检索结果-内蒙古大学图书馆

Intelligent Technologies (CONIT), International Conference on

作者： Shobha Gupta Shubham Vishwakarma Kriti Srivastava Dept. of Electronics Dwarkadas J. Sanghvi College of Engineering Mumbai India Dept. of Computer and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798350349900

ISBN: (纸本)9798350349917

This study offers a novel approach that uses generative AI models such as stable diffusion models to produce a large number of jewellery designs, improve the design process, and increase consumer involvement. The jewellery business, which relies on designers’ expertise and creativity, is on the verge of a dramatic shift with the integration of AI-driven technologies. Our proposed approach serves as a creative middleman, combining consumer preferences and artistic ideas to provide a wide range of jewellery pictures. By allowing customers to choose from these AI-generated designs, the technology not only meets their expectations but also dramatically streamlines the designer’s productivity. This synergy between AI-generated solutions and human ingenuity not only reduces the time and effort required in the initial design phase, but also guarantees that the final product resonates more strongly with customer preferences. We go into the technical details of stable diffusion models, highlighting their ability to generate and customise high-quality images. Furthermore, we discuss how this technology affects efficiency, satisfaction, and creative expression. Our findings indicate that this method not only promotes a more collaborative and consumer-centric design process, but it also creates new opportunities for innovation in the jewellery sector. This study attempts to show how the combination of artificial intelligence and human creativity may reshape the paradigms of jewellery creation, making it more inclusive, efficient, and responsive to consumer demands.

关键词： Productivity Industries Technological innovation Generative AI Design methodology Merging Collaboration

来源：评论

学校读者我要写书评

暂无评论

Enhancing Hospital Mortality Prediction for Heart Failure Patients through Hyperparameter Optimization and Interpretability Analysis with LIME and SHAP

Enhancing Hospital Mortality Prediction for Heart Failure Pa...

引用

Women in Computing (InCoWoCo), International Conference for

作者： Meena S Monisha Murthy Ashwini Kodipalli Dept. of Computer Science and Engineering Global Academy of Technology Bengaluru Karnataka India Dept. of Artificial Intelligence & Data Science Global Academy of Technology Bengaluru Karnataka India

ISBN: (数字)9798331518943

ISBN: (纸本)9798331518950

Heart failure is one of the primary causes for deaths caused in the hospital. Predicting mortality rate of such patients is extremely important for the efficient use of health care resources. This research aims to estimate the hospital mortality rate of Heart Failure(HF) patients using machine learning(ML). Using computational technique, the obtained model has given the most efficient accuracy. This paper uses the classification model to detect two outcomes (0 and 1, i.e., if the patient will survive or not). The classification models used for the hospital mortality prediction are, single classifiers such as Logistic regression, SVM, KNN, Decision tree (Ginni and Entropy);with Logistic regression obtaining highest accuracy of 88.9%, Bagging and boosting models such as Randomforest, Adaptive boosting, Gradient boosting, XG boosting, Categorical boosting; with CatBoost obtaining highest accuracy of 90.2%. To achieve the best accuracy, ensemble models were used out of which ensemble classifier ensemble gave 91.1% accuracy. To understand the features playing important role in decision making, explainable AI(XAI) is used. LIME and SHAP are considered. LIME generated local explanations, it explained the decision of a complex model for a specific instance or observation. In contrast, SHAP provided global explanations, it explained the overall behavior of the model across all instances.

关键词： Logistic regression Accuracy Machine learning algorithms Hospitals Computational modeling Mortality Predictive models Boosting Prediction algorithms data models

来源：评论

学校读者我要写书评

暂无评论

The Evolution of Spatial data Infrastructures with Policy, Integration, and Metadata Management for Effective Geospatial data Handling

The Evolution of Spatial Data Infrastructures with Policy, I...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Mohammad, Duaa Jasim Anjimoon, Shaik Anandhi, R.J. Singh, Navdeep Parmar, Ashish Bhasha, A. National University of Science and Technology College of Health and Medical Technology Dhi Qar64001 Iraq Institute of Aeronautical Engineering Hyderabad Dundigal India New Horizon College of Engineering Department of Information Science Engineering Bangalore India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India St. Martin's Engineering College Dept. of It Telangana Secunderabad India

