检索结果-内蒙古大学图书馆

Advanced Technology (KhPIWeek), IEEE KhPI Week on

作者： Nataliia Lutska Nataliia Zaiets Lidiia Vlasenko Andrii Zhyltsov dept. of Automation and Computer Technologies of Control Systems National University of Food Technologies Kyiv Ukraine dept. of Automation and Robotic Systems National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine dept. of Software Engineering and Cyber Security State University of Trade and Economics Kyiv Ukraine dept. of electromagnetic systems The Institute of Electrodynamics of the National Academy of Sciences of Ukraine Kyiv Ukraine

ISBN: (数字)9798350384499

ISBN: (纸本)9798350384505

The work demonstrates the process of developing a machine learning model for a system for monitoring and controlling the quality of predough at a bakery. This system will provide continuous analysis of the predough parameters, such as temperature, humidity, lifting force and titranic acidity, which will ensure timely detection of deviations in the quality of the predough and avoid production problems. In addition, it will help automate the quality control process and ensure the stability of production processes. Analysis and forecasting of dough parameters will improve the quality of produced bread or other bakery products. Management based also on the predicted values of technological indicators of the predough will allow the enterprise to avoid unnecessary costs of materials and energy and increase economic efficiency. As part of the study, seven machine learning models were created and reviewed, including three linear and four varieties of binary decision trees. An analysis of the best model - a regression decision tree - was carried out, confirming its effectiveness and the validity of the resulting hierarchical structure, in particular, the prediction of important indicators of predough with a high degree of reliability, which indicates its importance in practical applications in production. The created model can be used to monitor and control product quality in real time, allowing operators to quickly identify and correct any deviations in process performance. Also, by analyzing changes in the variables of the predough production process, it is possible to identify precursors of possible production accidents or deviations in product quality, which will allow timely measures to be taken to avoid them.

关键词： Force Process control Production Machine learning Quality control Humidity Predictive models Stability analysis Monitoring Thermal stability

来源：评论

学校读者我要写书评

暂无评论

Towards Adjoint Sensing and Acting Schemes and Interleaving Task Planning for Robust Robot Plan

Towards Adjoint Sensing and Acting Schemes and Interleaving ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Shuo Yang Xinjun Mao Shuo Wang Huaiyu Xiao Yuanzhou Xue Key Laboratory of Software Engineering for Complex Systems College of Computer National University of Defense Technology

Robots operating in open environments expect to have robust plans to achieve tasks successfully under environment uncertainties. However, both partial observability and dynamics of environment states have significantly decreased the robustness of task achievement, making robot task planning much more challenging. The partially observable states require the robot to obtain observations for optimally acting of the task goal. Also, state dynamics expects the robot to continuously observe surroundings for acting safely. Both challenges practically demand the purposeful and tight interactions between robot state-changing actuating actions and sensor-based observation actions. This paper proposes a novel model of Adjoint Sensing and Acting (ASA) that explicitly defines two parallel and sequential interaction schemes between actuating and observation actions, as well as an extended Behavior Tree for a concrete implementation of above schemes. We further propose an interleaving task planning approach for planning ASA-style plans, which integrates a deliberative POMDP planner for pursuing task goals, and a reactive Behavior Tree executive for fast responding to unexpected events. We experimentally demonstrate that ASA interaction schemes are practical and applicable to model and plan the open environment robot tasks. The plans from the interleaving task planning approach are both reactive in run-time response and efficient in task achievement.

关键词： Uncertainty Automation Conferences Robot sensing systems Robustness Planning Sensors

来源：评论

学校读者我要写书评

暂无评论

Arabic Sentiment Analysis of Food Delivery Services Reviews

Arabic Sentiment Analysis of Food Delivery Services Reviews

引用

International Symposium on Networks, computers and Communications (ISNCC)

作者： Dheya Mustafa Safaa M. Khabour Ahmed S. Shatnawi Eyad Taqieddin Dept. of Computer Engineering Faculty of Engineering The Hashemite University Zarqa Jordan Dept. of Information Systems Faculty of Information Technology and Computer Sciences Yarmouk University Irbid Jordan Dept. of Software Engineering Jordan University of Science & Technology Irbid Jordan Dept. of Cyber Security School of Computing and Informatics Al-Hussein Technical University Amman Jordan

