology entails a thorough evaluation and comparison of diverse semantic segmentation models, supplemented by the integration of advanced pre-processing strategies and optimal training techniques. Such a holistic approach culminates in a marked enhancement in model performance, as evidenced by a significant uptick in the mean Intersection over Union (mIoU). This research offers granular, object-oriented insights that substantially augment player tracking, action recognition, and event detection in football. The conclusive remarks of the study highlight prospective avenues for further research, emphasizing the potential incorporation of Explainable AI and advanced Metamorphic and Security Testing to fortify sports analytics.

关键词： Semantic Segmentation Sports Analytics Football Computer Vision Deep learning Convolutional Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Cloud-based Data Analytics for Automated Coastal Cleanup Robots with Convolutional Neural Network 8

Cloud-based Data Analytics for Automated Coastal Cleanup Rob...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Babu, A. Ramesh Basavaraddi, Chethan Chandra S. Ramesh, S. Mouleeswaran, S.K. Sahoo, Santosh Kumar Solainayagi, P. Vidya Vikas Institute of Engineering and Technology School of Computer Applications Karnataka Mysore India R&D Don Bosco Institute of Technology Bangalore Vtu Department of Artificial Intelligence and Machine Learning Karnataka Belagavi India College of Engineering and Technology Srm Institute of Science and Technology School of Computing Department of Computing Technologies Tamil Nadu Chennai India Vit University Department of Engineering and Technology Madhya Pradesh Bhopal India Dayananda Sagar University Department of Computer Science and Engineering Karnataka Bangalore India Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350376425

The growing danger of coastal pollution requires novel, automated remediation methods. This paper proposes combining autonomous robots with sophisticated sensor technologies and a Convolutional Neural Network (CNN)-based data analytics system to clean up coastal areas. The robots autonomously cruise coastal settings, discover and categories marine waste using onboard sensors, and send data to a cloud-based infrastructure for analysis. The proposed method relies on CNN, a deep learning model known for image recognition. For reliable identification and classification, CNN is trained on a broad collection of marine waste images. The cloud-based data analytics platform receives, processes, and stores cleaning robot data. It handles massive datasets effectively using cloud computing scalability and processing power. The technology uses real-time cloud image processing to identify garbage and enable robots to adjust their cleaning tactics. The data analytics platform generates detailed reports and visualizations to analyze cleaning efficiency and environmental effect. It advances automated coastal cleaning technology by integrating advanced robotics, sensor technologies, and deep learning. The proposed approach improves coastal cleaning speed, accuracy, and flexibility to protect marine habitats and biodiversity. © 2024 IEEE.

关键词： Cloud-based Infrastructure Environmental Monitoring Image Recognition Real-time Processing Sensor Technologies

来源：评论

学校读者我要写书评

暂无评论

Enhanced Camouflage Detection Using Advanced Image Processing Techniques for Real-Time Object Recognition and Pattern Differentiation 5

Enhanced Camouflage Detection Using Advanced Image Processin...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Manikandan, G. Deepa, R. Jayalakshmi, V. Thilakavathy, P. Surendran, R. St. Joseph's College of Engineering Anna University Department of Artificial Intelligence and Machine Learning Chennai India School of Computing SRM Institute of Science and Technology Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Computer Science and Applications Chennai India Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Computer Science and Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

The identification of objects that blend in with their surroundings has long been a concern in fields including defence, wildlife monitoring, and surveillance due to the difficulty of detecting such objects. This finding is significant because it could greatly enhance our capacity to detect camouflaged objects, transforming the field of real-time object detection. Existing image processing methods often fail miserably when adequately capturing this aspect. This dissertation's primary focus is identifying devices with complicated patterns, legacy interference, and inadequate contrast;nonetheless, in disguised scenarios, all of these features cause identification to be unsuccessful. This research often suggests a new approach called the Linear Edge Detecting Scheme for Camouflaged Object Detection (LEDS-COD) in these difficult cases. The LEDS-COD system can enhance item visibility in low-comparison settings by highlighting critical edges and descriptions. Pattern differentiation methodologies and modern facility-side recognition techniques are combined to accomplish this goal. The approach successfully differentiated items because it zeroed in on texture and comparative details that would otherwise go unnoticed by humans or advanced algorithms. LEDS-COD is useful in many areas, including the Navy, autonomous surveillance systems, and animal protection, where the real-time identification of hidden devices is essential. Results from a simulation study using various datasets, including concealed objects, show that LEDS-COD surpasses conventional detection methods in recognition accuracy, processing speed, and perseverance. The recommended technique exceeded the requirements for obtaining improved object detection estimates for challenging conditions like those with complex backdrops and changing illumination. According to this study, LEDS-COD can be devastating in improving real-time camouflage detection. © 2024 IEEE.

