检索结果-内蒙古大学图书馆

Application of Kronecker convolutions in deep learning technique for automated detection of kidney stones with coronal CT images

引用

Information Sciences 2023年 640卷

作者： Patro, Kiran Kumar Allam, Jaya Prakash Neelapu, Bala Chakravarthy Tadeusiewicz, Ryszard Acharya, U Rajendra Hammad, Mohamed Yildirim, Ozal Plawiak, Pawel Department of Electronics and Communication Engineering Aditya Institute of Technology and Management AP Tekkali532201 India Department of Electronics and Communication Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India Department of Biotechnology and Medical Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India AGH University of Science and Technology Department of Biocybernetics and Biomedical Engineering Krakow Poland School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia EIAS Data Science Lab College of Computer and Information Sciences Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology Faculty of Computers and Information Menoufia University Shibin El Kom32511 Egypt Department of Software Engineering Firat University Elazig Turkey Department of Computer Science Faculty of Computer Science and Telecommunications Cracow University of Technology Warszawska 24 Krakow31-155 Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Baltycka 5 Gliwice44-100 Poland

Kidney stone disease is a serious public health concern that is getting worse with changes in diet, obesity, medical conditions, certain supplements etc. A kidney stone also called a renal calculus, is a hard buildup of urine minerals that form in the kidneys. Computed tomography (CT) is one of the imaging models used to identify kidney stones by clinical experts. Due to the low resolution of these images, sometimes detecting kidney stones is tedious with the naked eye, which may lead to false alarms. In this work, a computer-based diagnosis system with a deep learning technique has been developed as a practical solution to aid clinicians in their diagnosis. The traditional convolutional neural network (CNN)-based deep learning technology can detect stones in the kidney. Still, it suffers from the performance and standard implementation of the convolution operations in convolution layers. A Kronecker product-based convolution technique is incorporated in the proposed deep learning architecture to reduce the redundancy in feature maps without convolution overlapping. Our proposed method helps to make the network more effective by extracting abstract and in-depth features from the input images. The publicly available GitHub kidney stone CT scans are utilized to develop the proposed architecture. Our automated model detected kidney stones with an accuracy of 98.56% utilizing CT images. Our system is more effective than the most recent and cutting-edge techniques developed for identifying kidney stones of any size, including the smallest ones. © 2023 The Author(s)

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Classification of Soil Images using Convolution Neural Networks

Classification of Soil Images using Convolution Neural Netwo...

引用

2021 IEEE International Conference on Communications, Computing, Cybersecurity and informatics, CCCI 2021

作者： Chatterjee, Kajal Obaidat, Mohammad S. Samanta, Debabrata Sadoun, Balqies Islam, Sk Hafizul Chatterjee, Rajdeep University Department of Computer Science Karnataka Bangalore India University of Sharjah College of Computing and Informatics Sharjah27272 United Arab Emirates Al-Balqa' Applied University College of Engineering Al Salt Jordan Indian Institute of Information Technology Kalyani Department of CSE West Bengal 741235 India KIIT Deemed to Be University School of Computer Engineering Bhubaneswar India

ISBN: (纸本)9781665432085

Classification of soil is crucial for the agricultural domain as it is an essential task in geology and engineering domains. Various procedures are proposed to classify soil types in the literature, but many of them consumed much time or required specially designed equipments/applications. Classification of soil involves the accounting of various factors due to its diversified nature. It can be observed that several critical domain-oriented decisions often depend on the type of soil like farmers might be benefitted from knowing the kind of soil to choose crops accordingly for cultivation. We have employed different Convolution Neural Network (CNN) architectures to identify the soil type accurately in real-time. This paper describes the comparative evaluation in terms of performances of various CNN architectures, namely, ResNet50, VGG19, MobileNetV2, VGG16, NASNetMobile, and InceptionV3. These CNN models are used to classify four types of soils: Clay, Black, Alluvial, and Red. The performance of the ResNet50 model is the best with a training accuracy and training loss of 99.47% and 0.0252, respectively compared to other competing models considered in this paper. © 2021 IEEE.

关键词： Soils

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Based Deep Neural Network Model for Electrocardiogram Records Classification 23

Convolutional Neural Network Based Deep Neural Network Model...

