检索结果-内蒙古大学图书馆

5th EAI International Conference on Cognitive Computing and Cyber Physical systems, IC4S 2024

作者： N, Srinivasa Gupta Valarmathi, B. Kavitha, A. Gopini, Sai Bhuvan Seela, Hari Kumar Department of Manufacturing Engineering School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Department of Mathematics School of Advanced of Sciences Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9783031770777

Maternal health is among the greatest challenges in the world, especially in rural areas as there lack medical practitioners, they do not have easily accessible publics clinics and transport is difficult. Therefore, high rates of maternal as well as infant morbidity and mortalities are recorded. This research utilizes Artificial Intelligence (AI) with machine learning algorithms to forecast and address maternal health hazards right at their onset stage. The current research utilizes the concept of AI along with many Machine Learning (ML) methods like the Ensemble Learning Model (ELM), Random Forest (RF), K-Nearest Neighbour (KNN), Decision-Tree (DT), XG-Boost (XGB), Cat Boost (CB), and Gradient Boosting (GB), along with Synthetic Minority Over-sampling Technique (SMOTE) algorithm used for dealing with the problem class imbalance within the data set. SMOTE algorithm is utilized for the dataset balancing process. The handling system involves refining data preprocessing with the help of feature engineering and robust data cleaning which makes sure that anomalies do not erode the reliability of the predictive model. The existing methods [1] used RF (90%), DT (87%), XGB (85%), CB (86%), and GB (81%) algorithms and were compared with the accuracies of the proposed models like Logistic Regression (LR), Ensemble Learning Bagging (ELB), Ensemble Learning Stacking (ELS), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The existing methods used only imbalance dataset. The accuracies of the proposed models with using SMOTE algorithm (balanced dataset) are LR (61.33%), KNN (81%), ELB (92.33%), ELS (90.66%) CNN (40.67%), RNN (59.67%), LSTM (54%), GRU (56%) respectively. Among these methods, ELB achieved 92.33% of accuracy with using SMOTE algorithm using imbalanced dataset. Whereas the accuracies of the proposed models without using SMOTE algorithm (imbalanced dataset) are LR (66.09%), KNN (68.47%)

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Do Developers Benefit from Recommendations when Repairing Inconsistent Design Models? a Controlled Experiment

Do Developers Benefit from Recommendations when Repairing In...

引用

2024 software engineering, SE 2024

作者： Marchezan, Luciano Assunção, Wesley Michelon, Gabriela Egyed, Alexander Johannes Kepler University Linz Institute of Software Systems Engineering Altenberger Straße 69 Linz4040 Austria

来源：评论

学校读者我要写书评

暂无评论

Evaluation of low-cost microcontroller-based systems for simple sensor applications

引用

Proceedings of the Institution of Civil Engineers: Smart Infrastructure and Construction 2023年第4期176卷 183-193页

作者： Burse, Benjamin Aicher, Andreas Doycheva, Kristina Walther, Christian Ringert, Jan Oliver Software Engineering Bauhaus-Universität Weimar Weimar Germany Connected Mobility and Infrastructure Fraunhofer Institute for Transportation and Infrastructure Systems IVI Dresden Germany Hochschule Hof - University of Applied Sciences Hof Germany Institute of Structural Mechanics Bauhaus-Universität Weimar Weimar Germany

Single-board computers, such as Raspberry Pi, have enabled a wide variety of monitoring applications. Microcontroller development boards offer a similar functionality but at a lower cost. Still, they are not widely used, because they are supposed to be slow. This paper aims to evaluate the abilities of modern microcontrollers and compares them with those of single-board computers. For this purpose, experiments concerning power consumption and performance evaluation are conducted. The results suggest that promising low-cost microcontrollers exist, which could be applied to reduce cost and energy consumption per node or increase the number of nodes used simultaneously in one monitoring system. © 2023 ICE Publishing. All rights reserved.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Intelligent Daycare: Enhancing Child Safety with IoT and Machine Learning Innovations 9

Intelligent Daycare: Enhancing Child Safety with IoT and Mac...

