检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 115-126页

作者： Mondal, Rahul Pal, Tandra Dey, Prasenjit National Institute of Technology Durgapur Department of Computer Science and Engineering Durgapur713209 India Cooch Behar Government Engineering College Department of Computer Science and Engineering Cooch Behar736170 India

The immunity of multilayer perceptron (MLP) is less effective toward input noise. In this article, we have focused on the robustness of MLP with respect to input noise where noise can be additive or multiplicative. Here, we have proposed a DropConnect-based regularized MLP to reduce the coadaptation among the neurons of the hidden layer. At first, we have empirically and statistically shown that by reducing coadaptation among the hidden neurons, an MLP can achieve better noise immunity. We have also empirically shown that an MLP with input noise injection and $l_{2}$ regularizer is an effective approach to improve its noise immunity. However, the results indicate that it does not adjust the coadaptation among the hidden neurons. Therefore, for further improvement, we have proposed a hybrid regularized MLP (HRMLP), where DropConnect is combined with the noise injection and $l_{2}$ regularizer. In addition to input noise, we have also verified the robustness of HRMLP with respect to $\mathbf {20\%}$ outliers in the dataset. To justify the effectiveness of the proposed HRMLP, we have compared it with MLP, MLP with noise injection, MLP with $l_{2}$ regularizer, MLP with noise injection and $l_{2}$ regularizer, and MLP with DropConnect along with two state-of-the-art works based on $\mathbf {20}$ standard datasets. The experimental results for both noisy inputs and outliers confirm that the performance of HRMLP is significant compared to other methods. © 2020 IEEE.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Recognition of Handwritten Words from Digital Writing Pad Using MMU-SNet

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 3551-3564页

作者： V.Jayanthi S.Thenmalar Department of Computer Science and Engineering SRM Institute of Science and TechnologyKattankulathurTamilnaduIndia

In this paper,Modified Multi-scale Segmentation Network(MMU-SNet)method is proposed for Tamil text *** texts from digi-tal writing pad notes are used for text *** words recognition for texts written from digital writing pad through text file conversion are challen-ging due to stylus pressure,writing on glass frictionless surfaces,and being less skilled in short writing,alphabet size,style,carved symbols,and orientation angle *** pressure on the pad changes the words in the Tamil language alphabet because the Tamil alphabets have a smaller number of lines,angles,curves,and *** small change in dots,curves,and bends in the Tamil alphabet leads to error in recognition and changes the meaning of the words because of wrong alphabet ***,handwritten English word recognition and conversion of text files from a digital writing pad are performed through various algorithms such as Support Vector Machine(SVM),Kohonen Neural Network(KNN),and Convolutional Neural Network(CNN)for offline and online alphabet *** proposed algorithms are compared with above algorithms for Tamil word *** proposed MMU-SNet method has achieved good accuracy in predicting text,about 96.8%compared to other traditional CNN algorithms.

关键词： Digital handwritten writing pad tamil text recognition syllable dialect

来源：评论

学校读者我要写书评

暂无评论

Encryption of medical data based on blockchain and multi-chaotic maps

引用

Multimedia Tools and Applications 2025年第17期84卷 17871-17892页

作者： Sharma, Suvita Rani Singh, Birmohan Kaur, Manpreet Department of Computer Science and Engineering Sant Longowal Institute of Engineering and Technology Punjab Longowal148106 India Department of Electrical and Instrumentation Engineering Sant Longowal Institute of Engineering and Technology Punjab Longowal148106 India

In this work, the SHA-256 mapper of the blockchain has been utilized to secure medical data from brute-force attacks. The uniform distribution and lower correlation of the encrypted data are achieved using the multi-chaotic in the encryption approach. Also, the circular shift method is employed in the approach to avoid differential attacks. The encryption approach is applied to secure the patient information, medical signals (ECG and EEG), and medical images (Grayscale, RGB, and Hyperspectral). The performance of the proposed approach has been analyzed for twenty signals and fifty medical images. Performance metrics such as MSE, SNR, PSNR, entropy, histogram, variance, chi-square, NPCR, UACI, and SSIM have been considered to check the resilience of the proposed approach against various types of attacks. The proposed approach satisfies the requirements of performance metrics by achieving higher MSE values with lower SNR and PSNR values for the encrypted data. Furthermore, the proposed methodology attains an entropy approaching 8, signifying robust randomness and resistance against entropy attacks. The SSIM values for encrypted images are close to 0, indicating significant dissimilarity from the original images. The NPCR values surpassing 99.60% and UACI exceeding 33.40% demonstrate resilience against differential attacks in the proposed approach. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

