检索结果-内蒙古大学图书馆

Pneumonia Net: Pneumonia Detection and Categorization in Chest X-ray Images

Recent Advances in computer science and Communications 2024年第3期17卷 20-31页

作者： Srivastava, Somya Verma, Seema Das, Nripendra Narayan Sharma, Shraddha Dubey, Gaurav Department of Computer Science ABES Engineering College Ghaziabad India Department of Computer Science and Engineering Guru Gobind Singh Indraprastha University Delhi India Department of Information Technology Manipal University Jaipur Rajasthan Jaipur India Department of Computer Science Pandit Deendayal Energy University Gujarat India Department of Computer Science KIET Group of Institutions Ghaziabad India

Background: Pneumonia is one of the leading causes of death and disability due to respiratory infections. The key to successful treatment of pneumonia is in its early diagnosis and correct classification. PneumoniaNet is a unique deep-learning model based on CNN for identifying pneumonia on chest X-rays. Objective: A deep learning model that combines convolutional, pooling, and fully connected layers is presented in this study. Methods: In order to learn how to identify cases of pneumonia and healthy controls on chest X-ray pictures, PneumoniaNet was trained on a large labeled library of such images. A robust data augmentation technique was adopted to enhance the model generalization and training set diversity. Standard measures like as accuracy, precision, recall, and F1-score were applied to PneumoniaNet's performance evaluation. Results: The suggested model performed effectively in detecting pneumonia cases with an accuracy of 93.88%. Conclusion: The model was evaluated against the current state-of-art methods and showed that PneumoniaNet outperformed the other models. © 2024 Bentham science Publishers.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation for Medical Image Classification Based on Gaussian Laplacian Pyramid Blending With a Similarity Measure

引用

IEEE Journal of Biomedical and Health Informatics 2025年第6期29卷 3886-3893页

作者： Kumar, Abhinav Sharma, Anshul Singh, Amit Kumar Singh, Sanjay Kumar Saxena, Sonal Department of Computer Science and Engineering Varanasi221005 India National Institute of Technology Patna Department of Computer Science and Engineering Patna800005 India Indian Veterinary Research Institute Division of Veterinary Biotechnology Izatnagar243122 India

Breast cancer is a devastating disease that affects women worldwide, and computer-aided algorithms have shown potential in automating cancer diagnosis. Recently Generative Artificial Intelligence (GenAI) opens new possibilities for addressing the challenges of labeled data scarcity and accurate prediction in critical applications. However, a lack of diversity, as well as unrealistic and unreliable data, have a detrimental impact on performance. Therefore, this study proposes an augmentation scheme to address the scarcity of labeled data and data imbalance in medical datasets. This approach integrates the concepts of the Gaussian-Laplacian pyramid and pyramid blending with similarity measures. In order to maintain the structural properties of images and capture inter-variability of patient images of the same category similarity-metric-based intermixing has been introduced. It helps to maintain the overall quality and integrity of the dataset. Subsequently, deep learning approach with significant modification, that leverages transfer learning through the usage of concatenated pre-trained models is applied to classify breast cancer histopathological images. The effectiveness of the proposal, including the impact of data augmentation, is demonstrated through a detailed analysis of three different medical datasets, showing significant performance improvement over baseline models. The proposal has the potential to contribute to the development of more accurate and reliable approach for breast cancer diagnosis. © 2013 IEEE.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Align Is Not Enough: Multimodal Universal Jailbreak Attack Against Multimodal Large Language Models

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5475-5488页

作者： Wang, Youze Hu, Wenbo Dong, Yinpeng Liu, Jing Zhang, Hanwang Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Hefei230009 China Tsinghua University Department of Computer Science and Technology Beijing100084 China Institute of Automation Chinese Academy of Science Beijing100190 China Nanyang Technological University School of Computer Science and Engineering Jurong West 639798 Singapore

Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human intelligence, which processes a variety of data forms beyond just text. Despite advancements, the undesirable generation of these models remains a critical concern, particularly due to vulnerabilities exposed by text-based jailbreak attacks, which have represented a significant threat by challenging existing safety protocols. Motivated by the unique security risks posed by the integration of new and old modalities for MLLMs, we propose a unified multimodal universal jailbreak attack framework that leverages iterative image-text interactions and transfer-based strategy to generate a universal adversarial suffix and image. Our work not only highlights the interaction of image-text modalities can be used as a critical vulnerability but also validates that multimodal universal jailbreak attacks can bring higher-quality undesirable generations across different MLLMs. We evaluate the undesirable context generation of MLLMs like LLaVA, Yi-VL, MiniGPT4, MiniGPT-v2, and InstructBLIP, and reveal significant multimodal safety alignment issues, highlighting the inadequacy of current safety mechanisms against sophisticated multimodal attacks. This study underscores the urgent need for robust safety measures in MLLMs, advocating for a comprehensive review and enhancement of security protocols to mitigate potential risks associated with multimodal capabilities. © 1991-2012 IEEE.

关键词： Human form models

来源：评论

学校读者我要写书评

暂无评论

Leveraging Network Slicing in SDNs for Handling Application Failures

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第4期51卷 409-421页

作者： Lokesh, Bommareddy Rajagopalan, Narendran School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati522237 India Department of Computer Science and Engineering National Institute of Technology Puducherry Karaikal609609 India

Unlike traditional networks, Software-defined networks (SDNs) provide an overall view and centralized control of all the devices in the network. SDNs enable the network administrator to implement the network policy by programming applications on top of the SDN controller using generic APIs. One or more controller instances can be deployed to administer the data flow by maintaining unified control of the entire network. The controller is expected to respond quickly to queries from forwarding devices. Presuming quick responses from the controller while enforcing a complex security mechanism is unreasonable. In this paper, the authors propose a unique, adaptive, lightweight, yet efficient technique called ISOLATOR to mitigate the effect of insider attacks and malfunctioning of distributed applications in an SDN-enabled cloud. The proposed security application upon detecting any suspicious activity by a virtual machine, isolates it by removing the interface to its respective shared network and reconnects it through a restricted network operating in a highly selective mode. By subjecting the data traffic to deep packet inspection, the restricted network searches for a match with a known worm pattern. The application is programmed for the OpenDayLight controller and the results show a significant improvement in identifying malicious activities with minimal latency and computational cost. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

COVID-19 detection from Chest X-ray images using a novel lightweight hybrid CNN architecture

引用

Multimedia Tools and Applications 2025年第13期84卷 11295-11317页

作者： Pradeep Dalvi, Pooja Reddy Edla, Damodar Purushothama, B.R. Dharavath, Ramesh Department of Computer Science and Engineering National Institute of Technology Farmagudi Goa Ponda403401 India Dhanbad India

The pandemic of COVID-19 has affected worldwide population. Diagnosing this highly contagious disease at an initial stage is essential for controlling its spread. In this paper, we propose a novel lightweight hybrid convolutional neural network to identify COVID-19-positive patients from Chest X-ray images using building blocks of MobileNet and ResNet50. This model shows improvement over the base models when applied to the same dataset independently. The proposed model is trained and tested on same configuration and dataset as that of its base models, for better performance analysis and comparison. It also has fewer parameters as compared to MobileNet and ResNet50, which makes it lightweight, adding to its better performance. It achieves an accuracy of 98.47 % with very few false negative predicted samples, which is extremely beneficial in medical diagnosis. Concerning the parameters, this model is built with only 200,034 trainable parameters, which marks a parameter reduction percentage of 99.15 % concerning ResNet50 and 93.82% compared to MobileNet. The generalisation performance of our proposed model is evaluated using stratified 5-fold cross validation technique. Our model achieved very good accuracy with very less parameters as compared to various state-of-the-art models. The model also classified Pneumonia images from Normal ones with an accuracy of 98.9 %. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Anomaly-Focused Augmentation Method for Industrial Visual Inspection