Customer reviews on online platforms have grown to become an important source of insight into a company's performance. Food delivery services (FDS) companies aim to effectively use customers' feedback to identify areas for improvement of customer satisfaction. Although Arabic is becoming one of the most widely used languages on the Internet, only a few studies have focused on Arabic sentiment analysis to date. The present study conducts an extensive emotion mining and sentiment analysis on FDS-related reviews in Arabic, exploiting natural language processing, and machine learning techniques to extract information that reflects customers' subjective viewpoints, recognize their feelings, and determine polarity in the FDS domain. This work begins with collecting the FDS dataset (Talabat), and then extracting and creating a dialects lexicon for Arabic dialects, followed by walking the reader through detailed steps of cleaning and pre-processing a manually annotated dataset. Finally, we examined classification algorithms including Decision Tree (DT), and Support Vector Machine (SVM). We achieved a maximum accuracy of about 82% using the SVM classifier.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal Fusion for Enhanced Parkinson's Disease Screening: Integrating Brain MRI, Hand Drawing, Facial Expressions, and Voice Analysis

Multimodal Fusion for Enhanced Parkinson's Disease Screening...

引用

Advancements in Computing (ICAC), International Conference on

作者： Naveen Warnakulasuriya Shalinika De Silva Janani Madushika Sadali Gamage Sanath Jayawardena Anuradha Karunasena Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Science and Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Systems Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

Parkinson's disease (PD) profoundly impacts millions in Sri Lanka, emphasizing the importance of early detection for better patient outcomes. We introduce “NeuraTrace PD,” an innovative application for early PD screening, combining brain MRI, hand-drawn image analysis, facial expression assessment, and voice analysis. For brain MRI analysis, we employed a Graph Convolutional Network (GCN), achieving an impressive accuracy of 91% and identifying distinct graph connectivity patterns using graph theory. We also use a deep Convolutional Neural Network (CNN) to reach 90% accuracy in analyzing hand-drawn images, while optimizing image resolution for efficiency and information retention. Facial expression analysis is a vital component, leveraging CNN and Constrained Local Models (CLM) to accurately extract Facial Action Units (FAUs), which contribute to a remarkable 95% accuracy using the XGBoost machine learning model. We introduce a Machine Learning (ML) algorithm and advanced signal processing to enhance voice feature analysis, offering a thorough understanding and classification of PD patients. It reaches 99% accuracy. In summary, our approach holds significant promise for advancing early PD diagnosis, ultimately improving the quality of life for those affected by this challenging condition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Algorithms for Intrusion Detection Performance Evaluation and Comparative Analysis

Machine Learning Algorithms for Intrusion Detection Performa...

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： B. Md. Irfan V. Poornima S Mohana Kumar Upendra Singh Aswal N. Krishnamoorthy Ramya Maranan Department of Information Technology Nalsar University of Law Hyderabad Telengana India Department of Computer Science VISTASPallavaram Chennai Department of Computer Science and Engineering Ramaiah Institute of Technology Bengaluru Karnataka India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Software Systems and Engineering Vellore Institute of Technology Vellore Campus Vellore Tamilnadu Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

The security of computer networks is increasingly difficult to maintain due to the rising complexity and frequency of cyber-attacks. Important tools for finding and neutralizing these dangers are intrusion detection systems. This study sets out to do a thorough examination and comparison of the efficacy of several machine learning algorithms for use in intrusion detection. This research study evaluates the efficacy of several machine learning algorithms in correctly categorizing instances of network traffic as normal or invasive via extensive experiments performed on representative datasets. Algorithms like random forests, decision trees, SVMs, DL models and NNs are all being tested and rated. Effectiveness is measured and compared using a variety of performance indicators including accuracy, recall, precision, false positive rate, and F1-score. The results of this study emphasize the potential of deep learning models and Random Forests for use in intrusion detection and add to the body of knowledge around machine learning methods for this task. Professionals in the field of network security might use the results to their advantage when building intrusion detection systems. Future research areas are also mentioned, which will hopefully lead to even greater improvements in the field and safer, more reliable intrusion detection systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Editorial: Advanced deep learning approaches for medical neuroimaging data with limitation

