检索结果-内蒙古大学图书馆

Machine and deep learning methods in identifying malaria through microscopic blood smear: A systematic review

ENGINEERING applications OF artificial INTELLIGENCE 2024年第PartE期133卷

作者： Sukumarran, Dhevisha Hasikin, Khairunnisa Khairuddin, Anis Salwa Mohd Ngui, Romano Sulaiman, Wan Yusoff Wan Vythilingam, Indra Divis, Paul C. S. Univ Malaya Fac Engn Dept Biomed Engn Kuala Lumpur Malaysia Univ Malaya Fac Engn Dept Elect Engn Kuala Lumpur Malaysia Univ Malaysia Sarawak Fac Med & Hlth Sci Dept Para Clin Sci Sarawak Malaysia Univ Malaya Fac Med Dept Parasitol Kuala Lumpur Malaysia Univ Malaysia Sarawak Fac Med & Hlth Sci Malaria Res Ctr Sarawak Malaysia Univ Malaya Fac Engn Ctr Intelligent Syst Emerging Technol CISET Kuala Lumpur Malaysia

Despite the persistency of World Health Organization to eliminate malaria since 1987, malaria disease continues to pose a significant threat to global health. As the severity of malaria persists over the years, there is a critical need for an automated diagnosis system for more efficient diagnosis and effective treatment administration. To mitigate the increase in mosquito-borne diseases, there has been a heightened interest in the application of artificial intelligence (AI), specifically deep learning. With the assistance of the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) framework, an extensive review of current state of automated malaria diagnosis systems utilizing machine learning and deep learning approaches was performed across eight scientific databases, with 50 articles shortlisted from the years 2015-2023. Besides, identifying the research gaps, we synthesise the existing literature, analyse the outcomes, and explore the critical parameters that influence model performance. From the review, the prevailing models primarily focus on binary classification while disregarding cross-dataset validations and multi-stage classification. This gap challenges the delivering effective treatments, especially considering potential drug resistance. Established protocols and classification models are needed to anticipate the specific malaria species. The keywords in automated malaria diagnosis that we identified include machine learning, deep learning, transfer learning, and convolutional neural networks. Through examinations of the constraints in current methodologies, we provide valuable suggestions that could propel the field of automated malaria diagnosis. This systematic review provides a comprehensive overview, critical insights, and a roadmap for future research endeavours in this vital domain of healthcare.

关键词： Malaria Machine learning Conventional machine learning Deep learning Convolutional neural network Transfer learning

来源：评论

学校读者我要写书评

暂无评论

AI Based Automated Food Recognition Using CNN for Fitness Mobile Application

AI Based Automated Food Recognition Using CNN for Fitness Mo...

引用

IEEE Symposium on Industrial Electronics & applications (ISIEA)

作者： Atif Mahmood Rafay Mahmood Saaidal Razalli Azzuhri Zati Hakim Azizul Hasan Miss Laiha Mat Kiah Faculty of Information Technology And Computer Science University of Central Punjab Lahore Pakistan Department of Computer System & Technology Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia Department of Artificial Intelligence Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia

Eating a healthy, balanced diet with regular exercise is important for maintaining physical and mental health. Healthy diet and exercise promise a healthier lifestyle. Other than that, people competing in different sports need a customized, strict workout and diet plan. Trainees offer their best at gymnasium by following a strict workout plan recommended by their coaches. However, there is no way till now to determine if the trainees are taking the prescribed diet strictly. Therefore, an optimized application with the feature of real time scanning of the prescribed meal can be helpful to overcome this problem. For this purpose, we have used Convolutional neural networks (CNN) along with image processing. Using ResNet50 with activation functions of ReLU and Softmax, our trained CNN model and the proposed architecture achieved an accuracy of 82.70 percent. We used CNN pre-trained models such as InceptionV3 with LeakyReLU and Softmax, InceptionV3 with ReLU and Softmax, VGG16 with ReLU and Softmax, VGG16 with ReLU and Softmax, and ResNet50 with ReLU and Softmax, so the achieved accuracy, respectively, is 78%, 71%, 58%, 56%, and 82.7%. Therefore, the proposed model has the potential to achieve high performance on real time food scanning which can be used in online fitness platforms(mobile applications and websites) and fitness gadgets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

image compression and enlargement algorithms

引用

International Journal of Circuits, Systems and Signal processing 2021年 15卷 836-846页

作者： Burova, I.G. Dem’yanovich, Yu.K. Terekhov, A.N. Altynova, A.Yu. Satanovskiy, A.D. Babushkin, A.A. St. Petersburg State University 7/9 Universitetskaya nab St.Petersburg199034 Russia

In some cases, there are problems associated with the compression and enlargement of images. The use of splines is quite effective in some cases. In this paper, a new image compression algorithm is presented. The features of increasing the size of an image when using local polynomial or non-polynomial splines are considered. The main method for enlarging an image is based on the use of splines of the second and third order of approximation. Polynomial and trigonometric splines are considered. To speed up the process of enlarging the image, we used the parallelization techniques. © 2021, North Atlantic University Union NAUN. All rights reserved.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Smart Sorting: Enhancing Almond Quality with DenseNet-201-Based image Classification

Smart Sorting: Enhancing Almond Quality with DenseNet-201-Ba...

