检索结果-内蒙古大学图书馆

Autonomous embodied navigation task generation from natural language dialogues

science China(information sciences) 2025年第5期68卷 119-132页

作者： Haifeng XU Yongchang LI Lumeng MA Chunwen LI Yanzhi DONG Xiaohu YUAN Huaping LIU Department of Automation Tsinghua University School of Physics and Electronic Information Yantai University School of Electrical and Electronic Engineering Shanghai Institute of Technology Department of Computer Science and Technology Tsinghua University

Robots are increasingly being deployed in densely populated environments, such as homes, hotels, and office buildings, where they rely on explicit instructions from humans to perform tasks. However, complex tasks often require multiple instructions and prolonged monitoring, which can be time-consuming and demanding for users. Despite this, there is limited research on enabling robots to autonomously generate tasks based on real-life scenarios. Advanced intelligence necessitates robots to autonomously observe and analyze their environment and then generate tasks autonomously to fulfill human requirements without explicit commands. To address this gap, we propose the autonomous generation of navigation tasks using natural language dialogues. Specifically, a robot autonomously generates tasks by analyzing dialogues involving multiple persons in a real office environment to facilitate the completion of item transportation between various *** propose the leveraging of a large language model(LLM) through chain-of-thought prompting to generate a navigation sequence for a robot from dialogues. We also construct a benchmark dataset consisting of 625 multiperson dialogues using the generation capability of LLMs. Evaluation results and real-world experiments in an office building demonstrate the effectiveness of the proposed method.

关键词： proactive robot robot navigation service robot large language model

来源：评论

学校读者我要写书评

暂无评论

Modeling Task Engagement to Regulate Reinforcement Learning-based Decoding for Online Brain Control

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年第3期17卷 606-614页

作者： Zhang, Xiang Shen, Xiang Wang, Yiwen Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Department of Chemical and Biological Engineering Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Brain-Machine Interfaces (BMIs) offer significant promise for enabling paralyzed individuals to control external devices using their brain signals. One challenge is that during the online Brain Control (BC) process, subjects may not be completely immersed in the task, particularly when multiple steps are needed to achieve a goal. The decoder indiscriminately takes the less engaged trials as training data, which might decrease the decoding accuracy. In this paper, we propose an alternative kernel RL-based decoder that trains online with continuous parameter update. We model neural activity from the medial prefrontal cortex (mPFC), a reward-related brain region, to represent task engagement. This information is incorporated into a stochastic learning rate using an exponential model, which measures the relevancy of neural data. The proposed algorithm was evaluated in the experiment where rats performed a cursor-reaching BC task. We found the neural activities from mPFC contained the engagement information which was negatively correlated with trial response time. Moreover, compared to the RL method without task engagement modeling, our proposed method enhanced the training efficiency. It used half of the training data to achieve the same reconstruction accuracy of the cursor trajectory. The results demonstrate the potential of our RL framework for improving online brain control tasks. © 2016 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Data Hiding Methods Using Voting Strategy and Mapping Table

引用

Journal of Internet Technology 2024年第3期25卷 365-377页

作者： Chi, Hengxiao Chang, Chin-Chen Lin, Chia-Chen Department of Information Engineering and Computer Science Feng Chia University Taiwan Department of Computer Science and Information Engineering National Chin-Yi University of Technology Taiwan

With advancements in technology, the study of data hiding (DH) in images has become more and more important. In this paper, we introduce a novel data hiding scheme that employs a voting strategy to predict pixels based on their neighbors, then embeds data into the predicted pixels according to a designed mapping table. To extract the information, it is only necessary to use the voting strategy to predict the pixels again, then to compare the predicted and hidden pixels to extract the secret data with the assistance of the mapping table. Our experimental results demonstrate that the proposed hiding scheme has a high embedding capacity, and preserves a satisfactory visual quality. Additionally, it attains a high peak signal-to-noise ratio (PSNR) even at high embedding capacity. © 2024 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

A Novel CAPTCHA Recognition System Based on Refined Visual Attention

引用

computers, Materials & Continua 2025年第4期83卷 115-136页

作者： Zaid Derea Beiji Zou Xiaoyan Kui Monir Abdullah Alaa Thobhani Amr Abdussalam School of Computer Science and Engineering Central South UniversityChangsha410083China College of Computer Science and Information Technology Wasit UniversityWasit52001Iraq Department of Computer Science and Artificial Intelligence College of Computing and Information TechnologyUniversity of BishaBisha67714Saudi Arabia Electronic Engineering and Information Science Department University of Science and Technology of ChinaHefei230026China

Improving website security to prevent malicious online activities is crucial,and CAPTCHA(Completely Automated Public Turing test to tell computers and Humans Apart)has emerged as a key strategy for distinguishing human users from automated ***-based CAPTCHAs,designed to be easily decipherable by humans yet challenging for machines,are a common form of this ***,advancements in deep learning have facilitated the creation of models adept at recognizing these text-based CAPTCHAs with surprising *** our comprehensive investigation into CAPTCHA recognition,we have tailored the renowned UpDown image captioning model specifically for this *** approach innovatively combines an encoder to extract both global and local features,significantly boosting the model’s capability to identify complex details within CAPTCHA *** the decoding phase,we have adopted a refined attention mechanism,integrating enhanced visual attention with dual layers of Long Short-Term Memory(LSTM)networks to elevate CAPTCHA recognition *** rigorous testing across four varied datasets,including those from Weibo,BoC,Gregwar,and Captcha 0.3,demonstrates the versatility and effectiveness of our *** results not only highlight the efficiency of our approach but also offer profound insights into its applicability across different CAPTCHA types,contributing to a deeper understanding of CAPTCHA recognition technology.

