检索结果-内蒙古大学图书馆

BIT Conference (BITCON), International

作者： S.E. Viswapriya D. Rajeswari Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Chennai India

ISBN: (数字)9798331518394

ISBN: (纸本)9798331518400

Medical image segmentation plays a crucial role in treatment planning, disease diagnosis, and guiding surgical navigation. Research should focus on medical image segmentation to achieve substantial breakthroughs or fill knowledge gaps that could lead to discoveries and improvements. Deep learning (DL) techniques have recently become necessary in creating advanced models, particularly for medical image segmentation. This paper introduces a novel segmentation algorithm specifically designed for MRI images. Initially, the paper will discuss the introduction and challenges in medical image segmentation. Later, developing a novel attentive feature-based segmentation algorithm is focused and their corresponding evaluation steps are measured. The evaluation metrics are finally compared with other existing segmentation algorithms and concluded that the proposed model surpasses the cutting-edge methods by notable differences in performance, showing the adaptability and overall effectiveness of the proposed model.

关键词： Deep learning Image segmentation Adaptation models Magnetic resonance imaging Semantic segmentation Surgery Computer architecture Feature extraction Medical diagnostic imaging Testing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Long Short Term Memory for Early Alzheimer's Disease Prediction

引用

Intelligent Automation & Soft computing 2023年第2期35卷 1277-1293页

作者： M.Vinoth Kumar M.Prakash M.Naresh Kumar H.Abdul Shabeer Department of Information Science and Engineering Dayananda Sagar Academy of Technology&ManagementKanakapura Main Road560082BangaloreIndia Department of Data Science and Business Systems School of Computing SRM Institute of Science and TechnologyKattankulathurChengalpattu603203TamilnaduIndia Department of ECE Vardhaman College of EngineeringHyderabad501218India IBM India Pvt Ltd. DLF IT ParkChennai600125India

The most noteworthy neurodegenerative disorder nationwide is appar-ently the Alzheimer's disease(AD)which ha no proven viable treatment till date and despite the clinical trials showing the potential of preclinical therapy,a sen-sitive method for evaluating the AD has to be developed *** to the correla-tions between ocular and brain tissue,the eye(retinal blood vessels)has been investigated for predicting the ***,en enhanced method named Enhanced Long Short Term Memory(E-LSTM)has been proposed in this work which aims atﬁnding the severity of AD from ocular ***ﬁnd the level of disease severity,the new layer named precise layer was introduced in E-LSTM which will help the doctors to provide the apt treatments for the patients *** avoid the problem of overﬁtting,a dropout has been added to *** the existing work,boundary detection of retinal layers was found to be inaccurate during the seg-mentation process of Optical Coherence Tomography(OCT)image and to over-come this issue;Particle Swarm Optimization(PSO)has been *** the best of our understanding,this is theﬁrst paper to use Particle Swarm *** compared with the existing works,the proposed work is found to be per-forming better in terms of F1 Score,Precision,Recall,training loss,and segmen-tation accuracy and it is found that the prediction accuracy was increased to 10%higher than the existing systems.

关键词： Alzheimer's disease enhanced LSTM particle swarm optimization OCT image boundary detection

来源：评论

学校读者我要写书评

暂无评论

Emoji Anticipation and Prediction Using Deep Neural Network Model

Emoji Anticipation and Prediction Using Deep Neural Network ...

引用

International Conference on Power, Energy, Control and Transmission systems (ICPECTS)

作者： J. Shobana S. Amudha Siva Kumar A Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Chengalpattu(DT) Tamilnadu India

ISBN: (纸本)9781665462761

Emojis are tiny pictorial depictions of feelings or objects that are frequently used in text messaging to enhance intercultural dialogue. Emojis are increasingly being used by users of social media sites like Twitter and Instagram in their text messages to express broader emotions that are frequently challenging to express in words alone. Combining text and emojis to express emotion has become a crucial part of how people communicate in the twenty-first century. In order to ascertain the connection between these text messages and the emojis used in them, a problem statement has been developed. In this study, we offer a technique for anticipating several emojis for a given text-based tweet message. Three modules make up the suggested model. The given text data is preprocessed in the first module, the model on which the data is trained is in the second, and a multi-class classifier is used in the third module to predict the emojis that the given text would evoke. This proposed deep neural network model aims to understand the underlying semantics of a text sentence using natural language processing techniques in order to predict appropriate emojis. Experiments performed utilizing a sizable data collection of Twitter-sourced real-world emoji usage.

