检索结果-内蒙古大学图书馆

International Conference on Communications, Information System and computer engineering (CISCE)

作者： Bo Dang Wenchao Zhao Yufeng Li Danqing Ma Qixuan Yu Elly Yijun Zhu Computer Science San Francisco Bay University Fremont CA US School of Software Engineering University of Science and Technology of China Hefei Anhui China School of Electronics and Computer Science University of Southampton Southampton UK Computer Science Stevens Institute of Technology Hoboken NJ US College of Computing Georgia Institute of Technology Atlanta GA US

ISBN: (数字)9798350353174

ISBN: (纸本)9798350353181

The prevalence of mobile technology offers unique opportunities for addressing healthcare challenges, especially for individuals with visual impairments. This paper explores the development and implementation of a deep learning-based mobile application designed to assist blind and visually impaired individuals in real-time pill identification. Utilizing the YOLO framework, the application aims to accurately recognize and differentiate between various pill types through real-time image processing on mobile devices. The system incorporates Text-to-Speech (TTS) to provide immediate auditory feedback, enhancing usability and independence for visually impaired users. Our study evaluates the application's effectiveness in terms of detection accuracy and user experience, highlighting its potential to improve medication management and safety among the visually impaired community.

关键词： Deep learning YOLO Computational modeling Visual impairment Medical services Real-time systems User experience

来源：评论

学校读者我要写书评

暂无评论

Difficulty-Aware Data Augmentor for Scene Text Recognition

Difficulty-Aware Data Augmentor for Scene Text Recognition

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Guanghao Meng Tao Dai Bin Chen Naiqi Li Yong Jiang Shu-Tao Xia Tsinghua Shenzhen International Graduate School Tsinghua University Peng Cheng Laboratory Shenzhen China College of Computer Science and Software Engineering Shenzhen University Department of Computer Science and Technology Harbin Institute of Technology Shenzhen

Deep neural network (DNN) based scene text recognition (STR) methods usually require a large amount of annotated data for training, which is time-consuming and cost-expensive in practice. To address this issue, many data augmentation methods have been developed to train recognizers by improving the diversity of training samples. However, most existing methods neglect the difficulty inherent in samples, and easily suffer from the problem of over-diversity, i.e., the distribution of the augmented data significantly deviates from that of clean data. In this paper, we propose a novel difficulty-aware data augmentation framework for scene text recognition, which jointly considers the difficulty of samples and the strength of augmentations. Specifically, our framework first predicts the sample difficulty, followed by an adaptive data augmentation strategy. Furthermore, we build a more diverse set of augmentation methods for STR and integrate it into our augmentation framework. Extensive experiments on scene text recognition benchmarks show that our augmentation framework significantly improves the performance of recognizers.

关键词： Training Measurement Deep learning Text recognition Neural networks Speech recognition Signal processing

来源：评论

学校读者我要写书评

暂无评论

RAT: A Refactoring-Aware Traceability Model for Bug Localization

RAT: A Refactoring-Aware Traceability Model for Bug Localiza...

引用

International Conference on software engineering (ICSE)

作者： Feifei Niu Wesley K. G. Assunção LiGuo Huang Christoph Mayr-Dorn Jidong Ge Bin Luo Alexander Egyed State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Institute for Software Systems Engineering Johannes Kepler University Linz Austria Department of Computer Science and Engineering Southern Methodist University Dallas Texas USA

A large number of bug reports are created during the evolution of a software system. Locating the source code files that need to be changed in order to fix these bugs is a challenging task. Information retrieval-based bug localization techniques do so by correlating bug reports with historical information about the source code (e.g., previously resolved bug reports, commit logs). These techniques have shown to be efficient and easy to use. However, one flaw that is nearly omnipresent in all these techniques is that they ignore code refactorings. Code refactorings are common during software system evolution, but from the perspective of typical version control systems, they break the code history. For example, a class when renamed then appears as two separate classes with separate histories. Obviously, this is a problem that affects any technique that leverages code history. This paper proposes a refactoring-aware traceability model to keep track of the code evolution history. With this model, we reconstruct the code history by analyzing the impact of code refactorings to correctly stitch together what would otherwise be a fragmented history. To demonstrate that a refactoring aware history is indeed beneficial, we investigated three widely adopted bug localization techniques that make use of code history, which are important components in existing approaches. Our evaluation on 11 open source projects shows that taking code refactorings into account significantly improves the results of these bug localization techniques without significant changes to the techniques themselves. The more refactorings are used in a project, the stronger the benefit we observed. Based on our findings, we believe that much of the state of the art leveraging code history should benefit from our work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An efficient ROS package searching approach powered by knowledge graph 33

An efficient ROS package searching approach powered by knowl...