关键词： Text-based CAPTCHA recognition refined visual attention web security computer vision

来源：评论

学校读者我要写书评

暂无评论

Malicious iOS Apps Detection Through Multi-Criteria Decision-Making Approach

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第1期49卷 207-220页

作者： Bhatt, Arpita Jadhav Sardana, Neetu Department of Computer Science & Engineering and Information Technology Jaypee Institute of Information Technology Indonesia

In today’s era, smartphones are used in daily lives because they are ubiquitous and can be customized by installing third-party apps. As a result, the menaces because of these apps, which are potentially risky for user’s privacy, have increased. information on smartphones is perhaps, more personal than compared to data stored on desktops or computers, making it an easy target for intruders. After Android, the most prevalently used mobile operating system is Apple’s iOS. Both Android and iOS follow permission-based access control to protect user’s privacy. However, the users are unaware whether the app is breaching the user’s privacy. To combat this problem, in the paper we propose a hybrid approach to detect malicious iOS apps based on its permissions. In the first phase, weights have been assigned to app permissions using multi-criteria decision-making (MCDM) approach namely Analytic Hierarchy Process (AHP), and in the second phase machine learning& ensemble learning techniques have been employed to train the classifiers for detecting malicious apps. To test the efficacy of the proposed method dataset comprising 1150 apps from 12 app categories has been used. The results demonstrate the proposed approach improves the efficacy of detecting malicious iOS apps for majority of categories. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

WebFLex:A Framework for Web Browsers-Based Peer-to-Peer Federated Learning Systems Using WebRTC

引用

computers, Materials & Continua 2024年第3期78卷 4177-4204页

作者： Mai Alzamel Hamza Ali Rizvi Najwa Altwaijry Isra Al-Turaiki Department of Computer Science College of Computer and Information SciencesKing Saud UniversityRiyadhKingdom of Saudi Arabia Department of Computer Science and Engineering Punjab Engineering CollegeChandigarhIndia

Scalability and information personal privacy are vital for training and deploying large-scale deep learning *** learning trains models on exclusive information by aggregating weights from various devices and taking advantage of the device-agnostic environment of web ***,relying on a main central server for internet browser-based federated systems can prohibit scalability and interfere with the training process as a result of growing client ***,information relating to the training dataset can possibly be extracted from the distributed weights,potentially reducing the privacy of the local data used for *** this research paper,we aim to investigate the challenges of scalability and data privacy to increase the efficiency of distributed training *** a result,we propose a web-federated learning exchange(WebFLex)framework,which intends to improve the decentralization of the federated learning *** is additionally developed to secure distributed and scalable federated learning systems that operate in web browsers across heterogeneous ***,WebFLex utilizes peer-to-peer interactions and secure weight exchanges utilizing browser-to-browser web real-time communication(WebRTC),efficiently preventing the need for a main central *** has actually been measured in various setups using the MNIST *** results show WebFLex’s ability to improve the scalability of federated learning systems,allowing a smooth increase in the number of participating devices without central data *** addition,WebFLex can maintain a durable federated learning procedure even when faced with device disconnections and network ***,it improves data privacy by utilizing artificial noise,which accomplishes an appropriate balance between accuracy and privacy preservation.

关键词： Federated learning web browser privacy deep learning

来源：评论

学校读者我要写书评

暂无评论

RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第7期9卷 1-10页

作者： Li, Jiahang Zhan, Yikang Yun, Peng Zhou, Guangliang Chen, Qijun Fan, Rui College of Electronic and Information Engineering Tongji University Shanghai China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

The recent advancements in deep convolutional neural networks have shown significant promise in the domain of road scene parsing. Nevertheless, the existing works focus primarily on freespace detection, with little attention given to hazardous road defects that could compromise both driving safety and comfort. In this article, we introduce RoadFormer, a novel Transformer-based data-fusion network developed for road scene parsing. RoadFormer utilizes a duplex encoder architecture to extract heterogeneous features from both RGB images and surface normal information. The encoded features are subsequently fed into a novel heterogeneous feature synergy block for effective feature fusion and recalibration. The pixel decoder then learns multi-scale long-range dependencies from the fused and recalibrated heterogeneous features, which are subsequently processed by a Transformer decoder to produce the final semantic prediction. Additionally, we release SYN-UDTIRI, the first large-scale road scene parsing dataset that contains over 10,407 RGB images, dense depth images, and the corresponding pixel-level annotations for both freespace and road defects of different shapes and sizes. Extensive experimental evaluations conducted on our SYN-UDTIRI dataset, as well as on three public datasets, including KITTI road, CityScapes, and ORFD, demonstrate that RoadFormer outperforms all other state-of-the-art networks for road scene parsing. Specifically, RoadFormer ranks first on the KITTI road benchmark. Our source code, created dataset, and demo video are publicly available at ***/RoadFormer. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Drug–target interactions prediction based on similarity graph features extraction and deep learning

