检索结果-内蒙古大学图书馆

Computing, Sciences and Communications (ICCSC), International conference on

作者： Hariram Sampath Kumar Shambhavi Pande Archana Singh Partha Sarathi Mangipudi Dept. of Artificial Intelligence (of ASET) Amity University Noida Uttar Pradesh India Dept. of Computer Science & Engineering (of ASET) Amity University Noida Uttar Pradesh India

ISBN: (数字)9798350353648

ISBN: (纸本)9798350353655

High-resolution aerial imaging is crucial in the field of military applications for gathering intelligence and devising strategic plans. This research examines super-resolution approaches, with a specific emphasis on three Deep Learning neural Models: Super-Resolution Convolutional neural networks (SRCNN), Generative Adversarial networks (GAN), and Super-Resolution Generative Adversarial networks (SRGAN). The study does a rigorous comparison investigation of these models, with the goal of determining their effectiveness in producing high-resolution aerial photographs. In order to conduct a thorough evaluation of these models, a wide range of datasets is utilised, which includes MNIST, Fashion MNIST, DIV2K, and DOTA. This extensive range of options enables a comprehensive evaluation of the models' performance across a wide range of data complexities, ranging from simple geometric forms to complicated real-world aerial landscapes. This research offers detailed analysis of the datasets, allowing for a thorough examination of the strengths and shortcomings of the models. It provides valuable insights into how these models might be applied to real-world military situations. The results of this study have important consequences for military intelligence. Efficiently generating super-resolved aerial images can improve target recognition, terrain analysis, and threat assessment. Furthermore, comprehending the relative strengths of various models enables military agencies to customise their image processing approaches to meet unique operational needs. This research facilitates the integration of modern deep learning techniques with the complexities of military intelligence, thereby enabling better informed decision-making processes and eventually strengthening national security operations.

关键词： Deep learning Target recognition Superresolution Decision making Imaging Reconnaissance Generative adversarial networks Threat assessment Complexity theory National security

来源：评论

学校读者我要写书评

暂无评论

Ship recognition and classification using silhouettes extracted from optical images

Ship recognition and classification using silhouettes extrac...

引用

IEEE Signal processing and Communications applications (SIU)

作者： Göktuğ Kağan Yüksel Buğra Yalıtuna Ömer Faruk Tartar Faiz Caner Adlı Kaan Eker Onur Yörük Bilkent Universitesi Ankara TR

In this paper, extraction of ship signatures from silhouette images of three-dimensional ship models and ship recognition from optical images are investigated. First of all, from the silhouette images of 3-dimensional ship models, with the help of feature vectors, ship signatures are created. Using three-dimensional ship models gets rid of the difficulty of obtaining real videos for the database and makes it possible to obtain information about ships from every angle. Then, created ship signatures are collected in a synthetic database. In the next stage, using segmentation and artificial neural networks, ship recognition and classification are performed. In this paper, how all of the stages are done is explained and obtained numerical results are provided to illustrate used theoretical solutions.

关键词： Marine vehicles Solid modeling Computational modeling Analytical models image recognition Optical imaging Databases

来源：评论

学校读者我要写书评

暂无评论

Multimodal Learning Data Intelligent Personalized Learning Resource Recommendation System for Web-Based Classrooms

Multimodal Learning Data Intelligent Personalized Learning R...

引用

IEEE International conference on artificial Intelligence and Computer applications (ICAICA)

作者： Shan Wang Shandong Vocational College of Science and Technology Weifang China

ISBN: (数字)9798350377255

ISBN: (纸本)9798350377262

Traditional recommender systems are difficult to fully explore the complex correlation between multimodal data and cannot meet learners' personalized needs. To this end, this paper proposes an intelligent personalized learning resource recommendation system (MDRS) based on multimodal data, which achieves accurate recommendation of learning resources by integrating advanced technologies such as natural language processing, computer vision, and deep learning, and at the same time, by introducing a multimodal data processing mechanism and personalized knowledge graph construction. First, we introduce a multimodal feature embedding module for the model, which utilizes deep neural networks for feature extraction and embedding of data in different modalities, such as text, image, audio, and video, in order to capture the multidimensional characteristics of resources. Subsequently, through the cross-modal fusion and attention mechanism module, the model performs weighted fusion of multimodal features to strengthen the expression of features related to user learning needs. By dynamically adjusting the weights of each modality, the system is able to automatically focus on the features that are most important for learning resource recommendation and eliminate redundant information. This mechanism ensures the system's adaptive fusion of different modalities, allowing multimodal information to be deeply related at the feature level. Next, we design a personalized knowledge graph module to associate users' learning behaviors with resource knowledge points to provide background knowledge support for the recommendation process, which updates the knowledge graph in real time by tracking learners' learning paths, preferences, and knowledge mastery and optimizes the recommended content based on learners' dynamic needs. Finally, through the recommendation optimization module, the recommendation strategy is dynamically adjusted in combination with user feedback to enhance the learning

