检索结果-内蒙古大学图书馆

1st South Aceh international conference on Engineering and Technology (SAICOET)

作者： Putra, D. S. Weru, Y. U. W. Fitriady Politekn Aceh Selatan Informat Engn Tapaktuan 23711 Indonesia Politekn Aceh Ind Elect Engn Banda Aceh 23119 Indonesia

EMG is an electric signal in the human muscle layer. This signal is caused by muscle contraction activity. The main purpose of this study was to explore the pattern of electromyography signal for wrist movement in open finger extensor. The EMG can be recorded using a device called electromyography (EMG). It can be acquired by attaching an electrode to the surface of the skin and the electrode was capturing the raw of EMG signal. Volunteers involved in this study were six people where each individual have 10 datasets the EMG signals. The electrodes are installed in the lower arm muscles. The EMG raw signal was processed by normalizing zero-mean. After pre-processing, the EMG signal has been done a feature extraction process to get the EMG data which was be an input vector in learning Vector Quantization (LVQ). The feature extraction method was mean absolute value (MAV), root mean square (RMS), minimum value (Min), maximum value (Max), variance (Var), standard deviation (stD), and length of data (LoD). This study indicates that the classification accuracy for training and testing data of the EMG signal for wrist movement in open finger extensor (OFE) and grasping finger extensor (GFE) was 70.83% and 83.33% respectively. Therefore, the EMG signal can be used for identifying muscle disorder, artificial hand control and biometric identity.

关键词： EMG signal LVQ human muscle layer muscle contraction activity

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised machine learning Approach in Remote Sensing Data 19th

An Unsupervised Machine Learning Approach in Remote Sensing ...

引用

19th international conference on Computational Science and Its Applications (ICCSA)

作者： Mazzei, Mauro CNR Ist Anal Sistemi & Informat Antonio Ruberti Via Taurini 19 I-00185 Rome Italy

ISBN: (纸本)9783030243029

The analysis, image recognition, the classification in remote sensing data always up to date is for the insiders a very useful system for the management, planning, protection of our territory. Technological evolution the succession of applications and tools in GIS environment, have refined more and more techniques allowing us to computerize much of the territory bringing an enrichment of geographical data distributed more or less updated, remote sensing, digital orthoimage help us in the areas where the local computerization is not always updated. In this paper I want to demonstrate that an approach based on machine learning applied to territorial analysis using dynamic matrices, provides for the definition of numerical indices assigned to each recognized pattern. The numerical indices will be the elements of recognition where the territorial computerization is insufficient. The data from remote sensing or digital orthoimage are variable matrices where the numerical indices have to express their potential. The goal is to educate the recognition in matrix form to obtain a dynamic topology where the computerization has not been updated.

关键词： Data mining Spatial data mining Spatial data analysis Spatial statistical model

来源：评论

学校读者我要写书评

暂无评论

The classification of facial expressions with multi-cultural backgrounds: an event-related fMRI study 2

The classification of facial expressions with multi-cultural...

引用

2nd international conference on image and Video processing, and Artificial Intelligence (IPVAI)

作者： Song, Sutao Liu, Chunyu Huang, Lijie Cao, Zhiyuan Zhang, Jiacai Wei, Shuhua Dong, Jimei Univ Jinan Sch Educ & Psychol Jinan 250022 Peoples R China Beijing Normal Univ Coll Informat Sci & Technol Beijing 100875 Peoples R China Beijing Normal Univ State Key Lab Cognit Neurosci & Learning Beijing 100875 Peoples R China

ISBN: (数字)9781510634107

ISBN: (纸本)9781510634107

Expression recognition is important for our social interaction and communications, but the role of face-selective regions in discriminating various facial expressions remain unclear, especially when the expressions came from multi-cultural backgrounds. In this study, 800 facial expressions collected from 5 different facial expression databases with western or eastern cultural backgrounds were shown to the subjects in a slow event-related fMRI experiment. The subjects were instructed to indicate the category of facial expressions (happy, disgust, angry or neutral) by pressing different buttons. One multivariate pattern analysis method, support vector machine was trained to predict the categories of facial expressions. Results showed that: (1) the face selective regions differed in their ability for expression decoding, but a similar pattern was observed, with a predominance to classify facial expressions with opposite valence, i.e. happy vs. fear and happy vs. disgust. Besides,angry vs. disgust and happy vs. neutral achieved the lowest results. (2) the accuracies of facial expression classification cross-databases were as high as the accuracy of the generalization across runs within-database. These results provided evidence for the consistency of the representation of facial expressions in human brain with different culture backgrounds.

