检索结果-内蒙古大学图书馆

BioWolf: A Sub-10-mW 8-Channel Advanced Brain-Computer Interface Platform With a Nine-Core Processor and BLE Connectivity

引用

IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS And SYSTEMS 2019年第5期13卷 893-906页

作者： Kartsch, Victor Tagliavini, Giuseppe Guermandi, Marco Benatti, Simone Rossi, Davide Benini, Luca Univ Bologna Dept Elect Elect & Informat Engn I-40126 Bologna Italy Swiss Fed Inst Technol Integrated Syst Lab CH-8092 Zurich Switzerland

Advancements in digital signal processing (DSP) and machine learning techniques have boosted the popularity of brain-computer interfaces (BCIs), where electroencephalography is a widely accepted method to enable intuitive human-machine interaction. Nevertheless, the evolution of such interfaces is currently hampered by the unavailability of embedded platforms capable of delivering the required computational power at high energy efficiency and allowing for a small and unobtrusive form factor. To fill this gap, we developed BioWolf, a highly wearable (40mm 20 mm 2 mm) BCI platform based on Mr. Wolf, a parallel ultra low power system-on-chip featuring nine RISC-V cores with DSP-oriented instruction set extensions. BioWolf also integrates a commercial 8-channel medical-grade analog-to-digital converter, and an ARM-Cortex M4 microcontroller unit (MCU) with bluetooth low-energy connectivity. To demonstrate the capabilities of the system, we implemented and tested a BCI featuring canonical correlation analysis (CCA) of steady-state visual evoked potentials. The system achieves an average information transfer rate of 1.46 b/s (aligned with the state-of-the-art of bench-top systems). Thanks to the reduced power envelope of the digital computational platform, which consumes less than the analog front-end, the total power budget is just 6.31mW, providing up to 38h operation (65mAh battery). To our knowledge, our design is the first to explore the significant energy boost of a parallel MCU with respect to single-core MCUs for CCA-based BCI.

关键词： Blockchain Protocols Privacy Charging stations Electric vehicle charging Public key Elliptic curves Body sensor networks brain-computer interfaces digital signal processing electroencephalography internet of things low-power electronics multicore processing

来源：评论

学校读者我要写书评

暂无评论

Doodle Recognition using machine learning for hearing and speech-impaired people

Doodle Recognition using machine learning for hearing and sp...

引用

international conference on signal processing and Communication (ICSPC)

作者： Evangelyn D Monica Praharsha Davu Cynthia P Caroline D.J Jagannath Karunya Institute of Technology and sciences Coimbatore India

In this paper, we test the different classifiers used in machine learning and compare the different accuracies for the doodles which are obtained from Google's Quick Draw Dataset. The classifier with the best accuracy can be fed into an application for the hearing and speech impaired people through which the can be trained to draw their immediate needs, and the machine learning model could classify it into the correct category, so it would be easy for the people nearby to help them.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning Approach to Semantic Segmentation in 3D Point Cloud Intra-oral Scans of Teeth 2

Deep Learning Approach to Semantic Segmentation in 3D Point ...

引用

2nd international conference on Medical Imaging with Deep learning (MIDL)

作者： Zanjani, Farhad Ghazvinian Moin, David Anssari Verheij, Bas Claessen, Frank Cherici, Teo Tan, Tao de With, Peter H. N. Eindhoven Univ Technol NL-5600 MB Eindhoven Netherlands Promaton Inc NL-1076 GR Amsterdam Netherlands

Accurate segmentation of data, derived from intra-oral scans (IOS), is a crucial step in a computer-aided design (CAD) system for many clinical tasks, such as implantology and orthodontics in modern dentistry. In order to reach the highest possible quality, a segmentation model may process a point cloud derived from an IOS in its highest available spatial resolution, especially for performing a valid analysis in finely detailed regions such as the curvatures in border lines between two teeth. In this paper, we propose an end-to-end deep learning framework for semantic segmentation of individual teeth as well as the gingiva from point clouds representing IOS. By introducing a non-uniform resampling technique, our proposed model is trained and deployed on the highest available spatial resolution where it learns the local fine details along with the global coarse structure of IOS. Furthermore, the point-wise cross-entropy loss for semantic segmentation of a point cloud is an ill-posed problem, since the relative geometrical structures between the instances (e.g. the teeth) are not formulated. By training a secondary simple network as a discriminator in an adversarial setting and penalizing unrealistic arrangements of assigned labels to the teeth on the dental arch, we improve the segmentation results considerably. Hence, a heavy post-processing stage for relational and dependency modeling (e.g. iterative energy minimization of a constructed graph) is not required anymore. Our experiments show that the proposed approach improves the performance of our baseline network and outperforms the state-of-the-art networks by achieving 0.94 IOU score.