关键词： Adaptation models Computational modeling Knowledge graphs Learning (artificial intelligence) Feature extraction Data processing Data models Real-time systems Recommender systems Optimization

来源：评论

学校读者我要写书评

暂无评论

Multi scale multi directional shear operator for personal recognition using Conjunctival vasculature

Multi scale multi directional shear operator for personal re...

引用

IEEE conference on Technologies for Homeland Security

作者： Sriram Pavan Tankasala Plamen Doynov Computer Science and Electrical Engineering UMKC Kansas City MO US MRI Global Kansas City MO US

In this paper, we present the results of a study on utilization of Conjunctival vasculature pattern as a biometric modality for personal identification. The visible red blood vessel patterns on the sclera of the eye is gaining acceptance as a biometric modality due to its proven uniqueness and easy accessibility for imaging in the visible spectrum. After acquisition, the images of Conjunctival vascular patterns are enhanced using the difference of Gaussian (DoG). The feature extraction is performed using a multi-scale, multi-directional shear operator (Shearlet transform). Linear discriminant analysis (LDA), neural networks (NN) and pairwise distance metrics were used for classification. In the study, images of 50 subjects are acquired with a DSLR camera at different gazes and multiple distances (CIBIT-I dataset). Additionally, the performance of the proposed algorithms is tested using different gaze images acquired from 35 subjects using an iPhone (CIBIT-ii dataset). ROC AUC analysis is used to test the classification performance. Areas under the curve (AUC) and equal error rates (EER) are reported for all acquisition scenarios and different processing algorithms. The best EER value of 0.29% is obtained for a CIBIT-I dataset using NN and a 2.44% EER value for a CIBIT-ii dataset using LDA.

关键词： Transforms Feature extraction image segmentation Measurement artificial neural networks Cameras

来源：评论

学校读者我要写书评

暂无评论

AI based Analysis of Hyperspectral images with Spectacular Efficacy in Video Analytics

AI based Analysis of Hyperspectral Images with Spectacular E...

引用

Intelligent & Innovative Practices in Engineering & Management (iiPEM), International conference on

作者： Samarth Yogesh Jadhav Rutuja Rajatam More Bhagyashree Ashok Tingare G. Prasanna Lakshmi Shivam Kolse N.K. Darwante Department of Information Technology Sanjivani College of Engineering Kopargaon MH India Department of Artificial Intelligence and Data Science D Y Patil College of Engineering Akurdi Pune School of Computer Science and Engineering Sandip University Nashik Maharashtra Department of Electronics and Computer Engineering Sanjivani College of Engineering Kopargaon MH India

ISBN: (数字)9798350390049

ISBN: (纸本)9798350390056

Hyperspectral imaging and artificial intelligence (AI) have transformed imaging and data processing through their ability to capture and analyze detailed spectral information. This paper explores the integration of hyperspectral imaging with AI, focusing on its impact on video analytics. Hyperspectral imaging provides comprehensive, multi-dimensional data by capturing a wide range of spectral wavelengths, enabling precise material identification and environmental monitoring beyond traditional RGB imaging. The synergy between hyperspectral imaging and AI enhances real-time analysis and decision-making by leveraging deep learning algorithms for pattern recognition and anomaly detection. This study introduces a novel AI-based hyperspectral image analysis approach for video analytics, utilizing convolutional neural networks (CNNs) and hybrid CNN-attention models to improve object recognition and classification. The methodology is validated through experiments that measure classification accuracy, processing speed, and resilience to varying conditions. Results demonstrate significant improvements in accuracy and efficiency over traditional methods, highlighting the potential for advanced applications in surveillance, environmental monitoring, and industrial quality control.

