检索结果-内蒙古大学图书馆

Conference on Information and Communication Technology (CICT)

作者： Ravi Shanker Santosh Prakash Chouhan Shivam Bhardwaj Ankur Kumar Mahua Bhattacharya Indian Institute of Information Technology Ranchi Ranchi Jharkhand India Atal Bihari Vajpayee Indian Institute of Information Technology and Management Gwalior Madhya Pradesh India

ISBN: (数字)9798331531539

ISBN: (纸本)9798331531546

Recent advancements in technologies such as artificial intelligence, computer vision, and the Internet of Things have expanded into numerous fields, particularly enhancing surveillance systems that demand real-time facial recognition for security. This study introduces a novel integration of edge computing and computer vision to create an efficient, cost-effective facial recognition system with real-time capabilities. Unlike traditional systems that rely on high-powered servers or cloud infrastructure, which often result in latency, privacy concerns, and increased costs, this approach utilizes Convolutional neural networks (CNNs) and the You Only Look Once (YOLO) algorithm on edge devices like the Raspberry Pi. By combining CNNs for precise image classification with YOLO for fast object detection, the system performs high-speed processing directly on the edge device, enabling secure and efficient facial recognition without the need for continuous cloud connectivity. This research thoroughly examines both hardware and software optimizations, showing how this edge-based solution not only reduces latency but also provides scalability and flexibility, making it well-suited for practical security applications.

关键词： YOLO Ethics Computer vision Cloud computing Face recognition image edge detection Surveillance Real-time systems Hardware Testing

来源：评论

学校读者我要写书评

暂无评论

An Action Recognition Algorithm Based on Two-Stream Deep Learning for Metaverse applications

An Action Recognition Algorithm Based on Two-Stream Deep Lea...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Jiayue Liu Tianqi Mao Yicheng Huang Dongxuan He MIIT Key Laboratory of Complex-Field Intelligent Sensing Beijing Institute of Technology Beijing China Yangtze Delta Region Academy Beijing Institute of Technology (Jiaxing) Jiaxing China Department of Electronic Engineering Tsinghua University Beijing China School of Information and Electronics Beijing Institute of Technology Beijing China

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

Action recognition algorithms have gained significant attention in recent years, which can be indispensable for a plethora of cutting-edge applications like extended reality or Metaverse. These services often pose stringent requirement on immediate sensing and cognition of the surroundings, which necessitates immediate classifications of the captured actions (e.g., video data) that classical signal processing methods can hardly attain. In this paper, we introduced a residual artificial neural network with two-stream structure to further improve the accuracy of action recognition algorithm. Specifically, two residual networks (ResNet101) are trained separately, one by spatial RGB image streams, and another by optical flow streams. The two-strem network outputs are then fed into a fusion classifier, in which information extracted by spatial network and temporal network jointly determines the classification result. Moreover, in the training process, hyper-parameters setting and optimizer selection are performed numerically to achieve optimal performance. Finally, the recognition accuracy of the proposed algorithm has been compared to other existing widely-employed counterparts, where UCF101 data set is utilized for training and testing. Simulations validates aiming that the network can achieve higher recognition accuracy than traditional algorithms, and the two-stream method shows its superiority over the single-network counterpart.

关键词： Training Wireless communication Accuracy Metaverse Signal processing algorithms Signal processing Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Delayed Memory Unit: Modelling Temporal Dependency Through Delay Gate

arXiv

引用

arXiv 2023年

作者： Sun, Pengfei Wu, Jibin Zhang, Malu Devos, Paul Botteldooren, Dick Department of Information Technology WAVES Research Group Ghent University Technologiepark Zwijnaarde 126 Ghent9052 Belgium Department of Data Science and Artificial Intelligence The Department of Computing The Hong Kong Polytechnic University Hong Kong School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu610054 China

Recurrent neural networks (RNNs) are widely recognized for their proficiency in modeling temporal dependencies, making them highly prevalent in sequential data processing applications. Nevertheless, vanilla RNNs are confronted with the well-known issue of gradient vanishing and exploding, posing a significant challenge for learning and establishing long-range dependencies. Additionally, gated RNNs tend to be over-parameterized, resulting in poor computational efficiency and network generalization. To address these challenges, this paper proposes a novel Delayed Memory Unit (DMU). The DMU incorporates a delay line structure along with delay gates into vanilla RNN, thereby enhancing temporal interaction and facilitating temporal credit assignment. Specifically, the DMU is designed to directly distribute the input information to the optimal time instant in the future, rather than aggregating and redistributing it over time through intricate network dynamics. Our proposed DMU demonstrates superior temporal modeling capabilities across a broad range of sequential modeling tasks, utilizing considerably fewer parameters than other state-of-the-art gated RNN models in applications such as speech recognition, radar gesture recognition, ECG waveform segmentation, and permuted sequential image classification. Copyright © 2023, The Authors. All rights reserved.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

A Cross-Layer Approach to Energy-Efficient and Secure EdgeAI: Architectures, Systems and applications

A Cross-Layer Approach to Energy-Efficient and Secure EdgeAI...

