检索结果-内蒙古大学图书馆

Detection of Acute Lymphoblastic Leukemia Using a Novel Bone Marrow Image Segmentation

Tsinghua science and technology 2025年第2期30卷 610-623页

作者： M.Anline Rejula Ben M Jebin Ravi Selvakumar S.Amutha Eberlein George Department of Computer Applications-PG Scott Christian College(Autonomous)Nagercoil 629003India Department of Computer Science Malankara Catholic CollegeMariagiri 629153India School of Computer Science and Engineering Vellore Institute of TechnologyChennai 600127India Department of Pediatrics Government Medical College and HospitalGovernment of Tamil NaduNamakkal 637001India

In our study,we present a novel method for automating the segmentation and classification of bone marrow images to distinguish between normal and Acute Lymphoblastic Leukaemia(ALL).Built upon existing segmentation techniques,our approach enhances the dual threshold segmentation process,optimizing the isolation of nucleus and cytoplasm *** is achieved by adapting threshold values based on image characteristics,resulting in superior segmentation outcomes compared to previous *** address challenges,such as noise and incomplete white blood cells,we employ mathematical morphology and median filtering *** methods effectively denoise the images and remove incomplete cells,leading to cleaner and more precise ***,we propose a unique feature extraction method using a hybrid discrete wavelet transform,capturing both spatial and frequency *** allows for the extraction of highly discriminative features from segmented images,enhancing the reliability of *** classification purposes,we utilize an improved Adaptive Neuro-Fuzzy Inference System(ANFIS)that leverages the extracted *** enhanced classification algorithm surpasses traditional methods,ensuring accurate identification of acute lymphoblastic *** innovation lies in the comprehensive integration of segmentation techniques,advanced denoising methods,novel feature extraction,and improved *** extensive evaluation on bone marrow samples from the Acute Lymphoblastic Leukemia Image DataBase(ALL-IDB)for Image Processing database using MATLAB 10.0,our method demonstrates outstanding classification *** segmentation accuracy for various cell types,including Band cells(96%),Metamyelocyte(99%),Myeloblast(96%),***(97%),***(97%),and Neutrophil cells(98%),further underscores the potential of our approach as a high-quality tool for ALL diagnosis.

关键词： Adaptive Neuro-Fuzzy Inference System(ANFIS) blood cells segmentation leukemia classification

来源：评论

学校读者我要写书评

暂无评论

Allocation of Resources in the Cloud Conducted Efficiently Through the Use of Machine Learning 1

Allocation of Resources in the Cloud Conducted Efficiently T...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Ahamed, B. Shamreen Poornima, D. Sheela, A.C. Santha Nivetha, S. Sathyabama Institute of Science & Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350359756

Allocating sources correctly within the ever-changing world of cloud computing is vital for maintaining uninterrupted guide of apps and offerings at the same time as preserving charges down. Machine mastering's flexibility to accommodate unique duties and person conduct makes it an appealing option for assembly those desires. As a end result of factors including variable workloads, special application desires resource allocation in the cloud area provides a number of difficulties. Allocation strategies based on static parameters generally fail to fulfill these demanding situations. By integrating past facts, future predictions, and immediately feedback, MLT provide a promising opportunity for developing a flexible and powerful technique of allocating resources. This paper introduces a novel approach to cloud useful resource allocation referred to as Dynamic Resource Allocation with Reinforcement Predictive Learning (DRA-RPL). DRA-RPL combines reinforcement studying with predictive analytics to provide a flexible allocation mechanism that could respond to converting requirements in actual time. This technique seeks to find the candy spot between performance, efficiency, and cost to assure swift and powerful deployment of assets. DRA-RPL uses a cloud-based totally reinforcement mastering agent. The workloads, useful resource availability, and alertness performance are in reality some of the factors that this agent is continuously tracking. The technique uses predictive analytics to foresee useful resource demands primarily based on previous statistics and patterns. This predictive thing enables the reinforcement mastering agent count on future requirements. The simulation effects show the way the approach handles versions in surroundings and workload, imparting sturdy evidence of its effectiveness. With the ability to reinforce resource utilization, fee-effectiveness, and client delight across cloud-based totally offerings, DRA-RPL is a possible method that would help

