检索结果-内蒙古大学图书馆

international conference on Intelligent Communication and Computational Techniques (ICCT)

作者： Anubha Parashar Computer Science and Engineering Manipal University Jaipur Jaipur India

The following topics are dealt with: learning (artificial intelligence); feature extraction; Internet of Things; image classification; Internet; image segmentation; health care; medical image processing; cloud computi...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ishara-Bochon: The First Multipurpose Open Access Dataset for Bangla Sign Language Isolated Digits 2nd

Ishara-Bochon: The First Multipurpose Open Access Dataset fo...

引用

2nd international conference on Recent Trends in Image processing and Pattern Recognition, RTIP2R 2018

作者： Islam, Md. Sanzidul Mousumi, Sadia Sultana Sharmin Jessan, Nazmul A. Rabby, Akm Shahariar Azad Abujar, Sheikh Hossain, Syed Akhter Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh

ISBN: (纸本)9789811391804

Ishara-Bochon, the first multipurpose comprehensive open access isolated digits dataset for Bangladeshi Sign Language (BdSL) is introduced in this article. Sign language digits is a major part of communication for deaf and hearing impaired people. It is important in their everyday stuff, such as – in routine accounting and to interact with general people. Ishara-Bachon dataset contains 100 sets of 10 Bangla basic sign digits (0, 1, 2.. 9), collected from different deaf and general volunteers from different institutes. After discarding maximum errors and performing different preprocessing methods, 1000 images of Bangla sign language isolated digits were included in the first dataset. After collectiong raw data, some effective preprocessing methods were performed for making those data useable for computer vision model and any other application development purposes. © 2019, Springer Nature Singapore Pte Ltd.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Interference management in dense inband D2D network using spectral clustering & dynamic resource allocation

引用

WIRELESS NETWORKS 2019年第7期25卷 4431-4441页

作者： Kasi, Shahrukh Khan Naqvi, Ijaz Haider Kasi, Mumraiz Khan Yaseen, Faisal Lahore Univ Management Sci Sch Sci & Engn Lahore Pakistan Balochistan Univ Informat Technol Engn & Manageme Comp Sci Quetta Pakistan

Device-to-device (D2D) communication has emerged as a promising concept to improve resource utilization in fifth generation cellular networks. D2D network's architectural capability to offload traffic from the backhaul network to direct links enables it to be used for internet of things (IoT) services. In a densely deployed setting of IoT devices, D2D network may experience critical interferences due to a limited number of spectral resources. To increase the overall signal-to-interference-plus-noise ratio (SINR) of the network while reducing the computational load on a macro base station, a novel decentralized interference management methodology is proposed for dense in-band D2D underlay LTE-A network. The proposed interference management scheme can decouple interference in a network into cross-cluster and intra-cluster interference and tackle with them separately. To mitigate the cross-cluster interference in a dense D2D network we propose dividing the densely deployed D2D user equipments (UEs) network into well-separated clusters using spectral clustering with modified kernel weights. The proposed spectral clustering scheme obtains well-separated clusters with regards to cross-cluster interference, that is, the UEs that offer maximum interference to each other are grouped into the same cluster. Thereafter, a dynamic resource allocation algorithm is proposed within each cluster to reduce the intra-cluster interference. The proposed dynamic resource allocation algorithm uses graph coloring to allocate resources in such a manner that after each spectrum allocation, a small cell base station updates the interference graph and assigns the next largest interference affected UE a spectrum resource that minimizes the overall intra-cluster interference the most. In conventional graph coloring, the adjacent UEs are allocated different spectrum resources without taking into consideration if the allocated spectrum resource might result in increased interference in the cluster

关键词： Device-to-device Communication Interference management Spectral clustering Dynamic resource allocation

来源：评论

学校读者我要写书评

暂无评论

A vision-based human action recognition system for moving cameras through deep learning 2

A vision-based human action recognition system for moving ca...

引用

2nd international conference on signal processing and machine learning, SPML 2019

作者： Chang, Ming-Jen Hsieh, Jih-Tang Fang, Chiung-Yao Chen, Sei-Wang National Taiwan Normal University No. 88 Sec. 4 Tingzhou Rd. Wenshan Dist. Taipei City116 Taiwan

ISBN: (纸本)9781450372213

This study presents a vision-based human action recognition system using a deep learning technique. The system can recognize human actions successfully when the camera of a robot is moving toward the target person from various directions. Therefore, the proposed method is useful for the vision system of indoor mobile robots. The system uses three types of information to recognize human actions, namely, information from color videos, optical flow videos, and depth videos. First, Kinect 2.0 captures color videos and depth videos simultaneously using its RGB camera and depth sensor. Second, the histogram of oriented gradient features is extracted from the color videos, and a support vector machine is used to detect the human region. Based on the detected human region, the frames of the color video are cropped and the corresponding frames of the optical flow video are obtained using the Farnebäck method (https://***=.org/3.4/d4/dee/***). The number of frames of these videos is then unified using a frame sampling technique. Subsequently, these three types of videos are input into three modified 3D convolutional neural networks (3D CNNs) separately. The modified 3D CNNs can extract the spatiotemporal features of human actions and recognize them. Finally, these recognition results are integrated to output the final recognition result of human actions. The proposed system can recognize 13 types of human actions, namely, drink (sit), drink (stand), eat (sit), eat (stand), read, sit down, stand up, use a computer, walk (horizontal), walk (straight), play with a phone/tablet, walk away from each other, and walk toward each other. The average human action recognition rate of 369 test human action videos was 96.4%, indicating that the proposed system is robust and efficient. © 2019 Association for Computing machinery.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Information Extraction Model for Afan Oromo News Text 2nd

