检索结果-内蒙古大学图书馆

Optimized Deep Learning Classification Model for Intelligent Edge devices

Journal of engineering Science and technology Review 2024年第3期17卷 88-94页

作者： Naveen, Soumyalatha Kounte, Manjunath R Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal India School of Electronics and Communication Engineering REVA University Karnataka Bangalore560064 India

Deep learning models enable state-of-the-art accuracy in computer vision applications. However, the deeper, computationally expensive, and densely connected architecture of deep neural networks (DNN) have limitations for deploying the model on resource-constraint embedded IoT devices. We propose an efficient neural network compression framework that performs filter pruning, fine-tuning and 8-bit quantization to reduce computational complexity, inference time, and memory footprint. Furthermore, reducing the bit widths of activation and weights helps design a compact deployment model on resource-limited IoT devices such as smartphones. The proposed system is evaluated extensively on the CIFAR-10 dataset for Resnet34 and VGG16 models. In addition, we examine the efficacy of a larger model. The result shows that pruning followed by quantization compresses the neural network and compared to the baseline model, achieved an accuracy of 78.01% for Resnet34 and 82.34% for Vgg16 after pruning and quantization which is © 2024 School of Science, DUTH. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

VeriCombTest: Automated Test Case Generation Technique Using a Combination of Verification and Combinatorial Testing 18

VeriCombTest: Automated Test Case Generation Technique Using...

引用

18th International Conference on Evaluation of Novel Approaches to Software engineering, ENASE 2023

作者： Godboley, Sangharatna Department of Computer Science and Engineering National Institute of Technology Telangana Warangal India

ISBN: (纸本)9789897586477

We propose VeriCombTest which is the combination of Verification and Combinatorial Testing. We experimented with 38 C-Programs from The RERS challenge repository. Verification (CBMC) produced 940 test cases and Combinatorial Testing (PICT) populated a total of 42053 test cases. The good point is that for 40 programs, PICT consumed only 2.6 Minutes to populate the test inputs, however, CBMC which is a Static Symbolic Executor consumed 546.99 Minutes to generate the test inputs. We performed mutation analysis for this work. VeriCombTest has 355 extra killed mutants as compared to the baseline. VeriCombTest is a fully automated tool. Copyright © 2023 by SCITEPRESS - Science and technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

关键词： C (programming language)

来源：评论

学校读者我要写书评

暂无评论

AutoML - Learning, Understanding and Applying Machine Learning to Datasets 9

AutoML - Learning, Understanding and Applying Machine Learni...

引用

9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Patankar, Shreya Prajapati, Hitesh Shah, Jeet Upadhyay, Ankit K J Somaiya Institute of Technology Department of Computer Engineering Mumbai India

ISBN: (纸本)9798350397376

Current scenario of the digital world is loaded with sample amounts of data and to smartly analyze this data requires researching an interesting machine learning model to suit a dataset which is a topic of research and is more focused upon. Various state of art machine learning models like supervised, unsupervised and reinforcement models along with deep learning models are available to analyze varied datasets and for a given machine learning task, selecting one model from a large pool of options is a surprisingly challenging problem, particularly if there is a lack of evaluation data to distinguish between models and this requires for a thorough understanding of the dataset which you are using to solve the task. Dataset plays an important role in the performance of any machine learning model and not always you will get a clean / well balanced dataset to directly apply the model on. The key contribution of this paper is focused on the challenge of picking a good model which can be reformulated by doing a proper analysis and cleaning of the dataset, with the objective of recommending a suitable model for a given task based on the performance of a small set of probe models under the domain of classification and regression. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Prediction Accuracy of Corn Leaf Diseases Using A Pre-Trained Network Model

Analyzing the Prediction Accuracy of Corn Leaf Diseases Usin...