引用

Proceedings of the 7th International Conference on Future Networks and Distributed Systems

作者： Ahmed Mahmood Khudhur Mohammed Hasan Alwan Qayssar Al Omairi Omar Abdulkareem Mahmood Yousif I Hammadi Mohammed Saleh Ali Muthanna Ahmed Aziz Ammar Muthanna Information Technology Department Kirkuk University Iraq Department of Communications Engineering University of Diyala Iraq Department of Computer Engineering University of Diyala Iraq Dep. of Medical Instruments Engineering Techniques Bilad Alrafidain University College Iraq Institute of Computer Technologies and Information Security Southern Federal University Russia Department of computer science Benha university Egypt and International Business Management Department Tashkent State University of Economics Uzbekistan Department of Telecommunication Networks and Data Transmission The Bonch Bruevich Saint Petersburg State University of Telecommunications Russia and Department of Applied Probability and Informatics Peoples Friendship University of Russia Russia

ISBN: (纸本)9798400709036

Сardiovascular diseases, also known as CVDs, currently rank as the primary incidence of mortality. The present approach for identifying illnesses involves the analysis of the Electrocardiogram (ECG), an electronic diagnostic device utilized to capture the rhythm of the heart. Regrettably, the process of seeking out specialists to conduct analysis on a substantial volume of electrocardiogram (ECG) data results in a significant depletion of medical capabilities. Hence, the utilization of deep learning algorithms for the identification of ECG characteristics has progressively gained prominence. Nevertheless, there exist certain limitations associated with these conventional approaches, which necessitate the need for manual characteristic identification, intricate models, and extensive training duration. This study presents a novel and effective approach for categorizing the five different types of heartbeats in the MIT-BIH Arrhythmia database. The proposed method involves the utilization of a 16-layer deep one-dimensional convolutional neural network, which exhibits both robustness and efficiency in its classification performance. Thus, the designed model is consisting of five-groups, first to fourth groups are the main feature extraction and mapping blocks, while the fifth group is fully connected and classification layers. The findings indicate that the model presented in this study has superior performance in terms of accuracy, precision, and F1-score. The proper classification of medical cases has a significant impact on the conservation of medical resources, hence positively influencing clinical practice. Additionally, the model training phase is characterized by its efficiency, since it does not significantly deplete resources.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep and handcrafted feature supported diabetic retinopathy detection: A study

引用

Procedia computer Science 2023年 218卷 2675-2683页

作者： Seifedine Kadry Rubén González Crespo Enrique Herrera-Viedma Sujatha Krishnamoorthy Venkatesan Rajinikanth Faculty of Applied Computing and Technology Noroff University College Kristiansand 94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de La Rioja 26006 Andalusian Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Chennai 600119 Tamil Nadu India

The eye is the prime sensory organ in physiology, and the abnormality in the eye severely influences the vision system. Therefore, eye irregularity is commonly assessed using imaging schemes, and Fundus Retinal Image (FRI) supported eye screening is one of the ophthalmological practices. This work proposed a Deep-Learning Procedure (DLP) to recognize Diabetic Retinopathy (DR) in FI. The proposed work presents the experimental work with different DLP methods found in the literature. This work is executed with two modes; (i) DR detection using conventional deep-features and (ii) DR discovery using deep ensemble features. To demonstrate this work, 1800 fundus images (900 regular and 900 DR class) are considered for the assessment, and the advantage of proposed plan is confirmed using various performance metrics. The experimental outcome of this study confirms that the AlexNet-based detection provides a better detection (>96%), and the deep ensemble features of AlexNet, VGG16, and ResNet18 provide a detection accuracy of >98% on the chosen FRI database.

关键词： Eye abnormality Diabetic retinopathy Fundus imaging Deep-Learning Classification

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of lung nodule in CT scan slices using CNN segmentation schemes: A study

引用

Procedia computer Science 2023年 218卷 2786-2794页

作者： Seifedine Kadry Enrique Herrera-Viedma Rubén González Crespo Sujatha Krishnamoorthy Venkatesan Rajinikanth Faculty of Applied Computing and Technology Noroff University College Kristiansand 94612 Norway Research Institute in Data Science and Computational Intelligence University of Granada Granada Andalusian Spain Computer Science Department School of Engineering and Technology Universidad Internacional de La Rioja 26006 Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Chennai 600119 Tamil Nadu India

The lung is one of the prime respiratory organs in human physiology, and its abnormality will severely disrupt the respiratory system. Lung Nodule (LN) is one of the abnormalities, and early screening and treatment are necessary to reduce its harshness. The proposed work aims to implement the Convolutional-Neural-Network (CNN) segmentation methodology to extract the LN in various lung CT slices, such as axial, coronal, and sagittal planes. This work consists of the following phases; (i) Image collection and pre-processing, (ii) Ground-truth generation, (iii) CNN-supported segmentation, and (iv) Performance evaluation and validation. In this work, the merit of pre-trained CNN segmentation schemes is verified using (i) One-fold training and (ii) Two-fold training methods. The test images for this study are collected from The Cancer Imaging Archive (TCIA) database. The experimental investigation is executed using Python®, and the outcome of this study confirms that the VGG-SegNet helps to get better values of Jaccard (>88%), Dice (>93%), and Accuracy (>96%) compared to other CNN methods.

