检索结果-内蒙古大学图书馆

Advanced skin lesion segmentation and classification using adaptive contextual GLCM and deep learning hybrid models

Egyptian Informatics Journal 2025年 30卷

作者： Vinit Kumar D.L. Shanthi Tummala Ranga Babu Narendra Kumar Rakesh Kumar Godi Dr Arun G Professor Galgotias College of Engineering and Technology Greater Noida India Assistant Professor Department of Computer Science and Engineering BMS Institute of Technology and Management Bangalore Karnataka India Professor Electronics & Communication Engineering R.V.R. & J.C.College of Engineering India Associate Professor Department of CSE Amity University Jharkhand Ranchi Jharkhand India Department of Computer Science Central University of Karnataka Kalaburagi 585367 India Assistant Professor Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India

One of the most common and dangerous types of cancer, skin cancer, especially melanoma, is distinguished by its quick spread and high death rate if left untreated. It is impossible to overestimate the significance of early detection and precise diagnosis as they are essential for successful treatment and greatly raise patient survival rates. To improve skin lesion segmentation and classification, this work presents a state-of-the-art image analysis technique that uses hybrid deep learning models in conjunction with the Adaptive Contextual Gray Level Co-occurrence Matrix (GLCM). DeepLabV3 + is used to segment the skin lesion from pre-processed input images with high accuracy. A Long Short-Term Memory (LSTM) network trained on characteristics collected by the Adaptive Contextual GLCM is included to further evaluate the segmented images. Because of this special combination, the model can accurately capture contextual information and tiny texture differences, both of which are essential for differentiating between benign and malignant skin lesions. Our suggested approach performs very well in tasks involving both segmentation and classification. In particular, it attains a remarkable 98.34 % accuracy, 99.13 % specificity, 97.25 % sensitivity, 97.15 % Dice coefficient, and 98.6 % F1 score. These findings demonstrate the method’s stability and dependability, which makes it a potentially useful instrument for raising the detection accuracy of skin cancer. This approach has the potential to transform early detection procedures by providing improved diagnostic accuracy and resilience, eventually contributing to better patient outcomes and more effective management of skin cancer cases.

关键词： Skin cancer Machine Learning Deeplabv3 Adaptive Contextual Gray Level Co-occurrence Matrix Long Short-Term Memory

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning: A novel approach towards drug discovery

引用

AIP Conference Proceedings 2023年第1期2477卷

作者： Nishath Ansari Amjan Shaik Patluri Harika Boga Varasree K. Purnachand Saikumar Tara Assistant Professor Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur Telangana India Professor Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur Telangana India Assistant Professor Department of Computer Science and Engineering Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Assistant Professor Department of Information Technology Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Associate Professor Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur Telangana India Associate Professor Department of Electronics and Communication Engineering CMR Technical campus Hyderabad Telangana India

Reinforcement learning has been giving new strategies to ad-lib in the fields of medication and the drug industry. It is probably the best strategy among all the AI strategies. Reinforcement learning has been compelling to discover strategies that could treat the immense number of deadly infections. In this paper, a detailed new methodology about what Reinforcement Leaning and what is drug revelation and what are various techniques utilized in Reinforcement learning, how Reinforcement learning could be utilized in different utilization of medication plan such as target identification, hit discovery, hit to lead, lead optimization. The consequence of the paper illustrates the summarized data of different approaches for the development and discovery of drugs. A clear illustration of various work done in the field of drug discovery, discuss different pros and cons of Reinforcement learning as well emphasize primary challenges need to handle and how to defeat them in the future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A High-Band Compact Microstrip Patch Antenna For 5G Wireless Technologies

A High-Band Compact Microstrip Patch Antenna For 5G Wireless...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： G. Santhakumar R. Muthukumar Asa Jyothi G S. Balakumar Ramya Maranan Roshan Bonde Department of Electronics and Communication Engineering Sri Krishna College of Technology Coimbatore Tamil Nadu India Department of EEE Erode Sengunthar Engineering College Erode Tamil Nadu India ECE Department Malla Reddy Engineering College Maisamma Guda Hyderabad Telangana India Faculty of Electrical & Computer Engineering Arba Minch University Arba Minch Ethiopia Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India Assistant Professor Dr. Babasaheb Ambedkar Technological University Lonere Raigad India