引用

2023 International Conference on Advancement in Computation and computer Technologies, InCACCT 2023

作者： Ashwini, C. Sellam, V. SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350396485

During corn's exploration and manufacturing phases, farmers have a complicated issue in accurately diagnosing corn crop infections. To solve this issue, this work provides a method for specific position three prevalent diseases of corn leaves: grey spot, leaf blight, and rusty depending on grouping and an upgraded deep learning method. Deep learning advancements paved the path for enhancing prediction accuracy as its significance is adopted over various research fields. Disease prediction and classification is time-consuming due to the lesser foreground and background intensity information. To identify three illnesses, first cluster reference images using the clustering technique, then input them into the enhanced deep network. The influences of various 'k' values on corn diagnostic techniques are investigated in this research. The trial findings show that the approach has the most significant identification impact on observations with the analytical prediction of corn disease, rust, and grey spot disease. Here, VGG-16 and ResNet18 likewise produce the best diagnostic findings, with an average diagnostic accuracy, respectively. The technique presented in this study has a diagnostic performance of 95% for the three corn diseases. It has a more substantial diagnostic impact than another four techniques and can be used to safeguard crops in the agricultural area. The simulation is done in the MATLAB 2020a environment, and various performance metrics like accuracy, precision, F1-score, recall and some other statistical measures are evaluated and compared with existing approaches. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Delaunay triangulation-based improved energy-aware clustering algorithm for WSNs

A Delaunay triangulation-based improved energy-aware cluster...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： Sivadasan, Sreeram Nagarajan, Govindan Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9798350305708

Energy efficiency is an important constraint in Wireless Sensor Networks (WSNs). In this paper, we propose a Delaunay triangulation-based approach for the efficient participation of nodes. Following a Delaunay triangulation-based mobile node placement, we introduce an Equi-Quadrant Division-based Clustering for shortest path routing to the base station (BS). The proposed method not only allows us to address issues like coverage holes and sensing range identification of a node in a random distribution but also improves node participation. Our experiments on a simulated environment show that the proposed simple algorithm is capable of giving competitive results compared to traditional clustering algorithms like FL-LEACH [11] and GA-APTEEN [12]. © 2023 IEEE.

关键词： Clustering Coverage hole Delaunay triangulation Wireless sensor network

来源：评论

学校读者我要写书评

暂无评论

Fish Species Classifier for Allergic People using CNN Algorithm 7

Fish Species Classifier for Allergic People using CNN Algori...

引用

7th International Conference on Computing Methodologies and Communication, ICCMC 2023

作者： Reddy, Puchalapalli Surya Vradhan Krishna, Mannepalli Vamsi Aishwarya, R. Yogitha, R. Kumar, K. Ashok Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9781665464086

Some people may be allergic to a variety of crustaceans, including prawns, crab, and lobster, or they may be sensitive to some types of fish. Cross-reactivity is the term for this kind of condition. This approach is useful because it is challenging to predict which fish will cause an allergic reaction in you. It is challenging to determine which fish may cause an allergic reaction. Deep learning has been a huge help in recent years in solving numerous issues. Real-time datasets are not implemented in the current systems, and they additionally the current systems are not very accurate. The proposed system utilizes CNN algorithm for detecting and classifying fish that cause allergies. The implemented system aims to help people with seafood allergies, clinical immunology, or allergies. specialist in image analysis of caught fish, detection, and species classification of fish from images. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Visual Question Answering Optimized Framework using Mixed Precision Training

Visual Question Answering Optimized Framework using Mixed Pr...

引用

2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance technology Conference, ATCON-1 2023

作者： Chowdhury, Souvik Soni, Badal National Institute of Technology Silchar Department of Computer Science and Engineering Silchar India

ISBN: (纸本)9781665456272

Thanks to the emergence and continued devel-opment of machine learning, particularly deep learning, the research on visual question and answer, also known as VQA, has advanced dramatically, with great theoretical research significance and practical application value. This field of study makes use of multimodal learning, computer vision, and natural language processing techniques. Except for a few academics who presented different types of optimized bi-linear fusion approaches that integrate text and image characteristics in an efficient way, there haven't been many efforts to optimize the VQA framework. In order to optimize the VQA problem, we offer a unique Visual Question Answering framework in this research. Because both 16-bit and 32-bit floating points provide automatic mixed precision, deep learning architectures can now be optimized with less computation and execution time. Using the VQA 2.0 and CLEVR datasets, the proposed framework has been tested against two models. In terms of overall accuracy and execution time, the experimental findings demonstrated a significant improvement. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Know Them: Convolutional Neural Networks for Facial Emotion Recognition 1

Know Them: Convolutional Neural Networks for Facial Emotion ...