关键词： culture expression recognition emotion pattern classification event-related fMRI multi-voxel pattern analysis

来源：评论

学校读者我要写书评

暂无评论

recognition and translation of Ancient Brahmi Letters using deep learning and NLP

Recognition and translation of Ancient Brahmi Letters using ...

引用

2019 international conference on Advancements in Computing, ICAC 2019

作者： Nilupuli Wijerathna, K.A.S.A. Sepalitha, Rashmi Indika, Thuiyadura Athauda, Harshana Suranjini, P.D. Silva, J.A.D.C. Jayakodi, Anuradha Sri Lanka Institute of Information Technology Faculty of Computing Malabe Sri Lanka

ISBN: (纸本)9781728141701

Inscriptions are major resources for studying the ancient history and culture of civilization in any country. Analyzing, recognizing and translating the ancient letters (Brahmi letters) from the inscription is a very difficult work for present generation. There is no any automatic system for translating Brahmi letters to Sinhala language. However, they are using manual method for translating inscriptions. The method that used in epigraphy is being taken a long period to decipher, analyze and translate the inscribed text in inscriptions. This research mainly focuses on recognition of ancient Brahmi characters written the time period between 3rd B.C and 1st A. D. First, we remove the noise, segment the letters from the inscription image and convert it into the binary image using image processing techniques. Secondly, we recognize the correct Brahmi letters, broken letters and then identify the time period of the inscriptions using Convolution Neural Networks in deep learning. Finally, the Brahmi letters are translated into modern Sinhala letters and provide the meaning of the inscription using Natural Language processing. This proposed system builds up solution to overcome the existing problems in epigraphy. © 2019 IEEE.

关键词： Binary images

来源：评论

学校读者我要写书评

暂无评论

A Two stage approach for Detection of Invasive and Cervical Intra-Epithelial Neoplasia using machine learning and image processing Methodologies 1

A Two stage approach for Detection of Invasive and Cervical ...

引用

1st international conference on Advanced Technologies in Intelligent Control, Environment, Computing and Communication Engineering, ICATIECE 2019

作者： Ojha, Ananya D. Yerremreddy, Sai Navelkar, Ananya Soni, Jainam Bide, Pramod Sardar Patel Institute of Technology Department of Computer Engineering India

ISBN: (纸本)9781728104188

Representing around 6.6% of the cancer cases in women, Cervical Cancer is the fourth most common cancer in women. Cancer is a pernicious disease marked by rapid multiplication and growth of malignant cells in the body. The threat that it poses is evident from the fact that it is the second leading cause of death worldwide and consumes about 1 in 6 individuals worldwide. Of all the types of cancer, Cervical Cancer is the eighth most occurring cancer. Cancer causing infections, such as hepatitis and Human Papilloma Virus (HPV), are accountable for nearly 25% of cancer instances in low-and middle-income countries. Diagnosed in around 122,844 women in India and the cause of death for 67,477 women, this morbid disease can be best tackled when there is early diagnosis. It occurs when there is an aberrant growth of the cells of the cervix which further infect other tissues of the body. The lower part of the uterus that connects it with vagina is the cervix. The abnormal growth of cells mentioned earlier is caused by Human Papilloma Virus (HPV) infection, a sexually transmitted *** infection spreads in three stages of Cervical Intra-epithelial Neoplasia (CIN), and finally the most severe stage results in the onset of Cervical Cancer. This paper aims at implementing various machine learning Methodologies for first detecting the likelihood of transmission of HPV infection, the leading cause of Cervical Cancer by using a questionnaire involving questions related to the sexual activity of the individuals. Later, it aims at classifying the stage of Cervical Intra-Epithelial Neoplasia which can help in diagnosis and early treatment of the disease, to avert the onset of Cervical Cancer. For achieving this, we use a set of classifiers on the personal and medical detail provided by the user for predicting the likelihood of onset of cervical cancer in stage 1. In stage 2, image processing techniques are used to obtain features which are then given to the classifier to class

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Bio-medical image enhancement using adaptive multi-resolution technique 1

Bio-medical image enhancement using adaptive multi-resolutio...

