检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Maheswari, M. Alabdeli, Haider Aruna, T.M. Reddy, R. Archana Revathi, R. School of Computing Srm Institue of Science and Technology Department of Computational Intelligence Kattankulathur India College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Artificial Intelligence and Machine Learning Bengaluru India School of Computer Science and Engineering Sr University Warangal India Karpagam Academy of Higher Education Department of Computer Science Echanari Coimbatore India

ISBN: (纸本)9798350373110

In recent times, face recognition is a kind of biometric authentication which is widely used for security purpose in many areas like image processing, pattern recognition. However, recognizing the human face was very difficult as the poses in the input images vary, various conditions of light, brightness, expressions, ages. To overcome from it, a proposed method was introduced in this paper known as Faster Region-based Convolutional Neural Network (RCNN). The main advantage of using the proposed method is it will minimize the training process time as it consisting of two fully connected layers namely classifier and regression layer. Initially, the proposed method was implemented on ORL database consisting of 40 classes, then the images in the database undergoes image resizing and enhancing in the preprocessing stage. Where, Image resizing id done to reduce images size so that every image is same in size that will minimize the processing time and image enhancing was done to adjust the brightness of the image. In further, for extracting the features from preprocessed images, CNN is used, so that extracted features are given to the classification stage to detect the face of human or not. In detecting the faces, proposed Faster RCNN achieved high accuracy of 98.64% when compared with other existing methods like IFC, EFRA and VGG16. © 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

learning to intervene on concept bottlenecks 24

Learning to intervene on concept bottlenecks

引用

Proceedings of the 41st International Conference on machine learning

作者： David Steinmann Wolfgang Stammer Felix Friedrich Kristian Kersting Artificial Intelligence and Machine Learning Group TU Darmstadt Germany Artificial Intelligence and Machine Learning Group TU Darmstadt Germany and Hessian Center for Artificial Intelligence (hessian.AI) Darmstadt Germany Artificial Intelligence and Machine Learning Group TU Darmstadt Germany and Hessian Center for Artificial Intelligence (hessian.AI) Darmstadt Germany and Centre for Cognitive Science TU Darmstadt Germany and German Center for Artificial Intelligence (DFKI).

While deep learning models often lack interpretability, concept bottleneck models (CBMs) provide inherent explanations via their concept representations. Moreover, they allow users to perform interventional interactions on these concepts by updating the concept values and thus correcting the predictive output of the model. Up to this point, these interventions were typically applied to the model just once and then discarded. To rectify this, we present concept bottleneck memory models (CB2Ms), which keep a memory of past interventions. Specifically, CB2Ms leverage a two-fold memory to generalize interventions to appropriate novel situations, enabling the model to identify errors and reapply previous interventions. This way, a CB2M learns to automatically improve model performance from a few initially obtained interventions. If no prior human interventions are available, a CB2M can detect potential mistakes of the CBM bottleneck and request targeted interventions. Our experimental evaluations on challenging scenarios like handling distribution shifts and confounded data demonstrate that CB2Ms are able to successfully generalize interventions to unseen data and can indeed identify wrongly inferred concepts. Hence, CB2Ms are a valuable tool for users to provide interactive feedback on CBMs, by guiding a user's interaction and requiring fewer interventions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Model Depending on Optimized Support Vector machine

引用

computers, Materials & Continua 2023年第7期76卷 499-515页

作者： Amel Ali Alhussan Fatma M.Talaat El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Doaa Sami Khafaga Mona Alnaggar Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Machine Learning&Information Retrieval Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Robotics and Intelligent Machines Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt

In computer vision,emotion recognition using facial expression images is considered an important research *** learning advances in recent years have aided in attaining improved results in this *** to recent studies,multiple facial expressions may be included in facial photographs representing a particular type of *** is feasible and useful to convert face photos into collections of visual words and carry out global expression *** main contribution of this paper is to propose a facial expression recognitionmodel(FERM)depending on an optimized Support Vector machine(SVM).To test the performance of the proposed model(FERM),AffectNet is *** uses 1250 emotion-related keywords in six different languages to search three major search engines and get over 1,000,000 facial photos *** FERM is composed of three main phases:(i)the Data preparation phase,(ii)Applying grid search for optimization,and(iii)the categorization *** discriminant analysis(LDA)is used to categorize the data into eight labels(neutral,happy,sad,surprised,fear,disgust,angry,and contempt).Due to using LDA,the performance of categorization via SVM has been obviously *** search is used to find the optimal values for hyperparameters of SVM(C and gamma).The proposed optimized SVM algorithm has achieved an accuracy of 99%and a 98%F1 score.