引用

IEEE Access 2025年 13卷 89118-89139页

作者： Melvinlara, Melvin A. Hameed, Ibrahim A. Koziorek, Jiri Faculty of Electrical Engineering and Computer Science Department of Cybernetics and Biomedical Engineering Ostrava70800 Czech Republic Department of Mechanical Engineering and Technology Management Ås1433 Norway

In industrial inspection, the detection of surface defects - such as scratches, dents, or other defects - is crucial for ensuring product quality. However, the limited availability of annotated images of such defects poses challenges for developing reliable detection models. This paper proposes a novel image augmentation algorithm to address this limitation by generating synthetic imperfections from a small sample set. Unlike traditional approaches that augment entire images, the proposed approach isolates defects and applies spatial transformations (e.g., rotation, shear) before blending them into background images. This allows for the creation of diverse training datasets. The algorithm employs a 2D binary map to encode the spatial relationship between defect and background regions of images and then applies an AI-driven model to generate new realistic blended images. By leveraging a generator-discriminator framework, the augmentation process is iteratively refined during training to maintain the style and texture of the original imperfections. Experimental results show that the proposed method significantly enhances the performance of defect detection models compared to existing augmentation techniques while preserving the realism of the generated images. © 2013 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Deep analysis of MFCC and MEL spectrogram features to recognize and classify stuttered speech

引用

Multimedia Tools and Applications 2025年 1-20页

作者： Banerjee, Nilanjan Sethi, Nilambar Borah, Samarjeet Department of Computer Science and Engineering GIET University Odisha India Department of Computer Applications Sikkim Manipal Institute of Technology Sikkim Manipal University Sikkim India

Human thoughts, feelings, and ideas are expressed through speech. Stuttering, also referred to as stammering, is an impediment to speech that affects millions of people across the globe. Stuttering speech recognition is a good deal of research within the realm of speech signal processing. Classification of eight different types of stuttering including fluent, interjections, broken words, prolongations, word repetitions, phrase–repetitions, part-word repetitions, and sound repetitions is the main motivation in this research. Stuttering speech recognition is becoming easier with the advancement of machine learning and deep learning. The present study focuses on the efficacy of stuttering speech recognition through the application of machine learning & deep learning. Analysis in this study began with traditional machine learning algorithms, such as Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). It is seen, feature extraction is an essential component in achieving accurate classification for machine learning algorithms. MFCC & MEL spectrogram features are extracted for this experiment. Furthermore, Delta2 MFCC and Delta2 Mel Spectrogram are derived by second-order derivatives on MFCC & Mel Spectrogram features. Therefore, a variety of these features are employed as input to the model. In comparison with all the aforesaid traditional machine learning models, the KNN model results in the highest accuracy of 69.1% based on MFCC-40 input features. To improve accuracy, we move to a deep learning approach. In this experiment, the convolutional neural network (CNN) model produces better outcomes than traditional machine learning. The study presents a comprehensive analysis of the CNN model with MFCC & MEL spectrogram features, as well as its efficiency. It is noted that MFCC-40 input features in CNN model results in the highest accuracy of 89% after 400 epochs. © The Author(s), under exclusive licence to Springer science+Bus

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

PLD-Det: plant leaf disease detection in real time using an end-to-end neural network approach based on improved YOLOv7

引用

Neural Computing and Applications 2024年第34期36卷 21885-21898页

作者： Mehedi, Md Humaion Kabir Nawer, Nafisa Ahmed, Shafi Khan, Md Shakiful Islam Hasib, Khan Md Mridha, M.F. Alam, Md. Golam Rabiul Nguyen, Thanh Thi Department of Computer Science and Engineering BRAC University Dhaka Bangladesh Department of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka Bangladesh Department of Computer Science American International University Dhaka Bangladesh Department of Data Science and AI Monash University Wellington Rd Clayton MelbourneVIC3800 Australia

