检索结果-内蒙古大学图书馆

Managing Multi-site artificial neural networks' Activation Rates and Activation Cycles Experiments on Cross-Enterprise, Multi-site Deep Learning Systems 14th

Managing Multi-site Artificial Neural Networks' Activation R...

引用

14th International Symposium on Business Modeling and Software Design (BMSD)

作者： Grum, Marcus Univ Potsdam J Chair Business Informat Syst Esp AI Based Appl Sys D-14482 Potsdam Germany

ISBN: (纸本)9783031640728;9783031640735

Traditionally, business models and software designs used to model the usage of artificial intelligence (AI) at a very specific point in the process or rather fix implemented application. Since applications can be based on AI, such as networked artificial neural networks (ANN) on top of which applications are installed, these on-top applications can be instructed directly from their underlying ANN compartments [1]. However, with the integration of several AI-based systems, their coordination is a highly relevant target factor for the operation and improvement of networked processes, such as they can be found in cross-organizational production contexts spanning multiple distributed locations. This work aims to extend prior research on managing artificial knowledge transfers among interlinked AIs as coordination instrument by examining effects of different activation types (respective activation rates and cycles) on by ANN-instructed production machines. In a design-science-oriented way, this paper conceptualizes rhythmic state descriptions for dynamic systems and associated 14 experiment designs. Two experiments have been realized, analyzed and evaluated thereafter in regard with their activities and processes induced. Findings show that the simulator [2] used and experiments designed and realized, here, (I) enable research on ANN activation types, (II) illustrate ANN-based production networks disrupted by activation types and clarify the need for harmonizing them. Further, (iii) management interventions are derived for harmonizing interlinked ANNs. This study establishes the importance of site-specific coordination mechanisms and novel forms of management interventions as drivers of efficient artificial knowledge transfer.

关键词： AI-based Software Specification artificial neural networks Experiments Simulation

来源：评论

学校读者我要写书评

暂无评论

Transforming recommender system by integrating attention-based neural network for multimodal sentiment analysis using artificial intelligence

引用

INTERNATIONAL JOURNAL OF COMPUTER applications IN TECHNOLOGY 2024年第1-2期74卷 136-145页

作者： Vinitha, V. Bargavi, S. K. Manju Jain Univ Bengaluru Karnataka India

Sentiment analysis represents an emerging field of study in both natural language processing and computational intelligence. Recommender systems play a pivotal role in enhancing user experiences across various platforms by suggesting personalised content based on user preferences. However, conventional recommender systems often lack the capability to understand the nuanced sentiments associated with multimedia content, such as textual and visual clues which are increasingly prevalent in the digital landscape. This study proposes the architecture of a deep multi-view attention-based network model. Attention-based multimodal sentiment classification combines convolutional neural networks for image data with bidirectional encoder representations from transformers for textual data. The synergy between these two modalities enhances the model's capability of capturing abundant contextual information and visual signals. Extensive experiments on the publicly available interactive emotional dyadic motion capture data set show that the suggested method performs with an accuracy of 99.87% in capturing complicated sentiment patterns across multiple domains.

关键词： sentiment analysis recommender system artificial intelligence natural language processing BERT multimodal analysis convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A systematic review on diabetic retinopathy detection and classification based on deep learning techniques using fundus images

引用

PEERJ COMPUTER SCIENCE 2024年 10卷 e1947页

作者： Bhulakshmi, Dasari Rajput, Dharmendra Singh Vellore Inst Technol Sch Comp Sci Engn & Informat Syst Vellore Tamil Nadu India

Diabetic retinopathy (DR) is the leading cause of visual impairment globally. It occurs due to long-term diabetes with fluctuating blood glucose levels. It has become a significant concern for people in the working age group as it can lead to vision loss in the future. Manual examination of fundus images is time-consuming and requires much effort and expertise to determine the severity of the retinopathy. To diagnose and evaluate the disease, deep learning -based technologies have been used, which analyze blood vessels, microaneurysms, exudates, macula, optic discs, and hemorrhages also used for initial detection and grading of DR. This study examines the fundamentals of diabetes, its prevalence, complications, and treatment strategies that use artificial intelligence methods such as machine learning (ML), deep learning (DL), and federated learning (FL). The research covers future studies, performance assessments, biomarkers, screening methods, and current datasets. Various neural network designs, including recurrent neural networks (RNNs), generative adversarial networks (GANs), and applications of ML, DL, and FL in the processing of fundus images, such as convolutional neural networks (CNNs) and their variations, are thoroughly examined. The potential research methods, such as developing DL models and incorporating heterogeneous data sources, are also outlined. Finally, the challenges and future directions of this research are discussed.

