检索结果-内蒙古大学图书馆

International Conference on image processing and Capsule Networks, ICIPCN 2020

作者： Raj Kiran, G.S.S. Rohit, Palakodeti Manognya, Katapally Likhith, K. Raju, N. v. Ganapathi Lakshmi, K. Prasanna Department of Information Technology GRIET HyderabadTelangana India

ISBN: (纸本)9783030518585

A classification model was evolved to classify the severity of the dengue incidence by training on Kerala state’s data. The model was developed by implementing supervised machine learning algorithms such as support vector classifier, logistic regression, and Naïve Bayes classifier to classify dengue cases. The model tries to classify a month into two class labels. The class labels are categorized based on the frequency of dengue cases recorded in that particular month. 0 (n ≤ 400) when the number of cases recorded in that particular month is either equal or under 400, 1 (n > 400) when the number of cases recorded in that particular month is greater than 400 based on the meteorological data of the particular month. Among the classification algorithms, SvC (support vector classifier) with an accuracy of 92.85% and precision – 0.93, recall – 0.92, and f1 score – 0.93 was the most successful in classifying the severity of the situation. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： Tropics

来源：评论

学校读者我要写书评

暂无评论

Segmentation versus detection: Development and evaluation of deep learning models for prostate imaging reporting and data system lesions localisation on Bi-parametric prostate magnetic resonance imaging

引用

CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY 2024年第0期

作者： Min, Zhe Bianco, Fernando J. Yang, Qianye Yan, Wen Shen, Ziyi Cohen, David Rodell, Rachael Barratt, Dean C. Hu, Yipeng Shandong Univ Sch Control Sci & Engn Jinan Peoples R China UCL Ctr Med Image Comp & Wellcome EPSRC Ctr Intervent & Surg Sci London England Urol Res Network Miami Lakes FL USA City Univ Hong Kong Hong Kong Peoples R China

Automated prostate cancer detection in magnetic resonance imaging (MRI) scans is of significant importance for cancer patient management. Most existing computer-aided diagnosis systems adopt segmentation methods while object detection approaches recently show promising results. The authors have (1) carefully compared performances of most-developed segmentation and object detection methods in localising prostate imaging reporting and data system (PIRADS)-labelled prostate lesions on MRI scans;(2) proposed an additional customised set of lesion-level localisation sensitivity and precision;(3) proposed efficient ways to ensemble the segmentation and object detection methods for improved performances. The ground-truth (GT) perspective lesion-level sensitivity and prediction-perspective lesion-level precision are reported, to quantify the ratios of true positive voxels being detected by algorithms over the number of voxels in the GT labelled regions and predicted regions. The two networks are trained independently on 549 clinical patients data with PIRADS-v2 as GT labels, and tested on 161 internal and 100 external MRI scans. At the lesion level, nnDetection outperforms nnUNet for detecting both PIRADS >= 3 and PIRADS >= 4 lesions in majority cases. For example, at the average false positive prediction per patient being 3, nnDetection achieves a greater Intersection-of-Union (IoU)-based sensitivity than nnUNet for detecting PIRADS >= 3 lesions, being 80.78% +/- 1.50% versus 60.40% +/- 1.64% (p < 0.01). At the voxel level, nnUnet is in general superior or comparable to nnDetection. The proposed ensemble methods achieve improved or comparable lesion-level accuracy, in all tested clinical scenarios. For example, at 3 false positives, the lesion-wise ensemble method achieves 82.24% +/- 1.43% sensitivity versus 80.78% +/- 1.50% (nnDetection) and 60.40% +/- 1.64% (nnUNet) for detecting PIRADS >= 3 lesions. Consistent conclusions are also drawn from results on the external data

关键词： artificial intelligence medical image processing robotics

来源：评论

学校读者我要写书评

暂无评论

Realizing Mathematics of Arrays Operations as Custom Architecture Hardware-Software Co-Design Solutions

引用

INFORMATION 2022年第11期13卷 528页

作者： Grout, Ian Andrew Mullin, Lenore Univ Limerick Dept Elect & Comp Engn Limerick V94T9PX Ireland Univ Albany State Univ New York Coll Engn & Appl Sci Dept Comp Sci Albany NY 12222 USA