This examination presents a High Increase, Overhauled Bandwidth Patch antenna for 5G Undertakings. Using an inset-took care of taking care of method for the microstrip patch antenna wave band, the double band is achieved. Two rectangular apertures are embedded on the patch's transmitting component to provide it a high increase. The anticipated antenna Consolidating three stages at the edge of the rectangular patch increases bandwidth. Fifth-generation (5G) networks clearly outperform 4G because to reduced idleness, more transmission speed, greater bandwidth, and a higher possibility of integrating with more notable various devices. For impending 5G association technologies, this paper studies and presents a microstrip patch antenna working at 28 GHz. The outcome of this reenactment is superior to the previous one. It typically acts as a dependable choice for 5G wireless innovation as a result. The performance of the suggested antenna is superior to that of earlier antennas spread in logical diaries.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Terms Estimation of S Robotics using MTRS as well as FEM

The Terms Estimation of S Robotics using MTRS as well as FEM

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： R. Gopal Mustafa Mudhafar Amjad Hashem Venkadeshan Ramalingam Dibyahash Bordoloi Muhammad Numan Ali Khan Myasar Mundher Adnan Zahraa N. Abdulhussain Assistant Professor Information and communication Engineering College of Engineering University of Buraimi Sultanate of Oman Department of Medical Physics Faculty of Medical Applied Sciences University of Kerbala Karbala Iraq Computer Engineer Department Al-kunooze University College Basra Iraq Network Computing College of Computing and Information Sciences University of Technology and Applied Sciences– Shinas Sultanate of Oman Dept of CSE Graphic Era Hill University Adjunct professor Graphic Era Deemed to be University Dehradun Uttarakhand Faculty – Network Computing College of Computing and Information Sciences University of Technology and Applied Sciences – Shinas Sultanate of Oman Department of computers Techniques engineering College of technical engineering The Islamic university Najaf Iraq College of Technical Engineering National University of Science and TechnologyDhi Qar Iraq

ISBN: (数字)9798350360165

ISBN: (纸本)9798350360172

This look at addresses the critical project of reaching dependable and precise proprioception in soft robots, it really is essential for his or her effective deployment in complicated environments. By integrating multi-tap resistive sensors in the robot’s form, our technique lets in for the distinct sensing of nearby deformations at various factors throughout the robotics’ frame, moving beyond traditional techniques that anticipate steady curvature. We beautify the decision of these deformations and couple the sensory facts with a strong finite detail technique (FEM) model. This included framework allows the correct estimation of the smooth robot’s form and the significance of outside forces applied to it, attaining a mean relative inaccuracy of about 4%. Additionally, our technique proves its software program in tender manipulation structures, in which it achieves thirteen% relative mistakes in external force estimation inside diverse zero to five N. The approach gives a promising direction for enhancing robotic interactions in sensitive and dynamic responsibilities, providing massive enhancements in robotic proprioception without reliance on outdoor monitoring generation.

关键词： Deformable models Deformation Force Estimation Soft robotics Robot sensing systems Software

来源：评论

学校读者我要写书评

暂无评论

Artificial super intelligence: Barriers and limitations

引用

AIP Conference Proceedings 2024年第1期3209卷

作者： Rahul Goyal Neha Sharma Amanpreet Kaur Student Department of Computer Science and Engineering Chitkara University Institute of Engineering & technology Chitkara University Punjab India. Assistant Professor Department of Computer Science and Engineering Chitkara University Institute of Engineering & Technology Chitkara University Punjab India Professor Department of Computer Science and Engineering Chitkara University Institute of Engineering & Technology Chitkara University Punjab India.

In urban studies, artificial intelligence systems are a widely recognized technology that provides an alternate approach to dealing with complicated and dynamic issues. Despite the risks of implementing more powerful artificial intelligence, many big tech companies are working towards it. So, this paper aims to show the barriers to artificial intelligence. Also, this paper illustrates barriers in machines that prevent artificial superintelligence from being achieved. Further, the paper discusses how machine neural networks differ from human neural networks and the existential threats posed by artificial intelligence and superintelligence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Experimental Assessment of Random Forest Classification Performance Improvisation with Sampling and Stage Wise Success Rate Calculation

引用

Procedia computer Science 2020年 167卷 1711-1721页

作者： Anjali S. More Dipti P. Rana Research Scholar Computer Engineering Department SVNIT Surat India 395007 Assistant Professor Computer Engineering Department SVNIT Surat India 395007