关键词： Accuracy Image processing Surveillance Image edge detection Wildlife Lighting Object detection Real-time systems Object recognition Protection

来源：评论

学校读者我要写书评

暂无评论

Recursive Feature Elimination based Multi-variate Naïve Bayes Classification for Product Recommendation 4

Recursive Feature Elimination based Multi-variate Naïve Bay...

引用

4th International Conference on Emerging Research in Electronics, Computer Science and technology, ICERECT 2022

作者： Parameshachari, B.D. Gollagi, S.G. Pareek, Piyush Kumar Karamthoti, Mohandas Nitte Meenakshi Institute of Technology Electronics and Communications Engineering Bengaluru India KLE College of Engineering and Technology Computer Science & Engineering Belagavi India Nitte Meenakshi Institute of Technology Artificial Intelligence & Machine Learning Bengaluru India Edu Infotech International Res Inc AtlantaGA United States

ISBN: (纸本)9781665456357

Today's most important E-commerce apps are those that use the latest AI and machine learning technologies. Unlike humans, computers are unable to comprehend non-digital alternatives. Therefore, it is vital that consumers learn about things like food, clothing, and medicine. Human perceptions have certain limits, but expanding them is no easy feat. Because of the rapid development has quickly become a common way for people to make purchases and get content. Performing an efficient way to increase consumer happiness. Because of shifts in sequence length, textual order, and complex logic, imagining the true polarity of user evaluations remains a formidable challenge. It is recommended that SA work be broken down into four distinct phases: I data gathering (DC), (ii) pre-processing, (iii) features extraction (FE) or term weighting-(TW), (iv) feature-selection-(FS), and (v) polarity or sentiment classifications (SC). To begin, the data collection process begins with the Web Arguing Tool (WST) being used to scrape product reviews from E-commerce sites. The data acquired from the web scrape is then preprocessed. These cleaned data are further processed using Term Frequency-based inverse class frequency by passing them via TW and FS. The purpose of this study is to use two common Naive Bayes approaches - Classification - to determine if a review of a product is positive or negative. The optimal candidate feature subset is chosen by using a recursive feature elimination strategy on the data. The study also seeks to determine which of the two methods is more effective for the provided data. A '2' yardstick dataset is used for comparing the proposed classifier to the current state of the art. Consequences show that, associated to state-of-the-art procedures, the suggested model provides the highest performance in SC © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Investigation of Student Engagement Monitoring System using machine learning

Investigation of Student Engagement Monitoring System using ...

引用

International Conference on Inventive Computing and Informatics (ICICI)

作者： Amish Abraham G Titus Issac J Sebastian Terrance Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore Tamil Nadu India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore Tamil Nadu India

ISBN: (数字)9798350373295

ISBN: (纸本)9798350373301

This research study aims to enhance the intelligent classroom ecosystem by integrating the Local Binary Pattern Histogram (LBPH) algorithm with human expertise to identify students' faces. Monitoring student attentiveness is crucial for effective learning. To support this, this study uses Mediapipe to analyze students' body posture, providing insights into their engagement levels. Additionally, the proposed framework includes the Eye Aspect Ratio (EAR) Algorithm to detect signs of drowsiness and yawning. By continually refining the proposed framework, this study intends to improve intelligent classroom ecosystems, helping educators to create environments that increase student success.

关键词： Histograms Tracking Scalability Ecosystems Refining Ear User experience

来源：评论

学校读者我要写书评

暂无评论

Optimizing FAANG Stock Forecasting: The Power of Feature engineering and LSTM in Financial Analysis

Optimizing FAANG Stock Forecasting: The Power of Feature Eng...