引用

1st international conference on Applied machine learning, ICAML 2019

作者： Satapathy, Lalit Mohan Das, Pranati Bhubaneswar India SarangOdisha India

ISBN: (纸本)9781728139081

The enhancement, resolution, and accuracy are the basic requirements of digital image processing. But in the field of medical, the local details of the images are necessary. In this contest, the Contrast Limited Adaptive Histogram Equalization (CLAHE) is an effective approach, which is used for enhancing the local feature. The downside of CLAHE is the contrast overstretching and noise enhancement. To overcome this problem the low frequency and high-frequency details of an image were considered separately. This paper proposes a new biomedical image enhancement technique based on Bi-dimensional Empirical Mode Decomposition (BEMD) with CLAHE and Sobel Gradient. Where the image is decomposed using BEMD to separate the edge and detail information. The edge information is enhanced using CLAHE and the rest coefficients remain unchanged. Experiments are conducted on numerous brain, retina and tissue images to compare the performance of the proposed algorithm with the state of art approaches. The comparison is made quantitatively in terms of entropy ratio (ER), absolute mean brightness error (AMBE), the peak of signal to noise ratio (PSNR), structural similarity index (SSIM), and image quality index (IQI);qualitatively through visual comparisons. The results indicate a significant improvement especially in terms of structural and edge preservation. © 2019 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Automatic Estimation of Dog Age: The DogAge Dataset and Challenge 28th

Automatic Estimation of Dog Age: The DogAge Dataset and Chal...

引用

28th international conference on Artificial Neural Networks (ICANN)

作者： Zamansky, Anna Sinitca, Aleksandr M. Kaplun, Dmitry, I Dutra, Luisa M. L. Young, Robert J. Univ Haifa Informat Syst Dept Haifa Israel St Petersburg Electrotech Univ LETI St Petersburg Russia Univ Salford Sch Environm & Life Sci Manchester England

ISBN: (纸本)9783030305086;9783030305079

Automatic age estimation is a challenging problem attracting attention of the computer vision and pattern recognition communities due to its many practical applications. Artificial neural networks, such as CNNs are a popular tool for tackling this problem, and several datasets which can be used for training models are available. Despite the fact that dogs are the most well studied species in animal science, and that ageing processes in dogs are in many aspects similar to those of humans, the problem of age estimation for dogs has so far been overlooked. In this paper we present the DogAge dataset and an associated challenge, hoping to spark the interest of the scientific community in the yet unexplored problem of automatic dog age estimation.

关键词： CNN Computer vision Applications of deep learning Age estimation

来源：评论

学校读者我要写书评

暂无评论

Emotional state recognition with Micro-expressions and Pulse Rate Variability 20th

Emotional State Recognition with Micro-expressions and Pulse...

引用

20th international conference on image Analysis and processing (ICIAP)

作者： Belaiche, Reda Sabour, Rita Meziati Migniot, Cyrille Benezeth, Yannick Ginhac, Dominique Nakamura, Keisuke Gomez, Randy Yang, Fan Univ Bourgogne Franche Comte ImViA EA 7535 Dijon France Honda Res Inst Japan Co Ltd 8-1 Honcho Wako Saitama Japan

ISBN: (纸本)9783030306427;9783030306410

machine learning has known a tremendous growth within the last years, and lately, thanks to that, some computer vision algorithms started to access what is difficult or even impossible to perceive by the human eye. It is then natural that scientists began looking for ways to probe humans' emotions and their psyche with this technology. In this paper, we study the feasibility of recognizing and classifying the abstract concept of emotional states from videos of people facing a regular RGB camera. We do so by using the barely perceptible micro facial expressions humans cannot control, as well as the spontaneous variations of the pulse rate that we estimated using remote photoplethysmography. We compare these two modalities and our experimental results show that it is possible to classify emotional states from these implicit information gathered from regular cameras with encouraging performances.