引用

33rd International Conference on software engineering and Knowledge engineering, SEKE 2021

作者： Chen, Long Mao, Xinjun Zhang, Yinyuan Yang, Shuo Wang, Shuo College of Computer National University of Defense Technology Changsha China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha China

ISBN: (纸本)1891706527

Over the past several years, the Robot Operating System (ROS), has grown from a small research project into the most popular framework for robotics development. It offers a core set of software for operating robots that can be extended by creating or using existing packages, making it possible to program robotic software that can be reused on different hardware platforms. With thousands of packages available per stable distribution, encapsulating algorithms, sensor drivers, etc., it is the de facto middleware for robotics. However, finding the proper ROS package is a nontrivial task because ROS packages involve different functions and even with the same function, there are different ROS packages for different tasks. So it is time-consuming for developers to find suitable ROS packages for given task, especially for newcomers. To tackle this challenge, we build a ROS package knowledge graph, ROSKG, including the basic information of ROS packages and ROS package characteristics extracted from text descriptions, to comprehensively and precisely characterize ROS packages. Based on ROSKG, we support ROS packages search with specific task description or attributes as input. A comprehensive evaluation of ROSKG shows the high accuracy of our knowledge construction approach. A user study shows that ROSKG is promising in helping developers find suitable ROS packages for robotics software development tasks. © 2021 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

PVBF: A Framework for Mitigating Parameter Variation Imbalance in Online Continual Learning

arXiv

引用

arXiv 2025年

作者： Tao, Zelin Deng, Hao Liu, Mingqing Zhang, Lijun Zhao, Shengjie School of Computer Science and Technology Tongji University Shanghai201804 China College of Electronic and Information Engineering Tongji University Shanghai201804 China National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai201804 China

Online continual learning (OCL), which enables AI systems to adaptively learn from non-stationary data streams, is commonly achieved using experience replay (ER)-based methods that retain knowledge by replaying stored past during training. However, these methods face challenges of prediction bias, stemming from deviations in parameter update directions during task transitions. This paper identifies parameter variation imbalance as a critical factor contributing to prediction bias in ER-based OCL. Specifically, using the proposed parameter variation evaluation method, we highlight two types of imbalance: correlation-induced imbalance, where certain parameters are disproportionately updated across tasks, and layer-wise imbalance, where output layer parameters update faster than those in preceding layers. To mitigate the above imbalances, we propose the Parameter Variation Balancing Framework (PVBF), which incorporates: 1) a novel method to compute parameter correlations with previous tasks based on parameter variations, 2) an encourage-and-consolidate (E&C) method utilizing parameter correlations to perform gradient adjustments across all parameters during training, 3) a dual-layer copy weights with reinit (D-CWR) strategy to slowly update output layer parameters for frequently occuring sample categories. Experiments on short and long task sequences demonstrate that PVBF significantly reduces prediction bias and improves OCL performance, achieving up to 47% higher accuracy compared to existing ER-based methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

EMGSense: A Low-Effort Self-Supervised Domain Adaptation Framework for EMG Sensing

EMGSense: A Low-Effort Self-Supervised Domain Adaptation Fra...

引用

IEEE International Conference on Pervasive Computing and Communications (PerCom)

作者： Di Duan Huanqi Yang Guohao Lan Tianxing Li Xiaohua Jia Weitao Xu City University of Hong Kong Shenzhen Research Institute Department of Computer Science City University of Hong Kong Department of Software Technology Delft University of Technology Department of Computer Science and Engineering Michigan State University

This paper presents EMGSense, a low-effort self-supervised domain adaptation framework for sensing applications based on Electromyography (EMG). EMGSense addresses one of the fundamental challenges in EMG cross-user sensing—the significant performance degradation caused by time-varying biological heterogeneity—in a low-effort (data-efficient and label-free) manner. To alleviate the burden of data collection and avoid labor-intensive data annotation, we propose two EMG-specific data augmentation methods to simulate the EMG signals generated in various conditions and scope the exploration in label-free scenarios. We model combating biological heterogeneity-caused performance degradation as a multi-source domain adaptation problem that can learn from the diversity among source users to eliminate EMG heterogeneous biological features. To relearn the target-user-specific biological features from the unlabeled data, we integrate advanced self-supervised techniques into a carefully designed deep neural network (DNN) structure. The DNN structure can seamlessly perform two training stages that complement each other to adapt to a new user with satisfactory performance. Comprehensive evaluations on two sizable datasets collected from 13 participants indicate that EMGSense achieves an average accuracy of 91.9% and 81.2% in gesture recognition and activity recognition, respectively. EMGSense outperforms the state-of-the-art EMG-oriented domain adaptation approaches by 12.5%-17.4% and achieves a comparable performance with the one trained in a supervised learning manner.

