检索结果-内蒙古大学图书馆

2nd International conference on Information and Communication Technology for Intelligent systems (ICTIS)

作者： Desai, Mittal N. Dahiya, vishal Singh, A. K. Parul Univ Parul Inst Comp Applicat Fac IT & Comp Sci Vadodara India Indus Univ Ahmadabad Gujarat India ISRO Space Applicat Ctr Ahmadabad Gujarat India

ISBN: (纸本)9783319636733;9783319636726

In the era of any information on fingertip or on one click, medical diagnosis is context in which wrong diagnosis should be avoided using extensive information related to patients and symptoms. There should be an efficient system in diagnosis in terms of expert diagnostic opinion within short span of time, so that disease should be prevented to become chronic. To streamline this expert diagnostic opinion process to the patients, in daily routine, Expert System (ES) using artificial neural network can be employed. It is the method which can simulate two very important characteristics of humans, learning and generalization. Using ANN algorithms various types of medical data are handled and output is achieved with defining various relations between that data. Radiology is one of the branches of medical science in which various medical imaging techniques are used to diagnose difference internal medical problems. Digital image processing is the science of processing various digital images: such that important information will be generated. An Expert System is also an efficient tool from which diagnosis can be made. Integrating outcomes of neural network from diseased X-ray, to the knowledge based expert system;an expert opinion of diagnosing disease can be generated. In this paper a model is proposed for diagnosing, seven lower lumbar problems as degenerative diseases.

关键词： Radiology Medical imaging techniques Artificial neural network Lower lumbar diagnosis Expert system

来源：评论

学校读者我要写书评

暂无评论

Indian Sign Language converter using Convolutional Neural Networks

Indian Sign Language converter using Convolutional Neural Ne...

引用

International conference for Convergence of Technology (I2CT)

作者： Nishi Intwala Arkav Banerjee Meenakshi Nikhil Gala Mukesh Patel School of Technology Management and Engineering (Mumbai Campus) SVKM’s NMIMS University Mumbai Maharashtra India

ISBN: (数字)9781538680759

ISBN: (纸本)9781538680766

People with hearing and speech impairments have to face a lot of difficulties while communicating with the general public. Being a minority, the sign language used by them is not known to a majority of people. In this paper, an Indian sign language converter was developed using a Convolutional Neural Network algorithm with the aim to classify the 26 letters of the Indian Sign Language into their equivalent alphabet letters by capturing a real time image of that sign and converting it to its text equivalent. First a database was created in various backgrounds and various image pre-processing techniques were used to make the database ready for feature extraction. After feature extraction, the images were fed into the CNN using the python software. Several real time images were tested to find the accuracy and efficiency. The results showed a 96% accuracy for the testing images and an accuracy of 87.69% for real time images.

关键词： Assistive technology Gesture recognition image segmentation Convolutional neural networks Real-time systems Training Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhanced Machine Learning Approaches for Diagnosing Building systems

Enhanced Machine Learning Approaches for Diagnosing Building...

引用

International conference on Internet of Things, Embedded systems and Communications (IINTEC)

作者： Sondes Gharsellaoui Majdi Mansouri Shady S. Refaat Haitham Abu-Rub Hassani Messaoud National Higher Engineering School of Tunis Monfleury Tunisia Electrical and Computer Engineering Program Texas A&M University at Qatar Doha Qatar National Engineering School of Monastir Laboratory of Automatic Signal and Image Processing Monastir Tunisia