In embedded electronic system applications being developed today, complex datasets are required to be obtained, processed, and communicated. These can be from various sources such as environmental sensors, still image cameras, and video cameras. Once obtained and stored in electronic memory, the data is accessed and processed using suitable mathematical algorithms. How the data are stored, accessed, processed, and communicated will impact on the cost to process the data. Such algorithms are traditionally implemented in software programs that run on a suitable processor. However, different approaches can be considered to create the digital system architecture that would consist of the memory, processing, and communications operations. When considering the mathematics at the centre of the design making processes, this leads to system architectures that can be optimized for the required algorithm or algorithms to realize. Mathematics of Arrays (MoA) is a class of operations that supports n-dimensional array computations using array shapes and indexing of values held within the array. In this article, the concept of MoA is considered for realization in software and hardware using Field Programmable Gate Array (FPGA) and Application Specific Integrated Circuit (ASIC) technologies. The realization of MoA algorithms will be developed along with the design choices that would be required to map a MoA algorithm to hardware, software or hardware-software co-designs.

关键词： embedded systems MoA FPGA ASIC tensor products

来源：评论

学校读者我要写书评

暂无评论

Retinal image Enhancement via a Multiscale Morphological Approach with OCCO Filter

Retinal Image Enhancement via a Multiscale Morphological App...

引用

International Conference on Information Technology and systems, ICITS 2021

作者： Román, Julio César Mello Noguera, José Luis vázquez García-Torres, Miguel Benítez, veronica Elisa Castillo Matto, Ingrid Castro Universidad Americana Asunción Paraguay Facultad de Ciencias Exactas y Tecnológicas Universidad Nacional de Concepción Concepción Paraguay Division of Computer Science Universidad Pablo de Olavide Seville41013 Spain Departamento de Retina Catedra de Oftalmología Hospital de Clínicas Facultad de Ciencias Médicas Universidad Nacional de Asunción San Lorenzo Paraguay

ISBN: (纸本)9783030682842

Retinal images are widely used for diagnosis and eye disease detection. However, due to the acquisition process, retinal images often have problems such as low contrast, blurry details or artifacts. These problems may severely affect the diagnosis. Therefore, it is very important to enhance the visual quality of such images. Contrast enhancement is a pre-processing applied to images to improve their visual quality. This technique betters the identification of retinal structures in degraded retinal images. In this work, a novel algorithm based on multi-scale mathematical morphology is presented. First, the original image is blurred using the Open-Close Close-Open (OCCO) filter to reduce any artifacts in the image. Next, multiple bright and dark features are extracted from the filtered image by the Top-Hat transform. Finally, the maximum bright values are added to the original image and the maximum dark values are subtracted from the original image, previously adjusted by a weight. The algorithm was tested on 397 retinal images from the public STARE database. The proposed algorithm was compared with state of the art algorithms and results show that the proposal is more efficient in improving contrast, maintaining similarity with the original image and introducing less distortion than the other algorithms. According to ophthalmologists, the algorithm, by improving retinal images, provides greater clarity in the blood vessels of the retina and would facilitate the identification of pathologies. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Mathematical morphology

来源：评论

学校读者我要写书评

暂无评论

Automated Pest Detection in Crop Fields Using Deep Learning Techniques

Automated Pest Detection in Crop Fields Using Deep Learning ...

引用

Innovative Computing, Intelligent Communication and Smart Electrical systems (ICSES), International Conference on

作者： R. Premalatha Somasundaram R Prashant Atmakuri G.G. Sreeja Pooja P. Raj Loveleen Kumar Department of Microbiology CMS College of Science and Commerce Coimbatore Tamil Nadu India Department of Management Studies Kongu Engineering College Perundurai Erode Tamil Nadu India Department of CSE Prasad V Potluri Siddhartha Institute of Technology Vijayawada Andhra Pradesh India Department of Computer and Communication Engineering Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of CSE Dr. C.V Raman University Bilaspur C.G India Department of Computer Science & Engineering Swami Keshvanand Institute of Technology Management & Gramothan Jaipur Rajasthan India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