MFR-CNN: A modified faster R-CNN approach based on bounding box and reliable score for cloth image retrieval

引用

Multimedia Tools and Applications 2024年 1-29页

作者： Kaur, Navneet Pandey, Shreelekha Kalra, Nidhi Department of Computer Science and Engineering Thapar Institute of Engineering & ampTechnology Punjab Patiala147004 India School of Computer Science and Engineering RV University South Karnataka Bangalore560059 India

Today, machine learning is used in a broad variety of applications. Convolution neural networks (CNN), in particular, are widely used to analyze visual data. The fashion industry is catching up to the growing usage of machine learning in a variety of fields throughout the world. The proposed model named MFR-CNN, which is a modified Faster R-CNN approach, has been presented in this manuscript. The effectiveness of an algorithm is validated on cloth attributes by established datasets such as the Deep Fashion dataset and the Fashion Landmark dataset, alongside a new dataset created for the same manually. The proposed model detects clothes using bounding boxes and further classifies them. Apart from this, retrieval functionality has also been added. The effectiveness of the proposed model is evident through the learning rate analysis done for the modules present in the same. On the metrics of accuracy, execution time, and total loss, the model proposed here is contrast with existing techniques named R-CNN, Fast R-CNN, and Faster R-CNN. It is found that MFR-CNN is 50% more accurate in contrast to R-CNN. Also, the accuracy of MFR-CNN is 30% and 7% more accurate than the Fast R-CNN and Faster R-CNN, respectively. Moreover, MFR-CNN is quite effective in contrast to other approaches as it takes less time for execution. It consumes 33 seconds less in contrast to R-CNN. Also, the time taken by the MFR-CNN is 17 seconds and 3 seconds less in comparison to Fast R-CNN and Faster R-CNN, respectively. From the experimental results it is being inferred that the MFR-CNN approach for detecting and classifying clothes is both efficient and effective. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Optischedule Algorithm for Automatic Time Table Generator 3

Optischedule Algorithm for Automatic Time Table Generator

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Mamatha, T. Aditya, G.V. Meghana, S. Anvitha, S. Veekshitha, P. Sreenidhi Institute Of Science And Technology Computer Science And Engineering Department Telangana India Institute Of Science And Technology Computer Science And Engineering Department Telangana India

ISBN: (纸本)9798350318609

Automatic timetable generation is a complex optimization problem with practical applications in various domains such as education, healthcare, and event management. The challenge lies in efficiently scheduling activities while satisfying numerous constraints and objectives. In this study, we propose an OptiSchedule algorithm for automatic timetable generation. The algorithm employs a combination of heuristic search techniques and metaheuristic optimization methods to iteratively improve timetable solutions. It starts with initializing a timetable grid and iteratively refines the solution by generating neighbouring solutions and selecting the most promising ones based on an evaluation function. Through extensive testing and validation, our OptiSchedule algorithm demonstrates significant improvements in timetable quality and efficiency compared to existing approaches. The algorithm effectively minimizes conflicts, optimizes resource utilization, and balances workload distribution. Furthermore, it provides flexibility for users to input constraints and preferences, allowing customization to specific scheduling requirements. The OptiSchedule algorithm represents a significant advancement in the field of automatic timetable generation. Its ability to produce high-quality schedules while considering complex constraints makes it a valuable tool for educational institutions, healthcare facilities, and businesses alike. By streamlining scheduling processes and optimizing resource allocation, OptiSchedule contributes to improved operational efficiency and overall organizational performance. Through rigorous experimentation and evaluation, our study demonstrates the effectiveness of the OptiSchedule algorithm in improving timetable quality and reducing scheduling overhead. Compared to traditional methods, OptiSchedule generates timetables with fewer conflicts and better resource utilization, leading to enhanced productivity and satisfaction among stakeholders. Moreover, its fl

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Conditional adversarial segmentation and deep learning approach for skin lesion sub-typing from dermoscopic images

引用

Neural Computing and Applications 2024年第26期36卷 16445-16463页

作者： Mirunalini, P. Desingu, Karthik Aswatha, S. Deepika, R. Deepika, V. Jaisakthi, S.M. Department of Computer Science Engineering Sri Sivasubramaniya Nadar College of Engineering Chennai603110 India School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Chennai600127 India