ISBN: (数字)9781728151847

ISBN: (纸本)9781728151854

Fault Detection and Classification (FDC) in Heating, Ventilation, and Air Conditioning (HVAC) systems is an important approach to guarantee the human safety of these systems. Therefore, the implementation of a FDC framework is the focus in this paper. The developed approach aims at reducing the energy needs for buildings and improving indoor environment quality. It merges the benefits of multiscale representation, Principal Component Analysis (PCA), and Machine Learning (ML) classifiers in order to improve the efficiency of FDC in heating systems. Firstly, a multiscale decomposition is used to extract the dynamics of the systems at different scales. The multiscale representation gives several advantages for monitoring heating systems generally driven by events in different time and frequency responses. Secondly, the multiscaled data-sets are then introduced into the PCA model to extract more efficient characteristics. Thirdly, the ML algorithms are applied to the extracted and selected characteristics to deal with the problem of fault diagnosis. The FDC efficiency of the developed technique is evaluated using a simulated data extracted from heating systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

2nd International conference on Soft Computing systems, ICSCS 2018

2nd International Conference on Soft Computing Systems, ICSC...

引用

2nd International conference on Soft Computing systems, ICSCS 2018

ISBN: (纸本)9789811319358

The proceedings contain 87 papers. The special focus in this conference is on Soft Computing systems. The topics include: Ultrasonic Signal Modelling and Parameter Estimation: A Comparative Study Using Optimization algorithms;a Histogram Based Watermarking for videos and images with High Security;enhanced Empirical Wavelet Transform for Denoising of Fundus images;kernelised Clustering algorithms Fused with Firefly and Fuzzy Firefly algorithms for image Segmentation;performance Analysis of Wavelet Transform Based Copy Move Forgery Detection;high Resolution 3D image in Marine Exploration Using Neural Networks - A Survey;ship Intrusion Detection System - A Review of the State of the Art;Novel Work of Diagnosis of Liver Cancer Using Tree Classifier on Liver Cancer Dataset (BUPA Liver Disorder);Performance Analysis and Error Evaluation Towards the Liver Cancer Diagnosis Using Lazy Classifiers for ILPD;a Weight Based Approach for Emotion Recognition from Speech: An Analysis Using South Indian Languages;exploring Structure Oriented Feature Tag Weighting Algorithm for Web Documents Identification;MQMS - An Improved Priority Scheduling Model for Body Area Network Enabled M-Health Data Transfer;data Compression Using Content Addressable Memories;heart Block Recognition Using image processing and Back Propagation Neural Networks;design and Development of Laplacian Pyramid Combined with Bilateral Filtering Based image Denoising;diabetes Detection Using Deep Neural Network;Multi-label Classification of Big NCDC Weather Data Using Deep Learning Model;object Recognition Through Smartphone Using Deep Learning Techniques;hot Spot Identification Using Kernel Density Estimation for Serial Crime Detection;analysis of Scheduling algorithms in Hadoop;smart Transportation for Smart Cities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

1st International conference on 'Mechatronics and Artificial Intelligence' (ICMAI-2021)

引用

Journal of Physics: conference Series 2021年第1期1950卷

PREFACE It was a matter of pleasure to organize 1st International conference on 'Mechatronics and Artificial Intelligence' (ICMAI-2021) at Shree Guru Gobind Singh Tricentenary (SGT) University, Gurugram on 26th and 27th February 2021. The conference was organized in Association of Engineering & Technocrats, Faculty of Engineering and Technology, SGT University. The objective of this conference was to provide a common platform to scientists and researchers from all over India for exchanging their knowledge and views to deal with global challenges. The theme of this conference was not only the fundamental technology in the field of engineering science but also can change our society by exploring new horizons and continuous progress. A diverse range of topics from the neural network, digital image processing, machine learning, programmable logic controller, health care, IoT based systems, deep learning, lean manufacturing, abrasive flow machining, welding technology and simulation-based studies are featured in the conference. In addition to that, you will also hear about the incremental forming, automation integration techniques, wireless sensor techniques, non-invasive methods of diagnosis, robot assembly, data mining and various evolutionary algorithms in different applications. I hope, therefore, that you will get a chance to explore recent emerging technologies. We are delighted to deliver special thanks to IOP Publishing as our publication partner to publish the conference proceedings in JPCS. We sincerely thanks to our sponsors Council of Scientific and Industrial Research (CSIR) Human Resource Development Group (HRDG) and 'Sanranchana', SGT University Center of Research Innovation. We believe that the conference had provided the opportunity to the students and the young researchers for enriching their knowledge through interaction with eminent researchers from various NITs, IITs, state universities and reputed organizations. We hope that everybody had a great ex

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Gaussian Recursive Filter Parallel Implementation with Overlapping

A Gaussian Recursive Filter Parallel Implementation with Ove...