关键词： Affective computing Facial expressions LBP Pulse rate variability Remote photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Synthetic bootstrapping of convolutional neural networks for semantic plant part segmentation

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2019年 161卷 291-304页

作者： Barth, R. IJsselmuiden, J. Hemming, J. Van Henten, E. J. Wageningen Univ & Res Greenhouse Hort POB 644 NL-6700 AP Wageningen Netherlands Wageningen Univ & Res Farm Technol Grp POB 16 NL-6700 AA Wageningen Netherlands Harvard Univ Biorobot Lab 60 Oxford St Cambridge MA 02138 USA

A current bottleneck of state-of-the-art machine learning methods for image segmentation in agriculture, e.g. convolutional neural networks (CNNs), is the requirement of large manually annotated datasets on a per-pixel level. In this paper, we investigated how related synthetic images can be used to bootstrap CNNs for successful learning as compared to other learning strategies. We hypothesise that a small manually annotated empirical dataset is sufficient for fine-tuning a synthetically bootstrapped CNN. Furthermore we investigated (i) multiple deep learning architectures, (ii) the correlation between synthetic and empirical dataset size on part segmentation performance, (iii) the effect of post-processing using conditional random fields (CRF) and (iv) the generalisation performance on other related datasets. For this we have performed 7 experiments using the Capsicum mutton (bell or sweet pepper) dataset containing 50 empirical and 10,500 synthetic images with 7 pixel-level annotated part classes. Results confirmed our hypothesis that only 30 empirical images were required to obtain the highest performance on all 7 classes (mean IOU = 0.40) when a CNN was bootstrapped on related synthetic data. Furthermore we found optimal empirical performance when a VGG-16 network was modified to include a trous spatial pyramid pooling. Adding CRF only improved performance on the synthetic data. Training binary classifiers did not improve results. We have found a positive correlation between dataset size and performance. For the synthetic dataset, learning stabilises around 3000 images. Generalisation to other related datasets proved possible.

关键词： Computer vision Semantic segmentation Synthetic dataset Bootstrapping Big data

来源：评论

学校读者我要写书评

暂无评论

Interval Type-2 Fuzzy Restricted Boltzmann machine for the Enhancement of Deep learning

Interval Type-2 Fuzzy Restricted Boltzmann Machine for the E...

引用

IEEE international conference on Fuzzy Systems (FUZZ-IEEE)

作者： Janmaijaya, Manvendra Shukla, Amit K. Seth, Taniya Muhuri, Pranab K. South Asian Univ Dept Comp Sci New Delhi 110021 India

ISBN: (纸本)9781538617281

Deep learning (DL) has played a crucial role in many domains of image and pattern recognition, extraction of features from video and text processing etc. One of the quintessential elements of deep learning is Restricted Boltzmann machines (RBM). RBMs are capable of extracting the high-level features from raw data very efficiently. Nevertheless, feature extraction process is prone to external and unwanted noises, which introduces uncertainty in the decision making process. Moreover, existing RBM-based DL methods are not robust enough to handle such noises in the data samples while training within layers. To tackle these drawbacks, Fuzzy Restricted Boltzmann machine (FRBM) had been available in the literature. FRBM utilizes Type-1 Fuzzy Sets (T1FS) to handle such uncertainties in governing parameters of the system. However, membership values of membership functions used in T1FSs are also crisp. Thus, in this state-of-art paper, we propose the use Interval Type-2 Fuzzy Sets (IT2FSs) to model parameters in RBM for training, as they are efficient in handling higher level of uncertainty. Experiments performed for MNIst digits show more generative and discriminative capabilities of IT2FRBM over RBM and FRBM.

关键词： Deep learning Interval Type-2 Fuzzy Sets Interval Type-2 Fuzzy Restricted Boltzmann machine Restricted Boltzmann machine

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：