关键词： Facial expression recognition machine learning linear dis-criminant analysis(LDA) support vector machine(SVM) grid search

来源：评论

学校读者我要写书评

暂无评论

A Review on the Applications of machine learning Algorithms for Mental Stress Detection 2

A Review on the Applications of Machine Learning Algorithms ...

引用

2nd DMIHER International Conference on artificial intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Motghare, Renuka Bhoyar, Shivam Verma, Prateek Tale, Abhay Barhate, Aditya Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Sawangi Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Sawangi Maharashtra Wardha442001 India

ISBN: (纸本)9798331528713

Stress, a widespread issue affecting both individual well-being and societal productivity, has attracted significant research interest. Defined as a state of mental or emotional strain, stress arises from various factors such as work, relationships, and health concerns, manifesting physically, emotionally, and behaviorally. This paper provides a review of machine learning (ML) techniques to detect mental stress using physiological signals like ECG, GSR, and EEG. Through a review of existing studies, the paper highlights the progress made in this area and the challenges that remain, particularly concerning data quality, algorithm accuracy, and the practical deployment of stress monitoring devices. The study underscores the potential for real-time monitoring and personalized interventions, especially in daily activities. Future research should focus on enhancing model robustness, integrating multiple data sources, and addressing real-world applicability. This paper emphasizes the importance of early stress identification and personalized treatment to improve mental health outcomes © 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

Implementing a Unique Identification System for Improved Traceability and Prevention of Counterfeit Drugs in the Supply Chain

Implementing a Unique Identification System for Improved Tra...

引用

2023 International Conference on Self Sustainable artificial intelligence Systems, ICSSAS 2023

作者： Kalpana, R. Priya, P. Indira Manju, M. Anitha, R. Venusamy, Kanagaraj Vels Univesity Department of Computer Science and Engineering chennai India Rajalakshmi Engineering College Department of Artificial Intelligence and Machine Learning chennai Thandalam India Rajalakshmi Engineering College Department of Mechatronics Engineering Chennai Thandalam India

ISBN: (纸本)9798350300857

Block chain technology provides a secure and impenetrable platform for locating and tracking counterfeit medications within the supply chain of the pharmaceutical industry. This research proposes a novel Block chain-Enabled Unique Identification System (BEUIS) designed to revolutionize traceability and combat counterfeit drugs. BEUIS leverages block chain technology to create an immutable and transparent ledger, ensuring the authenticity of pharmaceutical products at every stage of the supply chain. Through the integration of smart contracts, it automates verification processes, significantly enhancing efficiency and reliability. The decentralized nature of block chain minimizes the risk of data manipulation and establishes a trustworthy environment for all stakeholders. BEUIS also promotes interconnectivity, allowing seamless integration with existing systems, thus offering a scalable and sustainable approach to addressing the global counterfeit drug epidemic. This research presents a comprehensive framework, emphasizing the implementation of BEUIS as a pivotal solution to safeguard public health and restore trust in the pharmaceutical sector. Its transparency and immutability make it a promising solution for improving public health. By utilizing block chain technology, the system offers an extremely secure and unalterable platform for the system provides a highly secure and tamper-proof platform for detecting and tracking counterfeit drugs. Its transparency and immutability make it a promising solution for improving public health outcomes. © 2023 IEEE.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Integrating Data Mining and Predictive Modeling Techniques for Enhanced Retail Optimization

arXiv

引用

arXiv 2024年

作者： Sri Darshan, M. Nithinraj, N. Jaisachin, B. Department of Artificial Intelligence and Machine Learning SRM University Chennai India Department of Computer Science SRM University Chennai India

