检索结果-内蒙古大学图书馆

Using Goal-Conditioned Reinforcement Learning with Deep Imitation to Control Robot Arm in Flexible Flat Cable Assembly Task

引用

IEEE Transactions on Automation Science and engineering 2024年第4期21卷 6217-6228页

作者： Li, Jingchen Shi, Haobin Hwang, Kao-Shing Northwestern Polytechnical University School of Computer Science Xi'an710072 China National Sun Yat-sen University Department of Electrical Engineering Kaohsiung81164 Taiwan Kaohsiung Medical University Department of Healthcare Administration and Medical Informatics Kaohsiung80708 Taiwan

Leveraging reinforcement learning on high-precision decision-making in Robot Arm assembly scenes is a desired goal in the industrial community. However, tasks like Flexible Flat Cable (FFC) assembly, which require highly trained workers, pose significant challenges due to sparse rewards and limited learning conditions. In this work, we propose a goal-conditioned self-imitation reinforcement learning method for FFC assembly without relying on a specific end-effector, where both perception and behavior plannings are learned through reinforcement learning. We analyze the challenges faced by Robot Arm in high-precision assembly scenarios and balance the breadth and depth of exploration during training. Our end-to-end model consists of hindsight and self-imitation modules, allowing the Robot Arm to leverage futile exploration and optimize successful trajectories. Our method does not require rule-based or manual rewards, and it enables the Robot Arm to quickly find feasible solutions through experience relabeling, while unnecessary explorations are avoided. We train the FFC assembly policy in a simulation environment and transfer it to the real scenario by using domain adaptation. We explore various combinations of hindsight and self-imitation learning, and discuss the results comprehensively. Experimental findings demonstrate that our model achieves fast and advanced flexible flat cable assembly, surpassing other reinforcement learning-based methods. Note to Practitioners - The motivation of this article stems from the need to develop an efficient and accurate FFC assembly policy for 3C (computer, Communication, and Consumer Electronic) industry, promoting the development of intelligent manufacturing. Traditional control methods are incompetent to complete such a high-precision task with Robot Arm due to the difficult-to-model connectors, and existing reinforcement learning methods cannot converge with restricted epochs because of the difficult goals or trajectories. To

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Exploring Ensemble Machine Learning Models for Attention and Memory Assesment 46

Exploring Ensemble Machine Learning Models for Attention and...

引用

46th International Conference on Telecommunications and Signal Processing, TSP 2023

作者： Gramouseni, Foteini Prapas, Georgios Bellos, Christos Angelidis, Pantelis Giannakeas, Nikolaos Tsipouras, Markos G. University of Western Macedonia Department of Electrical and Computer Engineering Kozani Greece University of Ioannina Department of Informatics and Telecommunications Ioannina Greece

ISBN: (纸本)9798350303964

EEG analysis for attention and memory assessment is an important research topic that has gained a lot of attention in recent years. Virtual Reality (VR) is an innovative technology that provides the ability to design experiments suitable for research in this field. This study explores the feasibility of utilizing ensemble classification algorithms to analyze EEG signals obtained during VR stimulation for the purpose of evaluating memory encoding and attention orienting. The obtained results indicate that EEG analysis can accurately assess memory and attention levels in VR environment setting with a high degree of certainty (84.90% accuracy, and an average of 0.86 true positive rate, 0.88 positive predicted value, 0.89 area under the ROC curve, and 0.89 true negative rate). © 2023 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Face image authentication scheme based on MTCNN and SLT

引用

Multimedia Tools and Applications 2025年 1-43页

作者： Thabit, Rasha Al-Askari, Mohanad A. Mohammed, Dunya Zeki Anaam, Elham Abdulwahab Mahmood, Zainab H. Jabbar, Dina Jamal Salih, Zahraa Aqeel Information System Department College of Computer Sciences and Information Technology University of Al-Anbar Al-Anbar Iraq Computer Engineering Department College of Engineering Al-Iraqia University Baghdad Iraq Electronic and Communications Engineering Department College of Engineering Gilgamesh University Baghdad Iraq Faculty of Computing and Informatics Multimedia University Selangor Cyberjaya Malaysia Department of Cybersecurity Engineering College of Information Engineering Al-Nahrain University Baghdad Iraq Electrical Engineering Technical Collage Middle Technical University Baghdad Iraq Department of Business Administration Alamaal University College Baghdad Iraq