ISBN: (纸本)9798350373783

Because of the critical role that spatial data infrastructures (SDIs) play in the efficient management of geospatial data, it is necessary for them to undergo continuous development in order to meet the difficulties that are always developing. Temporal Policy-Driven Integration with Dynamic Metadata augmentation (TPDIME) is a revolutionary approach that is presented in this paper. TPDIME blends temporal policy modeling, adaptive data integration, and semantic metadata augmentation within its framework. The Evolutionary Framework (TEF), Spatial Harmony Protocol (SHP), and Geo Integrator Pro (GIP) are among the six classic approaches that represent the benchmarks against which the suggested method is evaluated. In addition to adaptability, interoperability, usability, governance impact, resilience, and semantic interoperability, the assessment criteria include more. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Forecasting Air Pollution of Urban Chennai Localities using Artificial Intelligence

Forecasting Air Pollution of Urban Chennai Localities using ...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： Rayaan Faiz Tisha Agarwal D Rajeswari Dept. of Data Science and Business Systems School of Computing College of engineering and Technology SRM Institute of Science and Technology Chennai India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

India’s air quality deteriorated significantly in 2023, ranking third worst globally, highlighting the urgency for effective monitoring and mitigation measures. To comprehend past trends and predict future patterns, historical air pollution data from seven urban areas in Chennai was analyzed using the XGBoost Algorithm. This study aims to gain insights into Chennai’s air quality, identify abnormalities, and issue timely warnings to the public and governing authorities. XGBoost was employed to forecast AQI, NO2, PM2.5, NOx, PM10, CO, SO2, NH3, and Ozone levels, outperforming traditional LSTM, Prophet, and ARIMA models. Evaluation using RMSE and MAE scores revealed XGBoost’s efficacy, with scores of 20.65 and 14.35, respectively. The research highlights regions like Alandur, Arumbakkam, and Manali with notable concentrations of contaminants, emphasizing the need for immediate action. These findings highlight the significance of utilizing advanced algorithms for accurate air quality forecasting and proactive pollution management.

关键词： Gases Atmospheric modeling Urban areas Lead Predictive models Air pollution Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Online 3D Bin Packing Using a Combination of Tree Structures and Deep Reinforcement Learning

Online 3D Bin Packing Using a Combination of Tree Structures...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Kenji Fukuda Masaki Yamakita Hiroyuki Oyama Dept. of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan Data Science Laboratories NEC Corporation Kanagawa Japan

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

The online 3D bin packing problem (online 3D-BPP) is crucial for optimizing packing efficiency in various industrial applications. In this work, we introduce two external areas: an item buffer for the selection of packing items, and a temporary backup space to allow the rearrangement of items already packed in the bin. We propose a novel method that combines a deep reinforcement learning-based placement position planner with a movement sequence planner structured as a tree with the use of these external areas. This approach enables efficient planning of item placement and movement sequences without expanding the learning space, regardless of the size of external areas. Through numerical experiments, our method demonstrates a consistent improvement in spatial filling rates and robustness against constraints like physical stability. Notably, by utilizing these external areas, we elevated the performance of existing DRL methods by approximately 15 % in the scenario involving complex constraints such as physical stability. These results suggest that our approach is highly effective for complex, real-time packing scenarios in logistics and warehousing.