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Enhanced ERP Transaction Integrity Architecture and PoET Consensus

引用

computers, Materials & Continua 2022年第1期70卷 1089-1109页

作者： Tehreem Aslam Ayesha Maqbool Maham Akhtar Alina Mirza Muhammad Anees Khan Wazir Zada Khan Shadab Alam Department of Computer Engineering National University of Sciences and TechnologyIslamabad44000Pakistan Department of Electrical Engineering National University of Sciences and TechnologyIslamabad44000Pakistan Department of Management Studies Bahria Business SchoolIslamabad44000Pakistan Department of Computer Science Capital University of Science and TechnologyIslamabad44000Pakistan Department of Computer Science College of Computer Science and ITJazan UniversityJazan67714Saudi Arabia

Enterprise Resource Planning(ERP)software is extensively used for the management of business *** offers a system of integrated applications with a shared central *** all business-critical information in a central place raises various issues such as data integrity assurance and a single point of failure,which makes the database *** paper investigates database and Blockchain integration,where the Blockchain network works in synchronization with the database system,and offers a mechanism to validate the transactions and ensure data *** research exists on Blockchain-based solutions for the single point of failure in *** established in our study that for concurrent access control andmonitoring of ERP,private permissioned Blockchain using Proof of Elapsed Time consensus is more *** study also investigated the bottleneck issue of transaction processing rates(TPR)of Blockchain consensus,specifically ERP’s *** paper presents systemarchitecture that integrates Blockchain with an ERP system using an application interface.

关键词： Transaction security enterprise systems blockchain transaction integrity hyperledger sawtooth PoET consensus

来源：评论

学校读者我要写书评

暂无评论

Text-to-Sketch Synthesis via Adversarial Network

引用

computers, Materials & Continua 2023年第7期76卷 915-938页

作者： Jason Elroy Martis Sannidhan Manjaya Shetty Manas Ranjan Pradhan Usha Desai Biswaranjan Acharya Department of Information Science and Engineering NMAM Institute of Technology(Nitte Deemed to be University)NitteIndia Department of Computer Science and Engineering NMAM Institute of Technology(Nitte Deemed to be University)NitteIndia School of Computing Skyline University CollegeUniversity CitySharjahUAE Department of Electronics and Communication Engineering SR UniversityWarangalTelanganaIndia Department of Computer Engineering–AI&BDA Marwadi UniversityRajkotGujaratIndia

In the past,sketches were a standard technique used for recognizing offenders and have remained a valuable tool for law enforcement and social security ***,relying on eyewitness observations can lead to discrepancies in the depictions of the sketch,depending on the experience and skills of the sketch *** the emergence of modern technologies such as Generative Adversarial Networks(GANs),generating images using verbal and textual cues is now possible,resulting in more accurate sketch *** this study,we propose an adversarial network that generates human facial sketches using such cues provided by an ***,we have introduced an Inverse Gamma Correction Technique to improve the training and enhance the quality of the generated *** evaluate the effectiveness of our proposed method,we conducted experiments and analyzed the results using the inception score and Frechet Inception Distance *** proposed method achieved an overall inception score of 1.438±0.049 and a Frechet Inception Distance of 65.29,outperforming other state-of-the-art techniques.

关键词： Generative adversarial networks inverse gamma correction sketch attributes text-to-sketch synthesis deep learning techniques

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Improve Domain Generalization in EEG-based Emotion Classification using Feature Fusion Learning Model 14

Multi-Task Improve Domain Generalization in EEG-based Emotio...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Menaka, S. Joshi, Riddhi. S. Varun, M. SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350335095

The use of Electroencephalography (EEG) signals for emotion identification tasks is common. However, the domain shift issue may cause EEG-based emotion detection models' performance to decline when used in new domains. In this article, we present a feature fusion learning model-based multi-task learning strategy to enhance domain generalization in EEG-based emotion classification. By simultaneously learning a shared feature extractor and numerous domain-specific classifiers, we train a single model to categorize emotions across various domains. Additionally, we present a feature fusion module that combines time-domain, frequency-domain, and wavelet-domain EEG characteristics. We run trials on the DEAP and SEED EEG emotion recognition datasets to assess our suggested methodology. The experimental findings show that our suggested strategy outperforms a number of cutting-edge techniques in terms of classification accuracy, both within- and across-domains. © 2023 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

PakhiderChobi: A Comprehensive Dataset for Real-time Detection of Bangladeshi Birds 26

PakhiderChobi: A Comprehensive Dataset for Real-time Detecti...

