检索结果-内蒙古大学图书馆

IEEE Conference on Robotics, Automation and Mechatronics

作者： Wenhao Luo Jun Peng Weirong Liu Jing Wang Wentao Yu Department of Automation Key Laboratory of System Control And Information Processing Shanghai China School of Information Science and Engineering Hunan Engineering Laboratory for Advanced Controland Intelligent Automation Changsha China Computer Engineering Program Bethune-Cookman University Daytona Beach FL USA

This paper presents an efficient analytic method for a mobile robot to determine a collision-free trajectory with unified optimization. The robot kinodynamic constraints and the geometric constraints due to obstacles are addressed by considering a set of constrained inequalities from parameterized trajectories model. Two optimal performance matrices are employed to assess optimization problems. Particularly, both the constraints and performance functions are incorporated by similar forms in terms of trajectory parameters, which thereby can be considered in a uniform way. A parameter space of adjustable trajectory parameters is constructed to solve the unified optimization problem with constraints and results in more flexible and better optimal performance. The proposed approach is complete and enhances methods of deterministic real-time planning by overcoming typical drawbacks as intermediate configuration, curvature discontinuities, vertical singularities and incomplete optimization. Simulation results verify the validity and superiority of the proposed method.

关键词： Trajectory Robot kinematics Collision avoidance Mobile robots Acceleration Optimization

来源：评论

学校读者我要写书评

暂无评论

AV Navigation in 3D Urban Environments with Curriculum-based Deep Reinforcement Learning

AV Navigation in 3D Urban Environments with Curriculum-based...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Kevin Braathen de Carvalho Iure Rosa L. de Oliveira Alexandre S. Brandão Department of Electrical Engineering Graduate Program in Computer Science Nucleus of Specialization in Robotics Universidade Federal de Viçosa Viçosa MG Brazil Department of Electrical Engineering Federal University of Viçosa Viçosa MG Brazil

Unmanned Aerial Vehicles (UAVs) are widely used in various applications, from inspection and surveillance to transportation and delivery. Navigating UAVs in complex 3D environments is a challenging task that requires robust and efficient decision-making algorithms. This paper presents a novel approach to UAV navigation in 3D environments using a Curriculum-based Deep Reinforcement Learning (DRL) approach. The proposed method utilizes a deep neural network to model the UAV’s decision-making process and to learn a mapping from the state space to the action space. The learning process is guided by a reinforcement signal that reflects the performance of the UAV in terms of reaching its target while avoiding obstacles and with energy efficiency. Simulation results show that the proposed method has a positive trade off when compared to the baseline algorithm. The proposed method was able to perform well in environments with a state space size of 22 millions, allowing the usage in big environments or in maps with high resolution. The results demonstrate the potential of DRL for enabling UAVs to operate effectively in complex environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mitigation of Hallucinations in Language Models in Education: A New Approach of Comparative and Cross-Verification

Mitigation of Hallucinations in Language Models in Education...

引用

International Conference on Advanced Learning Technologies (ICALT)

作者： Wildemarkes de Almeida da Silva Luis Carlos Costa Fonseca Sofiane Labidi José Chrystian Lima Pacheco Post-Graduation Program in Computer and Systems Engineering State University of Maranhão - UEMA São Luís Brazil Bachelor of Science and Technology Program -BICT Federal University of Maranhão - UFMA São Luís Brazil Graduation in Computer and Systems Engineering State University of Maranhão - UEMA São Luís Brazil