关键词： Deep learning Support vector machines Social networking (online) Neural networks Blogs Semantics Predictive models

来源：评论

学校读者我要写书评

暂无评论

Part-Based Convolutional Neural Network and Dual Interactive Wasserstein Generative Adversarial Networks for Land Mark Detection and Localization of Autonomous Robots in Outdoor Environment

Part-Based Convolutional Neural Network and Dual Interactive...

引用

International Conference on Computational science and Technology (ICCST)

作者： S. Sindhu M. Saravanan Department of Data Science and Business Systems Faculty of School of computing SRM Institute of Science and Technology Kattankulathur Department of Networking and Communications Faculty of School of computing SRM Institute of Science and Technology Kattankulathur

ISBN: (纸本)9781665476560

Robot localization is a fundamental competency required by an autonomous robot because the robot's location knowledge is an essential precursor to making decisions about future actions. Accurate localization of robots or autonomous vehicles is the most important requirement for autonomous applications. In this manuscript, a part-based convolutional neural network and dual interactive Wasserstein generative adversarial networks for landmark detection and localization of autonomous robots in an outdoor environment are proposed (P-CNN-DIWGAN-LMD-LZ). This research contains two phases landmark detection phase and the localization phase. In the landmark detection phase, the part-based convolutional neural network (P-CNN) is proposed to detect landmarks in capturing images. This landmark detection process creates 3 categories of responses for every detected landmarks instance: bounding box, label, and score. The bounding box has positioning with the sizing of detected landmarks at the input imagery. Label implicates detected landmark's class name. A score signifies an abjectness score that scales bounding box membership for landmarks or background classes. In the localization phase, a dual interactive Wasserstein generative adversarial network (DIWGAN) is proposed to determine robot location coordinates. Finally, the proposed method attains high robot localization recall at high accuracy in the real-world environment. Here, the outdoor robot localization dataset is taken from the KITTI dataset. The proposed method is implemented in Python; its performance is estimated under certain performance metrics, like mean absolute error (MAE), cosine proximity (CP), and accuracy. The performance of the proposed method shows higher accuracy compared with existing approaches, like DQP-ODA-LMD-LZ, TDL-LMD-LZ, and 3D-RISS-MLEVD- LMD-LZ.

关键词： Location awareness Measurement Scientific computing Robot kinematics Generative adversarial networks Robot localization Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Phylogenetic-Informed Generative Adversarial Network for Predicting Mutations in SARS-CoV-2

Phylogenetic-Informed Generative Adversarial Network for Pre...

引用

Networking and Communications (ICNWC), International Conference on

作者： Vijay Chandar Vishnu G Nair Rajeswari D Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Chennai India

ISBN: (数字)9798350365269

ISBN: (纸本)9798350365276

In the pursuit of developing more effective vaccines against viruses like SARS-CoV-2, understanding their potential mutations is crucial. In order to generate protein sequences, this study presents a unique framework that synergistically blends phylogenetic data with Generative Adversarial Networks (GANs). The proposed method combines the strengths of two models: TEMPO, a transformer-based model proficient in leveraging phylogenetic data for mutation detection in SARS-CoV-2, and MutaGAN, a GAN-based model adept in generating synthetic protein sequences. The phylogenetic data from TEMPO is used in this novel design as the input for the MutaGAN generator, replacing the conventional random noise input used in GANs. The generator may now create synthetic protein sequences that are impacted by the evolutionary past included in the phylogenetic data resulting in the creation of artificial protein sequences that are more biologically significant and lifelike. The discriminator portion of the model, similar to MutaGAN, is still in charge of determining whether or not the input sequences comprise a valid parent-child pair and uses sequences produced by the first GAN as extra negative cases. This prevented the model from going too far off its planned route. Additional investigation into this fascinating confluence of bioinformatics and AI may be possible as a result of this study’s conclusions. This approach has tremendous promise in many applications, such as the production of more powerful vaccinations, protein engineering, medication design, and improving our knowledge of biological systems, by forecasting how SARS-CoV-2 could change. A precision of 0.662 and an accuracy of around 0.671, together with a Matthews Correlation Coefficient (MCC) score of 0.313, show that the framework performs very well. These scores show that the framework performs better than a number of cutting-edge baseline techniques. The synthetic protein sequences generated by the framework not only bea

关键词： Proteins Protein engineering Biological system modeling Generative adversarial networks Transformers data models Generators

来源：评论

学校读者我要写书评

暂无评论

Anonymous Crime Reporting using Blockchain and Smart Contract

Anonymous Crime Reporting using Blockchain and Smart Contrac...