引用

International Conference on Information Science and Communications Technologies (ICISCT)

作者： Arpanpreet Kaur Amit Kumar Mishra Bura Vijay Kumar Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Computer Science and Engineering Graphic Era Hill University Dehradun Graphic Era Deemed to be University Dehradun Uttarakhand India School of Computer Science and Artificial Intelligence SR University Warangal India

ISBN: (数字)9798331527921

ISBN: (纸本)9798331527938

Considered as two varieties: damaged and undamaged, almonds are a rather consumed agricultural product. Maintaining consumer satisfaction and industry standards depends on good detection of damaged almonds., which could be influenced by mechanical damage., mold, or pests. On the other hand, slow, labor-intensive hand inspection methods prone to mistake demand automated classification systems. This work meets that demand by automating the categorization process using DenseNet-121, a convolutional neural network (CNN), therefore lowering labor expenses and increasing accuracy. Particularly considering the tiny dataset of 1,000 photos split equally between damaged and undamaged almonds, DenseNet-121's architecture-with its dense connections and capacity to reuse features-is well-suited for the almond classification challenge. Pre-trained on imageNet and polished for this particular purpose, the model-trained across 60 epochs using a 32-batch size-achieved an accuracy of 95.27%. Random horizontal flips, resizing., and center cropping among other data augmentation techniques improved the model's generalizing capability. This work demonstrates the model's ability to substitute human methods in actual environments by showing how well it employs little visual information to classify almonds. Automating almond sorting speeds and provides higher consistency in quality control as well as efficiency of sorting. This work opens the road for further research of machine learning techniques in agricultural processing with possible applications in food quality assurance.

关键词： Accuracy Quality assurance Process control Quality control Machine learning Data augmentation Data models Convolutional neural networks Sorting image classification

来源：评论

学校读者我要写书评

暂无评论

Designing DNNs for a trade-off between robustness and processing performance in embedded devices*

Designing DNNs for a trade-off between robustness and proces...

引用

Conference on Design of Circuits and Integrated Circuits (DCIS)

作者： Jon Gutiéerrez-Zaballa Koldo Basterretxea Javier Echanobe Dept. of Electronics Technology University of the Basque Country Bilbao Spain Dept. of Electricity and Electronics University of the Basque Country Leioa Spain

ISBN: (数字)9798350364392

ISBN: (纸本)9798350364408

Machine learning-based embedded systems employed in safety-critical applications such as aerospace and autonomous driving need to be robust against perturbations produced by soft errors. Soft errors are an increasing concern in modern digital processors since smaller transistor geometries and lower voltages give electronic devices a higher sensitivity to background radiation. The resilience of deep neural network (DNN) models to perturbations in their parameters is determined, to a large extent, by the structure of the model itself, and also by the selected numerical representation and used arithmetic precision. When compression techniques such as model pruning and model quantization are applied to reduce memory footprint and computational complexity for deployment, both model structure and numerical representation are modified and thus, soft error robustness also changes. In this sense, although the choice of activation functions (AFs) in DNN models is frequently ignored, it conditions not only their accuracy and trainability, but also compressibility rates and numerical robustness. This paper investigates the suitability of using bounded AFs to improve model robustness against DNN parameter perturbations, assessing at the same time the impact of this choice on deployment in terms of model accuracy, compressibility, and computational burden. In particular, we analyze encoder-decoder fully convolutional models aimed at performing semantic segmentation tasks on hyperspectral images for scene understanding in autonomous driving. Deployment characterization is performed experimentally on an AMD-Xilinx’s KV260 SoM.

关键词： Performance evaluation Program processors image coding Computational modeling Perturbation methods artificial neural networks Robustness Numerical models Autonomous vehicles Resilience

来源：评论

学校读者我要写书评

暂无评论

Cross-Site Scripting (XSS) and SQL Injection Attacks Multi-classification Using Bidirectional LSTM Recurrent neural Network

Cross-Site Scripting (XSS) and SQL Injection Attacks Multi-c...