Predictive modeling and time-pattern analysis are increasingly critical in this swiftly shifting retail environment to improve operational efficiency and informed decision-making. This paper reports a comprehensive application of state-of-the-art machine learning to the retailing domain with a specific focus on association rule mining, sequential pattern mining, and time-series forecasting. Association rules: Relationship Mining This provides the key product relationships and customer buying patterns that form the basis of individually tailored marketing campaigns. Sequential pattern mining: Using the PrefixSpan algorithm, it identifies frequent sequences of purchasing products-extremely powerful insights into consumer behavior and also better management of the inventories. What is applied for sales trend forecasting models Prophet applies on historical transaction data over seasonality, holidays, and long-term growth. The forecast results allow predicting demand variations, thus helping in proper inventory alignment and avoiding overstocking or understocking of inventory. Our results are checked through the help of metrics like MAE (Mean Absolute Error) and RMSE (Root Mean Squared Error) to ensure our predictions are strong and accurate. We will combine the aspects of all of these techniques to prove how predictive modeling and temporal pattern analysis can help optimize control over inventory, enhance marketing effectiveness, and position retail businesses as they rise to ever greater heights. This entire methodology demonstrates the flexibility with which data-driven strategies can be leveraged to revitalize traditional retailing practices. Copyright © 2024, The Authors. All rights reserved.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Biomedical Interventions in Precision Medicine for Diabetics 3

Biomedical Interventions in Precision Medicine for Diabetics

引用

3rd International Conference on Smart Technologies, Communication and Robotics, STCR 2023

作者： Madhumitha, A. Dhananjayan, V. Bannari Amman Institute of Technology Dept. of Computer Science and Bussiness System Tamil Nadu Sathyamangalam India Bannari Amman Institute of Technology Dept. of Artificial Intelligence and Machine Learning Tamil Nadu Sathyamangalam India

ISBN: (纸本)9798350370867

Precision medicine is the need of the hour strategy that deals with precision from diagnosis to treatment. There is a growing need for continuous monitoring of blood glucose levels and an effective algorithm to determine the right insulin dosages to achieve precision medicine for diabetes. This work intends to review the impact and importance of biomedical interventions in precision medicine for diabetes. It addresses the barriers that persist in practicing precision medicine for diabetes by strengthening the techniques of precision diagnosis and prognosis, precision therapeutics, precision treatments, and precision monitoring using predictive algorithms. The review emphasizes the significance of biomedical interventions in advancing the future directions of precision medicine for diabetes, including the integration of clinical trials with large datasets and continuous evaluation and monitoring of patients through regular measurements of blood glucose levels. By focusing on these biomedical interventions, this review aims to provide insights into the role of precision medicine in diabetes and its potential for improving patient outcomes. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Face based eCrime Identification using First Information Report 3

An Analysis of Face based eCrime Identification using First ...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Pandiaraja, P. Vanarasan, S. Dharani, S. Dharshini, R. Harani, S. Selvarathi, C. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai600 062 India Sri Sairam College of Engineering Department of Artificial Intelligence and Machine Learning Banglore562 106 India M. Kumarasamy College of Engineering Department of Computer Science and Engineering Karur639 113 India

ISBN: (纸本)9798331509675

Face based e-crime identification initiative combines cutting-edge technologies to detect criminals in video footage, allowing for quick and effective online FIR (First Information Report) reporting. Furthermore, it uses blockchain technology to securely store and manage sensitive data, as well as to ensure the integrity of evidence and to facilitate robust facial recognition using the Inception V3 algorithm. The proliferation of electronic crimes (eCrimes) in today's digital age poses a huge challenge to law enforcement organizations worldwide. In the face of continuously shifting criminal strategies, traditional means of identifying and reporting offenders frequently fall short. The fundamental functionality of the technology is around identifying offenders using video footage. It makes use of the potent Inception V3 algorithm, a cutting-edge deep learning model noted for its efficient image recognition skills. This algorithm analyses video frames, detects and matches facial traits, and identifies suspects. This not only improves the accuracy of criminal identification but also speeds up the investigation. In addition to identifying criminals, the streamlines the FIR reporting process. Victims and witnesses can now conveniently file FIRs online, eliminating the need for physical visits to police stations. The integration of digital reporting platforms enhances the efficiency of law enforcement agencies, making the process more accessible to the public. Blockchain technology is used to provide data security and immutability. A blockchain-based database stores all data relevant to criminal identification and FIR reporting. The combination of improved facial recognition, online reporting, and secure blockchain data management promises to make identifying and reporting criminals more efficient and secure. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Computationally Efficient machine learning Methodology for Indian Nobel Laureate Classification