引用

CSI Symposium on Real-Time and Embedded Systems and Technologies (RTEST)

作者： Muhammad Shafique NYU Abu Dhabi United Arab Emirates

ISBN: (数字)9798331529284

ISBN: (纸本)9798331529291

Modern Machine Learning (ML) and artificial Intelligence (AI) approaches, such as, the Deep neural networks (DNNs) and Large Language Models (LLMs), have shown tremendous improvement over the past years to achieve a significantly high accuracy for a certain set of tasks, like image classification, object detection, natural language processing, medical data analytics, and generative AI. However, these DNNs/LLMs require huge processing, memory, and energy costs, thereby posing gigantic challenges on building energy-efficient tinyML and EdgeAI solutions for a wide range of applications from Smart Cyber Physical Systems (CPS) and Internet of Thing (IoT) domains on resource/energy-constrained devices subjected to unpredictable and harsh scenarios. Moreover, in the era of growing cyber-security threats and nano-scale devices, the intelligent features of a smart CPS and IoT system face new type of attacks and reliability threats, requiring novel design principles for robust *** my eBRAIN lab at New York University (AD, US), I have been extensively investigating the foundations for the next-generation energy efficient, dependable and secure AI/ML computing systems, while addressing the above-mentioned challenges across different layers of the hardware and software stacks. This talk will present design challenges, advanced techniques and cross-layer frameworks for building highly energy-efficient and robust cognitive systems for the tinyML and EdgeAI applications, which jointly leverage optimizations at different layers of the software and hardware stacks, and at different design stages (e.g., design-time vs. run-time approaches). These techniques provide crucial steps towards enabling the wide-scale deployment of energy-efficient and secure embedded AI in autonomous systems like UAVs, UGVs, autonomous vehicles, Robotics, IoT-Healthcare / Wearables, Industrial-IoT, smart transportation, smart homes and cities, etc. Towards the end, I will show some glimpses of our recent a

关键词： Cross layer design Tiny machine learning Urban areas Energy efficiency Hardware Software Software reliability Smart transportation Internet of Things Wearable devices

来源：评论

学校读者我要写书评

暂无评论

脉冲视觉研究进展

引用

中国图象图形学报 2022年第6期27卷 1823-1839页

作者：黄铁军余肇飞李源施柏鑫熊瑞勤马雷王威北京大学计算机学院视频与视觉技术国家工程研究中心北京100871 北京大学人工智能研究院北京100871 北京智源人工智能研究院北京100084 北京通用人工智能研究院北京100080

视频是视觉信息处理的基础概念,传统视频的帧率只有几十Hz,不能记录光的高速变化过程,成为限制机器视觉速度的天花板,其根本原因在于视频概念脱胎于胶片成像,未能发挥电子和数字技术的潜力。脉冲视觉模型通过感光器件捕获光子,累积能量... 详细信息

视频是视觉信息处理的基础概念,传统视频的帧率只有几十Hz,不能记录光的高速变化过程,成为限制机器视觉速度的天花板,其根本原因在于视频概念脱胎于胶片成像,未能发挥电子和数字技术的潜力。脉冲视觉模型通过感光器件捕获光子,累积能量达到约定阈值时产生脉冲,形成脉冲的时间越长,表明收到的光信号越弱,反之光信号越强,据此可估计任意时刻的光强,从而实现连续成像。采用普通器件,研制了比影视视频快千倍的超高速成像芯片和相机,进而基于脉冲神经网络实现了超高速目标检测、跟踪和识别,打破了机器视觉提速依赖算力线性增长的传统范式。本文从脉冲视觉模型表达视觉信息的生物学基础和物理原理出发,介绍了脉冲视觉原理的软件模拟器及其模拟真实世界光子传播的计算过程,描述了基于脉冲视觉原理的高灵敏光电传感器件及芯片的工作机理和结构设计、基于脉冲视觉的影像重建原理以及脉冲视觉信号与普通图像信号融合的计算摄像算法与计算摄像系统,介绍了基于脉冲神经网络的超高速运动目标检测、跟踪与识别,通过对比国际国内相关研究内容和发展现状,展望了脉冲视觉的发展与演进方向。脉冲视觉芯片和系统在工业(高铁、电力和轮机等不停机监测,智能制造高速监视等)、民用(高速相机、智能交通、辅助驾驶、司法取证和体育判罚等)以及国防(高速对抗)等领域都具有巨大应用潜力,是未来值得重点关注和研究的一个重要方向。

关键词：脉冲视觉脉冲神经网络视觉信息处理类脑视觉人工智能

来源：评论

学校读者我要写书评

暂无评论

Extreme Weather Recognition Using Convolutional neural networks

Extreme Weather Recognition Using Convolutional Neural Netwo...