ISBN: (数字)9798350362053

ISBN: (纸本)9798350362060

The rapid growing application of language models (LLMs) in education offers exciting prospects for personalized learning and interactive experiences. However, a critical challenge emerges - the risk of "hallucinations," where LLMs generate factually incorrect or misleading information. This paper proposes Comparative and Cross-Verification Prompting (CCVP), a novel technique specifically designed to mitigate hallucinations in educational LLMs. CCVP leverages the strengths of multiple LLMs, a Principal Language Model (PLM) and Auxiliary Language Models (ALMs), to verify the accuracy and educational relevance of the PLM's response to a prompt. Through a series of prompts and assessments, CCVP harnesses the diverse perspectives of various LLMs and incorporates human expertise for intricate cases. This method addresses the limitations of relying on a single model and fosters critical thinking skills in learners within the educational context. We detail the CCVP approach with examples specifically applicable to educational settings, such as geography. We also discuss its strengths and limitations, including computational cost, data reliance, and ethical considerations. We highlight its potential applications in educational disciplines, including fact-checking content, detecting bias, and promoting responsible LLM use. CCVP presents a promising avenue for ensuring the accuracy and trustworthiness of LLM-generated educational content. Further research and development will refine its scalability, address potential biases, and solidify its position as a vital tool for harnessing the power of LLMs while fostering responsible knowledge dissemination in education.

关键词： Geography Solid modeling Accuracy Scalability Prevention and mitigation Computational modeling Education

来源：评论

学校读者我要写书评

暂无评论

Ontology Model-Based Static Analysis on Java programs

Ontology Model-Based Static Analysis on Java Programs

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Lian Yu Jun Zhou Yue Yi Ping Li Qianxiang Wang School of Software and Microelectronics Peking University Beijing China IBM Joint Research National High-Tech Research and Development Program of China School of Electronics Engineering and Computer Science Peking University Beijing China

Typical enterprise and military software systems consist of millions of lines of code with complicated dependence on diverse library abstractions. Manually debugging these codes imposes developers overwhelming workload and difficulties. To address software quality concerns efficiently, this paper proposes an ontology-based static analysis approach to automatically detect bugs in the source code of Java programs. First, we elaborate bug list collected, classify bugs into different categories, and translate bug patterns into SWRL (semantic Web rule language) rules using an ontology tool, Protege. An ontology model of Java program is created according to Java program specification using Protege as well. Both SWRL rules and the program ontology model are exported in OWL (Web ontology language) format. Second, Java source code under analysis is parsed into the abstract syntax tree (AST), which is automatically mapped to the individuals of the program ontology model. SWRL bridge takes in the exported OWL file (representing the SWRL rules model and program ontology model) and the individuals created for the Java code, conduits to Jess (a rule engine), and obtains inference results indicating any bugs. We perform experiments to compare bug detection capability with well-known FindBugs tool. A prototype of bug detector tool is developed to show the validity of the proposed static analysis approach.

关键词： Java OWL computer bugs Ontologies Cognition Bridges Analytical models

来源：评论

学校读者我要写书评

暂无评论

MODELING THE HUMAN VISUAL SYSTEM: COMPARATIVE INSIGHTS FROM RESPONSE-OPTIMIZED AND TASK-OPTIMIZED VISION MODELS, LANGUAGE MODELS, AND DIFFERENT READOUT MECHANISMS

arXiv

引用

arXiv 2024年

作者： Saha, Shreya Chadha, Ishaan Khosla, Meenakshi Department of Electrical and Computer Engineering University of California La Jolla San DiegoCA92093 United States Halıcıoglu Data Science Institute University of California La Jolla San DiegoCA92093 United States Department of Cognitive Science University of California La Jolla San DiegoCA92093 United States

Over the past decade, predictive modeling of neural responses in the primate visual system has advanced significantly, largely driven by various deep neural network approaches. These include models optimized directly for visual recognition, cross-modal alignment through contrastive objectives, neural response prediction from scratch, and large language model embeddings. Likewise, different readout mechanisms—ranging from fully linear to spatial-feature factorized methods—have been explored for mapping network activations to neural responses. Despite the diversity of these approaches, it remains unclear which method performs best across different visual regions. In this study, we systematically compare these approaches for modeling the human visual system and investigate alternative strategies to improve response predictions. Our findings reveal that for early to mid-level visual areas, response-optimized models with visual inputs offer superior prediction accuracy, while for higher visual regions, embeddings from Large Language Models (LLMs) based on detailed contextual descriptions of images and task-optimized models pretrained on large vision datasets provide the best fit. Through comparative analysis of these modeling approaches, we identified three distinct regions in the visual cortex: one sensitive primarily to perceptual features of the input that are not captured by linguistic descriptions, another attuned to fine-grained visual details representing semantic information, and a third responsive to abstract, global meanings aligned with linguistic content. We also highlight the critical role of readout mechanisms, proposing a novel scheme that modulates receptive fields and feature maps based on semantic content, resulting in an accuracy boost of 3-23% over existing SOTAs for all models and brain regions. Together, these findings offer key insights into building more precise models of the visual system. © 2024, CC BY-NC-ND.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Balancing collaboration and discipline in software development processes