关键词： DR DL Convolutional neural networks Recurrent neural networks Generative adversarial networks Fundus image

来源：评论

学校读者我要写书评

暂无评论

Code-Free Machine Learning Solutions for Microscopy image processing: Deep Learning

引用

TISSUE ENGINEERING PART A 2024年第19-20期30卷 627-639页

作者： Chechekhina, Elizaveta Voloshin, Nikita Kulebyakin, Konstantin Tyurin-Kuzmin, Pyotr Lomonosov Moscow State Univ Fac Med Dept Biochem & Regenerat Biomed Moscow Russia Lomonosov Moscow State Univ Fac Med Dept Biochem & Regenerat Biomed Moscow 119991 Russia

In recent years, there has been a significant expansion in the realm of processing microscopy images, thanks to the advent of machine learning techniques. These techniques offer diverse applications for image processing. Currently, numerous methods are used for processing microscopy images in the field of biology, ranging from conventional machine learning algorithms to sophisticated deep learning artificial neural networks with millions of parameters. However, a comprehensive grasp of the intricacies of these methods usually necessitates proficiency in programming and advanced mathematics. In our comprehensive review, we explore various widely used deep learning approaches tailored for the processing of microscopy images. Our emphasis is on algorithms that have gained popularity in the field of biology and have been adapted to cater to users lacking programming expertise. In essence, our target audience comprises biologists interested in exploring the potential of deep learning algorithms, even without programming skills. Throughout the review, we elucidate each algorithm's fundamental concepts and capabilities without delving into mathematical and programming complexities. Crucially, all the highlighted algorithms are accessible on open platforms without requiring code, and we provide detailed descriptions and links within our review. It's essential to recognize that addressing each specific problem demands an individualized approach. Consequently, our focus is not on comparing algorithms but on delineating the problems they are adept at solving. In practical scenarios, researchers typically select multiple algorithms suited to their tasks and experimentally determine the most effective one. It is worth noting that microscopy extends beyond the realm of biology;its applications span diverse fields such as geology and material science. Although our review predominantly centers on biomedical applications, the algorithms and principles outlined here are equally appli

关键词： deep learning open-source code-free microscopy image analysis artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Differential image-Based Scalable YOLOv7-Tiny Implementation for Clustered Embedded Systems

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第11期25卷 16036-16047页

作者： Hong, Sunghoon Park, Daejin Kyungpook Natl Univ Dept Elect & Elect Engn Daegu 41566 South Korea Kyungpook Natl Univ Sch Elect Engn Daegu 41566 South Korea

Convolutional neural networks (CNNs) for powerful visual image analysis are gaining popularity in artificial intelligence. The main difference in CNNs compared to other artificial neural networks is that many convolutional layers are added, which improve the performance of visual image analysis by extracting the feature maps required for image classification. However, algorithm optimization is required to run applications that require low-latency in edge compute modules with limited processing resources. In this paper, we propose a novel algorithm optimization method for fast CNNs by using continuous differential images. The main idea is to reduce computation variably by using the differential value of the input in each convolutional layer. Also, the proposed method is compatible with all types of CNNs, and the performance is better when the pixel value difference of continuous images is low. We use the DarkNet framework to evaluate our algorithm using fast convolution and half convolution approaches on a clustered system. As a result, when the input frame rate is 10 fps, FLOPs are reduced by about 4.92 times compared to the original YOLOv7-tiny. By reducing the FLOPs of the convolutional layer, the inference speed increases to about 4.86 FPS, performing 1.57 times faster than the original YOLOv7-tiny. In the case of parallel processing that used two edge compute modules for using half convolution approach, FLOPs reduced more, and the response speed improved. In addition, faster Object detection implementation is possible by additionally expanding up to 7 compute modules in a scalable clustered embedded system as much as the user wants.