Automatic skin lesion subtyping is a crucial step for diagnosing and treating skin cancer and acts as a first level diagnostic aid for medical experts. Although, in general, deep learning is very effective in image processing tasks, there are notable areas of the processing pipeline in the dermoscopic image regime that can benefit from refinement. Our work identifies two such areas for improvement. First, most benchmark dermoscopic datasets for skin cancers and lesions are highly imbalanced due to the relative rarity and commonality in the occurrence of specific lesion types. Deep learning methods tend to exhibit biased performance in favor of the majority classes with such datasets, leading to poor generalization. Second, dermoscopic images can be associated with irrelevant information in the form of skin color, hair, veins, etc.;hence, limiting the information available to a neural network by retaining only relevant portions of an input image has been successful in prompting the network towards learning task-relevant features and thereby improving its performance. Hence, this research work augments the skin lesion characterization pipeline in the following ways. First, it balances the dataset to overcome sample size biases. Two balancing methods, synthetic minority oversampling TEchnique (SMOTE) and Reweighting, are applied, compared, and analyzed. Second, a lesion segmentation stage is introduced before classification, in addition to a preprocessing stage, to retain only the region of interest. A baseline segmentation approach based on Bi-Directional ConvLSTM U-Net is improved using conditional adversarial training for enhanced segmentation performance. Finally, the classification stage is implemented using EfficientNets, where the B2 variant is used to benchmark and choose between the balancing and segmentation techniques, and the architecture is then scaled through to B7 to analyze the performance boost in lesion classification. From these experiments, we find

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

An innovative Telugu text summarization framework using the pointer network and optimized attention layer

引用

Multimedia Tools and Applications 2024年第37期83卷 84539-84564页

作者： M, Varaprasad Rao Chakma, Kunal Jamatia, Anupam Rudrapal, Dwijen Department of Computer Science & amp Engineering National Institute of Technology Agartala Tripura799046 India Department of Computer Science & amp Engineering CVR College of Engineering Telangana Hyderabad501510 India

Summarizing lengthy text involves distilling crucial information into a concise form by covering the key events in the source text. Previous researchers mostly explored the supervised approaches for the task, but due to its strong reliance on the quality of text features, the resulting summaries often lack precision and coherence. The performance of the state-of-the-art summarizers becomes poor when applied to various Indian languages due to several challenges. The current research paper proposes a summarization approach for Telugu text based on a Pointer Network with an Optimised Attention Layer (PN-OAL). In this approach, the attention layer’s weights are adjusted using a hybrid optimization method that combines the Fusion of Coyote Optimization and Squirrel Search method (FCO-SSA). Weight optimization is conducted in order to address the goal function, which involves the maximization of the cosine similarity between the source text and the summary text. A novel loss function is incorporated within the framework of the constructed network architecture to generate a robust summary. The proposed approach is experimented with alternative baseline approaches in order to validate its efficacy for summarizing Telugu documents. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Multilevel chaotic encryption model with cyclic redundancy check for medical data

引用

Neural Computing and Applications 2025年第5期37卷 3581-3603页

In telemedicine applications, it is crucial to ensure the authentication, confidentiality, and privacy of medical data due to its sensitive nature and the importance of the patient information it contains. Communication through open networks is insecure and has many vulnerabilities, making it susceptible to unauthorized access and misuse. Encryption models are used to secure medical data from unauthorized access. In this work, we propose a bit-level encryption model having three phases: preprocessing, confusion, and diffusion. This model is designed for different types of medical data including patient information, clinical data, medical signals, and images of different modalities. Also, the proposed model is effectively implemented for grayscale and color images with varying aspect ratios. Preprocessing has been applied based on the type of medical data. A random permutation has been used to scramble the data values to remove the correlation, and multilevel chaotic maps are fused with the cyclic redundancy check method. A circular shift is used in the diffusion phase to increase randomness and security, providing protection against potential attacks. The CRC method is further used at the receiver side for error detection. The performance efficiency of the proposed encryption model is proved in terms of histogram analysis, information entropy, correlation analysis, signal-to-noise ratio, peak signal-to-noise ratio, number of pixels changing rate, and unified average changing intensity. The proposed bit-level encryption model therefore achieves information entropy values ranging from 7.9669 to 8.000, which is close to the desired value of 8. Correlation coefficient values of the encrypted data approach to zero or are negative, indicating minimal correlation in encrypted data. Resistance against differential attacks is demonstrated by NPCR and UACI values exceeding 0.9960 and 0.3340, respectively. The key space of the proposed model is 1096, which is substantially mor

关键词： Telemedicine

来源：评论

学校读者我要写书评

暂无评论

Innovative Rumor Detection on Social Media Text: A Comprehensive Study of Dual Co-Attention Ensemble Based Voting Approach 5th

Innovative Rumor Detection on Social Media Text: A Comprehen...