Balancing collaboration and discipline in software developme...

引用

International Conference on Software engineering (ICSE)

作者： Andrea Magalhaes Magdaleno NP2Tec-Research and Practice Group in Information Technology UNIRIO Brazil COPPE/PESC-System Engineering and Computer Science Program UFRJ Rio de Janeiro Rio de Janeiro Brazil

Neither traditional, agile or free/open software development models can be effective to all projects contexts. We claim that collaboration and discipline can be the driver to tailor software development processes to meet projects and organizations needs. This work proposes that process tailoring can be conducted through a context management approach.

关键词： Context Collaboration programming Software Social network services Organizations Context modeling

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning for EEG-Based Brain-computer Interfaces: A Review of Progress Made Since 2016

arXiv

引用

arXiv 2020年

作者： Wu, Dongrui Xu, Yifan Lu, Bao-Liang The Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Brain Science and Technology Research Center Qing Yuan Research Institute Shanghai Jiao Tong University 800 Dong Chuan Road Shanghai200240 China

A brain-computer interface (BCI) enables a user to communicate with a computer directly using brain signals. The most common non-invasive BCI modality, electroencephalogram (EEG), is sensitive to noise/artifact and suffers between-subject/within-subject non-stationarity. Therefore, it is difficult to build a generic pattern recognition model in an EEG-based BCI system that is optimal for different subjects, during different sessions, for different devices and tasks. Usually, a calibration session is needed to collect some training data for a new subject, which is time-consuming and user unfriendly. Transfer learning (TL), which utilizes data or knowledge from similar or relevant subjects/sessions/devices/tasks to facilitate learning for a new subject/session/device/task, is frequently used to reduce the amount of calibration effort. This paper reviews journal publications on TL approaches in EEG-based BCIs in the last few years, i.e., since 2016. Six paradigms and applications - motor imagery, event-related potentials, steady-state visual evoked potentials, affective BCIs, regression problems, and adversarial attacks - are considered. For each paradigm/application, we group the TL approaches into cross-subject/session, cross-device, and cross-task settings and review them separately. Observations and conclusions are made at the end of the paper, which may point to future research directions. Copyright © 2020, The Authors. All rights reserved.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

IoT System for Floating Raft Hydroponics: Nutrient Monitoring and Automation 13

IoT System for Floating Raft Hydroponics: Nutrient Monitorin...

引用

13th International Physics Seminar 2024, IPS 2024

作者： Purwalaksana, A.Z. Wahyu, S. Ndari, W.E.W. Syah, S.A. Rismawati, E. Kusumadjati, A. Suharmanto, P. Department of Physics Universitas Negeri Jakarta Jl. Rawamangun Muka Jakarta13220 Indonesia Department of Physics Education Universitas Negeri Jakarta Jl. Rawamangun Muka Jakarta13220 Indonesia Physics Study Program Indonesia Defense University IPSC Sentul Area West Java16810 Indonesia Department of Industrial Engineering Faculty of Engineering and Computer Science Universitas Indraprasta PGRI Jl. Nangka Raya No.58 C Jakarta12530 Indonesia