引用

IEEE International Symposium on Multimedia

作者： Ziqi Zhu Li Zhuo Panling Qu Kailong Zhou Jing Zhang Signal & Information Processing Laboratory Beijing University of Technology Beijing China Collaborative Innovation Center of Electric Vehicles in Beijing Beijing China

ISBN: (纸本)9781509045723

Extreme weather always brings potential risk to driving, which leads to people's life and property being put into great dangers. Therefore, the automatic recognition of extreme weather plays an important role in the application of the highway traffic condition warning, automobile auxiliary driving, climate analysis and so on. Generally, multiple sensors are adopted in traditional methods of automatic extreme weather recognition with artificial participation and low accuracy. A new extreme weather recognition method based on images by using computer vision manners has been proposed in this paper. Since the weather is affected by many factors, features that can accurately represent various weather characteristics are difficult to be extracted. Therefore, in this paper, convolutional neural networks (CNNs) are applied to settle this problem. Features of extreme weather and recognition models are generated from big data. Moreover, a large-scale extreme weather dataset, "WeatherDataset", has been collected, in which 16635 extreme weather images are divided into four classes (sunny, rainstorm, blizzard, and fog), and complex scenes are coverd. A recognition model for extreme weather is obtained through two steps: Pre-training and Fine Tuning. In Pre-training step, ILSVRC-2012 Dataset is trained to obtain the model of ILSVRC using GoogLeNet. A more accurate model for extreme weather recognition is obatined by further fine-tuning GoogLeNet on WeatherDataset. The experimental results show that the proposed method is able to achieve a high performance with the recognition accuracy rate of 94.5% and can meet the requirements of some real applications.

关键词： image recognition Feature extraction Training Sensors Road transportation Rain

来源：评论

学校读者我要写书评

暂无评论

基于STDP规则和忆阻桥突触的神经网络及图像处理

引用

中国科学：信息科学 2014年第7期44卷 920-930页

作者：王丽丹段美涛段书凯胡小方西南大学电子信息工程学院重庆400715 香港城市大学机械与生物医学工程系香港999077

忆阻器是具有记忆和类突触特性的非线性电路元件.基于此特性,文中提出了一个基于STDP(spike-time-dependent plasticity)学习规则的忆阻桥突触电路,它具有可以作为人工神经网络突触的优势.根据此优势,将这个新的电路与其他电路和网络结... 详细信息

忆阻器是具有记忆和类突触特性的非线性电路元件.基于此特性,文中提出了一个基于STDP(spike-time-dependent plasticity)学习规则的忆阻桥突触电路,它具有可以作为人工神经网络突触的优势.根据此优势,将这个新的电路与其他电路和网络结合,构成全新的电路和网络.首先将该忆阻桥突触电路和3个附加的晶体管结合在一起,实现神经网络的突触运算,并构建完整的忆阻桥突触神经网络.然后再将它与细胞神经网络结合用于图像去噪、边缘提取、角检测和汉字识别.最后,通过一系列的仿真实验证实了该方案的可行性,说明基于STDP学习规则的忆阻桥突触神经网络更具仿生特性,而且集成度更高、模板更易更换,有望解决实时的复杂的智能问题.

关键词：脉冲时间依赖的可塑性忆阻器突触神经网络图像处理

来源：评论

学校读者我要写书评

暂无评论

Super-resolving Compressed images via Parallel and Series Integration of Artifact Reduction and Resolution Enhancement

arXiv

引用

arXiv 2021年

作者： Luo, Hongming Zhou, Fei Liao, Guangsen Qiu, Guoping College of Electronics and Information Engineering Shenzhen University China Peng Cheng Laboratory Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen Key Laboratory of Digital Creative Technology China Shenzhen Institute for Artificial Intelligence and Robotics for Society Shenzhen China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Guangdong Shenzhen China