关键词： Accuracy image analysis Visual analytics Surveillance Quality control Real-time systems Environmental monitoring Object recognition artificial intelligence Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Monolithic-3D Inference Engine with IGZO Based Ferroelectric Thin Film Transistor Synapses

TechRxiv

引用

TechRxiv 2022年

作者： De, Sourav Lederer, Maximilian Raffel, Yannick Lehninger, David Thunder, Sunanda Jank, Michael P.M. Ali, Tarek Kämpfe, Thomas Seidel, Konrad Sanctis, Shawn Fraunhofer-Institut für Photonische Mikrosysteme IPMS Center Nanoelectronic Technologies Dresden Germany Fraunhofer-Institut für Integrierte Systeme und Bauelementetechnologie Erlangen Germany

Instigated by the plethora of data generated by edge devices and IoT devices, machine learning has become the de facto choice of everyone for solving many tasks. applications such as intelligent healthcare monitoring systems, smart watches, or autonomous cars require real-time processing of the data or image, which is done by machine learning algorithms with higher efficiency than humans. There are two possible methods for artificial intelligence-1. non-von-Neumann hardware-based implementation of neural networks 2. traditional computer science-based approach for neural networks or traditional von Neumann architecture-based implementation of neural networks The standard von-Neumann performance of neural networks, where the memory and computation parts are segregated, suffers from severe latency with an increasing number of edge devices. However, the multitude of edge devices used in our daily life imposes strict restrictions on latency, device area, and power consumption for hardware. Therefore, we need to take the route beyond the CMOS-based mixed-signal implementation of neural networks, where the memory bandwidth is not limited by the quintessential von Neumann architecture. The primary motivation of present-day research on the non-von-Neumann computing architecture is to build dedicated hardware modules for implementing low-power, fast-computing units without affecting the recent trend of scaling. This chapter focuses on amorphous indium-gallium-zinc-oxide (α-IGZO) based and their system-level applications. Back-end-of-line (BEoL) compatible indium IGZO-based multibit one-time programmable (OTP) ferroelectric thin film transistors (FeTFT) with lifelong retention capability were fabricated. The maximum temperature of the entire fabrication process was limited to 350oC. The gate-stack engineering by varying the thickness ratio of ferroelectric hafnium zirconium oxide (HZO) and IGZO layer fomented excellent data-retention capability and one-time programming propert

关键词： ii-VI semiconductors

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT-Edge Computation with Data Forwarding based Decentralized Deep neural networks

Enhancing IoT-Edge Computation with Data Forwarding based De...

引用

International conference on image Information processing

作者： Bmg Prasad Rachappa Jopate Pankaj Savita A Basi Reddy B Prabu Shankar M S Arunkumar Department of CSE Ravindra College of Engineering for Women(RCEW Autonomous) Kurnool Andhra Pradesh India Department of Information Technology University of Technology And Applied Sciences - Al Mussanah Al Muladha Muscat Sultanate of Oman Department of CSE Sagar Institute of Science & Technology Bhopal Organization-Sagar Institute of Science & Technology Bhopal Madhya Pradesh India Department of Computer Science and Engineering School of Computing Mohan Babu University Tirupati Andhra Pradesh India Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Banglore Karnataka India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

The incorporation of edge computing has become essential in the big data and Internet of Things age to tackle issues related to latency, real-time processing, and data scale. This paper delves into the imperative need for edge computing within the context of big data environments. Distributed deep learning methodologies are explored, encompassing a diverse array of deep learning models. Particularly, a novel paradigm named Data Forwarding based Decentralized Deep neural Network (DF-DDNN) is introduced to achieve low latency IoT-Edge computation. In order to reduce latency in Io T ecosystems, the DF-DDNN model makes use of edge devices’ processing capabilities. By strategically distributing data processing and computation at the edge, this model seeks to overcome inherent limitations of conventional Io T architectures, with a keen focus on network, processing, and overall latencies. The research provides a thorough performance evaluation that compares the DF-DDNN model’s performance versus conventional IoT models in a number of areas. The outcomes demonstrate how much better the suggested DF-DDNN model is than traditional IoT systems. Notably, improvements are evident in terms of reduced network latency, accelerated processing speeds, and overall latency mitigation. This research underscores the critical importance of embracing edge computing in the context of big data and deep learning applications. The DF-DDNN model emerges as a promising avenue for advancing IoT-Edge computation, effectively addressing latency concerns and augmenting the performance of IoT-enabled systems.

关键词： Deep learning Performance evaluation Computational modeling Biological system modeling artificial neural networks Big Data Data models

来源：评论

学校读者我要写书评

暂无评论

Real-time Background Subtraction via L1 Norm Tensor Decomposition

Real-time Background Subtraction via L1 Norm Tensor Decompos...

