检索结果-内蒙古大学图书馆

Meter Location System Base on Jetson NX 1

7th International Conference on Smart computing and Communication, SmartCom 2022

作者： Yang, Chengjun zhou, Ling Yang, Ce Hechi University Guangxi Hechi China School of Computer Science and Engineering Hunan University of Science and Technology Hunan Xiangtan China Hunan Key Laboratory for Service computing and Novel Software Technology Xiangtan China

ISBN: (数字)9783031281242

ISBN: (纸本)9783031281235

Analog meter is still widely used due to their mechanical stability and electromagnetic impedance. Relying on humans to read mechanical meters in some industrial scenarios is time-consuming or dangerous, it is difficult for current meter reading robots to operate quickly and maintain high accuracy in edge computing devices. Computer vision-based meter reading systems can solve such dilemmas. We designed an SSD network-based meter image acquisition system that can run in real time in an NVIDIA Jetson NX development board. Moreover, the model can quickly classify meter types and locate meter coordinates in the presence of light changes, complex backgrounds, and camera angle deflection. Tested on NVIDIA Jetson NX using TensorRT acceleration, the inference speed and accuracy reached 9.238 FPS and 53.95 mAP, respectively. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Prompting Continual Person Search 24

Prompting Continual Person Search

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhang, Pengcheng Yu, Xiaohan Bai, Xiao Zheng, Jin Ning, Xin School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Jiangxi Research Institute Beihang University Beijing China School of Computing Macquarie University Sydney Australia Institute of Semiconductors Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400706868

The development of person search techniques has been greatly promoted in recent years for its superior practicality and challenging goals. Despite their significant progress, existing person search models still lack the ability to continually learn from increasing real-world data and adaptively process input from different domains. To this end, this work introduces the continual person search task that sequentially learns on multiple domains and then performs person search on all seen domains. This requires balancing the stability and plasticity of the model to continually learn new knowledge without catastrophic forgetting. For this, we propose a Prompt-based Continual Person Search (PoPS) model in this paper. First, we design a compositional person search transformer to construct an effective pre-trained transformer without exhaustive pre-training from scratch on large-scale person search data. This serves as the fundamental for prompt-based continual learning. On top of that, we design a domain incremental prompt pool with a diverse attribute matching module. For each domain, we independently learn a set of prompts to encode the domain-oriented knowledge. Meanwhile, we jointly learn a group of diverse attribute projections and prototype embeddings to capture discriminative domain attributes. By matching an input image with the learned attributes across domains, the learned prompts can be properly selected for model inference. Extensive experiments are conducted to validate the proposed method for continual person search. The source code is available at https://***/PatrickZad/PoPS. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning 27

Video2Reward: Generating Reward Function from Videos for Leg...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Zeng, Runhao Zhou, Dingjie Liang, Qiwei Liu, Junlin Li, Hui Huang, Changxin Li, Jianqiang Hu, Xiping Sun, Fuchun Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9781643685489

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running. © 2024 The Authors.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Hybrid Parallel Inference for Large Model on Heterogeneous Clusters for High Throughput 29

Hybrid Parallel Inference for Large Model on Heterogeneous C...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Xu, Chaonong Kong, Weiming Liu, Min Zhang, Mingming Li, Chao Gong, Luqi Beijing Key Lab of Petroleum Data Mining Beijing China Institute of Intelligent Computing Zhejiang Lab Hangzhou China Bupt School of Computer Science National Pilot Software Engineering School Beijing China

ISBN: (纸本)9798350330717

In high-throughput intelligent computing scenarios, multi-device parallelism strategies based on data parallelism or pipeline parallelism have been extensively utilized to accelerate large deep neural network model inference. Data parallelism offers nearly linear improvement in inference speed, but it is limited by the memory capacity of a single device which constrains the model size. On the other hand, pipeline parallelism can support larger models, but the total communication of the activations among devices is high, which limits the improvement of the inference speed. To address the demand for efficient model inference in high-throughput heterogeneous scenarios, we proposes a hybrid parallelism strategy that combines data parallelism and pipeline parallelism. The strategy involves grouping heterogeneous device clusters and then employing inter-group data parallelism along with intra-group pipeline parallelism. Moreover, we propose an algorithm to find an optimal hybrid parallel inference strategy with maximum throughput. The control variables of the strategy includes the number of groups, group-device assignments and model partition ratios. Our experimental evaluation demonstrates that compared to PipeEdge, a pipeline parallel inference framework for heterogeneous cluster, our strategy can achieve 1.7× -3.4× acceleration in an 8-device heterogeneous cluster without loss of accuracy. © 2023 IEEE.