DeepFakes and face image manipulation methods have been widely distributed in the last few years and several techniques have been presented to check the authenticity of the face image and detect manipulation if exists. Most of the available manipulation detection techniques have been successfully applied to reveal one type of manipulation under specific conditions, however, many limitations and challenges can be encountered in this field. To overcome some limitations and challenges, this paper presents a new face image authentication (FIA) scheme based on Multi-Task Cascaded Conventional Neural Networks (MTCNN) and watermarking in Slantlet transform (SLT) domain. The proposed FIA scheme has three main algorithms that are face detection and selection, embedding, and extraction algorithms. Different block sizes have been used to divide the image into non-overlapping blocks followed by classifying them into two groups that are blocks from face area (FA) and blocks from the remaining area (RA) of the image. In the embedding algorithms, the authentication information is generated from FA blocks and embedded in the RA blocks. In the extraction algorithms, the embedded information is extracted from RA blocks and compared with the calculated data from FA blocks to reveal manipulations and localize the manipulated blocks if exist. Extensive experiments have been conducted to evaluate the performance of the proposed FIA scheme for different face images. The experimental work included tests for payload, capacity, visual quality, time complexity, and localization of manipulations. The results proved the efficiency of the proposed scheme in detecting and localizing different face image manipulations such as attributes attacks, retouching attacks, expression swap, face swap, and morphing attacks. The proposed scheme overcomes many limitations and it is 100% accurate in localizing the tampered blocks which makes it a better candidate for practical applications. © The Author(s), un

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Dynamic Day and Night Cycle Impact in a Serious VR Game 10

Dynamic Day and Night Cycle Impact in a Serious VR Game

引用

10th International Conference on Virtual Reality, ICVR 2024

作者： Damastuti, Fardani Annisa Firmansyah, Kenan Arif, Yunifa Miftachul Barakbah, Ali Ridho Hariadi, Mochamad Institut Teknologi Sepuluh Nopember Department of Electrical Engineering Surabaya Indonesia Electronic Engineering Polytechnic Institute of Surabaya Department of Creative Multimedia Technology Surabaya Indonesia Universitas Islam Negeri Maulana Malik Ibrahim Department of Informatics Engineering Malang Indonesia Electronic Engineering Polytechnic Institute of Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia Institut Teknologi Sepuluh Nopember Department of Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350364231

The immersive nature of virtual reality (VR) gaming is significantly improved by the implementation of dynamic environmental systems. This paper focuses on the development and impact of a dynamic day and night cycle in a serious VR game. This feature is intended to simulate a full 24-hour cycle within a 10-minute gameplay session, resulting in a seamless transition between different times of day that impacts both the visual aesthetics and gameplay mechanics. The day and night cycle introduces strategic depth by requiring players to adjust their management strategies according to the time of day, which affects resource availability, operational efficiency, and conditions. This system not only enhances visual fidelity but also directly impacts gameplay, necessitating that player modify their strategies in response to the changing environment. Visual aesthetics are expected to increase by 15%, strategic profundity will be improved by 20%, and player immersion will be enhanced by 25%, according to the research findings. This investigation underscores the importance of natural cycles in enhancing the strategic complexity, interactivity, and realism of virtual reality environments, thereby offering valuable insights for the creation of future virtual reality games. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Enhancing Restaurant Customer Review Analysis: Multi-Class Text Classification with BERT 6

Enhancing Restaurant Customer Review Analysis: Multi-Class T...

引用

6th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2023

作者： Sunarko, Budi Hasanah, Uswatun Hidayat, Syahroni Universitas Negeri Semarang Department of Informatics and Computer Engineering Education Semarang Indonesia Universitas Negeri Semarang Department of Computer Engineering Semarang Indonesia Universitas Negeri Semarang Department of Electrical Engineering Semarang Indonesia

