检索结果-内蒙古大学图书馆

proceedings of the 2019 8th international conference on Networks, Communication and computing

作者： Muhammad Fayyaz Cao Bin Waleed Almughalles Yun Li Liaqat Ali Key Lab of Mobile Communication Technology Chongqing University of Posts and Telecommunications

ISBN: (纸本)9781450377027

Computation-intensive applications can be enabled by mobile edge computing (MEC) in 5G networks because MEC carries cloud computing almost near to smart devices. In this paper, we study a multi-user MEC system, where several smart devices (SDs) can fulfill computation offloading over wireless channels to a MEC server. we study the minimization of a total sum cost which is energy consumption and time delay for all the smart devices (where smart devices can choose one out of three scenarios to execute the task, i.e., full local computing scenario, full offloading execution scenario, and partial offloading execution scenario) as our objective function optimization. We mutually optimize task partition, offloading decision and computation resource sharing to reduce the total cost of the MEC system. We used an extensive search method and Lagrange method to solve these problems. Statistical results prove the effectiveness of our proposed scheme.

关键词： computation offloading computing mode Mobile edge computing execution scenario task partition

来源：评论

学校读者我要写书评

暂无评论

A multi-feature selection approach for gender identification of handwriting based on kernel mutual information

引用

pattern recognition LETTERS 2019年第Apr.期121卷 123-132页

作者： Bi, Ning Suen, Ching Y. Nobile, Nicola Tan, Jun Sun Yat Sen Univ Guangzhou 510275 Guangdong Peoples R China Concordia Univ Montreal PQ H3G 1M8 Canada

this paper presents a new flexible approach to predict the gender of the writers from their handwriting samples. Handwriting features like slant, curvature, line separation, chain code, character shapes, and more, can be extracted from different methods. therefore, the multi-feature sets are irrelevant and redundant. the conflict of the features exists in the sets, which affects the accuracy of classification and the computing cost. this paper proposes an approach, named kernel mutual information (KMI), that focuses on feature selection. the KMI approach can decrease redundancies and conflicts. In addition, it extracts an optimal subset of features from the writing samples produced by male and female writers. To ensure that KMI can apply the various features, this paper describes the handwriting segmentation and handwritten text recognition technology used. the classification is carried out using a Support Vector Machine (SVM) on two databases. the first database comes from the ICDAR 2013 competition on gender prediction, which provides the samples in both Arabic and English. the other database contains the Registration-Document-Form (RDF) database in Chinese. the proposed and compared methods were evaluated on both databases. Results from the methods highlight the importance of feature selection for gender prediction from handwriting. (c) 2018 Elsevier B.V. All rights reserved.

关键词： Gender prediction Feature selection Kernel method Classification Handwriting Machine learning

来源：评论

学校读者我要写书评

暂无评论

Human Posture recognition using Artificial Neural Networks 8

Human Posture Recognition using Artificial Neural Networks

引用

IEEE 8th international Advance computing conference (IACC)

作者： Kale, Hrishikesh Mandke, Prathamesh Mahajan, Hrishikesh Deshpande, Vedant COEP Dept Elect & Telecommun Engn Pune Maharashtra India

ISBN: (纸本)9781538666784

this paper proposes the use of artificial neural networks(ANNs) to classify human postures, using an invasive(intrusive) approach, into 6 categories namely standing, sitting, sleeping and bending - forward and backward. Human posture recognition has numerous applications in the field of healthcare analysis like patient monitoring, lifestyle analysis, elderly care etc. Most importantly, our solution is capable of classifying the aforementioned postures in real-time, by wirelessly(Wi-Fi) acquiring and processing the sensor data on a Raspberry-Pi device with minimal lag. A data-set of 44,800 samples was collected - from 3 subjects - which was used to train and test the neural *** experimenting and testing with a plethora of network architectures, an optimal neural network architecture(6-9-6) with suitable hyper-parameters was determined which gave an overall accuracy of 97.589%.