引用

International IEEE conference on Signal-image Technologies and Internet-Based System

作者： Pasquale De Luca Ardelio Galletti Livia Marcellino Department of Computer Science University of Salerno Italy Department of Science and Technology University of Naples Parthenope Naples Italy

ISBN: (数字)9781728156866

ISBN: (纸本)9781728156873

Gaussian convolutions computation is required in several scientific fields and, to this aim, efficient approximation methods, based on Recursive Filters (RFs), have been developed recently. Among them, Gaussian Recursive Filters (RFs) are designed to approximate the Gaussian convolution in a very efficient way. The accuracy of these methods, as is well known, can be improved by means of the use of the so-called K-iterated Gaussian recursive filters, that is in the repeated application of the basic RF. To improve the provided accuracy, K-iterated versions of these methods are also considered. Since it is often necessary to handle large size one-dimensional input signals, a parallel approach becomes mandatory. Recently, we proposed a parallel algorithm for the implementation of the K-iterated first-order Gaussian RF on multicore architectures. Here, using a similar parallelization strategy, based on a domain decomposition with overlapping, we propose a new implementation that would exploit, in terms of both accuracy and performance, the GPU (Graphics processing Unit) capabilities on CUDA environment. Tests and experiments confirm the reliability and the efficiency of the proposed implementation.

关键词： Radio frequency Convolution Graphics processing units Parallel algorithms Tools Boundary conditions Instruction sets

来源：评论

学校读者我要写书评

暂无评论

Single-agent policy tree search with guarantees 32

Single-agent policy tree search with guarantees

引用

32nd conference on Neural Information processing systems, NeurIPS 2018

作者： Orseau, Laurent Lattimore, Tor Lelis, Levi H.S. Weber, Théophane DeepMind London United Kingdom Universidade Federal de Viçosa Brazil University of Alberta Canada

We introduce two novel tree search algorithms that use a policy to guide search. The first algorithm is a best-first enumeration that uses a cost function that allows us to prove an upper bound on the number of nodes to be expanded before reaching a goal state. We show that this best-first algorithm is particularly well suited for "needle-in-a-haystack" problems. The second algorithm is based on sampling and we prove an upper bound on the expected number of nodes it expands before reaching a set of goal states. We show that this algorithm is better suited for problems where many paths lead to a goal. We validate these tree search algorithms on 1,000 computer-generated levels of Sokoban, where the policy used to guide the search comes from a neural network trained using A3C. Our results show that the policy tree search algorithms we introduce are competitive with a state-of-the-art domain-independent planner that uses heuristic search. © 2018 Curran Associates *** rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

GAP-8: A RISC-V SoC for AI at the Edge of the IoT 29

GAP-8: A RISC-V SoC for AI at the Edge of the IoT

引用

29th Annual IEEE International conference on Application-Specific systems, Architectures and Processors (ASAP)

作者： Flamand, Eric Rossi, Davide Conti, Francesco Loi, Igor Pullini, Antonio Rotenberg, Florent benini, Luca GreenWaves Technol Villard Bonnot France Univ Bologna DEI Bologna Italy Swiss Fed Inst Technol Integrated Syst Lab Zurich Switzerland