The utilization of hydroponic cultivation in agriculture is increasing due to its high productivity even in limited spaces. However, in practice, monitoring and controlling nutrients in hydroponic systems often require intensive human supervision and intervention. This issue can be addressed through technological advancements, particularly with the adoption of microcontrollers, sensors, and the Internet of Things (IoT). Previous research has developed IoT-based monitoring and control systems for DFT hydroponics using the Blynk platform. This study aims to develop an IoT-based nutrient monitoring and automation system for floating raft hydroponics. Floating raft hydroponics was chosen for its simplicity, lower installation costs, and space optimization. The system developed in this study uses the HC-SR04 ultrasonic sensor with an average error of 1.229%, the DS18B20 water temperature sensor with an error of 0.415%, and the TDS sensor with an error of 2.055%. The sensor and actuator measurement data are presented via the Antares Web. This research has the potential to minimize the necessity for manual intervention in hydroponic systems, thereby enhancing both efficiency and consistency in nutrient delivery. © Published under licence by IOP Publishing Ltd.

关键词： Hydroponics

来源：评论

学校读者我要写书评

暂无评论

Hybrid Cryptography on Wireless Sensor Network: A Systematic Literature Review

Hybrid Cryptography on Wireless Sensor Network: A Systematic...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： R. Benny Gandara Gunawan Wang Ditdit Nugeraha Utama Master Program of Electrical Engineering Mereu Buana University Jakarta Indonesia Information Systems Management Department Bina Nusantara University Jakarta Indonesia Computer Science Department Bina Nusantara University Jakarta Indonesia

Wireless technology gradual growth in the latest years has facilitated it to bridge its applications operated extensively in many types of industry. Wireless sensor network (WSN) technology brings several benefits over traditional wired technology by reason of the lower cost, immense flexibility escalation, and scalability which is able to be obtained from the old-style one. However, in its application WSN still experience some constraints on resource limitations in the form: processor, memory and energy, and any more challenges that related to availability, reliability and security. Based on its benefits, limitation, and challenges, and also three systematic stages, the review study was performed. The result of study was portrayed in this paper. It is regarding investigation result of hybrid cryptography (HC, as one of defense methods) realized for WSN to methodically increase the security level and decrease the resources usage. The result concluded that HC was proven in escalating the security defense level and downgrading the resources use on WSN compared to symmetric and asymmetric algorithms.

关键词： Wireless sensor networks Cryptography Libraries Protocols Systematics Bibliographies

来源：评论

学校读者我要写书评

暂无评论

DACSR: Decoupled-Aggregated End-to-End Calibrated Sequential Recommendation

arXiv

引用

arXiv 2022年

作者： Chen, Jiayi Wu, Wen Shi, Liye Ji, Yu Hu, Wenxin Chen, Xi Zheng, Wei He, Liang School of Computer Science and Technology East China Normal University Shanghai200062 China Shanghai Key Laboratory of Mental Health and Psychological Crisis Intervention School of Psychology and Cognitive Science East China Normal University Shanghai200062 China School of Data Science and Engineering East China Normal University Shanghai200062 China Information Technology Services East China Normal University Shanghai200062 China

Sequential recommendations have made great strides in accurately predicting the future behavior of users. However, seeking accuracy alone may bring side effects such as unfair and overspecialized recommendation results. In this work, we focus on the calibrated recommendations for sequential recommendation, which is connected to both fairness and diversity. On the one hand, it aims to provide fairer recommendations whose preference distributions are consistent with users' historical behaviors. On the other hand, it can improve the diversity of recommendations to a certain degree. But existing methods for calibration have mainly relied on the post-processing on the candidate lists, which require more computation time in generating recommendations. In addition, they fail to establish the relationship between accuracy and calibration, leading to the limitation of accuracy. To handle these problems, we propose an end-to-end framework to provide both accurate and calibrated recommendations for sequential recommendation. We design an objective function to calibrate the interests between recommendation lists and historical behaviors. We also provide distribution modification approaches to improve the diversity and mitigate the effect of imbalanced interests. In addition, we design a decoupled-aggregated model to improve the recommendation. The framework assigns two objectives to two individual sequence encoders, and aggregates the outputs by extracting useful information. Experiments on benchmark datasets validate the effectiveness of our proposed model. Copyright © 2022, The Authors. All rights reserved.

关键词： Calibration

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：