引用

Pervasive computing and Social Networking (ICPCSN), International Conference on

作者： Prince Kumar Chaurasia Darshnilsinh Rana Rajaram V S. Srividhya Department of Networking and Communications School of Computing SRM Institute of Science and Technology Kattankulathur India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur India

ISBN: (数字)9798350386349

ISBN: (纸本)9798350386356

The traditional crime reporting systems face challenges such as inefficiencies, security vulnerabilities, and witness reluctance. Despite recent advancements like mobile applications and web platforms, challenges persist in ensuring data security, transparency, and user anonymity. These include maintaining confidentiality, data integrity, and preventing unauthorized access. To address these issues, this paper proposes leveraging blockchain technology and smart contracts. The primary objective is to enhance the security, efficiency, and anonymity of crime reporting processes. By utilizing the decentralized and immutable nature of blockchain, the system aims to ensure data integrity, transparency, and decentralization. Smart contracts will automate functions such as complaint validation and evidence verification, streamlining the reporting process. By addressing challenges in maintaining confidentiality, data integrity, and access control, the proposed solution seeks to revolutionize crime reporting, promoting trust, transparency, and accountability.

关键词： Pervasive computing Technological innovation Law enforcement Social networking (online) data integrity Smart contracts Robustness

来源：评论

学校读者我要写书评

暂无评论

Facial Image-Based Autism Detection:A Comparative Study of Deep Neural Network Classifiers

引用

Computers, Materials & Continua 2024年第1期78卷 105-126页

作者： Tayyaba Farhat Sheeraz Akram Hatoon SAlSagri Zulfiqar Ali Awais Ahmad Arfan Jaffar Faculty of Computer Science and Information Technology The Superior UniversityLahore54600Pakistan Intelligent Data Visual Computing Research(IDVCR) Faculty of Computer Science and Information TechnologyThe Superior UniversityLahore54600Pakistan Information Systems Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh12571Saudi Arabia School of Computer Science and Electronic Engineering(CSEE) University of EssexWivenhoe ParkColchesterCO43SQUK

Autism Spectrum Disorder(ASD)is a neurodevelopmental condition characterized by significant challenges in social interaction,communication,and repetitive *** and precise ASD detection is crucial,particularly in regions with limited diagnostic resources like *** study aims to conduct an extensive comparative analysis of various machine learning classifiers for ASD detection using facial images to identify an accurate and cost-effective solution tailored to the local *** research involves experimentation with VGG16 and MobileNet models,exploring different batch sizes,optimizers,and learning rate *** addition,the“Orange”machine learning tool is employed to evaluate classifier performance and automated image processing capabilities are utilized within the *** findings unequivocally establish VGG16 as the most effective classifier with a 5-fold cross-validation ***,VGG16,with a batch size of 2 and the Adam optimizer,trained for 100 epochs,achieves a remarkable validation accuracy of 99% and a testing accuracy of 87%.Furthermore,the model achieves an F1 score of 88%,precision of 85%,and recall of 90% on test *** validate the practical applicability of the VGG16 model with 5-fold cross-validation,the study conducts further testing on a dataset sourced fromautism centers in Pakistan,resulting in an accuracy rate of 85%.This reaffirms the model’s suitability for real-world ASD *** research offers valuable insights into classifier performance,emphasizing the potential of machine learning to deliver precise and accessible ASD diagnoses via facial image analysis.

关键词： Autism Autism Spectrum Disorder(ASD) disease segmentation features optimization deep learning models facial images classification

来源：评论

学校读者我要写书评

暂无评论

Nodule Detection Using Local Binary Pattern Features to Enhance Diagnostic Decisions

引用

Computers, Materials & Continua 2024年第3期78卷 3377-3390页

作者： Umar Rashid Arfan Jaffar Muhammad Rashid Mohammed S.Alshuhri Sheeraz Akram Faculty of Computer Science and Information Technology The Superior UniversityLahore54600Pakistan Intelligent Data Visual Computing Research(IDVCR) Lahore54600Pakistan Department of Computer Science National University of TechnologyIslamabad45000Pakistan Department of Radiological Sciences and Medical Imaging College of AppliedMedical SciencesPrince Sattam Bin Abdulaziz UniversityAl-Kharj16278Saudi Arabia Information Systems Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh12571Saudi Arabia