ISBN: (纸本)9798350358346

Online customer reviews can be valuable information when processed with the right techniques. Businesses aim to enhance their strategies in managing operations by leveraging sentiment analysis from their clientele. In a business context, the primary focus of SA is to capture individual perspectives on products. Presently, sentiment analysis not only deals with emotional polarity but also classifies sentiments towards various product-related aspects. This research aims to classify restaurant customer review data on Google Maps into categories such as 'menu,' 'taste,' 'indoor atmosphere,' and 'outdoor atmosphere'. We utilize 450 entries for this dataset. The model used is Bidirectional Encoder Representation from Transformers (BERT), a technique based on transformer-based neural networks, capable of learning grammatical structures, interpreting semantics, and deriving relationships among contextual entities. The results show a less satisfying accuracy score of 41.110/0. This is due to several inaccuracies in the label annotations of the utilized data. Further analysis is discussed in the Discussion and Conclusion section. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Integration of Advanced AI Chatbots for Biological Pathway Curation

Evaluation and Integration of Advanced AI Chatbots for Biolo...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Azam, Muhammad He, Fei Santosh, Krpns Xu, Dong Popescu, Mihail University of Missouri Department of Electrical Engineering and Computer Science ColumbiaMO United States University of Missouri Department of Health Management and Informatics ColumbiaMO United States

ISBN: (纸本)9798350386226

The rapid expansion of biological literature presents significant challenges in manually curating pathway knowledge from images for biological and medical research. Recent advancements in AI, particularly multimodal AI chatbots like GPT-4V, Claude, and Gemini, offer promising capabilities for image understanding and extraction of biological interactions. This study evaluates the effectiveness of these AI chatbots in curating gene interactions from 50 curated tumor signaling pathway images. Our results highlight the superior performance of GPT-4V, achieving a precision of 0.778, a recall of 0.664, an F1-score of 0.716 in non-directional analysis, and a precision of 0.566, a recall of 0.471, an F1-score of 0.512 in directional analysis. Claude followed with a precision of 0.735, recall of 0.594, and F1-score of 0.6571 in non-directional analysis, and a precision of 0.500, recall of 0.400, and F1-score of 0.445 in directional analysis. Gemini recorded the lowest performance metrics across both analyses. We further developed a model fusion integrating Claude-3 chatbots and our pathway curation pipeline, achieving notable improvements. © 2024 IEEE.

关键词： AI Chatbots Bio-Curation Gene Interactions Precision Oncology Signaling Pathways

来源：评论

学校读者我要写书评

暂无评论

Gestures detection and device control in AAL environments using machine learning and BLEs 12

Gestures detection and device control in AAL environments us...

引用

12th Mediterranean Conference on Embedded Computing, MECO 2023

作者： Spournias, Alexandros Faliagka, Evanthia Skandamis, Theodoros Antonopoulos, Christos Voros, Nikolaos S. Keramidas, Georgios University of the Peloponnese Electrical & Computer Engineering Department Patra Greece School of Informatics Aristotle University of Thessaloniki Thessaloniki Greece

ISBN: (纸本)9798350322910

This paper presents a system for detecting gestures and controlling devices in Ambient Assisted Living (AAL) environments using machine learning and Bluetooth Low Energy (BLE) technology. The system consists of two main components: a device equipped with a set of sensors to detect hand gestures via IMU sensor and a BLE-enabled hub that receives the gesture data and controls the lighting of the house. The hub uses machine learning algorithms to recognize hand gestures and transmit the corresponding commands to the devices. The hub, in turn, uses wifi to communicate with the devices and execute the appropriate actions based on the received commands. The proposed system's performance evaluation was carried out through a series of experiments in a AAL environment. The results demonstrate that the system is capable of accurately detecting hand gestures and controlling various devices such as lights, where the model's performance yields successful predictions with an accuracy rate of 90%. The proposed system provides a user-friendly and intuitive way for elderly or people with disabilities to control their environment without the need for complex interfaces or physical buttons. Furthermore, the system can be easily extended to support more gestures and devices, making it a flexible and scalable solution for AAL environments. © 2023 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Source Code Statement Classification using ANTLR and Random Forest 24

Source Code Statement Classification using ANTLR and Random ...