Information Extraction Model for Afan Oromo News Text

引用

2nd international conference on Information and Communication Technology for Development for Africa (ICT4DA)

作者： Abera, Sisay Tegegne, Tesfa Adigrat Univ Coll Engn & Technol POBOX 50 Adigrat Ethiopia Bahir Dar Univ Fac Comp Bahir Dar Inst Technol POBOX 26 Bahir Dar Ethiopia

ISBN: (纸本)9783030266301;9783030266295

Information Extraction (IE) concerned with the automatic extraction of facts from text and stores them in a database for easy use and management of the data. As the first research work on IE from Afan Oromo text, we designed a model that deals with Infrastructure news domains in the Oromo language. The proposed model has document preprocessing, learning and extraction and post processing as its main components. In this work recall, precision and F-measure are used as evaluation metrics for Afan Oromo Text Information Extraction (AOTIE). Being trained and tested for the dataset of size 3169 tokens, AOTIE performed 79.5% precision, 80.5% recall and 80% F-measure. These results are used as a baseline to experiment on AOTIE. We set up two main experimentation scenarios to experiment on AOTIE. The first scenario is conducted by developing a gazetteer. The second scenario is aimed at observing the influence of Afan Oromo grammatical structure. Both scenarios showed that, the performance of AOTIE is mostly dependent on grammatical structure of Afan Oromo.

关键词： Afan Oromo Text Information Extraction machine learning approaches to information extraction Information extraction

来源：评论

学校读者我要写书评

暂无评论

Autonomous Intelligence for FMV ISR Sensors With A Human In The Loop Decision Support System 2018

Autonomous Intelligence for FMV ISR Sensors With A Human In ...

引用

2nd international conference on Vision, Image and signal processing (ICVISP)

作者： Lewis, Rory Univ Colorado Colorado Springs Dept Comp Sci Colorado Springs CO 80918 USA

ISBN: (纸本)9781450365291

As the United States Air Force moves towards autonomous labelling of FMV from ISR sensors, it has experienced unforeseen technical and legal challenges. In terms of the technical challenges, this research effort identifies these obstacles and presents solutions for them with detailed step-by-step analysis of the processes, its testing and prototypes. In terms of the legal challenges, the USAF's goals of infusing artificial intelligence into autonomous labelling of FMV is also being challenged by a formidable, looming legal threat of new laws that will force the USAF to include 'humans in the loop' of its artificial intelligence and machine learning systems [20], [7], [15]. Again, we analyze these legal threats and present solutions to allow inclusion of a human in the loop. It is important to note that our solution to these technical and legal challenges form a two-pronged solution that yields a Bench to Battlefield, Government off-the-shelf (GOTS) autonomous FMV labelling system that will, as time goes by, learn and grow in its ISR identification abilities.

关键词： Artificial intelligence machine learning unmanned aircraft systems

来源：评论

学校读者我要写书评

暂无评论

ISR-Brain machine Intelligence for Unmanned Aircraft Systems 2018

ISR-Brain Machine Intelligence for Unmanned Aircraft Systems

引用

2nd international conference on Vision, Image and signal processing (ICVISP)

作者： Lewis, Rory Univ Colorado Colorado Springs Dept Comp Sci Colorado Springs CO 80918 USA

ISBN: (纸本)9781450365291

This paper presents a system for extrapolating knowledge and classification rules from existing ISR FMV and creating an ISR-Brain. As combat operations have grown to depend upon assured, live ISR support during operations, US forces are presented with formidable challenges to integrate artificial intelligence (AI) capabilities with existing ISR systems. The common challenge being the variance at which advances in commercial and academic AI are deployed compared to rate of speed that innovative AI systems are developed and utilized in military domains. ISR, USAF and SOCOM need to develop a means to seamlessly integrate military and commercial state-of-the-art systems. The ISR-Brain presented will be capable of converting classifiers in existing ISR FMV to machine learning rules for real time ISR sensor, multi-source, multi-enclave data and adaptable with ongoing research efforts with A2, SOCOM, REDO, MITRE and Project MAVEN to develop and test and ISR-Brain to enable the system to integrate with all ISR sensors and predict future Troops in Contact events (TIC) and IED events.

关键词： Artificial intelligence machine learning unmanned aircraft systems

来源：评论

学校读者我要写书评

暂无评论

Document Modeling with Hierarchical Deep learning Approach for Sentiment Classification 2018

Document Modeling with Hierarchical Deep Learning Approach f...