When it comes to discovering and eliminating pests, traditional methods are typically laborious, time-consuming, and hazardous to the environment. In recent years, deep literacy methods have emerged as interesting and potentially useful technologies for automating the finding of pests in agricultural fields. The purpose of this work is to provide a detailed evaluation of the operation of deep literacy methods in automated pest discovery. These methods include a variety of characteristics such as image processing, point birth, and bracket algorithms. In this paper, we discuss the difficulties and opportunities that are involved with the implementation of deep literacy-based pest discovery systems. These problems and opportunities include dataset reflection, model training, and scalability. In addition to this, we highlight recent developments, case stories, and new exploration directions in this rapidly developing field. Automated pest discovery systems have the potential to enhance agricultural operations by utilizing the powers of deep literacy. This would allow for the prompt and precise identification of pests, which would be necessary for the development of effective pest management techniques. Cutting-edge technology Within the scope of this investigation, Yolov3-Tiny, Yolov4, Yolov4-Tiny, Yolov6, and Yolov8 were utilized for detection. For object detection, each of these models was selected. images have been marked with Yolo. Yolov8 outperformed previous trials by having the highest mAP of 84.7% and an average loss of 0.7939 for the detection of tiny pests. An Android application that offered real-time insect detection utilized the Yolov8 paradigm. The purpose of this research is to develop and deploy novel deep-learning models, analytical tools, and a procedure for identifying crop pests for pest management.

关键词： Training Deep learning Geography Insects Scalability Machine vision Object detection Robustness Reflection Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Bistatic High-Frequency Coherent Radar Imaging of Ionospheric Disturbances

Bistatic High-Frequency Coherent Radar Imaging of Ionospheri...

引用

IEEE International Symposium on Phased Array systems and Technology

作者： Ian T. Cummings Christopher A. Jeffery Jeremiah J. Rushton Erin H. Lay Todd S. Anderson Andrew C. Beveridge Steven D. Dobson Harald E. Edens Joshua L. Ennis W. Brian Haynes Tara S. Len Donathan J. Ortega Eric v. Ottosen Andrea C. Schmidt Xuan-Min Shao Electromagnetic Sciences & Cognitive Space Applications Group (ISR-2) Los Alamos National Laboratory Los Alamos NM USA Electronics & Signal Processing Group (ISR-4) Los Alamos National Laboratory Los Alamos NM USA Space Remote Sensing & Data Science Group (ISR-6) Los Alamos National Laboratory Los Alamos NM USA Electrodynamics Group (AOT-AE) Los Alamos National Laboratory Los Alamos NM USA Instrument Realization Group (ISR-5) Los Alamos National Laboratory Los Alamos NM USA

ISBN: (数字)9798350392142

ISBN: (纸本)9798350392159

High-frequency (HF) communications links are drastically affected by ionospheric disturbances. Experiments that artificially disturb the ionosphere while imaging that disturbance with sufficient resolution for comparison with relevant modeling tools could help improve those models. This work describes a proposed bistatic HF phased array radar system that will image ionospheric disturbances created by the Highfrequency Active Auroral Research Program (HAARP) facility in Gakona, Alaska. The proposed array will use the Super Dual Auroral Radar Network (SuperDARN) system in Kodiak, Alaska as a transmitter of opportunity. This work presents a novel approach that incorporates ionospheric ray bending effects into the evaluation of coherent radar imaging (CRI) algorithms. We accomplish this via two-dimensional full-wave Fourier domain simulations that generate artificial data for each receive antenna, which is then fed into the CRI algorithms under evaluation. We compare these results with the traditional straight-ray simulated data approach. Initial results suggest that incorporating ray bending into the imaging algorithm used to process the data will be critical to properly localizing targets and that advanced imaging or deconvolution techniques may provide resolution improvements over standard imaging techniques even with more cluttered and complicated data sets.