引用

Neural Computing and Applications 2025年第6期37卷 4303-4322页

作者： Torkey, Hanaa El-Behery, Heba Attia, Abdel-Fattah El-Fishawy, Nawal Computer Science and Engineering Department Faculty of Electronic Engineering Menoufia University Menouf Egypt Department of Computer Science and Engineering Faculty of Engineering Kafrelsheikh University Kafrelsheikh Egypt Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia

Identifying drug–target interactions (DTIs) is a critical step in both drug repositioning. The labor-intensive, time-consuming, and costly nature of classic DTI laboratory studies makes it imperative to create efficient computer algorithms to forecast possible DTIs. However, current computational approaches that predict potential drug–target interactions (DTIs) suffer from some limitations, like finding the best similarity measures or negative samples, and thus require substantial performance improvement. This study proposes an integrated approach based on feature representation and deep learning to predict DTIs. We extract the relevant features of drugs and proteins from heterogeneous networks using graph mining techniques. The proposed approach constructs a heterogeneous graph from the known drug–protein interactions, protein–protein, and drug–drug similarities. Then applying two feature extraction techniques to extract the features, then utilizing these features in training a deep learning model to predict the potential DTIs. Also, a novel algorithm is proposed to find the negative samples based on the drug and protein similarity matrices. Four Benchmark datasets are used to evaluate the proposed approach. Our approach achieves the highest AUC (area under the ROC curve) across all datasets (0.98) with around 2% increases over the existing methods. Experimental results demonstrate that our proposed approach outperforms the baseline methods in predicting DTI, and our negative sample-identifying algorithm could be established as a competitive solution. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Reversible data hiding in encrypted images with block-based bit-plane reallocation

引用

Multimedia Tools and Applications 2024年第37期83卷 84911-84932页

作者： Liu, Li Chen, Chaofan Wu, Yingchun Chang, Chin-Chen Wang, Anhong College of Electronic Information and Engineering Taiyuan University of Science and Technology Taiyuan030024 China Department of Information Engineering and Computer Science Feng Chia University Taichung40724 Taiwan

As cloud storage and multimedia communication continue to evolve, the preservation of image privacy is becoming increasingly important. Reversible data hiding in encrypted images (RDHEI) is an effective method for enhancing the protection of personal privacy. To improve the embedding capacity, this paper introduces a novel scheme for RDHEI using block-based bit-plane reallocation. First, an effective optimized prediction method is utilized to predict the value of each pixel, followed by the calculation of prediction errors (PEs). Then, block-based bit-planes of PEs are extracted, and ten different bit-plane types are categorized to facilitate bit-plane reallocation, thereby freeing up redundant space. Finally, an adaptive encryption procedure is employed to encrypt the reallocated bit-plane, excluding the flag-bits. Experimental results demonstrate that the proposed scheme achieves average embedding rates (ER) of 3.584 bpp, 3.501 bpp, and 2.985 bpp on the three experimental datasets, all of which are higher than those of other state-of-the-art RDHEI schemes while ensuring both reversibility and security. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Dynamic Productivity Prediction and New Production Feature Selection Methods for Advanced Planning Scheduling

引用

Journal of information science and engineering 2024年第2期40卷 341-357页

作者： Tsai, Ming-Fong Li, Wei-Tse Chen, Lien-Wu Department of Electronic Engineering National United University Miaoli360302 Taiwan Department of Information Engineering and Computer Science Feng Chia University Taichung40724 Taiwan

Smart manufacturing is an important research field that is associated with production planning and scheduling, the Internet of Things and artificial intelligence technologies. Production lines use advanced planning and scheduling systems for production operations, time forecasting and planning;integrated manufacturing execution systems are used to collect real-time production information via the Internet of Things to strengthen scheduling control;and artificial intelligence machine learning technology is used to perform predictive maintenance to achieve high-accuracy planning and scheduling. Advanced planning and scheduling systems use genetic algorithms for planning with the aim of increasing speed and accuracy, and the integration of real-time production information from manufacturing execution systems and dynamic adjustments to shift planning are important issues in smart manufacturing. A traditional cyber-physical system integrates historical and real-time production information and carries out a machine learning analysis to improve the production scheduling efficiency, but the prediction of production times for new product orders is a topic that needs further research. This paper proposes new methods of dynamic productivity prediction and new production feature selection, with the aim of improving the performance of advanced planning and scheduling systems. A genetic ant colony algorithm is used to predict dynamic productivity based on real-time production information, to reduce the error between production time plans and actual operations. Historical production information is analysed, and the best correlation coefficient is used in new production feature selection, in order to reduce the discrepancy between production productivity forecasts and actual results. Our proposed dynamic productivity prediction method can reduce the error by at least 1.5% compared with other schemes in the literature, while the proposed production feature selection method can reduce

关键词： Forecasting

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：