引用

9th International Conference on Communication and Electronics systems, ICCES 2024

作者： Prathyanga, Amisha Shyaminda, Pasindu Chamikara, Pasan Lakshan, Sachin Thelijjagoda, Samantha Kasthurirathna, Dharshana Sri Lanka Institute of Information Technology Department of Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9798350377972

Child safety and well-being in daycare settings are important, thus it is vital that the persons in charge be attentive to them. This research tries to solve the problem by introducing a smart and detailed monitoring system that utilizes new technology to enhance safety and support caretakers. The system has various innovative features, such as child missing detection, behavior and facial expression analysis, cry analysis and categorization, and fall detection. Using high-resolution cameras and on-device Edge AI capabilities, it ensures real-time surveillance of children's activities while protecting privacy. The approach integrates behavior and facial expression analysis to assess emotional states, cry recognition to discover childcare needs, as well as a useful fall detection system that can tell the difference between falls and other movements. All these parts synergize to hand over the necessary information to the caregivers on time and in a way that they can act upon. The quantitative experiments in real-time childcare centers show high accuracy through all the components, attesting to the system's reliability and durability. This research has important significance in improving the safety and the frequency response in daycare centers because it gives caregivers automated tools to quickly address the needs of children. While promising, the system has drawbacks, such as potential biases in data models and a reliance on ideal environmental circumstances. Future work intends to improve flexibility across varied daycare situations, improve accuracy through larger datasets, and investigate ethical frameworks for wider application. © 2024 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

A Study on Mitigating Hard Boundaries of Decision-Tree-based Uncertainty Estimates for AI Models

A Study on Mitigating Hard Boundaries of Decision-Tree-based...

引用

2022 Workshop on Artificial Intelligence Safety, SafeAI 2022

作者： Gerber, Pascal Jöckel, Lisa Kläs, Michael Fraunhofer Institute for Experimental Software Engineering IESE Fraunhofer Platz 1 Kaiserslautern67663 Germany

Outcomes of data-driven AI models cannot be assumed to be always correct. To estimate the uncertainty in these outcomes, the uncertainty wrapper framework has been proposed, which considers uncertainties related to model fit, input quality, and scope compliance. Uncertainty wrappers use a decision tree approach to cluster input quality related uncertainties, assigning inputs strictly to distinct uncertainty clusters. Hence, a slight variation in only one feature may lead to a cluster assignment with a significantly different uncertainty. Our objective is to replace this with an approach that mitigates hard decision boundaries of these assignments while preserving interpretability, runtime complexity, and prediction performance. Five approaches were selected as candidates and integrated into the uncertainty wrapper framework. For the evaluation based on the Brier score, datasets for a pedestrian detection use case were generated using the CARLA simulator and YOLOv3. All integrated approaches achieved a softening, i.e., smoothing, of uncertainty estimation. Yet, compared to decision trees, they are not so easy to interpret and have higher runtime complexity. Moreover, some components of the Brier score impaired while others improved. Most promising regarding the Brier score were random forests. In conclusion, softening hard decision tree boundaries appears to be a trade-off decision. Copyright © 2022 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Scalable Communication for Mobile Multi-Agent Cooperative Detection 24

Scalable Communication for Mobile Multi-Agent Cooperative De...

引用

24th IEEE International Conference on Mobile Data Management, MDM 2023

作者： Gao, Hongye Zhou, Tianlong Rao, Weixiong Ye, Feng Tongji University School of Software Engineering Shanghai China Institute of Systems Engineering Military Academy of Sciences Beijing100101 China

ISBN: (纸本)9798350341010

Communication is an effective mechanism to coordinate the behavior of mobile multi-agent systems. We propose a general mobile multi-agent cooperative detection framework, which provides a detection system with enhanced collaboration capabilities based on graph neural networks and reinforcement learning. Each agent gains information about the surrounding area by heuristic KNN, and then exchanges this part of subgraph information through communication so as to obtain global information in a decentralized way. At the same time, to avoid the computation overhead caused by the increase of the number of agents, attention mechanism is used to filter and optimize the communication process to improve scalability. We evaluate our method on large-scale detection tasks. Our approach is able to outperform the baselines, while making superior communication efficiency1 © 2023 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Poster: Two-Phase KalmanNet Based Collaborative Detection Framework 43

Poster: Two-Phase KalmanNet Based Collaborative Detection Fr...

引用

43rd IEEE International Conference on Distributed Computing systems, ICDCS 2023

作者： Zhou, Tianlong Rao, Weixiong Ye, Feng School of Software Engineering Tongji University Shanghai China Institute of Systems Engineering Military Academy of Sciences Beijing100101 China

ISBN: (纸本)9798350339864

The collaborative detection problem has been widely used in many applications. Existing works typically exploit a Kalman Filter or its variant to estimate target state with an impractical assumption that the state space and environment are fully known. To address this issue, we propose a novel multi-Agent reinforcement learning (MARL) based collaborative detection framework. The key is (1) a Two-Phase Kalman Neural Network (TPKN) to estimate target state and (2) a reinforcement learning (RL) model by taking the target estimation state as input and generating an action to track targets. Our initial evaluation with 4 pursuer agents and 4 targets demonstrates that our framework outperforms the state-of-The-Art by a much higher tracking ability and lower localization error.11Weixiong Rao and Feng Ye are joint corresponding authors of the paper. © 2023 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Criteria-based comparsion of systems engineering and agile methods A fundamental comparison of two development methods 8

Criteria-based comparsion of Systems Engineering and agile m...