关键词： pattern-recognition neural-networks posture-recognition wearable-sensors accelerometers embedded systems real time movement classification sensor positioning

来源：评论

学校读者我要写书评

暂无评论

Experimental analysis of MPTCp congestion control algorithms;Lia, olia and Balia 4

Experimental analysis of MPTCp congestion control algorithms...

引用

4th international conference on Big Data Analytics, Data Mining and Computational Intelligence 2019, BigDaCI 2019 and the 8th international conference on theory and Practice in Modern computing 2019, TPMC 2019

作者： Kato, Toshihiko Diwakar, Adhikari Yamamoto, Ryo Ohzahata, Satoshi Suzuki, Nobuo University of Electro-Communications 1-5-1 Chofugaoka Chofu Tokyo182-8585 Japan Advanced Telecommunication Research Institute International 2-2-2 Hikaridai Seika-cho Sorakugun Kyoto619-0288 Japan Kindai University 11-6 Kashiwa-no-mori Iizuka Fukuoka820-0011 Japan

ISBN: (纸本)9789898533920

In Multipath TCP (MPTCP), the congestion control is realized by individual subflows (conventional TCP connections). However, there is some concern that the total data sending rate becomes too high compared with other single path TCPs if the associated subflows increase their own congestion windows independently. So, a coupled increase scheme of congestion windows, called Linked Increase Adaptation (LIA), is adopted as a standard congestion control algorithm for subflows comprising a MPTCP connection. But this algorithm supposes that TCP connections use Additive Increase and Multiplicative Decrease (AIMD) based congestion control, and if high speed algorithms such as CUBIC TCP are used, the throughput of MPTCP connections might be decreased. In order to increase the throughput of MPTCP connection, two modified congestion control algorithms, Opportunistic Linked-Increase Algorithm (OLIA) and Balanced Linked Adaptation (BALIA) are also introduced. However, they are still based on AIMD and there is some concern that they are weaker than high speed algorithms. this paper analyzes the performance of MPTCP congestion control algorithms through experiments. Specifically, this paper examines to compare LIA, OLIA or BALIA based MPTCP flow and a single TCP flow with TCP Reno or CUBIC TCP. these experiments show that LIA is weaker than both Reno and CUBIC, and OLIA and BALIA are weaker than CUBIC. © Multi conference on Computer Science and Information Systems, MCCSIS 2019. All rights reserved.

关键词： Transmission control protocol

来源：评论

学校读者我要写书评

暂无评论

ICDAR2019 robust reading challenge on multi-lingual scene text detection and recognition-RRC-MLT-2019 15

ICDAR2019 robust reading challenge on multi-lingual scene te...

引用

15th IAPR international conference on Document Analysis and recognition, ICDAR 2019

作者： Nayef, Nibal Liu, Cheng-Lin Ogier, Jean-Marc Patel, Yash Busta, Michal Chowdhury, Pinaki Nath Karatzas, Dimosthenis Khlif, Wafa Matas, Jiri Pal, Umapada Burie, Jean-Christophe L3i Laboratory University of la Rochelle France Computer Vision Center Universitat Autonoma de Barcelona Spain CVPR Unit Indian Statistical Institute India Robotics Institute Carnegie Mellon Universiry Pittsburgh United States Center for Machine Perception Department of Cybernetics Czech Technical University Prague Czech Republic National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China