关键词： data parallelism heterogeneous cluster hybrid parallelism model inference pipeline parallelism

来源：评论

学校读者我要写书评

暂无评论

Wireless and Service Allocation for Mobile Computation Offloading with Task Deadlines

arXiv

引用

arXiv 2023年

作者： Chen, Hong Todd, Terence D. Zhao, Dongmei Karakostas, George Department of Electrical and Computer Engineering Department of Computing and Software McMaster University HamiltonON Canada

In mobile computation offloading (MCO), mobile devices (MDs) can choose to either execute tasks locally or to have them executed on a remote edge server (ES). This paper addresses the problem of assigning both the wireless communication bandwidth needed, along with the ES capacity that is used for the task execution, so that task completion time constraints are satisfied. The objective is to obtain these allocations so that the average power consumption of the mobile devices is minimized, subject to a cost budget constraint. The paper includes contributions for both soft and hard task completion deadline constraints. The problems are first formulated as mixed integer nonlinear programs (MINLPs). Approximate solutions are then obtained by decomposing the problems into a collection of convex subproblems that can be efficiently solved. Results are presented that demonstrate the quality of the proposed solutions, which can achieve near optimum performance over a wide range of system parameters. Copyright © 2023, The Authors. All rights reserved.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

A Survey on Task Partitioning and Scheduling for Vehicular Edge computing 10

A Survey on Task Partitioning and Scheduling for Vehicular E...

引用

10th IEEE International Conference on Cyber Security and Cloud computing and 9th IEEE International Conference on Edge computing and Scalable Cloud, CSCloud-EdgeCom 2023

作者： Huang, Jing Wu, Wenyu Huang, Weihong Xiao, Yufeng Lisi, Li Sun, Jinxi Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology School of Computer Science and Engineering Xiangtan411201 China The Bilingual Experimental School HNSDFZ Changsha410006 China

ISBN: (纸本)9798350312461

Vehicle edge computing (VEC) has become an important research field in recent years. In VEC, computation offloading moves computationally intensive tasks from resource-constrained devices to the network edge, it provides service closer to the end-users. By processing tasks with abundant idle resources at the network edge, low-latency demands for some tasks can be met. However, the mobility and uncertainty of vehicles pose significant challenges to vehicle computation offloading. This paper focuses on the decision-making process of vehicle computation offloading, specifically task partitioning and scheduling decisions. This paper summarizes some hot problems and solutions, including latency optimization, reliability optimization, energy efficiency optimization, cost optimization, and mobility support. This study will help researchers discover important features of vehicle computation offloading and find the most suitable scheme to solve the vehicle offloading problem in different scenarios. © 2023 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Energy-saving Processors Two-phases Frequency Reduction Algorithm on Heterogeneous Embedded Systems 10

Energy-saving Processors Two-phases Frequency Reduction Algo...

引用

10th IEEE International Conference on Cyber Security and Cloud computing and 9th IEEE International Conference on Edge computing and Scalable Cloud, CSCloud-EdgeCom 2023

作者： Huang, Weihong Jiang, Kuan Huang, Jing Lisi, Li Xiao, Yufeng Deng, Zihao Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology School of Computer Science and Engineering Xiangtan411201 China The Bilingual Experimental School HNSDFZ Changsha410006 China

ISBN: (纸本)9798350312461

Energy saving has become a key issue for heterogeneous embedded systems. Previous energy-saving methods attempt to minimize the energy consumption of applications in heterogeneous embedded systems subject to deadline constraints by reducing the processor frequency. However, good scheduling strategy can also minimize energy consumption to some extent. This paper proposes a novel energy-saving scheduling algorithm, called the Energy-saving Processors Two-phases Frequency Reduction (EPTFR) Algorithm. In the first stage, within the deadline constraints, the maximum working frequency of each processor is reasonably and synchronously reduced;in the second phase, when running sub-applications on the processor, under the constraints of the earliest start time and latest end time of sub-applications, the actual operating frequency of the processor is reasonably reduced. Finally, the effectiveness of the EPTFR algorithm is verified through numerical experiments, and the results show that the proposed EPTFR algorithm can achieve a significant energy-saving effect. © 2023 IEEE.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Computer Vision Bound Fall Detection for Elderly People

Deep Learning Based Computer Vision Bound Fall Detection for...