ISBN: (纸本)9781538674796

Current ultra-low power smart sensing edge devices, operating for years on small batteries, are limited to low-bandwidth sensors, such as temperature or pressure. Enabling the next generation of edge devices to process data from richer sensors such as image, video, audio, or multi-axial motion/vibration has huge application potential. However, edge processing of data-rich sensors poses the extreme challenge of squeezing the computational requirements of advanced, machine-learning-based near-sensor data analysis algorithms (such as Convolutional Neural Networks) within the mW-range power envelope of always-ON battery-powered IoT end-nodes. To address this challenge, we propose GAP-8: a multi-GOPS fully programmable RISC-V IoT-edge computing engine, featuring a 8-core cluster with CNN accelerator, coupled with an ultra-low power MCU with 30 mu W state-retentive sleep power. GAP-8 delivers up to 10 GMAC/s for CNN inference (90 MHz, 1.0V) at the energy efficiency of 600 GMAC/s/W within a worst-case power envelope of 75 mW.

关键词： Edge processing Internet of Things Convolutional Neural Networks Near Sensor processing Parallel Architectures

来源：评论

学校读者我要写书评

暂无评论

VLSI Architecture for Fine Grained Pipelined Feature Extraction using Histogram of Oriented Gradient

VLSI Architecture for Fine Grained Pipelined Feature Extract...

引用

IEEE conference on systems, Process & Control (ICSPC)

作者： Arif Sasongko Bima Sahbani School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia

ISBN: (数字)9781728118260

ISBN: (纸本)9781728118277

The most popular field to support the massive growth of the intelligent based system in the recent year is object detection. The fundamental of the object detection technology is feature extraction. It becomes the main challenge due to the variability of application and the computation requirement. One of the challenging issue is to implement this computing system into hardware level architecture to get lower power, high speed, and lower cost computing system. According to some study, Histogram of Oriented Gradient (HOG) is the current most robust feature extraction. This paper proposes a novel hardware architecture for HOG based feature extraction. The architecture brings performance improvement and it opens various benefit in the utilization of VLSI system instead of GPU. This architecture implements tasks for HOG feature extraction including gradient extractor using edge filter algorithms, polar data representation using vectoring mode CORDIC, and histogram normalization using Barni's approximation method. The simulation shows very low (fraction of frame rate) output latency for various image size, therefore the system could support real-time processing, for those imaging rate. The processor successfully implemented for Stratix IV FPGA EP4SGX230 with logic utilization about 10%. With 100 MHz clock rate, it potentially performs up to 1.5 times faster than the GPU fast HOG implementation.

关键词： Histograms Feature extraction Computer architecture Object detection Graphics processing units image edge detection Process control

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based image Classification and Abnormalities Analysis of MRI Brain images

Deep Learning Based Image Classification and Abnormalities A...

引用

TEQIP III Sponsored International conference on Microwave Integrated Circuits, Photonics and Wireless Networks (IMICPW)

作者： Muthu Krishnammal P S. Selvakumar Raja Research Scholar Faculty of Electronics Sathyabama Institute of Science and Technology Tamil Nadu India Khakathiya institute of Science and Technology for Women Nizamabad India

ISBN: (纸本)9781728118826

Intensive researches are being carried out to study the abnormalities present in the brain structures and to detect the type of tumors based on the statistical and textural features extracted from the medical images. In MRI imaging, the images may be clear but the clinicians have to quantify the size and location of the tumors for further treatment planning. The image processing methodologies and the deep learning methods aid the different stages of treatment such as pre and postsurgical procedures. The images captured by Magnetic Resonance Imaging systems are processed by the different software based algorithms in order to segregate the malicious tumor regions from the non-tumor regions. The proposed method includes three phases: feature extraction, image classification and segmentation of tumors. The important features of the images are extracted with Wavelet transform, a multi-resolution technique. The Convolutional Neural Network, which is a very popular deep learning method is used in image classification stage which is helpful in disease or lesion detection, image classification and then the segmentation methods are used to segregate the infected regions from the rest. The proposed method provides better accuracy in classification and segmentation stages.

关键词： Feature extraction Tumors image segmentation Discrete wavelet transforms Convolution Magnetic resonance imaging

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：