关键词： Three-dimensional displays Warehousing Filling Robustness Real-time systems Planning Thermal stability Numerical stability Robots Logistics

来源：评论

学校读者我要写书评

暂无评论

SELFORMER: MOLECULAR REPRESENTATION LEARNING VIA SELFIES LANGUAGE MODELS

arXiv

引用

arXiv 2023年

作者： Yüksel, Atakan Ulusoy, Erva Ünlü, Atabey Dogan, Tunca Biological Data Science Lab Dept. of Computer Engineering Hacettepe University Turkey

Automated computational analysis of the vast chemical space is critical for numerous fields of research such as drug discovery and material science. Representation learning techniques have recently been employed with the primary objective of generating compact and informative numerical expressions of complex data, for efficient usage in subsequent prediction tasks. One approach to efficiently learn molecular representations is processing string-based notations of chemicals via natural language processing (NLP) algorithms. Majority of the methods proposed so far utilize SMILES notations for this purpose, which is the most extensively used string-based encoding for molecules. However, SMILES is associated with numerous problems related to validity and robustness, which may prevent the model from effectively uncovering the knowledge hidden in the data. In this study, we propose SELFormer, a transformer architecture-based chemical language model that utilizes a 100% valid, compact and expressive notation, SELFIES, as input, in order to learn flexible and high-quality molecular representations. SELFormer is pre-trained on two million drug-like compounds and fine-tuned for diverse molecular property prediction tasks. Our performance evaluation has revealed that, SELFormer outperforms all competing methods, including graph learning-based approaches and SMILES-based chemical language models, on predicting aqueous solubility of molecules and adverse drug reactions, while producing comparable results for the remaining tasks. We also visualized molecular representations learned by SELFormer via dimensionality reduction, which indicated that even the pretrained model can discriminate molecules with differing structural properties. We shared SELFormer as a programmatic tool, together with its datasets and pre-trained models. Overall, our research demonstrates the benefit of using the SELFIES notations in the context of chemical language modeling and opens up new possibilities fo

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Large-Area Ag/Cu Pastes Sintering on Cu Base Plates for Power Module Packaging

Large-Area Ag/Cu Pastes Sintering on Cu Base Plates for Powe...

引用

22nd International Conference on Electronics Packaging, ICEP 2023

作者： Tsai, Chin-Hao Steiner, Felix Ishikawa, Dai Kao, C. Robert Blank, Thomas Institute for Data Processing and Engineering Karlsruhe Institute of Technology Germany National Taiwan University Department of Materials Science and Engineering Taiwan Resonac Corporation Ltd. Inorganic Materials Research Dept. Japan

ISBN: (纸本)9784991191152

In this research, Ag, Cu, mixed Ag-In, and mixed Ag-SAC sinter pastes are used for large-area bonding in second-level power module packaging. Due to the large sintering area, different patterns with/without drying channels are tested in the pressure/pressureless sinter process. Besides, various bonding conditions, such as temperature and pressure, are investigated. To analyze large-area sintering effects, scanning acoustic microscopy is used to observe the interface of joints. Finally, the reliability of the large area sintered joints is assessed by thermal shock and bending tests. To conclude, this study explores the feasibility of multiple sintering pastes for large-area sintering. The results reveal that these pastes exhibit reliable properties under proper bonding conditions. © 2023 Japan Institute of Electronics Packaging.

关键词： Sintering

来源：评论

学校读者我要写书评

暂无评论

Redefining the Landscape of Wire Arc Additive Manufacturing: Pioneering Innovations for Residual Stress Mitigation and Process Efficiency

Redefining the Landscape of Wire Arc Additive Manufacturing:...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Abdullah, Falah Hassan Aswini, Kilaru Manjunatha Thethi, H. Pal Parmar, Ashish Bhavani, B. Ganga National University of Science and Technology College of Science Department of Forensic Sciences Dhi Qar64001 Iraq Institute of Aeronautical Engineering Hyderabad Dundigal India New Horizon College of Engineering Department of Mechanical Engineering Bangalore India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India St. Martin's Engineering College Dept. of It Telangana Secunderabad India