引用

Frontiers in Computational Neuroscience 2023年 17卷 1272448页

作者： Tang, Zhiri Li, Ming Hu, Ruihan Dev, Kapal Department of Computer Science City University of Hong Kong Kowloon Hong Kong Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Kowloon Hong Kong School of Software Harbin Institute of Technology Harbin China Department of Computer Science Munster Technological University Cork Ireland

This research topic collects the latest works focusing on approaches and analysis for medical neuroimaging data with limitations. With the increasing development of deep learning and artificial intelligence, it also attracts attention from researchers in medical and clinical fields [1]. Adopting deep learning technology in processing medical images and signals and benefiting from the powerful feature extraction ability of convolutional neural networks, deep learning-based artificial medicine has achieved great success in the past few years [2]. However, owing to the difference between natural and medical images, in other words, some specific characteristics of medical images, adopting deep learning to process medical images directly may face numerous problems. Particularly, medical imaging, including neuroimaging data, may acquire data with few annotations, low signal-to-noise ratio, or small experimental samples, resulting in serious performance degradation during data processing [3]. Hence, how to solve these issues and improve the data analysis performance is still a challenge. In recent years, some works have emerged towards these issues in medical neuroimaging data, such as semi-supervised learning [4], weakly supervised learning [5], unsupervised learning [6], transfer learning [7], and so on. In this research topic, there are also some feasible ways for medical neuroimaging data with limitations. In the first article of this topic [8], a Soft-DTW-based single-subject short-distance event-related potential averaging method is introduced for the low signal-to-noise ratio and feature extraction issues of N400 data. Specifically, N400 data is a time-domain EEG feature, which is thought to reflect the information processing ways of human brains. Leveraging the benefits of the differentiable and efficient Soft-DTW loss function, this work also involves performing partial Soft-DTW averaging within a single-subject range, effectively exploiting the advantages of the

关键词： neuroimaging analysis of insufficient data brain diseases data processing data augmentation neuroimaging application

来源：评论

学校读者我要写书评

暂无评论

Prediction of Polycystic Ovary Syndrome Using Genetic Algorithm-driven Feature Selection

Prediction of Polycystic Ovary Syndrome Using Genetic Algori...

引用

IT and Industrial Technologies (ICIT), International Conference on

作者： Fatima Faridoon Raja Hashim Ali Zain Ul Abideen Nazia Shahzadi Ali Zeeshan Ijaz Usama Arshad Nisar Ali Muhammad Imad Said Nabi Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany BCMaterials Basque Center for Materials Applications & Nanostructure Spain Faculty of Electronic Systems Engineering University of Regina Regina Canada

PolyCystic Ovary Syndrome (PCOS) is a hormonal disorder frequently found in women of reproductive age having a significant impact on the cause of infertility. It is an endocrine condition characterized by abnormalities in female hormone levels and aberrant synthesis of male hormones. This syndrome causes ovarian malfunction, increasing the risk of miscarriage and infertility. PCOS has a wide range of symptoms, making a diagnosis difficult. In this study, we proposed a feature selection method based on genetic algorithm with logistic regression to increase the accuracy of early diagnosis. A dataset containing the clinical and biochemical characteristics of 109 patients, including 36 with PCOS, is used. The genetic algorithm is used to extract the most important features from the dataset. Then, a logistic regression model is used for classification. The proposed model outperformed the baseline model that used all features, which had an accuracy of 86.2%, and produced a markedly improved accuracy of 95.4%. These results show that the proposed model effectively locates key characteristics for PCOS diagnosis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploiting Partial Observability and Optimized Simple State Representations in Deep Q-Learning

Exploiting Partial Observability and Optimized Simple State ...

引用

Frontiers of Information Technology (FIT)

作者： Danyaal Mahmood Usama Arshad Raja Hashim Ali Zain Ul Abideen Muhammad Huzaifa Shah Talha Ali Khan Ali Zeeshan Ijaz Nisar Ali Abu Bakar Siddique Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany BCMaterials Basque Center for Materials Applications & Nanostructure Spain Faculty of Electronic Systems Engineering University of Regina Regina Canada