Imbalanced data classification with Random Forest Classification (RFC) technique has gained huge prominence in today’s application era. Data imbalance between practical applications relates to either binary class imbalance or multiclass imbalance. Binary class imbalance constitutes one of the classes with majority data samples and other contains minor number of data samples. In case of multiclass there are two categories of multiclass imbalanced dataset as Multiclass Minority Imbalanced Class (MMinIC) and Multiclass Majority Imbalanced Class (MMajIC). Classification performance leans towards degradation for MMajIC than MMinIC due to major imbalance rate severity. In this paper, the study investigates the influence of RFC classification analysis method on binary and multiclass sample imbalanced datasets. The analytical study of RFC incorporates with measurement of classification accuracy with performance metrics as True Positive (TP) Rate, False Positive (FP) Rate, Precision (Pre), Recall (Rec) F-Measure, Operating Characteristics of Receiver (ROC) Area, Matthews Correlation Coefficient (MCC), Probabilistic Relevance Classification (PRC) area with respect to numerous classes in refereed dataset. This paper focuses the reduction of the negative influence of imbalanced data with the use of Synthetic Minority Oversampling Technique (SMOTE). Experimental analysis carried out with the use of Knowledge Extraction Evolutionary Learning (KEEL) imbalanced data learning repository incorporating RFC classification with SMOTE technique. It also deals with RFC model construction with stage wise success rate calculation in training and testing partition and its impact on accuracy. The incorporates with error analysis report of incorrectly classified instances. Experimental results of the study indicate that imbalanced data have significant impact on classification accuracy and RFC outperforms with SMOTE.

关键词： Random forest classification imbalanced data classification SMOTE oversampling KEEL

来源：评论

学校读者我要写书评

暂无评论

Attack prevention in IoT through hybrid optimization mechanism and deep learning framework

引用

Measurement: Sensors 2022年 24卷

作者： Nagaraju, Regonda Pentang, Jupeth Toriano Abdufattokhov, Shokhjakhon CosioBorda, Ricardo Fernando Mageswari, N. Uganya, G. Department of Information Technology St.Martin's Engineering College Dhulapally Secunderabad500100 India Western Philippines University Philippines Automatic Control and Computer Engineering Department Turin Polytechnic University in Tashkent Tashkent Uzbekistan Universidad Autónoma del Perú Lima Peru Department of ECE Ashoka Women's Engineering College Andhra Pradesh Kurnool India Department of ECE Saveetha School of Engineering SIMATS Assistant Professor Chennai India

The Internet of Things (IoT) connects schemes, programs, data management, and operations, and as they continuously assist in the corporation, they may be a fresh entryway for cyber-attacks. Presently, illegal downloading and virus attacks pose significant threats to IoT security. These risks may acquire confidential material, causing reputational and financial harm. In this paper hybrid optimization mechanism and deep learning,a frame is used to detect the attack prevention in IoT. To develop a cybersecurity warning system in a huge data set, the cybersecurity warning systems index system is first constructed, then the index factors are picked and measured, and finally, the situation evaluation is *** bio-inspired techniques were used to enhance the productivity of an IDS by lowering the data dimensionality and deleting unnecessary and noisy input. The Grey Wolf Optimization algorithm (GWO) is a developed bio-inspired algorithm that improves the efficacy of the IDS in detecting both regular and abnormal congestion in the network. The smart initialization step integrates the different pre-processing strategies to make sure that informative features are incorporated in the early development stages, has been improved. Researchers pick multi-source material in a big data environment for the identification and verification of index components and present a parallel reduction approach based on the classification significance matrix to decrease data underlying data characteristics. For the simulation of this situation, grey wolf optimization and whale optimization were combined to detect the attack prevention and the deep learning approach was presented. Utilizing system software plagiarism, the TensorFlow deep neural network is intended to classify stolen software. To reduce the noise from the signal and to zoom the significance of each word in the perspective of open-source plagiarism, the tokenization and weighting feature approaches are utilized. Malware spec

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Survey on Impact and Learning’s of the Online Courses on the Present Era

引用

Procedia computer Science 2020年 172卷 82-91页

作者： T. Anitha Kumari CH. Hemalatha M Subhani Ali R Naresh Assistant Professor Department of Computer Science Engineering HITAM Hyderabad Telangana 501401 India Associate Professor Department of Mechanical Engineering HITAM Hyderabad Telangana 501401 India Assistant Professor Department of Electrical and Electronics Engineering HITAM Hyderabad Telangana 501401 India