ISBN: (纸本)9781728128610

With the growing cosmopolitan culture of modern cities, the need of robust Multi-Lingual scene Text (MLT) detection and recognition systems has never been more immense. With the goal to systematically benchmark and push the state-of-the-art forward, the proposed competition builds on top of the RRC-MLT-2017 with an additional end-to-end task, an additional language in the real images dataset, a large scale multi-lingual synthetic dataset to assist the training, and a baseline End-to-End recognition method. the real dataset consists of 20,000 images containing text from 10 languages. the challenge has 4 tasks covering various aspects of multi-lingual scene text: (a) text detection, (b) cropped word script classification, (c) joint text detection and script classification and (d) end-to-end detection and recognition. In total, the competition received 60 submissions from the research and industrial communities. this paper presents the dataset, the tasks and the findings of the presented RRC-MLT-2019 challenge. © 2019 IEEE.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Detection and Analysis of Periodic Actions for Context-Aware Human Centric Cyber Physical System to Enable Adaptive Occupational therapy 10

Detection and Analysis of Periodic Actions for Context-Aware...

引用

10th IEEE international conference on Intelligent Data Acquisition and Advanced computing Systems - Technology and Applications (IDAACS)

作者： Neshov, Nikolay Manolova, Agata Tonchev, Krasimir Boumbarov, Ognian Tech Univ Sofia Fac Telecommun Blvd Kliment Ohridski 8 Sofia 1796 Bulgaria

ISBN: (纸本)9781728140681

In most of our daily lives, we observe repetitive (periodic) movements of our surrounding objects. In physiotherapy, for example, during the physical exercises, the analysis of the periodicity in the patient's performance would help to evaluate and monitor the his recovery process. Cyber Physical Systems for smart environments have great potential in providing context-aware, automated support in everyday life of people that need adaptive occupational therapy. We present a method and program-based algorithm for the detection and analysis of periodic activities of subjects performing physical exercises from video sequences. the algorithm detects the beginning of a series of exercises of a given type, measures the duration of each of them, detects the end of the sequence and measures the number of repetitions. Experimental results with publicly available video dataset will prove the applicability of the proposed method for detection of repetitive actions.

关键词： Human Action detection Human Action recognition Human Centric Cyber Physical System Occupational therapy

来源：评论

学校读者我要写书评

暂无评论

Solving Machine Part Cell Formation Problem Using Genetic Algorithm Based Evolutionary computing 8th

Solving Machine Part Cell Formation Problem Using Genetic Al...

引用

8th international conference on Soft computing and pattern recognition (SoCPaR) / 8th international conference on Computational Aspects of Social Networks (CASoN)

作者： Sowmiya, N. Valarmathi, B. Gupta, N. Srinivasa VIT Univ Sch Informat Technol & Engn Vellore Tamil Nadu India VIT Univ Sch Informat Technol & Engn Dept Software & Syst Engn Vellore Tamil Nadu India VIT Univ Sch Mech Engn Vellore Tamil Nadu India

ISBN: (纸本)9783319606187;9783319606170

Machine part cell formation is the group technology problem, in which the parts with near similar machining requirements are grouped into part families and the corresponding machines into machine cells. In this paper, a genetic algorithm with a fine tuning procedure is proposed to solve the group technology problem considering only one process plan for each part. the grouping efficacy achieved by the proposed method is comparable to the existing methods in general and better for 11.42% of the datasets.

关键词： Genetic algorithm Clustering Cell formation Cellular manufacturing Grouping efficacy

来源：评论

学校读者我要写书评

暂无评论

Reseeding LFSR for test pattern generation 8

Reseeding LFSR for test pattern generation

引用

8th IEEE international conference on Communication and Signal Processing, ICCSP 2019

作者： Dilip, Patare Snehal Somanathan, Geethu Remadevi Bhakthavatchalu, Ramesh Department of Electronic and Communication Amrita Vishwa Vidyapettham Amritapuri Kollam Kerala India