关键词： Phased arrays Surveys Transmitters Superresolution Imaging Receiving antennas Radar imaging Bending Arrays Standards

来源：评论

学校读者我要写书评

暂无评论

Noise Removal in Breast Cancer Using Hybrid De-noising Filter for Mammogram images 1

引用

International Conference on Computational vision and Bio-Inspired Computing (ICCvBIC)

作者： Devakumari, D. Punithavathi, v Govt Arts Coll Dept Comp Sci Coimbatore Tamil Nadu India Govt Arts Coll Coimbatore Tamil Nadu India

ISBN: (数字)9783030372187

ISBN: (纸本)9783030372187;9783030372170

Breast Cancer is a one of the major disease for women in today's world. The aim of this paper is to develop a robust and image pre-processing methods to realize mammogram images features with different dimensions. To categorize an image is to be illustrated or signified by particular features. In this paper, proposed a mammogram image pre-processing extraction process for deriving the image classification. The proposed method present two phases namely, (1) image Re-sizing: The original MIAS mammogram image database images are resized into predefined sizes;(2) image pre-processing. The Hybrid De-noising Filter is obtained by Median Filter and Applied Median Filter Integration. It is established out using Hybrid Denoising Filter (HDF) to discard the noise;Different image de-noising algorithms are discussed in literature review. The proposed Hybrid Denoising Filter algorithm performs an important function in image feature selection, segmentation, classification, and investigation. According to the experimental results the Hybrid Denoising Filter algorithm mainly focuses on discarding irrelevant noise and focuses on the execution time using MATLAB R2013a Tool. The proposed Hybrid Denoising Filter has less Root Mean Square Error (RMSE) variation and High Peak Signal Noise Ratio (PSNR) when compared with other de-noising algorithms of Gaussian, Wiener, Median and Applied Median Filters.

关键词： Breast Cancer image pre-processing Hybrid De-noising Filter MIAS

来源：评论

学校读者我要写书评

暂无评论

Pseudo-gradient algorithm for identification of doubly stochastic cylindrical image model 24

Pseudo-gradient algorithm for identification of doubly stoch...

引用

24th KES International Conference on Knowledge-Based and Intelligent Information and Engineering systems, KES 2020

作者： Krasheninnikov, victor Kuvayskova, Yuliya Subbotin, Alexey Ulyanovsk State Technical University 32 Severny Venets Ulyanovsk432027 Russia

Nowadays, image processing problems are becoming increasingly important due to development of the aerospace Earth monitoring systems, radio and sonar systems, medical devices for early diagnosis etc. But the most of the image processing works deal with images defined on rectangular two-dimensional grids or grids of higher dimension. In some practical situations, images are set on a cylinder. For example, images of a section of pipelines, worms, blood vessel, parts during turning, etc. The peculiarity of the domain for specifying such images requires its consideration in their models and processing algorithms. In the present paper, autoregressive models of cylindrical images are considered, expressions of the correlation function depending on the autoregression parameters are given. To represent heterogeneous images with random heterogeneities, «doubly stochastic» models are used in which one or more images control the parameters of the resulting image. The spiral scan of a cylindrical image can be considered as a quasiperiodic process due to the correlation of image rows. Pseudo-gradient algorithms for the modal identification are proposed. The statistical modeling showed that these algorithms give good model identification. © 2020 The Authors. Published by Elsevier B.v.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

A method for detecting spatiotemporal patterns of cancer biomarkers-evoked activity using radial basis function network extracted time-domain features from calcium imaging data

引用

JOURNAL OF NEUROSCIENCE METHODS 2024年 405卷 110097页

作者： Shcherban, Igor v. Fedotova, victoria S. Matukhno, Aleksey E. Shepelev, Igor E. Shcherban, Oxana G. v. Lysenko, Larisa Southern Fed Univ SFedU Res Ctr Neurotechnol 105-42 Bolshaya Sadovaya Str Rostov Na Donu 344006 Russia Rabochaya Sq 7 Apt 16 Rosto Von Don 344004 Russia