引用

Asia-Pacific Signal and Information processing Association Annual Summit and conference

作者： Taehyeon Kim Yoonsik Choe Yonsei University Seoul Korea

ISBN: (纸本)9781728102436;9789881476852

Currently, background subtraction is being actively studied in many image processing applications. Nuclear Norm Minimization (NNM) and Weighted Nuclear Norm Minimization (WNNM) are commonly used background subtraction methods based on Robust Principal Component Analysis (RPCA). However, these techniques approximate the RPCA rank function and take the form of an iterative optimization algorithm. Therefore, due to the approximation, the NNM solution can not converge if the number of frames is small. In addition, the NNM and WNNM processing times are delayed because of their iterative optimization schemes. Thus, NNM and WNNM are not suitable for real-time background subtraction. In order to overcome these limitations, this paper presents a real-time background subtraction method using tensor decomposition in accordance with the recent tensor analysis research trend. In this study, we used the closed form TUCKER2 decomposition solution to omit the iterative process while retaining the L1 norm of the RPCA rank function. This proposed method allows for convergence even when the number of frames is small. Compared to NNM and WNNM, the proposed method reduces the processing time by more than 80 times and has a higher precision even when the number of frames are less than 10.

关键词： Real-time systems artificial neural networks Optimization Minimization Principal component analysis Iterative algorithms

来源：评论

学校读者我要写书评

暂无评论

LeQC-At: Learning Quantization Configurations During Adversarial Training for Robust Deep neural networks

LeQC-At: Learning Quantization Configurations During Adversa...

引用

Euromicro Symposium on Digital System Design

作者： Siddharth Gupta Salim Ullah Akash Kumar Chair of Embedded Systems Ruhr-Universität Bochum Bochum Germany

ISBN: (数字)9798350380385

ISBN: (纸本)9798350380392

Due to the high feature learning capability of Deep neural networks (DNNs), they are widely used in state-of-the-art machine learning tasks such as image and text recognition and natural language processing. However, in the recent developments of deep learning models, it has been observed that specially crafted inputs (adversarial samples) can deceive DNNs and result in incorrect predictions with high confidence. Such incorrect predictions by adversarially attacked DNNs can have devastating results in safety-critical applications. This situation can be further exacerbated in quantized DNNs, which employ reduced precision numbers to reduce the overall computational complexity of DNNs. To this end, this work proposes a framework for the joint optimization of DNNs to improve the natural accuracy of quantized DNNs and increase the robustness of the quantized models against adversarial attacks. In particular, the proposed framework employs quantization step size aware adversarial training of DNNs. Our proposed framework is generic and can be utilized with any quantization scheme that allows learning of quantization configurations during training. Furthermore, we present a novel loss function for adversarial training to improve the quantized networks' accuracy. For example, our 3-bit quantized adversarial training of ResNet-18, ResNet-34, and WideResNet shows up to 21.63%, 24.49%, and 15.08% higher inference accuracy with attacked data, respectively, when compared to 3-bit vanilla quantized adversarial training on benchmark datasets.

关键词： Training Representation learning Quantization (signal) Accuracy Text recognition Tiny machine learning artificial neural networks Predictive models Robustness Optimization

来源：评论

学校读者我要写书评

暂无评论

Designing Real-Time Hand Gesture Recognition Systems for Hearing Impaired: Combining CNNs with Human-Centric HCI Approaches

Designing Real-Time Hand Gesture Recognition Systems for Hea...

引用

Global conference for Advancement in Technology (GCAT)

作者： Vidhya Shree N S Rajani G N Shilpa H M Gowri Ravishankar Dept. Information Science and Engineering Siddaganga Institute of Technology Tumakuru India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

The human-computer interaction (HCI) encompasses a variety of interactions, including gestural ones. In HCI, gesture recognition refers to nonverbal movements that can be utilized for communication. Information can be delivered by using a system that recognizes human gestures. This is a major area of HCI that deals with user interfaces and device interfaces. The goal of gesture recognition is to capture certain gestures that are then picked up by a camera or other *** are numerous applications where hand gestures can be utilized as a means of communication. People with a variety of disabilities, such as those suffering from strokes, hearing loss, or speech problems, can use it to communicate and take care of their fundamental needs. The goal of hand gesture recognition is to create more natural and intuitive ways for people to engage with computers while also opening up new avenues for *** gestures have been the subject of numerous studies in the past. Various methods for carrying out hand gesture experiments were suggested by some studies. There are several methods available for extracting characteristics from photos in image processing, and artificial intelligence offers a variety of classifiers for classifying different kinds of data. An efficient method is needed to extract images and identify different small motions and movements from 2D and 3D hand gestures. The goal of this work is to create a hand gesture recognition system based on artificial intelligence that can recognize a hand gesture automatically using the test dataset. Within the class of deep learning neural networks is the convolution neural network.

关键词： Hands Support vector machines Accuracy Heuristic algorithms neural networks Gesture recognition Auditory system Real-time systems Reliability Testing

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：