关键词： Deep learning 3D point cloud intra-oral scan semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

The Application of Transfer learning in Film and Television Works 2

The Application of Transfer Learning in Film and Television ...

引用

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

作者： Lian, Bihan Jin, Cong Wang, Nansu Li, Yajie Wang, Hongliang Commun Univ China Sch Comp & Cyberspace Secur Beijing 100024 Peoples R China Commun Univ China Sch Informat & Commun Engn Beijing 100024 Peoples R China Commun Univ China Advertising Sch Beijing 100024 Peoples R China

ISBN: (数字)9781510634107

ISBN: (纸本)9781510634107

Many personalized advertisement recommendation studies suffer from the problem of only certain tagged items can be recommended in video playback, which mean it can't recommend more produces to users that they really like. It also doesn't know the users really like at the source. Due to the large number of scene changes in different video, the users can choose more items they like. This study attempts to adopt transfer knowledge to solve the problem of data volume to provide users with a variety of options. Aiming at the image classification model of learning on big data set, this paper proposes a method to solve the problem of scene object recognition in TV program, such as movies,TV plays, and short video, by transferring a pre-trained depth image classification model to a specific task. In a small training set, learning high-level representations on a small training set to produce a task-specific target model. Experiments on small data sets and real face sets collected by myself show that the transfer learning is effective and efficient. In the application of video, this study provides a theoretical basis for personalized click recommendation of video users.

关键词： transfer learning image classification inception v3

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection for Water Supply Data using machine learning Technique 2

Anomaly Detection for Water Supply Data using Machine Learni...

引用

2nd international conference on Computer Information Science and Application Technology, CISAT 2019

作者： Fang, Shu Sun, Weize Huang, Lei College of Electronics and Information Engineering Shenzhen University China

The advent of the era of big data brings new challenges and opportunities to water data processing. Abnormal detection or authenticity verification of water supply data becomes an urgent problem in natural resource data processing. This article addresses the issue of anomaly detection for a set of measured water supply data that provided by the Ministry of Water Resources of China. The machine learning technique, namely, One-Class support vector machine, is used for anomaly detection, and a detailed analysis of the features of anomalies is also provided. Experiments on three situations, namely, one dimensional situation, three dimensional situation and seven dimensional situation are carried out to analyse the features of anomalies. The experiment results revealed that the cases with entries of large values more than 10 times of median, zero entries together with some large values and ascending or descending sequences tend to have high abnormality scores. © Published under licence by IOP Publishing Ltd.

关键词： Water supply

来源：评论

学校读者我要写书评

暂无评论

IEEE international conference on Intelligent Techniques in Control, Optimization and signal processing, INCOS 2019

IEEE International Conference on Intelligent Techniques in C...

引用

2019 IEEE international conference on Intelligent Techniques in Control, Optimization and signal processing, INCOS 2019

ISBN: (纸本)9781538695425

The proceedings contain 123 papers. The topics discussed include: advanced logic level design methodology for a secure DPA resistant FPGA;evaluation of charge density and sheet carrier concentration in the 2DEG area of AlGaN/AlN high electron mobility transistors (HEMTs);design and implementation of non-intrusive load monitoring using machine learning algorithm for appliance monitoring;experimental determination of MPPT using solar array simulator;AUTOSAR based dual core partitioning for power train application of BMS;cross-border infiltration detection and protection system;and an intelligent energy management system for grid connected DFIG based wind system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning Assisted Smart Glasses as Educational Aid for Visually Challenged Students 2

Deep Learning Assisted Smart Glasses as Educational Aid for ...

引用

2nd international conference on New Trends in Computing Sciences (ICTCS)

作者： AlSaid, Hawra AlKhatib, Lina AlOraidh, Aqeela AlHaidar, Shoaa Bashar, Abul Prince Mohammad Bin Fahd Univ Coll Comp Engn & Sci Al Khobar 31952 Saudi Arabia

ISBN: (纸本)9781728128825

Computer Vision Technology has played a significant role in assisting visually challenged people to carry out their day to day activities without much dependency on other people. Smart glasses in one such solution which enables blind or visually challenged people to "read" images. This paper is an attempt in this direction to build a novel smart glass which has the ability to extract and recognize text captured from an image and convert it to speech. It consists of a Raspberry Pi 3 B+ microcontroller which processes the image captured from a webcam super-imposed on the glasses of the blind person. Text detection is achieved using the OpenCV software and open source Optical Character Recognition (OCR) tools Tesseract and Efficient and Accurate Scene Text Detector ( EAST) based on Deep learning techniques. The recognized text is further processed by Google's Text to Speech (gTTS) API to convert to an audible signal for the user. A second feature of this solution is to provide location-based services to the blind people by identifying locations in an academic building using the RFID technology. This solution has been extensively tested in a university environment for aiding visually challenged students. The novelty of the implemented solution lies in providing the desired computer vision functionalities of image/text recognition which is economical, small-sized, accurate and uses open source software tools. This solution can be potentially used for both educational and commercial applications.