引用

Symposium of image, Signal processing, and artificial Vision (STSIVA)

作者： Abdulgbar A. R. Farea Chengliang Wang Ebraheem Farea Abdulfattah Ba Alawi School of Big Data & Software Engineering Chongqing University Chongqing China Software College Northeastern University Shenyang China Software Engineering Taiz University Taiz Yemen

ISBN: (纸本)9781665426565

E-commerce, ticket booking, banking, and other web-based applications that deal with sensitive information, such as passwords, payment information, and financial information, are widespread. Some web developers may have different levels of understanding about securing an online application. The two vulnerabilities identified by the Open Web Application Security Project (OWASP) for its 2017 Top Ten List are SQL injection and Cross-site Scripting (XSS). Because of these two vulnerabilities, an attacker can take advantage of these flaws and launch harmful web-based actions. Many published articles concentrated on a binary classification for these attacks. This article developed a new approach for detecting SQL injection and XSS attacks using deep learning. SQL injection and XSS payloads datasets are combined into a single dataset. The word-embedding technique is utilized to convert the word’s text into a vector. Our model used BiLSTM to auto feature extraction, training, and testing the payloads dataset. BiLSTM classified the payloads into three classes: XSS, SQL injection attacks, and normal. The results showed great results in classifying payloads into three classes: XSS attacks, injection attacks, and non-malicious payloads. BiLSTM showed high performance reached 99.26% in terms of accuracy.

关键词： Training Recurrent neural networks Cross-site scripting Passwords SQL injection Feature extraction Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

DAAN: A Deep Autoencoder-Based Augmented Network for Blind Multilinear Hyperspectral Unmixing

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷 1页

作者： Su, Yuanchao Zhu, Zhiqing Gao, Lianru Plaza, Antonio Li, Pengfei Sun, Xu Xu, Xiang Xian Univ Sci & Technol Coll Geomat Dept Remote Sensing Xian 710054 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Computat Opt Imaging Technol Beijing 100094 Peoples R China Xian Univ Sci & Technol Coll Geomat Xian 710054 Peoples R China Univ Extremadura Escuela Politecnica Dept Technol Comp & Commun Hyperspectral Comp Lab Caceres 10071 Spain Univ Elect Sci & Technol China Zhongshan Inst Artificial Intelligence & Comp Vis Lab Zhongshan 528402 Peoples R China

In recent years, deep learning (DL) has accelerated the development of hyperspectral image (HSI) processing, expanding the range of applications further. As a typical model of unsupervised DL, the autoencoder framework has been extensively applied for spectral unmixing due to its strong representation ability and scalability. Nowadays, most DL-based unmixing approaches adopt the linear mixture model (LMM) to estimate pure spectral signatures (endmembers) and their corresponding abundance fractions. However, since sunlight scattering is an inevitable physical phenomenon, the spectral mixture problem is inherently nonlinear. Moreover, most existing nonlinear unmixing approaches focus exclusively on spectral information, neglecting the spatial distribution of materials and the intrinsic correlation between pixels, making it challenging to explore latent features. To address these issues, this article develops a new deep autoencoder-based augmented network (DAAN). The proposed DAAN employs the multilinear mixture model (MLMM) to handle the nonlinear influence caused by multiple scattering. Meanwhile, the proposed DAAN constraints homogenous smoothing in the autoencoder architecture, enabling the aggregation of intrinsic correlations by means of spatial relationships to enhance the performance of abundance estimation. We achieve unsupervised nonlinear hyperspectral unmixing by combining spectral and spatial information. The effectiveness and advantages of DAAN are confirmed by several experiments with synthetic and real HSI datasets. The results indicate that the proposed method outperforms other DL-based unmixing approaches. The source codes of the proposed DAAN will be provided in the following link https://***/yuanchaosu/TGRS-daan.

关键词： Scattering Hyperspectral imaging Mixture models Convolutional neural networks Photonics Correlation Spatial resolution Autoencoder deep learning (DL) hyperspectral remote sensing nonlinear unmixing

来源：评论

学校读者我要写书评

暂无评论

Current state of artificial intelligence applications in ophthalmology and their potential to influence clinical practice