关键词： Degradation Training Pervasive computing Deep learning Supervised learning Neural networks Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

A multi-channel optical sensing system based on back propagation neural network for mixed ion solution

引用

Optik 2023年 291卷

作者： Hou, Junyong Peng, Jin Liu, Kunlin Liang, Zhongren Yao, Junmei Li, Jie Tang, Tingting School of Sciences Southwest Petroleum University Chengdu610500 China College of Optoelectronic Engineering Chengdu University of Information Technology Chengdu610225 China College of Computer Science and Software Engineering Shenzhen University China

As one of the mainstream sensing methods in the field, optical sensing has the characteristics of non-contact, anti-interference and fast transmission. The combination of multi-channel sensing and optical detection technology can realize multi-dimensional and multi-parameter detection in real-time. In this paper, we propose a portable multi-channel optical sensing system with compact structure, low cost, low detection limit and strong anti-interference ability for the detection of heavy metal concentration in water environment. A detection system based on back propagation neural network is designed, and a series of algorithms and related optical paths are used to achieve online simultaneous detection and calculation of different ion concentrations in mixed solutions. The neural network algorithm is introduced in the system to reduce the error, and improves the detection efficiency of mixed ion concentration, and further improves the detection performance of the system. It has unique advantages in the field of concentration measurement for mixed ion solutions. © 2023

关键词： Heavy metals

来源：评论

学校读者我要写书评

暂无评论

Development of a Prediction System for Criminality and Suicidal in Sri Lanka

Development of a Prediction System for Criminality and Suici...

引用

Advancements in Computing (ICAC), International Conference on

作者： D.P.D. Ranasinghe R.D.T.S. Fernando D.G. Girambe D.M.H.K.D. Arambegama Bhagyanie Chathurika Dulani Jayasinghe Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Information Technology Sri Lanka Institute of Information Technology Malabe Sri Lanka

This research confronts the growing challenges of rising suicide rates and crime in Sri Lanka through a dual approach, harnessing advanced machine learning and time series analysis. The innovative methodology, merging “Feature Importance Weighting and Ensemble of Diverse Trees with the Random Forest Regressor,” achieves impressive accuracy of 93% for factors and 94% for methods. Additionally, the accuracy rates of 94% for education and 93% for occupationbased predictions enhance this comprehensive approach, offering a profound understanding of suicidal incidents and enabling precise prevention strategies. Simultaneously this study employs an ensemble of AutoRegressive Integrated Moving Average (ARIMA) models for crime prediction. This approach consistently attains high accuracy, often surpassing 90%, such as 96% and 97%. Utilizing multiple models enhances predictive accuracy and hotspot identification, granting law enforcement and policymakers flexibility to address enduring yearly hotspots and evolving dynamic hotspots. This research bridges the comprehension of suicide and crime dynamics in Sri Lanka, providing invaluable insights for evidence-based policies and targeted interventions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling Thermal Sensation Prediction Using Random Forest Classifier 7th

Modeling Thermal Sensation Prediction Using Random Forest Cl...

引用

7th International Conference on Life System Modeling and Simulation, LSMS 2021, and the 7th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2021

作者： Jin, Linyi Liu, Tingzhang Ma, Jing School of Mechatronic Engineering and Automation Shanghai University Shanghai Shanghai China Department of Computer Science and Software Engineering Auckland University of Technology Auckland New Zealand

ISBN: (纸本)9789811672125

Indoor thermal comfort has been getting more attention while in growing demand. To achieve the optimal coordination of energy consumption and resident comfort, thermal sensation predition models are needed to guide HVAC (heating, ventilation and air conditioning) settings. This article is to develop a new thermal sensation vote (TSV) prediction model using random forest classifier, and experiments are carried out in data preprocessing, feature engineering, hyperparameter selection, training ratio and other aspects to improve the performance of the prediction model. After optimization, the final accuracy of prediction model reaches 67.1% for 7-point TSV, 72.7% for 5-point TSV and 98.6% for 3-point TSV. Compared with similar experiments conducted on ASHRAE PR-884, the model developed in this article has promising results, which proves the effectiveness of the optimization methods. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Leveraging artificial intelligence of things for anomaly detection in advanced metering infrastructures 2

Leveraging artificial intelligence of things for anomaly det...

引用

2nd IEEE International Conference on Cyberspace, CYBER NIGERIA 2020

作者： Ogu, Reginald E. Ikerionwu, Charles I. Ayogu, Ikechukwu I. Dept. of Software Engineering Federal University of Technology Owerri Owerri Nigeria Dept. of Computer Science Federal University of Technology Owerri Owerri Nigeria

ISBN: (纸本)9781665444095

The integration of more sensory and actuation components to the Smart Grid produces high volume of data. Consequently, this big data stretches the transmission, processing, and storage capabilities of the Smart Grid infrastructures. The vulnerability of advanced metering infrastructures (AMIs) is on the rise, as more devices are connected to the Internet these days. The aforementioned realities have continued to necessitate a debate on the future of cloud-centered artificial intelligence (AI) services for latency-sensitive user-centric IoT applications. It is rapidly becoming necessary to leverage on the applicability of EdgeAI directly on IoT sensory nodes involved in energy metering. This paper proposes the applicability of Artificial Intelligence situated on smart meter, to perform micro analytics at the edge of AMI networks: Artificial Intelligence of Things. Therefore, a functional AMI model based on IoT and EdgeAI is presented herein. Additionally, an integration architecture for the anticipated Smart Grid based on IoT and EdgeAI is presented. On implementation, the proposed model would provide high performance analytics and Edge computing capabilities to enable AMIs initiate instant data check at the source and relay relevant real-time data to the Utility through the Internet. © 2021 IEEE.

关键词： Energy utilization

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：