引用

5th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2024

作者： Gangone, Anjali Bharat Kumar, G.J. Swapna, Mandu Department of Computer Science and Engineering CMR Institute of Technology Hyderabad India Department of Computer Science and Engineering Sreyas Institute of Engineering and Technology Telangana Hyderabad India

ISBN: (纸本)9789819788606

This study delves into the crucial task of rumor detection amidst the rapid spread of information online, focusing on the efficacy of advanced dual co-attention ensemble models for ensuring digital communication’s reliability. By integrating Gated Recurrent Unit (GRU) Representation, Self-Attention (SA) Models, and Bidirectional Encoder Representation from Transformers (BERT) Sentiment Models, alongside various Natural Language Processing (NLP) techniques, the research examines the potential of these models to improve rumor detection accuracy significantly. The investigation encompasses eight distinct models: the GRU Representation Model, the SA Model, the BERT Sentiment Model, and various dual co-attention ensemble combinations thereof (GRU + SA, SA + BERT, BERT + GRU, and GRU + SA + BERT), employing a sophisticated voting mechanism for rumor classification. This comprehensive evaluation across key performance metrics Accuracy, Precision, Recall, and F1 Score revealed the substantial impact of leveraging dual co-attention ensemble model strengths, particularly through dual co-attention and a strategic voting mechanism. Among the dual co-attention ensemble models, the SA + GRU + BERT configuration emerged as a superior performer, achieving remarkable results with an accuracy of 93.5%, a precision of 92%, a perfect recall of 99%, and an F1 score of 95%. These findings underscore the dual co-attention ensemble models’ exceptional capability to address rumor detection challenges effectively. The study not only showcases the promising prospects of utilizing cutting-edge AI for rumor detection but also provides insights for refining these models further. It suggests avenues for future research, including model finetuning, ethical considerations, and the necessity for real-time monitoring. This research underscores the transformative potential of AI in enhancing the accuracy of online information, paving the way for future advancements in rumor detection. © The Author(s),

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Marine Life Ecosystem Analysis Based on Climate Change Detection Using Deep Learning Algorithms

引用

Remote Sensing in Earth Systems sciences 2025年第2期8卷 545-554页

作者： Rebecca, B. Sandhya, A. Pokkuluri, Kiran Sree Kanishka, Gunipati Shaik, Khasimbee Krishna, B. Murali Department of Computer Science and Engineering Marri Laxman Reddy Institute of Technology and Management Telangana Dundigal 500043 India Department of CSE SRM Institute of Science and Technology Chennai Ramapuram India Department of Computer Science and Engineering Shri Vishnu Engineering College for Women Andhra Pradesh Bhimavaram India Computer Science and Engineering (Cyber Security) Madanapalle Institute of Technology & Science Madanapalle India Department of Computer Science and Engineering Aditya University Andhra Pradesh Surampalem India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

The surrounding environmental and climatic conditions have a significant impact on the utilisation of ecosystem services for recreational purposes. Climate change poses a threat to future natural leisure opportunities because of this reliance. The way society functions is being challenged by climate change and significant adaptation will probably be needed to deal with future changes in weather patterns. Machine learning (ML) methods have advanced to the point that they are now being offered as a tool to support climate studies, in addition to being the source of advances in other fields of study. This research proposes a novel technique in marine life ecosystem–based climate change detection using deep learning model. Input is collected as climate change detection–based marine life ecosystem and processed for noise removal with normalisation. Then this data has been segmented and classified using watershed semantic fuzzy component analysis with quantile shrinkage convolutional regression model. The experimental analysis has been carried out in terms of training accuracy, specificity, recall, AUC and NSE. Suggested technique achieved training accuracy 98%, specificity 96%, NSE 45%, recall 95% and AUC 97%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Climate change detection Convolutional regression Deep learning Fuzzy component analysis Marine life ecosystem

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：