引用

1st IEEE International Conference on Networking and Communications, ICNWC 2023

作者： Swathi, S. Deepika Lakshmi, M.B. Minu Dhakshina, B.S. Aanandhini, S. Sri Sairam Institute of Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350336009

Humans are capable of thousands of facial actions during communication that varies in complexity, intensity, and meaning. Emotions play a major role in Human life. Visually challenged is one of the marginalized people who face day-To-day problems without seeing the world. They find it difficult to predict the emotional state of a person surrounding them, this project helps them to understand the emotions of others through the facial expressions and thus interact well with people socially especially in public places. The rapid advancement in technology has now helped visually challenged people to explore the world through mobile phones. Few features that help them use these devices are virtual assistants, text-To-voice converters, image recognizers etc. Know Them is an application that uses image processing methods and Convolutional Neural Network (CNN) algorithms to identify the emotions of the people that the visually challenged wanted to know. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Digital Assets Fair Estimation Using Artificial Intelligence 2

Digital Assets Fair Estimation Using Artificial Intelligence

引用

2nd IEEE International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies, ViTECoN 2023

作者： Mavuri, Shobitha Kathirvel, A. Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350347982

The prediction of digital asset prices is a challenging task, as the value of digital assets is influenced by a multitude of factors, including market sentiment, technological advancements, and macroeconomic events. Despite these challenges, various approaches to digital asset price prediction have been proposed, including time-series analysis, machine learning (ML) algorithms, and Deep Learning (DL) algorithms. These algorithms involve using historical price data to make estimation about future price movements. It is important to note that digital asset price predictions are inherently uncertain and should be viewed as a guide rather than a definitive forecast. This proposed system can estimate the price for Non-Fungible Token(NFTs) collection as it can provide an accurate and reliable estimate of the value of these NFTs in the market. This information can help inform investment decisions, support market analysis, and improve the buying and selling experience for collections NFTs. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Queueing delay-based congestion control technique for seamless routing in WRSN 9

Queueing delay-based congestion control technique for seamle...

引用

9th International Conference on Smart Computing and Communications, ICSCC 2023

作者： Siron Anita Susan, T. Nithya, B. Reji, Sneha Ann Avisha Rai, M. National Institute of Technology Department of Computer Science and Engineering Tamilnadu Tiruchirappalli India

ISBN: (纸本)9798350314090

Congestion in Wireless Sensor Network (WSN) and Wireless Rechargeable Sensor Network(WRSN) can significantly impact network performance. It is essential to find a congestion control policy that minimizes congestion while maximizing throughput and bandwidth utilization. Existing solutions use either a loss-based approach which depends on timeout or duplicate acknowledgements, or a delay-based approach which depends on RTT. These solutions detect congestion only after it has occurred but does not prevent it. Thus, it is important to have a congestion policy that can detect or forecast an upcoming congestion scenario and try to prevent it. In this paper, an Queueing Delay-based Congestion Control Technique(QDCCT) is proposed that prevents congestion before it occurs and thus maximizes throughput and minimize overhead. The proposed technique takes into account both its own data flow and other background flows to identify congestion level. With the aid of run time metrics such as RTT, queueing delay variation and congestion window growth factor, the proposed algorithm prevents /resolves the congestion on the network thus allowing more packets to be transmitted with minimal delays and losses. The proposed TCP variant has been simulated and the solution has been evaluated and analyzed with the existing algorithms in terms of throughput, goodput, Packet Loss Ratio(PLR) and Packet Loss Ratio(PDR). © 2023 IEEE.

关键词： Wireless sensor networks

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：