The advent of deep Q-learning has opened up new possibilities in training autonomous agents to perform intelligently in intricate settings. This research work examines the potential of deep Q-learning in the paradigmatic Snake game, which requires an agent to navigate a grid, ingest food items, and avoid collisions. We incorporated a partially observable game state, introducing a novel level of difficulty to the task. Our proposed approach utilizes a straightforward feed-forward neural network to estimate Q-values of potential actions, given the current state. The agent progressively learns to balance between exploration and exploitation, allowing it to navigate optimally in the game scenario. Most existing studies in deep Q-learning for the Snake game overlook the complexities posed by partial observability, focusing mainly on fully observable state representations. Furthermore, the majority of the investigations delve into the efficacy of complex neural network architectures, leaving a gap in the understanding of the performance of more simplistic feed-forward networks. Our study fills this gap by offering an in-depth exploration and analysis of deep Q-learning strategies, especially when applied to partially observable game states and simple neural networks. Simulations and results reveal that adopting simpler state representations can significantly boost the agent’s performance in the Snake game. A more detailed and intricate reward function is also observed to enhance the agent’s decision-making skills and overall proficiency in the game. These observations underscore the significance of optimizing state representations and reward functions for maximizing the performance of deep Q-learning agents in the Snake game.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Industrial Energy systems: A Multi-Objective Approach to Decarbonization and Cost Efficiency

Optimizing Industrial Energy Systems: A Multi-Objective Appr...

引用

Smart Power & Internet Energy systems (SPIES), International Conference on

作者： Simon Kammerer Constantin Chaumet Christian Rehtanz Jakob Rehof Institute of Energy Systems Energy Efficiency and Energy Economics TU Dortmund University Dortmund Germany Department of Computer Science Software Engineering by Algorithms and Logic TU Dortmund University Dortmund Germany Lamarr Institute for Machine Learning and Artificial Intelligence TU Dortmund University Dortmund Germany

ISBN: (数字)9798350368864

ISBN: (纸本)9798350368871

The transition to a renewable energy (RE) based future necessitates transformative changes in the industrial sector's energy infrastructure. As industries strive to maintain economic viability while achieving decarbonization goals, there is a pressing need for innovative strategies that integrate renewable energy sources, enhance energy efficiency, and optimize energy procurement. This paper presents a comprehensive approach that leverages a combination of simulation and optimization methods to address the challenges of designing and operating complex future industrial energy systems. A nested optimization approach is proposed, which combines Mixed-Integer Linear Programming (MILP) for operational optimization with black-box optimization techniques. The approach enables exploration of solutions for optimal infrastructure investment as well as operational strategies, allowing companies to benchmark a wide range of infrastructure and contractual options. This provides these companies with the means to determine long-term, cost-effective pathways that minimize CO2 emissions, avoid malinvestments, and ensure the sustainable operation of energy systems. A case study involving a German waste processing company illustrates the practical application of our approach, highlighting how strategic decisions in asset dimensioning, energy flexibility utilization, and renewable integration can significantly impact both costs and emissions.

关键词： Procurement Renewable energy sources Costs Closed box Optimization methods Companies Pressing Low carbon economy Mixed integer linear programming Investment

来源：评论

学校读者我要写书评

暂无评论

Trustworthy Hierarchical Federated Learning for Digital Healthcare

Trustworthy Hierarchical Federated Learning for Digital Heal...

引用

Artificial Intelligence of Things (AIoT), IEEE Annual Congress on

作者： Sarhad Arisdakessian Omar Abdel Wahab Osama Wehbi Azzam Mourad Hadi Otrok Computer and Software Engineering Polytechnique Montréal Montréal Canada Department of CS 6KU 6G Research Center Khalifa University UAE Department of CSM Artificial Intelligence & Cyber Systems Research Center Lebanese American University Beirut Lebanon

ISBN: (数字)9798350392296

ISBN: (纸本)9798350392302

Healthcare institutions and medical device manufacturers are under regulatory obligations to safeguard and protect the privacy of data they acquire from patients. This limits their ability to share the data with other institutions to collectively train machine learning models. Due to its ability in preserving the privacy of data used in training models, Federated Learning (FL) has been proposed as a tool in healthcare that mitigates some of the privacy concerns. However, the presence of less-engaging clients; or free-riders; in such environments is a major concern. Such clients reap the benefits of the global model (1) without actively participating in the learning rounds, and (2) by not contributing their system and data resources. In this work, we propose a mechanism that minimizes the presence of free-riders in such environments. Experimental results shows the effectiveness of our approach.

关键词： Training Data privacy Medical devices Federated learning Hospitals Games Data models

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：