引用

26th International Conference on computer and Information technology, ICCIT 2023

作者： Ataullha, Md Rahman, Mushfiqur Shahidur Rahman, M. Shahjalal University of Science and Technology Department of Computer Science and Engineering Sylhet Bangladesh

ISBN: (纸本)9798350359015

Urbanization and rapid development have led to a decline in natural habitats for birds, posing a threat to avian biodiversity worldwide. This study addresses the crucial task of accurately detecting and classifying bird species in urban environments, a vital component of bird conservation efforts, with a specific focus on Bangladeshi bird species. To overcome this challenge, we introduce the PakhiderChobi dataset, a collection of 8,670 annotated images featuring 33 commonly found Bangladeshi bird species. This dataset is designed to support real-time bird recognition and classification, encompassing a variety of scenarios, including instances where multiple birds of the same class occur, as well as cases where multiple bird species coexist within a single frame. To evaluate the quality of our dataset, we employ the YOLOv8 object detection model, achieving a mean average precision (mAP) of 95.3%, with efficient inference times of 6.6 milliseconds per image. © 2023 IEEE.

关键词： Avian Biodiversity Bangladeshi Birds Bird Classification Bird Detection Object Detection YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Deep 3D-CNN using Resonance Imaging for Diagnosing Alzheimer's 3

Deep 3D-CNN using Resonance Imaging for Diagnosing Alzheimer...

引用

3rd International Conference on Artificial Intelligence and Signal Processing, AISP 2023

作者： Ayub, Nadish Shah, Syed Zubair Ahmad Assad, Assif Din, Nusrat Mohi Ud Islamic University of Science and Technology Department of Computer Science and Engineering Awantipora India

ISBN: (纸本)9798350320749

Alzheimer's Disease (AD), the most prevalent type of dementia, is an incurable neurological disorder that leads to progressive mental decline. The majority of an AD diagnosis in practise is based on the patient's clinical history and neu- ropsychological information, such as magnetic resource imaging, despite the fact that an exact diagnosis of AD is challenging (MRI). Deep learning's use in recognising AD is the subject of growing research in recent few years. It enables for automatic AD identification using 3D brain MRI images. For AD recognition, the network makes use of a three-dimensional convolutional neural network (3DCNN). It is distinctive in that AD recognition accurately reflects the three-dimensional structure of the brain as a whole. Due to the fact that MRIs are 3D objects and utilise 3D Convolutional Neural Networks (CNNs) since using 3D CNNs the spatial integrity is maintained as compared to other methods that only employ a section of the MRI, such as ROI-based CNNs which works on some specific ROI, 2D slices that uses 2D slices, and 3D Patch-level that use 3D pathes. Four successive processing layers, two fully connected layers, and a classification layer is employed to design the CNN in this study. Each of the three groups in the structure is composed of three layers: a convolutional layer, a pooling layer, and a normalisation layer. The AD Neuroimaging Initiative's MRI data is used to train and evaluate the algorithm. The data used in this work is comprised of 1656 MRI scans of 382 patients. According to the results of the trial, the suggested algorithm had a 99% training accuracy of AD recognition with a validation accuracy of 73%. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Multilingual Exploration of the Kambaramayana: Analyzing Tamil Translations in Telugu, Malayalam, and Kannada Using mBERT and DistilBERT 1

Multilingual Exploration of the Kambaramayana: Analyzing Tam...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Swathi, K. Kamalam, G.K. Hemalatha, S. Jothimani, K. Dharshini, N. Aadhishri, A. Kongu Engineering College Department of Computer Science and Design Tamil Nadu India Kongu Engineering College Department of Information Technology Tamil Nadu India Kongu Engineering College Department of Computer Science and Engineering Tamil Nadu India