关键词： Lung nodule CT scan CNN segmentation VGG-SegNet Accuracy Detection

来源：评论

学校读者我要写书评

暂无评论

Morphosyntactic Probing of Multilingual BERT Models

arXiv

引用

arXiv 2023年

作者： Acs, Judit Hamerlik, Endre Schwartz, Roy Smith, Noah A. Kornai, Andras Budapest Hungary Budapest University of Technology and Economics Budapest Hungary Department of Applied Informatics Comenius University in Bratislava Faculty of Mathematics Physics and Informatics Bratislava Slovakia Hebrew University of Jerusalem Jerusalem Israel Paul G. Allen School of Computer Science and Engineering University of Washington SeattleWA United States Allen Institute for Artificial Intelligence SeattleWA United States

We introduce an extensive dataset for multilingual probing of morphological information in language models (247 tasks across 42 languages from 10 families), each consisting of a sentence with a target word and a morphological tag as the desired label, derived from the Universal Dependencies treebanks. We find that pre-trained Transformer models (mBERT and XLM-RoBERTa) learn features that attain strong performance across these tasks. We then apply two methods to locate, for each probing task, where the disambiguating information resides in the input. The first is a new perturbation method that "masks" various parts of context;the second is the classical method of Shapley values. The most intriguing finding that emerges is a strong tendency for the preceding context to hold more information relevant to the prediction than the following context. © 2023, CC BY.

关键词： Perturbation techniques

来源：评论

学校读者我要写书评

暂无评论

Design and Fabrication Challenges of Integrated Optical Circuits for Quantum Computing Applications

Design and Fabrication Challenges of Integrated Optical Circ...

引用

International Conference on Transparent Optical Networks

作者： Simeon I. Tsintzos Konstantinos Tsimvrakidis Alexandra Sinani Adonis Bogris James C. Gates Peter G.R. Smith Ali W. Elshaari Val Zwiller Christos Riziotis National Hellenic Research Foundation Theoretical & Physical Chemistry Institute Athens Greece Department of Informatics and Computer Engineering University of West Attica Egaleo Greece Optoelectronics Research Centre University of Southampton Southampton United Kingdom Department of Applied Physics Royal Institute of Technology (KTH) Stockholm Sweden Institute for Advanced Modelling and Simulation University of Nicosia Nicosia Cyprus

The paper presents current design issues, limitations, and fabrication challenges towards the development of hybrid integrated optical circuits with embedded single photon sources, which are critical components for future quantum computing, sensing, and communication systems. Optical nanowires with embedded quantum dots (NWQD) are very promising single photon sources, with several reported results of integration in high index platforms like silicon or silicon nitride. Silica on silicon is a favorable platform for optical computing, providing the high degree of customization when combined with direct laser writing techniques for definition of optical structures with refractive index modification. However, the low ~10 -3 achievable refractive index contrast imposes strict limitations on the compatibility with NWQD resulting in general in low coupling efficiency as shown in this work. Consideration of several design and fabrication issues demonstrates the potential for NQWD integration in laser written silica based optical circuits with adequate efficiency for practical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visualizing Quantum Circuit Probability estimating computational action for quantum program synthesis

arXiv

引用

arXiv 2023年

作者： Bach, Bao Gia Kundu, Akash Acharya, Tamal Sarkar, Aritra Faculty of Computer Science and Engineering Ho Chi Minh City University of Technology Viet Nam Viet Nam Joint Doctoral School Silesian University of Technology Gliwice Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland Independent Researcher Bengaluru India Quantum Machine Learning Research group Quantum Computing Division QuTech Netherlands Quantum Intelligence Research team Department of Quantum & Computer Engineering Delft University of Technology Netherlands

This research applies concepts from algorithmic probability to Boolean and quantum combinatorial logic circuits. A tutorial-style introduction to states and various notions of the complexity of states are presented. Thereafter, the probability of states in the circuit model of computation is defined. Classical and quantum gate sets are compared to select some characteristic sets. The reachability and expressibility in a space-time-bounded setting for these gate sets are enumerated and visualized. These results are studied in terms of computational resources, universality and quantum behavior. The article suggests how applications like geometric quantum machine learning, novel quantum algorithm synthesis and quantum artificial general intelligence can benefit by studying circuit probabilities. © 2023, CC BY-NC-SA.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Latent fingerprint enhancement and segmentation technique based on hybrid edge adaptive DTV model 2

Latent fingerprint enhancement and segmentation technique ba...