关键词： Detectors Convolution Accuracy Computational complexity Real-time systems Feature extraction Convolutional neural networks Classification algorithms Graphics processing units Embedded systems clustered systems deep learning fast convolution

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural Network in Medical image Analysis: A Review

引用

ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING 2023年第4期30卷 2793-2810页

作者： Kshatri, Sapna Singh Singh, Deepak Shri Shankaracharya Inst Profess Management & Tech Dept CSE Artificial Intelligence Raipur India Natl Inst Technol Dept Comp Sci & Engn Raipur India

Medical image analysis helps in resolving clinical issues by examining clinically generated images. In today's world of deep learning (DL) along with advances in computer vision, the available medical imaging data from scientific archives, academic publications, and clinical manuals along with advances in computer vision, present an opportunity could be of great use. The implication of artificial intelligence and DL has increased steadily over the past decades. Studies based on convolutional neural networks (CNNs) are the primary focus, as it is often regarded as one of the most effective tools for analyzing images and other structured data. CNN models naturally understand space and hierarchy using backpropagation, convolution, pooling, and link layers. Most of the research is concentrated on image pre-processing, classification, and evaluating various applications of CNN techniques in medical imaging. To explore this field of research, we carried out a survey wherein we analyzed the papers that were pertinent to MRI image analysis, specifically MRI pre-processing, segmentation and diagnosis. This article provides a thorough overview of medical image analysis by CNNs, along with its shortcomings and potential. The application of CNNs in medical image analysis, such as its use for brain magnetic resonance imaging (MRI) analysis, pre-processing, segmentation, data preparation, and post-processing were the main areas of focus. We further explored large-scale retrieval, which can increase MRI image processing efficiency. Overall, this study analyzed current advancements in this area and the associated major challenges. The publications were categorized by pattern recognition applications before classifying them using a taxonomy based on human architecture.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

ElasticDNN: On-Device neural Network Remodeling for Adapting Evolving Vision Domains at Edge

引用

IEEE TRANSACTIONS ON COMPUTERS 2024年第6期73卷 1616-1630页

作者： Zhang, Qinglong Han, Rui Liu, Chi Harold Wang, Guoren Chen, Lydia Y. Beijing Inst Technol Beijing 100081 Peoples R China Delft Univ Technol NL-2628 Delft Netherlands

Executing deep neural networks (DNN) based vision tasks on edge devices encounters challenging scenarios of significant and continually evolving data domains (e.g. background or subpopulation shift). With limited resources, the state-of-the-art domain adaptation (DA) methods either cause high training overheads on large DNN models, or incur significant accuracy losses when adapting small/compressed models in an online fashion. The inefficient resource scheduling among multiple applications further degrades their overall model accuracy. In this paper, we present ElasticDNN, a framework that enables online DNN remodeling for applications encountering evolving domain drifts at edge. Its first key component is the master-surrogate DNN models, which can dynamically generate a small surrogate DNN by retaining and training the large master DNN's most relevant regions pertinent to the new domain. The second novelty of ElasticDNN is the filter-grained resource scheduling, which allocates GPU resources based on online accuracy estimation and DNN remodeling of co-running applications. We fully implement ElasticDNN and demonstrate its effectiveness through extensive experiments. The results show that, compared to existing online DA methods using the same model sizes, ElasticDNN improves accuracy by 23.31% and reduces adaption time by 35.67x. In the more challenging multi-application scenario, ElasticDNN improves accuracy by an average of 25.91%.

关键词： Adaptation models Training Task analysis image edge detection artificial neural networks Graphics processing units Data models Edge vision deep neural networks domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Anomaly characterization for the condition monitoring of rotating shafts exploiting data fusion and explainable convolutional neural networks

引用

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 2025年

作者： Parziale, Marc Yeung, Yip Fun Youcef-Toumi, Kamal Giglio, Marco Cadini, Francesco MIT Dept Mech Engn Cambridge MA USA Politecn Milan Dept Mech Engn Via Masa 1 I-20156 Milan Italy

Condition monitoring of rotating shafts is a critical task in the maintenance of mechanical systems. Rotating shafts are essential components in many machines, and their failure can result in serious consequences, including system downtime, production loss, equipment damage, and safety issues. Advanced sensor technologies and deep learning algorithms have facilitated data collection and processing, providing vital insights into system health. However, despite the vast availability of sensors, the data used to train these algorithms often consists of single-nature signals, and systems are typically damaged to simulate different faulty scenarios. Additionally, the perceived opacity of deep learning algorithms, often referred to as black-box models, has raised concerns about their credibility in critical domains. Hence, this paper addresses these challenges by (i) proposing various explainable artificial intelligence (XAI) methods in a rotating shaft case study, (ii) using a novel data-fusion approach to combine multiple signals, and (iii) leveraging data from an innovative experimental set-up mimicking real-world industrial machines. The employed experimental set-up is equipped with a diverse array of sensors capable of capturing signals of varying nature, and it streamlines the automated introduction of four distinct fault types in an innovative manner. Applied to convolutional neural networks, the employed XAI methods enhance transparency in deep learning models, providing practical insights for complex systems. This approach not only addresses the limitations associated with single-nature signals and simulated faults but also contributes to the credibility and interpretability of deep learning models in critical applications.