Background: Two-photon calcium imaging is widely used to study the odor-evoked glomerular activity in the dorsal olfactory bulb of macrosmatic animals. The nonstationary character of activated patterns sets a limit on the use of a traditional image processing approaches. New method: The developed method makes it possible to automatically map cancer biomarkers-activated glomeruli in the rat dorsal olfactory bulb. We interpolated fluorescence intensity of calcium dynamics based on the Gaussian RBF network and synthesized the physiological fluorescence model of the receptive glomerular field. Results: The experiments on 5 rats confirmed the correctness of the developed approach. Patterns evoked by the 6-methyl-5-hepten-2-one (stomach cancer biomarker) and benzene (lung cancer biomarker) were correctly identified. Comparison with existing methods: The proposed method was compared with the nonnegative matrix factorization method and with the method based on computer vision algorithms. The developed approach showed better accuracy in experiments and provided the mathematical models of the odor-evoked patterns synthesis. These models can be used to generate synthetic images of odor-evoked glomerular activity and thus to overcome the problem of small experimental data collected in calcium imaging. Conclusions: The proposed method should be considered part of the toolkit for fully automatic analysis of calcium imaging-based studies. Currently available methodology is not able to use breath biomarkers to reliably discriminate between cancer patients and healthy controls. Nevertheless, the effective identification of the spatial patterns of cancer biomarkers-evoked glomerular activity can serve as the foundation for highly sensitive biohybrid systems for cancer screening.

关键词： volatile organic compounds (vOC) detection Calcium imaging analysis Odor-evoked glomerular activity Automatic identification Radial basis functions network Singular spectrum analysis

来源：评论

学校读者我要写书评

暂无评论

HEECCNB: An Efficient IoT-Cloud Architecture for Secure Patient Data Transmission and Accurate Disease Prediction in Healthcare systems

HEECCNB: An Efficient IoT-Cloud Architecture for Secure Pati...

引用

International Conference on image Information processing

作者： C. veena Mulagundla Sridevi Kazi Kutubuddin Sayyad Liyakat Bishal Saha Sheri Ramchandra Reddy N Shirisha Artificial intelligence (AI) Dept G.Pullaiah College of engineering and technology (GPCET Autonomous) Venkayapallu(V) Nandikotkur road Kurnool (city) Andhra Pradesh India Department of CSE CVR College of Engineering Vasthunagar Mangalpally Ibrahimpatnam R.R District Telangana India Department of Electrical Engineering Brahmdevdada Mane Institute of Technology Solapur Maharashtra India Department of Computer Science and Engineering Vellore Institute of Technology Vellore Tamilnadu India Department of CSE (AI&ML) CMR Technical Campus Hyderabad Telangana India Department of CSE MLR Institute of Technology Dundigal Hyderabad India

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

The rapid expansion of the Internet of Things (IoT) in various fields has brought about significant advancements in data processing capabilities, in particular with the advent of IoT-cloud-based devices. Among these advancements, the healthcare system stands as one of the most intriguing IoT-Cloud integration uses cases. However, ensuring the security and privacy of patient data has become a critical concern, necessitating the development of robust protective measures. This research addresses the challenges of data security and computation overhead in the context of an IoT-cloud-based health system. A novel strategy dubbed Homomorphic Encryption with Elliptical Curve Cryptography integrated with Naive Bayes (HEECCNB) is put forth to address these problems. This approach is intended to enable precise disease prediction based on the gathered IoT sensor data while simultaneously providing good patient data privacy inside the IoT Health Cloud system. By employing homomorphic encryption, sensitive patient information can be securely processed and analyzed within the cloud environment without the need for decryption, preserving the confidentiality of the data. Furthermore, the integration of Elliptical Curve Cryptography enhances the security of the system by providing efficient and robust cryptographic operations. The proposed HEECCNB approach demonstrates promising results in both data protection and disease prediction. Through experiments conducted on the IoT Health Cloud scheme, the research validates the effectiveness of the projected method in safeguarding patient data and accurately predicting diseases based on IoT sensor data. Hence, the HEECCNB approach presents a compelling solution to the data security and computation overhead challenges faced in IoT-cloud-based health systems. Its successful implementation could significantly enhance the overall functionality and trustworthiness of such systems, facilitating the integration of IoT technologies in healthcare fo

关键词： Cloud computing Data privacy Medical services Computer architecture Predictive models Prediction algorithms Internet of Things

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：