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356816

An essential and basic aspect of our existence are our emotions. Our behaviors and words reflect our feelings, even though they are not instantly obvious. This research looks at the multilingual features of the Kambaramayana, with a concentration on Tamil translates into Telugu, Malayalam, and Kannada. We study how linguistic and cultural subtleties show across translations using a varied dataset. We do a comparison study using sophisticated multilingual language models, specifically mBERT and DistilBERT, to identify semantic variances and similarities. We hope to uncover the subtle interplay among language and culture in literary text transmission by investigating vocabulary, grammar, and cultural allusions. Our findings not only improve the accuracy of cross-lingual text analysis, but also highlight the Ramayana's lasting relevance among South Indian language communities. The experiments clearly reveal that mBERT outperforms DistilBERT in emotion analysis tasks between languages. © 2024 IEEE.

关键词： Measurement Vocabulary Translation Accuracy Text analysis Semantics Robustness Multilingual Grammar Cultural differences

来源：评论

学校读者我要写书评

暂无评论

Adaptive Filtering for Low-Energy Data Aggregation 5th

Adaptive Filtering for Low-Energy Data Aggregation

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Panwar, Govind Singh Mrutyunjaya, M.S. Agarwal, Trapty Kamalraj, R. Department of Computer Science & Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Manduwala Dehradun Navgaon India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science and Information Technology Jain University Karnataka Bangalore India

ISBN: (纸本)9789819780426

Hyper Spectral Imaging (HSI) is a powerful approach used in far flung sensing packages that captures spatially contiguous set of spectrum statistics from a scene. HSI information incorporates beneficial facts about the goals within the scene;however, due to noise and various distortions, it can be tough to discover those objectives. Spatial filtering is a method used to reduce undesirable noise in images if you want to make goal identity easier and extra accurate. On this paper, we endorse a brand new technique evolved for applying spatial filters on HSI pics that utilizes a spatially adaptive sigma clear out to successfully lessen noise and improve target identity accuracy. The advanced method correctly carries spatial variability within the filter length and clear out parameters to obtains progressed goal discrimination overall performance. The proposed technique is evaluated the use of both simulated and actual HSI records sets and effects display progressed target accuracy when as compared to traditional spatial filters. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Optimized Task Scheduling in Diverse Distributed Systems with a Hybrid Genetic Algorithm Approach 3rd

Optimized Task Scheduling in Diverse Distributed Systems wit...

引用

3rd International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2023

作者： Muthusamy, Ramesh Kumar Kadu, Swati Ayyasamy, Karthikeyan Pichuka Veera Venkata Satya, Srinivas Arumugam, Ramachandran Ammasai, Viswanathan Sengan, Sudhakar Department of Information Technology V.S.B. College of Engineering Technical Campus Tamil Nadu Coimbatore642109 India Department of AI&DS AISSMS IOIT Pune411001 India Department of Computer Science and Engineering Panimalar Engineering College Tamil Nadu Chennai600123 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522502 India Department of Computer Science and Engineering Saveetha Engineering College Tamil Nadu Chennai602105 India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627012 India

ISBN: (纸本)9789819783540

In Heterogeneous Distributed Systems (HDS), efficient task scheduling (TS) across diverse resources remains a pressing challenge. This paper introduces a Hybrid Genetic Algorithm (HGA) as a solution, blending heuristic techniques with the evolutionary strengths of Genetic Algorithms (GAs) to optimize Task Scheduling (TS). Traditional algorithms often fall short in balancing computational speed with solution quality, especially in large-scale environments. This proposed HGA addresses this by leveraging domain-specific heuristics to provide a promising starting point for the GA's optimization process. The TS dilemma has been successfully defined by an all-encompassing logical system, which ensures the accuracy of the design of algorithms. In comparison tests, the HGA frequently comes out on top, demonstrating less makespan and a more excellent distribution of tasks among the resources available. Also, resources with more efficient processing capabilities will be provided priority in this recommended heuristic method, which focuses on tasks with higher computational demands. The findings of the present investigation demonstrate that the HGA may transform TS approaches by providing high-quality solutions while increasing performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Scheduling algorithms

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：