Computationally Efficient Machine Learning Methodology for I...

引用

IEEE Recent Advances in Intelligent Computational Systems (RAICS)

作者： Swastik Banerjee Helen. K. Joy Department of Computer Science Artificial Intelligence & Machine Learning CHRIST Deemed to be University Bengaluru INDIA Department of Computer Science CHRIST Deemed to be University Bengaluru INDIA

ISBN: (数字)9798350381689

ISBN: (纸本)9798350381696

A computationally efficient methodology for Indian Nobel Laureate classification is proposed in this study, emphasizing the optimization of image categorization through supervised learning techniques. Leveraging advancements in Convolutional Neural Networks (CNNs), the research aims to enhance the efficiency and precision of image classification tasks. The study utilizes Logistic Regression for dataset analysis, initially employing browser extensions for mass downloading categorized image data. Haar cascade classifiers are then used for data wrangling, focusing on facial, nose, and mouth recognition. Following this, feature engineering through wavelet transformation reduces image dimensionality, preparing the dataset for the chosen ML model, Logistic Regression. The primary focus is to simplify technology for improved image categorization. Support Vector machines (SVM), Random Forest, and Logistic Regression are examined, with Logistic Regression emerging as the most effective model, achieving an accuracy rate of 87.5%. A thorough evaluation using Confusion Matrices reveals Logistic Regression's superior performance in classifying images of Indian Nobel laureates. A strategic up-sampling approach is implemented to address dataset inconsistencies, ensuring balanced representation across classes. The Haar wavelet transform is then applied for feature extraction, optimizing the dataset for ML models. The dataset is split into training and testing sets (80–20), and the three models are trained and evaluated for accuracy. Logistic Regression proves to be the best performer, offering insights into prominent leaders' identification. The research offers a detailed pipeline for data preprocessing, feature engineering, and model assessment, culminating in a robust image categorization system. Logistic Regression emerges as a reliable method for biographical picture identification, demonstrating superior accuracy over SVM and Random Forest. This research underscores the import

关键词： Support vector machines Wavelet transforms Training Logistic regression Accuracy Biological system modeling Pipelines Image categorization Random forests Testing

来源：评论

学校读者我要写书评

暂无评论

Survey of Various machine learning Techniques for Analyzing IoMT-Based Remote Patient Monitoring System 1

引用

International Conference on Advances in Data science and Computing Technologies, ASDC 2022

作者： Johar, Sayyed Manjula, G.R. Assistant Professor Department of Artificial Intelligence and Machine Learning Jawaharlal Nehru New College of Engineering Karnataka Shivamogga India Professor Department of Computer Science and Engineering Jawaharlal Nehru New College of Engineering Karnataka Shivamogga India

ISBN: (数字)9789819936564

ISBN: (纸本)9789819936557

Internet of Medical Things (IoMT) consists of several medical devices used to capture patient health information. The recorded details are transmitted to the healthcare centers via computer networks. This transmitted information is stored in the cloud environment for making further clinical analysis. The continuous recordings of patient information help predict the patient’s chronic disease and help to initiate the respective solutions. This recorded information is processed by applying various machine learning and deep learning techniques to predict patient health conditions. Therefore, here the general discussion of IoMT and the impact of patient health monitoring systems are discussed. Along with this, various methodology’s respective pitfalls and advantages are analyzed to improve the healthcare system’s remote patient health monitoring process. The major goals of this study were to comprehend the role played by IoMT in remote patient monitoring and the effects of intelligent approaches on data analysis. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep learning

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：