检索结果-内蒙古大学图书馆

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Shyamala Devi, M. Janani, G. Fernandes, Jonita Maria Harshini, T. Nivetha, R. Joshika Rao, O.R. Panimalar Engineering College Department of Computer Science and Engineering Tamilnadu Chennai India Panimalar Engineering College Department of Artificial Intelligence and Data Science Tamilnadu Chennai India

ISBN: (纸本)9798350371314

In the agriculture sector, physical classification of fruits is a costly process that can produce inconsistent outcomes due to human negligence. Fruit categorization from snapshots is an extremely difficult venture, especially for mango fruits because various species of mango fruits share significant resemblance. This paper proposes Auxiliary Dense Layered LeNet (ADL-LeNet) that classifies the mango type with high accuracy. The Mango Varieties Classification and Grading dataset, which includes 1200 mango pictures was used for this work. The Mango image dataset is applied with the existing CNN model to select the best CNN model. The LeNet outperforms with the accuracy of 92.77% when compared to the other CNN model. Now LeNet is selected for finetuning the number of dense layers. Generally, the LeNet is composed of three convolutions, two subsampling followed by two dense layers. Now, the LeNet is modified by adding one extra dense layer at the end that compress the output further into vector size of 42 to suggest the proposed model ADL-LeNet. The ADL-LeNet composed of three convolutional, two subsampling and three dense layers ending with the final output layer. The Mango Image dataset has been applied with the existing CNN and proposed ADL-LeNet. The implementation shows that the proposed ADL-LeNet model outperforms with the high accuracy of 97.6% in mango type classification. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Patch Selection: An Improved Patch Sampling for No Reference Image Quality Assessment

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 541-555页

作者： Nandhini, C. Brindha, M. National Institute of Technology Department of Computer Science and Engineering Tiruchirappalli620015 India

Quality degradation due to the compression and the transmission of images is a significant threat to multimedia applications. Blind image quality assessment (BIQA) is a principal technique to measure the distortion and dynamically set the optimal parameters for developing image compression standards, image restoration algorithms, etc. Insufficient training data with quality scores are a challenge for image quality assessment (IQA) tasks. The existing solutions to deep-convolution-neural-network-based BIQA, which rely on patchwise training, struggle to find an ideal set of patches consistent with the human visual system. To address these issues, HIerarchical paTch Selection (HITS) is proposed. HITS keeps the patches with considerable details in each quadrant according to their intensity variance scatter ratio (IVSR). IVSR identifies the best nonhomogeneous patches by computing patch intensity variance. Extensive trials are conducted, and the performance reveals that the proposed approach achieves excellent performance on synthetic and authentic distortion datasets with less memory and processing power. Moreover, the proposed approach outperforms other BIQA methods that adapt patchwise training strategies. © 2023 IEEE.

关键词： Feature extraction

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

A Huffman-based short message service compression technique using adjacent distance array

引用

International Journal of Information and Communication Technology 2024年第2期25卷 118-136页

作者： Sarker, Pranta Rahman, Mir Lutfur Department of Computer Science and Engineering North East University Bangladesh Telihaor Sheikhghat Sylhet3100 Bangladesh Department of Computer Science University of Hertfordshire Hertfordshire United Kingdom

The short message service (SMS) is a wireless medium of transmission that allows you to send brief text messages. Cell phone devices have an uttermost SMS capacity of 1,120 bits in the traditional system. Moreover, the conventional SMS employs seven bits for each character, allowing the highest 160 characters for an SMS text message to be transmitted. This research demonstrated that an SMS message could contain more than 200 characters by representing around five bits each, introducing a data structure, namely, adjacent distance array (ADA) using the Huffman principle. Allowing the concept of lossless data compression technique, the proposed method of the research generates character’s codeword utilising the standard Huffman. However, the ADA encodes the message by putting the ASCII value distances of all characters, and decoding performs by avoiding the whole Huffman tree traverse, which is the pivotal contribution of the research to develop an effective SMS compression technique for personal digital assistants (PDAs). The encoding and decoding processes have been discussed and contrasted with the conventional SMS text message system, where our proposed ADA technique performs outstandingly better from every aspect discovered after evaluating all outcomes. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Personal digital assistants

来源：评论

学校读者我要写书评

暂无评论

A fast and highly scalable frequent pattern mining algorithm

引用

Future Generation computer Systems 2024年 160卷 854-868页

作者： Cheng, Wan-Shu Lin, Yi-Ting Huang, Peng-Yu Chen, Ju-Chin Lin, Kawuu W. Department of Computer Science and Information Management Providence University Taichung Taiwan Department of Computer Science and Information Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan

As the use of big data and its potential benefits become more widespread, public and private organizations around the world have realized the imperative of incorporating comprehensive and robust technologies into their business processes. In particular, companies are implementing more and more intelligent systems into their business processes, resulting in an exponential increase in the amount of data being collected and used in everyday life on a quarterly basis. Therefore, an algorithm that can efficiently explore the frequent patterns from big data will be able to productively analyze and utilize the generated data to better optimize resources and even develop new business models. Thus, in this urban data era, it is not only essential to make more efficient and accurate decisions to improve business profitability and customer satisfaction, but also a highly challenging core issue. In this study, a new approach, scalable FP mining, is proposed for the first time to achieve a certain level of performance and more efficient memory utilization despite large amounts of data. Experiment results for different data characteristics show that the best performance of the proposed method requires only 48.9% of the DP algorithm's execution time. In further experiments with increased exploration difficulty, the optimal execution time is only 37%. On specific associated databases, the proposed method maintains stable and excellent performance with 12.7% for different data characteristics. The experimental results with increasing exploration difficulty at each stage demonstrate the stability, robustness, and reliability of the proposed SFP, especially under high data complexity and exploration difficulty. © 2024