引用

2025 International Conference on artificial intelligence and Data engineering, AIDE 2025

作者： Tiwari, Priyanshu Patil, Soumya Ambareesh, S. Raj, Rishabh Sir M. Visvesvaraya Institute of Technology Dept. of Artificial Intelligence and Machine Learning Bengaluru India Sir M. Visvesvaraya Institute of Technology Dept. of Information Science and Engineering Bengaluru India

ISBN: (纸本)9798331527518

The unprecedented growth and market capitalization of the FAANG stocks - Facebook, Amazon, Apple, Netflix, and Google (Alphabet) - have mushroomed into the pay-off race of the leaders of the global financial market. Stock price volatility prediction attracts the focus of the investors and analysts in the pursuit of profit maximization relying on market movements. In order to enhance the precision of stock price predictions for FAANG companies, other more intricate methods for feature engineering are also coupled together with LSTM neural networks. Stock price dynamic intricacies are being reflected by the model using the complete set of financial indicators, predictive analytics, and market sentiment data as features. The work showed a phenomenal application of LSTM networks in the analysis and prediction of stock price trends compared to the classic methods on the sequential-by-nature front dealing with long dependencies. It is actually possible to build a strong base of data enabling the detection of such elusive trends in the performances of FAANG stocks and technical indicators, sentiment analysis, or economic metrics, for instance, thereby getting into working order for LSTM modeling. Results from experiments show the method provides better accuracy and reliability than conventional machine learning models, thus collecting valuable insights for certain financial-forecasting purposes. The paper serves as a demonstration illustrates how feature engineering and LSTM might be combined to improve predicting financial markets and provides one solution for investors, financial analysts, and policymakers who look to make informed investment decisions. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Travel Itineraries: A Multi-Objective machine learning Model Approach

Optimizing Travel Itineraries: A Multi-Objective Machine Lea...

引用

Applied artificial intelligence and Computing (ICAAIC), International Conference on

作者： X Samuel Roy Titus Issac J Sebastian Terrance Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore Tamil Nadu India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore Tamil Nadu India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

A travel itinerary is a complex problem that involves multiple objectives and constraints, such as cost, time, transportation modes, and comfort levels. This research study focuses on creating a real-time eco-friendly itinerary generator by integrating machine learning techniques. This research work explores two machine-learning algorithms: artificial Neural Networks (ANNs) and Multi-Layer Perceptron (MLP). These algorithms are evaluated for their suitability in generating user-friendly and environment-friendly itineraries. Through experimentation, the accuracy and precision of the proposed models are assessed, leading to the identification of an optimal travel planner model. The ultimate goal of this model is to provide a detailed itinerary that considers prominent modes of transportation while addressing the pressing environmental crisis. By prioritizing eco-friendly options, this approach sets itself apart from conventional travel planning tools.

关键词： machine learning algorithms Navigation Web services Biological system modeling Transportation artificial neural networks machine learning

来源：评论

学校读者我要写书评

暂无评论

GeneDroid Fuzz: An Android Intent Fuzzing Method Based on Gene Mutation

GeneDroid Fuzz: An Android Intent Fuzzing Method Based on Ge...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Lu, Runfeng Sun, Yuzhu Sun, Haofeng Fu, Xiao Luo, Bin Du, Xiaojiang Shi, Jin Aitsaadi, Nadjib Guizani, Mohsen Nanjing University State Key Laboratory for Novel Software Technology Nanjing China Stevens Institute of Technology Department of Electrical and Computer Engineering HobokenNJ United States Nanjing University School of Information Management Nanjing China Université Paris-Saclay David Uvsq Versailles France Mohamed Bin Zayed University of Artificial Intelligence Machine Learning Department Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350351255

With the rapid expansion of mobile internet usage, the prevalence of the Android operating system on smartphones is steadily growing. However, improper utilization of the Intent mechanism within Android applications can result in security vulnerabilities. Presently, the majority of Android security testing methods, which rely heavily on fuzzing, are predominantly focused on UI interactions, lacking sufficient testing capabilities for Intents. The motivation of this paper is to find a more effective testing method to improve the security detection capabilities of Intents. This paper introduces an Intent fuzzing method based on genetic mutation principles. Initially, we establish an Intent seed library using a text classification model, followed by employing Jaccard distance and minimum edit distance to refine high-quality seeds. Subsequently, we augment the seeds through extensive mutation using genetic algorithms, generating numerous test cases that exhibit structural similarity but contain varied content. During testing, we compare the state before and after Intent testing using image similarity to detect anomalies. Experimental results demonstrate that this method effectively enhances test coverage and identifies potential issues in edge cases. This approach offers an efficient means of conducting Intent security testing and enhances Android app robustness and security. © 2024 IEEE.

关键词： Android Fuzzing Gene Mutation Intent

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：