ISBN: (纸本)9781538675953

Testing of circuits became difficult as the scale of integration is increasing as said in Moore's Law. Conventional testing approach is not sufficient with the growth of device counts and density. Testing helps the developer to investigate faults and error present in developed circuit which helps to reduce time require to test and thus decreases chances of getting failed during operation. Test time is one of the most important parameters in digital circuit testing which effects the overall process of testing. Reducing the test time of the test pattern generation is one of the most effected solution for the process. Reseeding LFSR is one of the methods to generate the test patterns for testing. In this paper, pseudo-random test patterns are generated to test circuit using reseeding LFSR technique. this helps to reduce the test pattern required to be stored for testing. this technique can be applied with the principles which are required for low power as well as low test data volume. Fault coverage of proposed circuit is calculated using ISCAS'89 benchmark circuits. the technique is integrated with the benchmark circuits and comparison is done based on the performance and resource utilization. Proposed model reduces the need for memory to store seed value and the power utilization. Reseeding can mainly be applied for BIST which targets complete fault coverage and minimization of the test length. Data compression for reducing the test pattern required for testing will indirectly reduce the time required to check the circuits. Future work is to reduce time required for the test pattern generation. Hamming distance can be applied to calculate the number of bits changing during the test patterns transition. Hamming distance approach can be implemented to reduce the parameter. © 2019 IEEE.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Applicability of Soft computing and Optimization Algorithms in Software Testing and Metrics - A Brief Review 8th

Applicability of Soft Computing and Optimization Algorithms ...

引用

8th international conference on Soft computing and pattern recognition (SoCPaR) / 8th international conference on Computational Aspects of Social Networks (CASoN)

作者： Sharma, Deepak Chandra, Pravin Guru Gobind Singh Indraprastha Univ Univ Sch Informat & Commun Technol Delhi 110078 India

ISBN: (纸本)9783319606187;9783319606170

In spite of many years of work by scientists and specialists on various software qualities, testing stays one of the most broadly honed and concentrated on methodologies for evaluating and improving software quality. Our objective, in this paper, is to present how optimization techniques provide solutions to different and difficult issues in different areas of software engineering. Optimization algorithms are mathematical procedures, which intends to best optimal results for the defect, fault, failure to accomplish tractability, strength, and low arrangement cost. In this paper, a comprehensive overview of software testing and metrics based on soft computing and optimization techniques is presented. In this survey, we try to explain some major problems like defect prediction, software fault prediction and their solutions by soft computing and optimization algorithms. the paper presents an overview of the usage of Mathematical optimization Algorithms and soft computing approaches.

关键词： Optimization algorithms Soft computing Software testing Metrics Software fault prediction

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Detection of Active, New, and Closed Coal Mines with Reclamation Activity from Landsat 8 OLI/TIRS Images 8th

Unsupervised Detection of Active, New, and Closed Coal Mines...

引用

8th international conference on pattern recognition and Machine Intelligence (PReMI)

作者： Mukherjee, Jit Mukherjee, Jayanta Chakravarty, Debashish Aikat, Subhas Indian Inst Technol Adv Technol Dev Ctr Kharagpur W Bengal India Indian Inst Technol Dept Comp Sci & Engn Kharagpur W Bengal India Indian Inst Technol Dept Min Engn Kharagpur W Bengal India

ISBN: (纸本)9783030348694;9783030348687

Monitoring and classification of surface coal mine regions have several research aspects, as they have huge impacts on the eco-environment of a region. Mining regions change over time immensely. New potential mines get opened. Whereas, few mines stay active and many of them get closed. Closed mine regions are reclaimed to environment through plantation. In the past, semi-supervised and supervised techniques have been used to detect mine classes and assess the changes of land use and land cover classes. In this work, mine regions are detected in an adaptive manner from satellite images unlike the techniques in the literature. Further, a change detection technique is used to detect active, new, and closed surface coal mines in a region. Detected closed mines are further analysed to evaluate reclamation of that region. Average precision and recall of active, new, and closed mining regions of the proposed technique are found to be [84.7%, 62.8%], [74.2%, 64.5%], and [70.1%, 58.2%], respectively.

关键词： Clay mineral ratio Coal mine index Surface coal mine Change detection Mine classes Landsat 8

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：