关键词： Image Recognition Speech processing Optical Character Recognition Deep learning Raspberry Pi Python

来源：评论

学校读者我要写书评

暂无评论

Adaptation of the residual signal for filter failure detection in scenarios with multiple filter types 21

Adaptation of the residual signal for filter failure detecti...

引用

21st international conference on Transparent Optical Networks, ICTON 2019

作者： Barzegar, Sima Ruiz, Marc Velasco, Luis Barcelona Spain

ISBN: (纸本)9781728127798

To monitor the optical spectra of outgoing links, Optical Spectrum Analyzers (OSA) can deployed in the optical nodes acquiring the optical spectra of outgoing links and analyzing optical signals to detect those soft-failures that affect the shape of the spectrum, like Filter Shift and Filter Tightening. In this paper, we rely on the residual-based approach spectra analysis that uses a set of residual signals calculated by subtracting the measured signal by the OSA from an expected version of the signal. In this paper, we assume a network scenario, where nodes with optical filters of different characteristics (e.g., 2nd, 3rd, and 4th order Gaussian) are installed. In this scenario, the possibility of generating complete data set for machine learning training purposes that include every combination of filter and failure is difficult to achieve. Instead, we propose an adaptation mechanism that transform the expected effects of every filter type thus, emulating single filter-type networks. Exhaustive experiments are carried out to show the performance of the proposed adaptation under filter failures. © 2019 IEEE.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Generating Context-Free Group-Level Emotion Landscapes Using Image processing and Shallow Convolutional Neural Networks 2nd

Generating Context-Free Group-Level Emotion Landscapes Using...

引用

2nd international conference on Computing Analytics and Networking, ICCAN 2019

作者： Tribedi, Sabyasachi Barai, Ranjit Kumar Department of Electrical Engineering Jadavpur University Kolkata India

ISBN: (纸本)9789811524134

Emotion recognition is an integral part of any Human–machine Interaction (HMI) system. Proper emotion recognition allows for HMI systems to choose the successive appropriate responses, given context and the emotion expressed by human(s). The advent of deep learning using Deep Neural Networks (DNN) has made incredible strides in achieving and even exceeding human accuracy in image classification and face detection. Many papers have been published mentioning the successful applications of DNNs like the Convolutional Neural Networks (CNNs), which have now become the de facto algorithm for facial image classification tasks because they combine the feature extraction and classification steps into one mathematical model. They learn the desirable features by themselves from the input images and have been demonstrated to be robust to variations in facial image data. However, there is one big bottleneck for CNNs: the models with good accuracy have many hidden layers, and hence are very deep and require heavy computing power, memory space and, of course, time to train themselves. Our paper puts forward two experimental approaches that can be extremely beneficial to the domains of CNNs and HMI systems. For the first approach, we were able to achieve a very good accuracy in emotion classification using a shallow CNN with only three and four hidden layers. This was possible only because we passed the input images through a carefully designed pipeline of image preprocessing techniques before feeding them to the CNN for training. For the second approach, we developed the interpretation of emotion landscape or the distribution of emotion classes detected in static images or videos with many people’s faces visible. This is similar to the group-level emotion classification studies and publications with a distinct difference in possible applications. The rationale behind this integration is in advancing the idea of studying emotions expressed by people in a group setting and how they

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

ASU at TextGraphs 2019 shared task: Explanation regeneration using language models and iterative re-ranking 13

ASU at TextGraphs 2019 shared task: Explanation regeneration...

引用

13th Workshop on Graph-Based Methods for Natural Language processing, TextGraphs 2019, in conjunction with the 2019 conference on Empirical Methods in Natural Language processing and 9th international Joint conference on Natural Language processing, EMNLP-IJCNLP 2019

作者： Banerjee, Pratyay School of Computing Informatics and Decision Systems Engineering Arizona State University United States

ISBN: (纸本)9781950737864

In this work we describe the system from Natural Language processing group at Arizona State University for the TextGraphs 2019 Shared Task. The task focuses on Explanation Regeneration, an intermediate step towards general multi-hop inference on large graphs. Our approach consists of modeling the explanation regeneration task as a learning to rank problem, for which we use state-of-theart language models and explore dataset preparation techniques. We utilize an iterative reranking based approach to further improve the rankings. Our system secured 2nd rank in the task with a mean average precision (MAP) of 41.3% on the test set. © 2019 EMNLP-IJCNLP 2019 - Graph-Based Methods for Natural Language processing - proceedings of the 13th Workshop. All rights reserved.

关键词： Iterative methods

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：