引用

Student Conference on Research and Development (SCOReD)

作者： Mohamed Abdallah Abdoul-Halim Sivakumar Vengusamy Faculty of Computing Engineering & Technology School of Computing Science & Software Asia Pacific University of Technology & Innovation Kuala Lumpur Malaysia

ISBN: (数字)9798350318821

ISBN: (纸本)9798350318838

Due to the devastating effects, such as increased mortality and morbidity, falls among the elderly are a significant health issue globally. Supporting the elderly in their daily activities is a significant problem for society because they are the age group with the largest rate of population growth. An automated fall detection system has gained popularity in the healthcare sector due to the social and financial benefits it offers. Vision-based fall detection systems have a great promise now that Smart Homes are a growing trend and there are more cameras in our everyday environments. An autonomous real-time fall detection system based on vision is given in this paper. In this research, we suggested a 3D RGB camera-based method for fall detection. Machine learning algorithms, which were trained on characteristics retrieved by a deep learning-based computer vision algorithm, are used to distinguish between occlusion, falling, and routine everyday activities. Deep learning algorithms are used to identify people in videos. Two datasets—one developed locally and the other made public—were used for the experimental validation of the suggested methodology. Several assessment metrics are computed for evaluation. This analysis demonstrated the efficacy of the suggested solution. Temporal characteristics in a video series are captured using motion history images, and spatial features are then effectively retrieved for classification using a depth-wise convolutional neural network.

关键词： Deep learning Computer vision Machine learning algorithms Feature extraction Real-time systems History Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Automated Tool for Student Journey Orchestration & Optimization using Machine Learning 4

An Automated Tool for Student Journey Orchestration & Optimi...

引用

4th International Conference on Advancements in computing, ICAC 2022

作者： Ramanayaka, D.Y. Liyanagunawardana, A.P. Ekanayake, E.M.T.K.B. Weerarathna, U.U. Jayasingha, Thilini Buddhika Thilakarthna, Thusithanjana Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350398090

The customer journey is a full interaction that a customer has with a business. Every touchpoint of the business is an opportunity to provide good experiences that encourage future opportunities to become customers and consumers to be committed loyal customers through the customer journey. This research paper refers to the student's journey at university as a customer journey & considers the student's actions to map the next suitable actions. This paper proposed a machine learning-based novel approach to recommending the suitable next best action for the students based on their past performance at university by using customer journey orchestration and optimization. Customer journey orchestration is the process of coordinating customer experiences in real-time to encourage better engagement with the systems and organization. The journey orchestration of university students is currently a manual flow. The main goal of this research is to convert the manual flow of university journey orchestration into an automated flow. The proposed system orchestrates and optimizes the student journeys at each milestone of the university by recommending the suitable path or next best action as the outcome to help students make a successful path throughout their university journey. This research contributes to achieving the educational goals and professional career goals of university students successfully. Furthermore, from the perspective of the university, this proposed system supports everything to facilitate better directions for the students to complete their studies successfully. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Residential Electricity Power Forecasting using GRU-based CNN and SAE Ensembler

Residential Electricity Power Forecasting using GRU-based CN...

引用

2023 IEEE International Conference on Emerging Trends in engineering, Sciences and Technology, ICES and T 2023

作者： Raza, Ali Ali, Usman Ali, Zain Saeed, Muhammad Hamza Khan, Raja Jalees Ul Hussen Ayub, Nasir COMSATS University Islamabad Department of Computer Science WahCantt Campus Pakistan Riphah International University Computing Department Faisalabad Pakistan HITEC University Department of Electrical Engineering Taxila Pakistan National Textile University Department of Computer Science Faisalabad Pakistan Superior University Gold Campus Department of Software Engineering Lahore Pakistan Capital University of Science and Technology Department of Software Engineering Islamabad Pakistan

ISBN: (纸本)9781665455602

Smart grids play an important role to resolves issues related to electricity. Electrical load forecasting can be performed through smart grids to acquire knowledge about the electrical load that will be needed in the future. A combination of Stacked Autoencoding (SAE) and Gated Recurrent Unit (GRU) and a combination of Convolutional Neural Network (CNN), Grey Wolf Optimization (GWO), and GRU are proposed in this paper. Firstly, the historical load data is preprocessed and then preprocessed data is given to the feature selection and extraction methods to measure the importance of each feature. Features that have highest values are selected and input to the proposed classifiers. According to the results the proposed CNN-GRU-GWO gave the highest accuracy rate of 96.31%. This application of this article will help the utility purchase the exact amount of electricity from the grid, which will lead to grid stability. © 2023 IEEE.

关键词： Smart power grids

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：