关键词： Condition monitoring anomaly characterization convolutional neural networks explainable artificial intelligence data fusion

来源：评论

学校读者我要写书评

暂无评论

An innovative approach to parasite classification in biomedical imaging using neural networks

引用

ENGINEERING applications OF artificial INTELLIGENCE 2025年 143卷

作者： Aytac, Ozlem Senol, Feray Ferda Tuncer, Ilknur Dogan, Sengul Tuncer, Turker Elazig Fethi Sekin State Hosp Med Microbiol Elazig Turkiye Interior Minist Elazig Governorship Elazig Turkiye Firat Univ Technol Fac Dept Digital Forens Engn Elazig Turkiye

Background and objective: In light of the increasing demand for precise and effective parasite detection in biomedical imaging, current models frequently depend on widely used convolutional neural networks (CNNs), with minimal innovation in feature selection and engineering for artificial intelligence. This study addresses these gaps by introducing a novel CNN, termed BLGSNet (Batch Normalization, Layer Normalization, GELU - Gaussian Error Linear Unit - and Swish functions-based network), specifically designed for parasite detection. BLGSNet increases feature engineering deploying a unique intersection-based feature selection method integrated into the deep learning model to improve classification accuracy. Materials and methods: Using a publicly accessible image dataset with eight classes, including two blood cell types and six parasite types, we developed the BLGSNet architecture, which incorporates transformer-inspired design, convolution-based residual blocks, batch normalization, layer normalization, GELU, and Swish activation functions. The accompanying deep feature engineering model employs transfer learning and includes four key phases: (i) feature extraction using BLGSNet, (ii) feature selection using intersection methodology with neighborhood component analysis, chi-square, minimum redundancy maximum relevance, and ReliefF feature selectors, (iii) classification with k-nearest neighbors (kNN) and support vector machine (SVM), and (iv) automated selection of the optimal output. Results: The proposed BLGSNet was trained on the designated dataset, achieving a test accuracy of 99.25%, while the deep feature engineering model attained an improved test accuracy of 99.59%, demonstrating the model's robustness. Conclusion: The high classification accuracy achieved by BLGSNet and the feature engineering model highlights their potential in addressing the complex task of parasite detection.

关键词： artificial intelligence Intersection-based feature selection Deep feature engineering Parasite classification Cell detection Biomedical image classification

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis for Advancements and Challenges in Deep Learning Models for image processing 5th

A Comprehensive Analysis for Advancements and Challenges in ...

引用

5th International Conference on Data Science, Machine Learning and applications

作者： Ch, Ravikumar Chary, Kalvog Prakasha Srinivas, S. Bhavani, Tedla Veeranna Chaitanya Bharathi Inst Technol Dept Artificial Intelligence & Data Sci Hyderabad Telangana India CVR Coll Engn Dept CSE Cyber Secur Hyderabad Telangana India CVR Coll Engn Dept Comp Sci & Engn Hyderabad Telangana India Vardhaman Coll Engn Dept Comp Sci & Engn Hyderabad Telangana India Sri Indu Coll Engn & Technol Dept Informat Technol Hyderabad Telangana India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

Deep learning, a profound advancement in artificial intelligence, has demonstrated remarkable achievements, particularly in image processing. The rapid evolution of deep learning in architecture, training methods, and specifications has driven the expansion of image processing techniques. However, the increasing complexity of model structures challenges the effectiveness of the back propagation algorithm, and issues like the accumulation of unlabeled training data and class imbalances hinder deep learning performance. To address these challenges, there's a growing need for innovative deep models and cutting-edge computing paradigms to enable more sophisticated image content analysis. In this study, we conduct a comprehensive examination of four deep learning models utilizing Convolutional neural networks (CNNs), clarifying their theoretical foundations within the image processing context, opening the door for further research. CNNs are notably essential for image processing due to their ability to handle complex images effectively.

关键词： Deep learning image processing Backpropagation algorithm Convolutional neural networks (CNNs) Model structures

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：