In real-world applications, such as sharing photos on social media platforms, images are always not only sub-sampled but also heavily compressed thus often containing various artefacts. Simple methods for enhancing the resolution of such images will exacerbate the artefacts, rendering them visually objectionable. In spite of its high practical values, super-resolving compressed images is not well studied in the literature. In this paper, we propose a novel compressed image super resolution (CISR) framework based on parallel and series integration of artefacts removal and resolution enhancement. Based on a mathematical inference model for estimating a clean low-resolution (LR) image and a clean high-resolution (HR) image from a down-sampled and compressed observation, we have designed a CISR architecture consisting of two deep neural network modules: the artefacts removal module (ARM) and the resolution enhancement module (REM). The ARM and the REM work in parallel with both taking the compressed LR image as their inputs, at the same time they also work in series with the REM taking the output of the ARM as one of its inputs and the ARM taking the output of the REM as its other input. A technique called unfolding is introduced to recursively suppress the compression artefacts and restore the image resolution. A unique feature of our CISR system is that it exploits the parallel and series connections between the ARM and the REM, and recursive optimization to reduce the model's dependency on specific types of degradation thus making it possible to train a single model to super-resolve images compressed by different methods to different qualities. Experiments are conducted on a mixture of JPEG and WebP compressed images without assuming apriori compression type and compression quality factor. To demonstrate our technique's real-world application value, we have also applied the trained models directly to restore social media images which have undergone scaling and compre

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Optimized Flower Categorization Using Customized Deep Learning

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND applications 2022年第4期21卷 2250029-2250029页

作者： Rani, Ritu Pundhir, Sandhya Dev, Amita Sharma, Arun Indira Gandhi Delhi Tech Univ Women Ctr Excellence Artificial Intelligence New Delhi India DSEU Kasturba Inst Technol New Delhi India

Categorizing flowers is quite a challenging task as there is so much diversity in the species, and the images of the different flower species could be pretty similar. Flower categorization involves many issues like low resolution and noisy images, occluded images with the leaves and the stems of the plants and sometimes even with the insects. The traditional handcrafted features were used for extraction of the features and the machine learning algorithms were applied but with the advent of the deep neural networks. The focus of the researchers has inclined towards the use of the non-handcrafted features for the image categorization tasks because of their fast computation and efficiency. In this study, the images are pre-processed to enhance the key features and suppress the undesired information's and the objects are localized in the image through the segmentation to extract the Region of Interest, detect the objects and perform feature extraction and the supervised classification of flowers into five categories: daisy, sunflower, dandelion, tulip and rose. First step involves the pre-processing of the images and the second step involves the feature extraction using the pre-trained models ResNet50, MobileNet, DenseNet169, InceptionV3 and VGG16 and finally the classification is done into five different categories of flowers. Ultimately, the results obtained from these proposed architectures are then analyzed and presented in the form of confusion matrices. In this study, the CNN model has been proposed to evaluate the performance of categorization of flower images, and then data augmentation is applied to the images to address the problem of overfitting. The pre-trained models ResNet50, MobileNet, DenseNet169, InceptionV3 and VGG16 are implemented on the flower dataset to perform categorization tasks. The pre-trained models are empirically implemented and assessed on the various flower datasets. Performance analysis has been done in terms of the training, validation

关键词： Flower categorization deep learning ResNet50 MobileNet DenseNet169 CNN InceptionV3 VGG16

来源：评论

学校读者我要写书评

暂无评论

PC-BNA: Parallel Convolution Binary neural Network Accelerator

PC-BNA: Parallel Convolution Binary Neural Network Accelerat...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Haihui Liu Yuang Zhang Xiangwei Zheng Mengxin Yu Baoxu An Xiaojie Liu Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology School of Information Science and Engineering Shandong Normal University Jinan China

Binary neural network (BNN) is widely used in speech recognition, image processing and other fields to save memory and speed up computing. However, the accuracy of the existing binarization scheme in the realistic dataset is obviously low, and the input layer uses 32-bit floating point to avoid excessive precision loss, which requires additional computing units and increases the computational burden. Therefore, it is very important to improve the input layer, save computing resources and reduce precision loss. In this paper, we propose a parallel convolution binary neural network accelerator architecture (PC-BNA). Based on our proposed BNN model, we design an efficient field programmable gate array (FPGA) based accelerator. The input of the first layer is binarized, the traditional binary convolution layer is replaced by a parallel binary convolution, and the network building blocks are improved. The experimental results show that the proposed PC-BNA has higher accuracy and better performance on CIFAR-10. The image recognition accuracy is as high as 91.4%, which is superior to the state-of-art of the BNN accelerator. Compared to the state-of-the-art BNN model, when using the same model size, the use of look-up-table (LUT) saves 9.08%, and the digital signal processor (DSP) saves 27.7%. The results suggest that it is promising for PC-BNA in future high performance mobile artificial intelligence applications.

关键词： Performance evaluation Convolution neural networks Digital signal processors Speech recognition Logic gates Mobile handsets

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：