引用

8th International Conference on Information systems engineering, ICISE 2023

作者： Humpert, Lynn Mundt, Enrik Bretz, Lukas Anacker, Harald Bretz, Vanessa Dumitrescu, Roman Fraunhofer Institute For Mechatronic Systems Design Paderborn Germany GTZ/VPD Systems Engineering Miele And Cie. Kg Germany

ISBN: (纸本)9798400709173

This paper compares two popular design methods used in product development, namely systems engineering (SE) and agile methods. The comparison is based on various criteria, such as ease of implementation, object of innovation, software-dependency, customer relations, human centricity, organizational structure, values, and innovative capability, which were developed in a previous paper. The content of the comparison is supported by a literature review and a workshop with industry professionals. The findings show that both SE and agile methods have similarities and differences based on the criteria examined, and the choice of methodology depends on the project's specific context and objectives. While this paper provides only a general overview of each criterion and their compatibility, the results can assist product development teams in selecting the most appropriate approach for their needs. However, more research is necessary to enhance the effectiveness and efficiency of both approaches. This paper is a useful resource for practitioners and researchers interested in understanding the similarities and differences between SE and Agile and making informed decisions regarding their use. © 2023 Owner/Author.

关键词： Product development

来源：评论

学校读者我要写书评

暂无评论

Analysis and Propagation of Feature Revisions in Preprocessor-based software Product Lines

Analysis and Propagation of Feature Revisions in Preprocesso...

引用

2024 software engineering, SE 2024

作者： Michelon, Gabriela K. Assunção, Wesley K.G. Grünbacher, Paul Egyed, Alexander Institute of Software Systems Engineering and LIT Lab Johannes Kepler University Linz Linz4040 Austria Department of Computer Science North Carolina State University RaleighNC27695 United States Institute of Software Systems Engineering Johannes Kepler University Linz Linz4040 Austria

This is a summary of a paper [Mi23] published in the IEEE International Conference on software Analysis, Evolution and Reengineering (SANER) 2023. It describes a tool-supported approach for analyzing and propagating f... 详细信息

ISBN: (纸本)9783885797371

关键词： Computer software reusability

来源：评论

学校读者我要写书评

暂无评论

Leveraging the Potential of Large Language Models

引用

Informatica (Slovenia) 2024年第8期48卷 1-16页

作者： Prasad, Shreya Gupta, Himank Ghosh, Arup Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Computer Science and Information Technology Graceland University LamoniIA United States

This study focuses on enhancing Natural Language Processing (NLP) in generative AI chatbots through the utilization of advanced pre-trained models. We assessed five distinct Large Language Models (LLMs): TRANSFORMER MODEL, FALCON 7B, LAMINI-FLAN-T5-783M, LLAMA-2-7B, and LLAMA-2-13B to identify the most effective one. Our findings revealed that the LLAMA Model excels in comprehending user queries and delivering precise responses during conversations. The article elucidates the methodology employed to evaluate and select various models for our chatbot. Through rigorous testing, we determined that the LLAMA-2-13B model exhibits enhanced response time and accuracy. Additionally, we employed tools such as Facebook Artificial Intelligence Similarity Search (FAISS) and experimented with user interfaces like Streamlit and Chainlit to enhance the chatbot's user-friendliness. The research underscores the significance of selecting the appropriate model for crafting efficient chatbots. Ultimately, the LLAMA-13B model emerged as the standout performer, showcasing superior performance. Benchmark assessments, including HellaSwag and WinoGrande, which gauge common sense reasoning, were employed to evaluate our chatbot's capabilities. The study concludes that LLAMA-based models hold significant promise for the development of innovative and user-friendly chatbots in the future. Povzetek: Študija se osredotoča na izboljšanje obdelave naravnega jezika (NLP) v generativnih AI klepetalnicah z uporabo naprednih vnaprej usposobljenih modelov. Analizirali so pet modelov: TRANSFORMER MODEL, FALCON 7B, LAMINI-FLAN-T5-783M, LLAMA-2-7B in LLAMA-2-13B. Model LLAMA-13B se je izkazal kot najboljši z vrhunskimi rezultati na testih HellaSwag in WinoGrande. Raziskava uporablja orodja, kot je FAISS, in uporabniške vmesnike, kot sta Streamlit in Chainlit za izboljšanje uporabniške izkušnje. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Machine 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：