Day to day technology is changing to upgrade or adopt technology faculty as well as students preferring online courses like NPTEL. With the fast development of internet techniques, data and communication technology is being more and more employed in curricula, and learning portfolios may be mechanically retrieved and maintained as learners act through e-learning platforms. NPTEL provided open access to hundreds and thousands of learners to take the preferred courses and helped to become experts in a particular area. This paper describes the impact of the online courses (NPTEL) on the learners and challenges and learning’s from the online courses. The participants comprised 114 faculty, who were surveyed regarding their learning experiences, motivation, challenges and intentions to use NPTEL. And what can be improved from the Faculty and student point of view?

关键词： Online courses Learning’s Challenges Motivation

来源：评论

学校读者我要写书评

暂无评论

Novel Image Watermarking Approach against Noise and RST Attacks

引用

Procedia computer Science 2020年 167卷 213-223页

作者： Sheshang D. Degadwala Mohini Kulkarni Dhairya Vyas Arpana Mahajan Head of Department Computer Engineering Sigma Institute of Engineering Vadodara India PG Student Computer Engineering Sigma Institute of Engineering Vadodara India Assistant Professor E&C Engineering Sigma Institute of Engineering Vadodara India Assistant Professor Computer Engineering Sigma Institute of Engineering Vadodara India

Digital watermarking is used for copyright protection of intellectual properties and hence it is important to protect and recover data from attacks. Existing systems work on and recover the image from single attacks. This paper aims at proposing a technique for retrieval of cover image and watermarked data from dual attacks like rotation and noise attacks. The proposed system takes as input, Color images and then embeds data using alpha blending method. And also tries to recover from dual attacks using median filtering and pseudo Zernike moment. Proposed approach selects LH band from the 4 sub bands image divided into using DWT and for reducing noise from the image SVD is used. Proposed approach is giving better results in terms of PSNR and MSE as compared to other existing systems using QWT.

关键词： Digital watermark Noise attacks Rotation attack Scaling Translate Pseudo Zernike Moments

来源：评论

学校读者我要写书评

暂无评论

ADVANCED ATTACK MITIGATION IN IOT GATEWAY PROTOCOLS

引用

computers & Security 2025年 157卷

作者： K. Praveen Kumar Dr. N. Suresh Kumar Assistant Professor Department of Information Technology Kakatiya Institute of Technology and Science Warangal (KITSW) Telangana India Research Scholar Department of Computer Science and Engineering GITAM University Visakhapatnam Andhra Pradesh India Associate Professor Department of Computer Science Engineering GITAM Institute of Technology GITAM (Deemed to be University) Visakhapatnam India

With the increasing number of users on the internet, numerous cyberattacks are becoming more and more common. Proper detection of these attacks by Intrusion Detection Systems (IDS) is extremely important, particularly for IoT networks. Deep learning methods have proved to be very promising for enhancing IDS performance. This paper presents an end-to-end system for attack detection and prevention in IoT networks with the use of data augmentation, preprocessing, feature extraction, and deep machine learning algorithms. The class imbalance is resolved using the Enhanced Synthetic Minority Over-Sampling Technique (ESMOTE), and preprocessing operations normalize and clean the data for improved model performance. Feature extraction involves statistical features and Shannon entropy-based features, which are fused and sent through a feature selection process. A new 2D-LICM hyper-chaotic map combined with Walrus Optimization (2D-LICMHy-CM_WO) is used to enhance feature selection through enhanced search diversity, convergence rate, and eliminating redundancy. The Dense Convolutional Spatial Attention-based Enhanced Bi-GRU (DCSAtten_EBi-GRU) effectively extracts attack pattern dependencies for precise detection, and an Enhanced Double Deep Q-Learning Network (DoubleDQN) offers dynamic adaptive real-time countermeasures. Experimental findings prove that the proposed solution can obtain a 99.6% detection accuracy with an F1-score of 0.98 and outperforms current IDS models in false positive rate and detection time.

关键词： 2D-LICM hyper-chaotic map with Walrus Optimization (2D-LICMHy-CM_WO) Dense Convolutional Spatial Attention-based Enhanced Bi-GRU (DCSAtten_EBi-GRU) Double Deep Q-Learning Network (DoubleDQN) Enhanced Synthetic Minority Over-Sampling Technique (ESMOTE)

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：