引用

2nd International Conference on Smart Computing and Electronic Enterprise, ICSCEE 2021

作者： Hilles, Shadi M S Liban, Abdilahi Miaikil, Othman A.M. Mahmoud Altrad, Abdullah Baker El-Ebiary, Yousef A. Hilles, Mohanad M Contreras, Jennifer Istanbul OKAN University Software Engineering Department Istanbul Turkey Hargeisa University Computer Science Department Hargeisa Somalia Al-Madinah International University Computer Science Department Kuala Lumpur Malaysia Universiti Sultan Zainal Abidin Faculty of Informatics and Computing Trengganu Malaysia University College of Applied Science Information Technology Department Gaza Palestine FEU Institute of Technology Department of Information Technology Manila Philippines

ISBN: (纸本)9781665432221

Image enhancement and segmentation is widely used for fingerprint identification and authorization in biometrics devices, criminal scene is most challenges due to low quality of fingerprint, the most significant efforts is to develop algorithm for latent fingerprint enhancement which become challenging problem due to the complex and existing problem for instance, developing algorithms of latent fingerprint is able to extract features of image blocks and removing overlapping and isolate the poor and noisy background. however, it's still challenging and interested problem specifically latent fingerprint enhancement and segmentation. The aim study of this paper is to propose latent fingerprint enhancement and segmentation based on hybrid model and Chan-Vese method for segmentation, in order to reduce low image quality and increase the accuracy of fingerprint. The desired characteristics of intended technique are adaptive, effective and accurate, hybrid model of edge adaptive direction achieves accurate latent fingerprint enhancement and segmentation, the target needs to improve feature detection and performance, this research has proposed system architecture of research method in fingerprint enhancement and segmentation where is the method content two stages, the first is normalization and second is reconstruction, using EDTV model is required for adaptive noise, in addition Chan-vase technique contributed for identification of fingerprint image features, the result and testing using RMSE with three categories of fingerprint images good, bad and ugly show better performance for all three categories, as well RMSE shows the average of good latent fingerprint before and after enhancement. Latent Fingerprint Enhancement and Segmentation Technique Based on Hybrid Model Edge Adaptive Directional Total Variation © 2021 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Adaptive latent fingerprint image segmentation and matching using Chan-vese technique based on EDTV model 2

Adaptive latent fingerprint image segmentation and matching ...

引用

2nd International Conference on Smart Computing and Electronic Enterprise, ICSCEE 2021

作者： Hilles, Shadi M S Liban, Abdilahi Altrad, Abdullah Mahmoud Miaikil, Othman A.M. El-Ebiary, Yousef A. Baker Contreras, Jennifer Hilles, Mohanad M Istanbul OKAN University Software Engineering Department Istanbul Turkey Hargeisa University Computer Science Department Hargeisa Somalia Al-Madinah International University Computer Science Department Kuala Lumpur Malaysia Universiti Sultan Zainal Abidin Faculty of Informatics and Computing Trengganu Malaysia FEU Institute of Technology Department of Information Technology Manila Philippines University College of Applied Science Information Technology Department Gaza Palestine

ISBN: (纸本)9781665432221

Biometrics such as face, fingerprint, iris, voice and palm prints are the most widely used, and as well the fingerprints are one of the most frequently used biometrics to identify individuals and authenticate their identity. commonly categorized into three different categories which are rolled, plain and latent fingerprints. The reliability of image segmentation for latent fingerprint which is used in criminal issues still challenges, The difficulty of latent fingerprint image segmentation mainly lies in the poor quality of fingerprint patterns and the presence of the noise in the background, This research has investigated the fingerprint segmentation and matching based on EDTV and presented Chan-vese active contour segmentation technique, in addition, presented NIST SD27 for grayscale dataset of latent fingerprint which is standard by National institute of Standard and technology, where is dataset have varieties of fingerprint image samples, a total about 258 of latent fingerprint, those samples collected from crime scenes and matching fingerprint and shown the performance of matching accuracy ROC and CMC curves, To evaluate the performance of the matching ROC and CMC curves has been deployed, The area under curve (AUC) of the ROC of the good images performance is 72% with CMC rank1-idnetification of 42% and rank-20 identification of 79%. the result shows that the latent fingerprint method performance is better for good latent fingerprint images compare to bad and ugly images, while there is no much difference for bad and ugly image. © 2021 IEEE.

关键词： Biometrics

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：