ISBN: (纸本)9798350373783

This study introduces a comprehensive framework for Wire Arc Additive Manufacturing (WAAM) optimization, incorporating five key algorithms: Adaptive Layer Thickness Control, In-Situ Stress Monitoring, Dual-Wire Deposition, Thermal Management Strategies, and Machine Learning for Process Control. The Adaptive Layer Thickness Control Algorithm dynamically adjusts layer thickness based on geometric features and real-time feedback, contributing to stress mitigation. The In-Situ Stress Monitoring Algorithm ensures real-time stress distribution optimization. The Dual-Wire Deposition Algorithm introduces simultaneous deposition of two materials, optimizing multi-material properties. Thermal Management Strategies Algorithm focuses on controlling temperature gradient and adaptive cooling strategies. Machine Learning for Process Control Algorithm integrates input from preceding algorithms to predict optimal parameters, ensuring adaptive layer control and overall process optimization. Evaluation against existing methods demonstrates superior outcomes in residual stress reduction, geometric accuracy improvement, material integrity enhancement, process stability, build rate improvement, and energy efficiency. Visualizations and comparative tables confirm the proposed method's holistic excellence in WAAM. © 2024 IEEE.

关键词： Process control

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Algorithm for the Travelling Sales Man problem

An Evolutionary Algorithm for the Travelling Sales Man probl...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： Shaik Mohammad Waseem Jeshwanth N L Lingesh A Matta Jayanth Bhargavi C H Batini Dhanwanth Dept. of Computer Science and Engineering Panimalar Institute of Technology (Anna University) Chennai India Dept. of Artificial Intelligence and Data Science Panimalar Institute of Technology (Anna University) Chennai India Dept. of Computer Science and Engineering Sai Spurthi Institute of Technology India Dept. of AI Engineering Jönköping University Jönköping Sweden

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

This study explores the use of Genetic Algorithms (GA) to solve the NP-hard combinatorial optimization problem known as the Travelling Salesman Problem (TSP). The suggested GA, called GA-P, performs better than conventional techniques because it uses a new randomized crossover threshold. According to experimental assessments, GA-P outperforms a normal Genetic Algorithm with fixed crossover (GA-N, 628.6) and approaches the best Branch and Bound solutions (B&B, 560.6) with an average cost of 617.4 for 16-node graphs. With average execution times of 0.1347 seconds for 16 nodes, GA-P also demonstrates constant computational efficiency, outperforming B&B's exponentially growing temporal complexity (169.37 seconds for 16 nodes). In order to balance solution quality and computational cost, hyperparameter tweaking revealed the ideal values of population percentage (pp = 1.1), crossover proportion (cp = 0.8), mutation threshold (mt = 0.3), and exploration probability (ep = 0.2). The results show that GA-P is a scalable and efficient substitute for TSP, with room for improvement via parallelization and exploratory techniques.

关键词： Renewable energy sources Costs Evolutionary computation Computational efficiency Complexity theory Optimization Tuning Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Decentralized Network for Cloud Storage 2

Decentralized Network for Cloud Storage

引用

2nd Edition of IEEE Delhi Section Owned Conference, DELCON 2023

作者： Chirag, N. Kshitij, K. Gupta, Gaurav Sir M Visvesvaraya Institute of Technology Dept. of Information Science Engineering Bangalore India Shoolini University Yogananda School of Artificial Intelligence Computer and Data Sciences H.P Solan India

ISBN: (纸本)9798350322064

The amount of data loss on corporate servers in cloud environments has increased significantly. In the cloud, there are many security compromises and account hijackings, resulting in severe vulnerabilities for the service. Cloud computing is one of the most popular on-demand services. Over the past decade, cloud computing has been incorporated into various industries, including health care and the military. Security has, however, been a major concern with cloud computing. There have been many approaches and security implications implemented. However, when it comes to the security and privacy of data, there are loopholes. By decentralizing the cloud, which is currently a centralized entity, the authors attempt to improve cloud security. It is possible to solve these problems by deploying a decentralized cloud. Client software encrypts, fragments data, and then a client engine distributes the data among a number of hosting nodes (servers) spread throughout the world. As a result, the user has complete ownership of his data. In their study, the authors found that decentralizing cloud solved most of the problems of centralized cloud, since it increases the security of data by fragmenting and encrypting fragments. © 2023 IEEE.

关键词： Cloud security

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：