引用

24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023

作者： Putro, Hanson Prihantoro Yuhana, Umi Laili Yuniarno, Eko Mulyanto Purnomo, Mauridhi Hery Institut Teknologi Sepuluh Nopember Department of Electrical Engineering Surabaya Indonesia Universitas Islam Indonesia Department of Informatics Yogyakarta Indonesia Institut Teknologi Sepuluh Nopember Department of Informatics Surabaya Indonesia Institut Teknologi Sepuluh Nopember Department of Computer Engineering Department of Electrical Engineering Surabaya Indonesia

ISBN: (纸本)9798350313956

In software development, source code analysis is essential to maintain software. One of the metrics used to assess software quality is software complexity, which can be calculated by analyzing source code statements like declaration, expression, and control. However, analyzing source code statements using an existing popular technique, like NLP, requires another structured form of data, which can be obtained by converting the source code into a token stream using a programming language processor. This study aims to get the best source code statement classification from six observed models and two source code forms. The models are Decision Tree, Naïve Bayes, SVM, kNN, Rocchio Algorithm and Random Forest. The source code forms are the raw source code and token stream object. The dataset collection used 562 rows of source code statements from an open-source Java project in a public repository. Next, we use ANTLR to transform the raw source code and get the token stream object. Later, the dataset was modeled using TF-IDF as an NLP technique to get the source code features. Then, six machine learning models were built and evaluated as a comparison for the classification process. As a result, Random Forest became the best model with the highest accuracy values among other machine learning models. Moreover, the token stream became the best object over source code as a contribution from the ANTLR. The model successfully predicted source code statements with a 96.1% accuracy score using the Random Forest model and ANTLR tools. In advance, this multiclass classification was also evaluated and gave a result. No declaration statement was predicted as a control statement, and vice versa (100% accuracy), but some miss prediction was observed in declaration-expression and expression-control pairs. Nevertheless, the Random Forest model's high accuracy and precision make it suitable for classifying source code statements. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Design of Rule Translator for Temporal Rules Execution of BM-DEVS Model 15th

Design of Rule Translator for Temporal Rules Execution of BM...

引用

15th International Conference on computer Science and its Applications, CSA 2023 and 17th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2023

作者： Ahn, Jungsub Cho, Taeho Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of College of Computing and Informatics Sungkyunkwan University Suwon16419 Korea Republic of

ISBN: (纸本)9789819724468

With the increasing complexity of systems, various studies are being conducted to accurately express and solve problems. Discrete Event System Specification (DEVS), one of the simulation theories, expresses a problem as a hierarchical model. The Behavior Monitoring-DEVS (BM-DEVS) theory is an extension of DEVS. It monitors the behavior of interest by expressing it as temporal rules in the model. In BM-DEVS, the defined temporal rules need to be converted into Büchi automata and applied to the model to evaluate the behavior expressed by the rules. To achieve this, modelers need to translate temporal rules into automata and verify these. This consumes a substantial amount of time. To solve this problem, this paper proposes a method to automatically translate temporal rules into automata for rule evaluation. In this proposed method, when temporal rules are input, structuring work is performed to match the rule structure and model structure. Moreover, a more convenient modeling environment is provided to modelers through the rule expansion function. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Automata theory

来源：评论

学校读者我要写书评

暂无评论

Wrapper-Based Feature Selection to Improve The Accuracy of Intrusion Detection System (IDS) 10

Wrapper-Based Feature Selection to Improve The Accuracy of I...

引用

10th International Conference on Wireless and Telematics, ICWT 2024

作者： Jupriyadi Budiman, Arief Hamidi, Eki Ahmad Zaki Ahdan, Syaiful Negara, Ridha Muldina Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandarlampung Indonesia Universitas Gadjah Mada Department Computer Science and Electronics Yogyakarta Indonesia UIN Sunan Gunung Djati Bandung Electrical Engineering Department Bandung Indonesia Telkom University School of Electrical Engineering Bandung Indonesia

ISBN: (纸本)9798350377057

An Intrusion Detection System (IDS) is a system that can detect attacks on a network. IDS systems can be built using machine learning approaches. However, significant network traffic and many features cause machine learning algorithms to work slowly. Not all available features are essential for use as a reference in an intrusion detection system. Feature selection is important because it can reduce the dataset and speed up computing time in building models and detection systems. In this paper, feature selection using the wrapper method is proposed. Its performance is compared with filter-based feature selection, such as chi-square, information gain, gain ratio, and correlation-based feature selection (CFS). Based on the exploration, the results showed that the feature selection algorithm using the wrapper method was superior to other algorithms. The number of critical features discovered and the detection system's precision serve as proof of the wrapper approach. With only three features as a reference, the detection system produces an accuracy of 96.22%. It increases 5.84% from 90.38% to 96.22%. Computation time also increases because the number of features used is tiny compared to other algorithms and uses all features. © 2024 IEEE.

关键词： Network intrusion

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：