Pulmonary nodules are small, round, or oval-shaped growths on the lungs. They can be benign (noncancerous) or malignant (cancerous). The size of a nodule can range from a few millimeters to a few centimeters in diameter. Nodules may be found during a chest X-ray or other imaging test for an unrelated health problem. In the proposed methodology pulmonary nodules can be classified into three stages. Firstly, a 2D histogram thresholding technique is used to identify volume segmentation. An ant colony optimization algorithm is used to determine the optimal threshold value. Secondly, geometrical features such as lines, arcs, extended arcs, and ellipses are used to detect oval shapes. Thirdly, Histogram Oriented Surface Normal Vector (HOSNV) feature descriptors can be used to identify nodules of different sizes and shapes by using a scaled and rotation-invariant texture description. Smart nodule classification was performed with the XGBoost classifier. The results are tested and validated using the Lung Image Consortium database (LICD). The proposed method has a sensitivity of 98.49% for nodules sized 3–30 mm.

关键词： Pulmonary nodules segmentation histogram thresholding

来源：评论

学校读者我要写书评

暂无评论

Detection of Brain Tumor from MRI Images Using VGG-16 CNN Model with Transfer Learning

Detection of Brain Tumor from MRI Images Using VGG-16 CNN Mo...

引用

Pervasive computing and Social Networking (ICPCSN), International Conference on

作者： Bhanu Pratap Singh Rathore Rutul Dave Dhanasekaran K Priyadarsini K Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Chennai India

Brain tumors are a serious health concern caused by the abnormal growth of cells in or around the brain. These tumors can either be benign or malignant. Few of the causes for Brain tumors are genetic mutations, exposure to radiation, or environmental factors. Early detection of brain tumors is essential for effective treatment and improved patient outcomes. To address this, a novel approach has been proposed for brain tumor detection using transfer learning with the VGG-16 convolutional neural network (CNN) architecture. By leveraging the pre-trained VGG-16 model on the ImageNet dataset, which provides a broad range of data for learning and representing complex features of various objects, meaningful features can be extracted from MRI scans and differentiate between tumor and normal tissue accurately. This refined VGG-16 model can provide a more precise and reliable diagnosis, which is crucial for successful treatment. This research study demonstrates that the utilization of VGG-16 model for brain tumor diagnosis can provide an efficient and accurate method for identifying brain tumors. Moreover, this approach can be applied to develop automated systems to assist medical professionals in diagnosing and treating brain tumors more effectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DeepCNN:Spectro-temporal feature representation for speech emotion recognition

引用

CAAI Transactions on Intelligence Technology 2023年第2期8卷 401-417页

作者： Nasir Saleem Jiechao Gao Rizwana Irfan Ahmad Almadhor Hafiz Tayyab Rauf Yudong Zhang Seifedine Kadry Department of Electrical Engineering Faculty of Engineering and TechnologyGomal UniversityD.I.KhanPakistan Department of Computer Science University of VirginiaCharlottesvilleVirginiaUSA Department of Information Technology College of Computing and Information Technology at KhulaisUniversity of JeddahJeddahSaudi Arabia Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySkaka AljoufSaudi Arabia Centre for Smart Systems AI and CybersecurityStaffordshire UniversityStoke‐on‐TrentUK School of Computing and Mathematical Sciences University of LeicesterLeicesterUK Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) Ajman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon

Speech emotion recognition(SER)is an important research problem in human-computer interaction *** representation and extraction of features are significant challenges in SER *** the promising results of recent studies,they generally do not leverage progressive fusion techniques for effective feature representation and increasing receptive *** mitigate this problem,this article proposes DeepCNN,which is a fusion of spectral and temporal features of emotional speech by parallelising convolutional neural networks(CNNs)and a convolution layer-based *** parallel CNNs are applied to extract the spectral features(2D-CNN)and temporal features(1D-CNN)representations.A 2D-convolution layer-based transformer module extracts spectro-temporal features and concatenates them with features from parallel *** learnt low-level concatenated features are then applied to a deep framework of convolutional blocks,which retrieves high-level feature representation and subsequently categorises the emotional states using an attention gated recurrent unit and classification *** fusion technique results in a deeper hierarchical feature representation at a lower computational cost while simultaneously expanding the filter depth and reducing the feature *** Berlin database of Emotional Speech(EMO-BD)and Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets are used in experiments to recognise distinct speech *** efficient spectral and temporal feature representation,the proposed SER model achieves 94.2%accuracy for different emotions on the EMO-BD and 81.1%accuracy on the IEMOCAP dataset *** proposed SER system,DeepCNN,outperforms the baseline SER systems in terms of emotion recognition accuracy on the EMO-BD and IEMOCAP datasets.

关键词： decision making deep learning

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：