引用

COGENT ENGINEERING 2021年第1期8卷 Article: 1920707页

作者： Shetty, Dasharathraj K. Talasila, Abhiroop Shanbhag, Swapna Patil, Vathsala Hameed, Zeehan Naik, Nithesh Raju, Adithya Manipal Acad Higher Educ Manipal Inst Technol Dept Humanities & Management Manipal Karnataka India Manipal Acad Higher Educ Manipal Inst Technol Dept Comp Sci Engn Manipal Karnataka India LV Prasad Eye Inst Cornea & Ocular Surface Hyderabad Telangana India Manipal Acad Higher Educ Manipal Coll Dent Sci Dept Oral Med & Radiol Manipal Karnataka India Manipal Acad Higher Educ Kasturba Med Coll Dept Urol Manipal Karnataka India Manipal Acad Higher Educ Manipal Inst Technol Dept Mech & Mfg Engn Manipal Karnataka India Univ Stockholm KTH Royal Inst Technol Med Engn Brinellvagen 8 S-11428 Stockholm Sweden

artificial intelligence (AI) has emerged as a major frontier in healthcare and finds broad range of applications. It has the potential to revolutionize current procedures of disease diagnosis and treatment, thus influencing the clinical practice. artificial intelligence (AI) in ophthalmology, primarily concentrates on diagnostic and treatment pathways for eye conditions such as cataract, glaucoma, age-related macular degeneration (MDA) and diabetic retinopathy (DR). The purpose of this article is to systematically review the existing state of literature on the various AI techniques and its applications in the diagnosis and treatment of eye diseases and conduct an in-depth enquiry to identify the challenges in accurate detection, pre-processing of data, monitoring and assessment through various AI algorithms. The results suggest that all AI models proposed reduce the detection time considerably. The potential limitations and challenges in the development and application play a significant role in clinical practice. There is a need for the development of AI-assisted technologies that shall consider the clinical implications based on experience and guided by patient-centred healthcare principles. The diagnostic models should assist ophthalmologists on making quick and accurate decisions in determining the progression of various ocular diseases.

关键词： artificial intelligence machine learning neural networks ophthalmology deep learning diabetic retinopathy age-related macular degeneration diagnosis diagnostic imaging image interpretation

来源：评论

学校读者我要写书评

暂无评论

Learning biophysical determinants of cell fate with deep neural networks

引用

NATURE MACHINE INTELLIGENCE 2022年第7期4卷 636-+页

作者： Soelistyo, Christopher J. Vallardi, Giulia Charras, Guillaume Lowe, Alan R. UCL Inst Phys Living Syst London England UCL Dept Struct & Mol Biol London England UCL Dept Cell & Dev Biol London England UCL London Ctr Nanotechnol London England Alan Turing Inst London England

Deep learning is now a powerful tool in microscopy data analysis, and is routinely used for image processing applications such as segmentation and denoising. However, it has rarely been used to directly learn mechanistic models of a biological system, owing to the complexity of the internal representations. Here, we develop an end-to-end machine learning approach capable of learning an explainable model of a complex biological phenomenon, cell competition, directly from a large corpus of time-lapse microscopy data. Cell competition is a quality control mechanism that eliminates unfit cells from a tissue, during which cell fate is thought to be determined by the local cellular neighbourhood over time. To investigate this, we developed a new approach (tau-VAE) by coupling a probabilistic encoder to a temporal convolution network to predict the fate of each cell in an epithelium. Using the tau-VAE's latent representation of the local tissue organization and the flow of information in the network, we decode the physical parameters responsible for correct prediction of fate in cell competition. Remarkably, the model autonomously learns that cell density is the single most important factor in predicting cell fate-a conclusion that is in agreement with our current understanding from over a decade of scientific research. Finally, to test the learned internal representation, we challenge the network with experiments performed in the presence of drugs that block signalling pathways involved in competition. We present a novel discriminator network, which using the predictions of the tau-VAE can identify conditions that deviate from the normal behaviour, paving the way for automated, mechanism-aware drug screening. An end-to-end machine learning approach that can learn which mechanisms determine cell fate and competition from a large time-lapse microscopy dataset is developed. The approach makes use of a probabilistic autoencoder to learn an interpretable representation of the

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

人工神经网络在文物分类系统中的应用研究

引用

微机发展 2005年第2期15卷 94-96页

作者：白雪飞周明全耿国华西北大学计算机系陕西西安710069

人工神经网络由于其强大的学习和适应能力,广泛应用于模式识别、模式分类、自动控制、图像处理及智能系统的非线性建模等方面。文中对几种典型的人工神经网络的结构、功能、学习算法进行了综述,详细介绍了人工神经网络在文物分类系统中... 详细信息

人工神经网络由于其强大的学习和适应能力,广泛应用于模式识别、模式分类、自动控制、图像处理及智能系统的非线性建模等方面。文中对几种典型的人工神经网络的结构、功能、学习算法进行了综述,详细介绍了人工神经网络在文物分类系统中的应用,比较结果可以得出自组织竞争神经网络的分类效果要优于其它两种神经网络。

关键词：模式分类人工神经网络灰度共生矩阵

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：