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

A review on spreading and Forensics Analysis of Windows-Based ransomware

引用

Annals of data science 2024年第5期11卷 1503-1524页

作者： Chayal, Narendrakumar Mangilal Saxena, Ankur Khan, Rijwan Department of Computer Science and Technology Faculty of Engineering and Technology Department of Computer Engineering Sankalchand Patel University Visnagar India Department of Computer Science Indus Institute of Information and Communication Technology Dean-ICT & ampDirector-IIICT Indus University Gujarat Ahmedabad India Department of Computer Science and Engineering ABES Institute of Technology Ghaziabad Affiliated to AKTU Lucknow India

Ransomware is one of the most advanced malware which uses high computer resources and services to encrypt system data once it infects a system and causes large financial data losses to the organization and individuals. There are certain automatic ransomware detection and analysis strategies available nowadays. File system analysis reveals some essential patterns and artifacts that can be very useful to understand its behavior spreading mechanism, taxonomy for malware forensics experts. Current trend explores Ransomware as a service (RaaS) and Malware as a service (MaaS) on Darknet. This paper reveals a theory of digital forensic methodology to identify the spreading/infection mechanism and attack path, the cryptographic methodology, windows services, process, APIs, persistence mechanism, and system lockdown strategies and malware analysis methodology. This review could be helpful to learn and understand malware forensic analysis for threat researchers, students, cyber experts, etc. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Malware

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

A Review on the Applications of Machine Learning and Deep Learning Techniques for Skin Cancer Detection 4

A Review on the Applications of Machine Learning and Deep Le...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Wanjari, Ketan Verma, Prateek Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

Skin cancer is the most commonly reported type of cancer globally and one of the few cancers that can be effectively treated if detected in its early stages. Recent advancements in artificial intelligence (AI) have significantly improved skin cancer diagnosis through Machine Learning (ML) and Deep Learning (DL) models. This review explores ML and DL methodologies, including Random Forest, Convolutional Neural Networks (CNNs), Inception Networks, ResNets, and Support Vector Machines (SVMs), which have been widely used for automated diagnosis. However, existing AI-based systems face several challenges, including the need for balanced datasets, model interpretability issues, computational complexity, and difficulties in generalizing across diverse populations. Moreover, multimodal detection systems and Explainable AI (XAI) present additional challenges in making AI-driven diagnoses more reliable and transparent. This article discusses these challenges while also highlighting emerging techniques that integrate multiple data sources and individualized diagnostic tools to enhance precision. By addressing these challenges, this review aims to provide insights into the practical advancements and future directions of AI in skin cancer detection and treatment. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Classification Techniques on Detecting Diabetic Retinopathy dataset 7

Deep Learning Classification Techniques on Detecting Diabeti...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Revathi, B. Usharani, C. Kezial Elizabeth, S.K. Nagaraj, P. Nithya, D. Ramco Institute of Technology Department of Artificial Intelligence And Data Science Virudhunagar India Mangayarkarasi College of Engineering Department of Computer Science And Engineering Madurai India Kalasalingam Academy of Research And Education Department of Computer Science And Engineering Virudhunagar Krishnankoil India Theni Kammavar Sangam College of Technology Department of Computer Science And Engineering Theni India

ISBN: (纸本)9798350359299

Deep learning algorithms can summarize images to understand how to carry out necessary tasks. The purpose of this study is to compare several deep learning methods. Both experience-based and explanation-based learning are possible in deep learning. The most widely utilized algorithms, such as Convolutional Neural Networks (CNN), Multilayer Perceptron (MLP), Generative Adversarial Networks (GAN), Radial Basis Function Networks (RBFN), and Deep Belief Networks (DBN), and the Diabetic Retinopathy dataset is utilized in this study to evaluate the effectiveness of the algorithms. A comparative study of the classifiers reveals that CNN performs more accurately than the other approaches. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

An Improved Gannet Optimization Algorithm Based on Opposition-Based Schemes for Feature Selection Problems in High-Dimensional datasets

引用

SN computer science 2024年第1期5卷 183页

作者： Avinash, N. Sinha, Sitesh Kumar Shivamurthaiah, M. Department of computer science and engineering Rabindranath tagore university Bhopal India Department of Computer Science and Engineering APS College of Engineering Bangalore India

In the ever-evolving landscape of optimization algorithms for healthcare datasets, this study introduces an innovative fusion of the gannet optimization algorithm (GOA) with advanced opposition-based learning (OBL) techniques, including quasi-OBL, generalized OBL, and partial OBL. The primary novelty of our approach lies in the hybridization of GOA with OBL schemes. While GOA itself draws inspiration from the hunting behavior of gannets, OBL techniques introduce a layer of opposition-based learning that mimics the dialectical nature of opposing forces. By integrating these two distinct paradigms, we create a symbiotic relationship between exploration and exploitation. This synergy empowers our optimization framework to dynamically adapt to the complex landscape of high-dimensional healthcare datasets, underlining its prowess in classification tasks, particularly when employed with support vector machine (SVM) and k-nearest neighbor (KNN) classifiers. Statistical validation further underscores the significance of our results. The p value analysis reveals that our GOBL–GOA approach stands as a statistically superior alternative, making substantial strides in feature selection and classification accuracy. Beyond statistics, our approach excels in practicality, effectively identifying and selecting relevant features to provide accurate insights from complex healthcare data, as demonstrated by precision, recall, and F1-score metrics. In conclusion, our study not only introduces a paradigm shift in feature selection and optimization but also advances the cause of precise disease detection and prognosis, holding immense potential to enhance healthcare outcomes globally. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Feature selection Gannet optimization algorithm High-dimensional dataset Opposition-based 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：