引用

2nd international conference on Digital signal processing (ICDSP) / international conference on Computer Graphics and Virtuality (ICCGV)

作者： Ghosh, Monalisa Sanyal, Goutam Natl Inst Technol Dept CSE Durgapur India

ISBN: (纸本)9781450364027

Sentiment analysis has recently been considered as most active research field in NLP domain. Deep learning is a growing trend of machine learning due to its automatic learning capability with impressive results across different NLP task. In this paper a model is proposed to analyze the deep sentiment representation based on CNN and LSTM (modified version of RNN) network. We aim to improve the performance of traditional machine learning method by merging them with deep learning techniques to tackle the challenge of sentiment prediction of massive amount of unsupervised product review dataset. We make our model first learn to sentence representation with CNN. Next, the semantics of sentences are encoded with LSTM network for document representation. We conduct experiments on two review datasets based on movie review with evaluation metric 'accuracy'. The result shows that proposed model outperformed traditional machine learning as well as baseline neural network model

关键词： Sentiment Analysis Deep learning traditional machine learning Convolutional neural network (CNN) recurrent neural networks LSTM embedding algorithm etc.

来源：评论

学校读者我要写书评

暂无评论

Human Gait State Prediction Using Cellular Automata and Classification Using ELM

Human Gait State Prediction Using Cellular Automata and Clas...

引用

international conference on machine Intelligence and signal processing (MISP)

作者： Semwal, Vijay Bhaskar Gaud, Neha Nandi, G. C. Indian Inst Informat Technol Dept CSE Dharwad Karnataka India Vikram Univ Inst Comp Sci Ujjain Madhya Pradesh India Indian Inst Informat Technol Robot & AI Lab Allahabad Uttar Pradesh India

ISBN: (纸本)9789811309236;9789811309229

In this research article, we have reported periodic cellular automata rules for different gait state prediction and classification of the gait data using Extreme machine Leaning (ELM). This research is the first attempt to use cellular automaton to understand the complexity of bipedal walk. Due to nonlinearity, varying configurations throughout the gait cycle and the passive joint located at the unilateral foot-ground contact in bipedal walk resulting variation of dynamic descriptions and control laws from phase to phase for human gait is making difficult to predict the bipedal walk states. We have designed the cellular automata rules which will predict the next gait state of bipedal steps based on the previous two neighbor states. We have designed cellular automata rules for normal walk. The state prediction will help to correctly design the bipedal walk. The normal walk depends on next two states and has total eight states. We have considered the current and previous states to predict next state. So we have formulated 16 rules using cellular automata, eight rules for each leg. The priority order maintained using the fact that if right leg in swing phase then left leg will be in stance phase. To validate the model we have classified the gait Data using ELM (Huang et al. proceedings of 2004 IEEE international joint conference on neural networks, vol 2. IEEE, 2004, [1]) and achieved accuracy 60%. We have explored the trajectories and compares with another gait trajectories. Finally we have presented the error analysis for different joints.

关键词： Cellular automata (CA) Human gait Bipedal control Humanoid robot Extreme learning machine (ELM) Pseudo-inverse

来源：评论

学校读者我要写书评

暂无评论

A hybrid model for China's power grid investment demand forecasting based on variational mode decomposition, regularized extreme learning machine and support vector machine 2

A hybrid model for China's power grid investment demand fore...

引用

2nd international conference on Renewable Energy and Environment Engineering, REEE 2019

作者： Wu, Qianqian Zhu, Shaowen Li, Jinchao Chen, Wenjun Wu, Yunna School of Economics and Management North China Electric Power University Beijing China Beijing Key Laboratory of New Energy and Low-Carbon Development North China Electric Power University Beijing China

With the continuous maturity of China's power grid as well as the advancement of electricity market reform in China, accurate and efficient investment decision has become an inevitable requirement of power grid enterprises. However, China's Power grid investment demand has complicated nonlinear and non-stationary characteristics due to it's complex causes of formation, thus make it hard to be forecasted. Aiming at this problem, this paper puts forward a novel hybrid VMD-RELMLOO-PSOSVM forecasting model based on variational mode decomposition (VMD), leave-one-out cross validation error based optimal regularized extreme learning machine (RELM-LOO) and support vector machines optimized by particle swarm optimization algorithm (PSO-SVM). Firstly, the VMD method is employed to decompose the original power grid investment data sequence into several modes which have specific sparsity properties while producing main signal. Then, according to the different characteristics of each subsequence, the RELM-LOO and PSO-SVM model will be used to forecast different modes, respectively;Next, the prediction results of all modes are aggregated to obtain the final prediction results of China's power grid investment demand. Finally, this paper predicts China's power grid investment demand from 2018 to 2020 under 5 different scenarios based on the proposed VMD-RELMLOO-PSOSVM hybrid forecasting model. © 2019 The Authors, published by EDP Sciences.

关键词： Variational mode decomposition

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：