In order to maintain sustainable agriculture, it is vital to monitor plant health. Since all species of plants are prone to characteristic diseases, it necessitates regular surveillance to search for any symptoms, which is utterly challenging and time-consuming. Besides, farmers may struggle to identify the type of plant disease and its potential symptoms. Hence, the interest in research like image-based computer-aided automated plant leaf disease detection by analyzing the early symptoms has increased enormously. However, limitations in the plant leaf image database, for instance, unfitting backgrounds, blurry images, and so on, sometimes cause underprivileged feature extraction, misclassification, and overfitting issues in existing models. As a result, we have proposed a real-time plant leaf disease detection architecture incorporating proposed PLD-Det model, which is based on improved YOLOv7 with the intention of assisting farmers while reducing the issues in existing models. The architecture has been trained on the widely used PlantVillage dataset, which resulted in an accuracy of 98.53%. Furthermore, SHapley Additive exPlanations (SHAP) values have been analyzed as a unified measure of feature significance. According to the experimental findings, the proposed PLD-Det model, which is an improved YOLOv7 architecture, outperformed the original YOLOv7 model in test accuracy by approximately 4%. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Seed

来源：评论

学校读者我要写书评

暂无评论

Automated Red Deer Algorithm with Deep Learning Enabled Hyperspectral Image Classification

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 2353-2366页

作者： B.Chellapraba D.Manohari K.Periyakaruppan M.S.Kavitha Department of Information Technology Karpagam Institute of TechnologyCoimbatore641032TamilnaduIndia Department of Computer Science and Engineering St.Joseph’s Institute of TechnologyChennai600119India Department of Computer Science&Engineering SNS College of EngineeringCoimbatore641107India Department of Computer Science&Engineering SNS College of TechnologyCoimbatore641035India

Hyperspectral(HS)image classiﬁcation is a hot research area due to challenging issues such as existence of high dimensionality,restricted training data,*** recognition of features from the HS images is important for effective classiﬁcation ***,the recent advancements of deep learning(DL)models make it possible in several application *** addition,the performance of the DL models is mainly based on the hyperparameter setting which can be resolved by the design of *** this view,this article develops an automated red deer algorithm with deep learning enabled hyperspec-tral image(HSI)classiﬁcation(RDADL-HIC)*** proposed RDADL-HIC technique aims to effectively determine the HSI *** addition,the RDADL-HIC technique comprises a NASNetLarge model with Adagrad ***,RDA with gated recurrent unit(GRU)approach is used for the identiﬁcation and classiﬁcation of *** design of Adagrad optimizer with RDA helps to optimally tune the hyperparameters of the NASNetLarge and GRU models *** experimental results stated the supremacy of the RDADL-HIC model and the results are inspected interms of different *** comparison study of the RDADL-HIC model demonstrated the enhanced per-formance over its recent state of art approaches.

关键词： Hyperspectral images image classiﬁcation deep learning adagrad optimizer nasnetlarge model red deer algorithm

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approach for Cost Efficient Application Placement in Fog-Cloud Computing Environments

引用

computers, Materials & Continua 2024年第6期79卷 4127-4148页

作者： Abdulelah Alwabel Chinmaya Kumar Swain Department of Computer Sciences College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Computer Science and Engineering Institute of Management and Information TechnologyCuttackBPUTOdishaIndia

Fog computing has recently developed as a new paradigm with the aim of addressing time-sensitive applications better than with cloud computing by placing and processing tasks in close proximity to the data ***,the majority of the fog nodes in this environment are geographically scattered with resources that are limited in terms of capabilities compared to cloud nodes,thus making the application placement problem more complex than that in cloud *** approach for cost-efficient application placement in fog-cloud computing environments that combines the benefits of both fog and cloud computing to optimize the placement of applications and services while minimizing *** approach is particularly relevant in scenarios where latency,resource constraints,and cost considerations are crucial factors for the deployment of *** this study,we propose a hybrid approach that combines a genetic algorithm(GA)with the Flamingo Search Algorithm(FSA)to place application modules while minimizing *** consider four cost-types for application deployment:Computation,communication,energy consumption,and *** proposed hybrid approach is called GA-FSA and is designed to place the application modules considering the deadline of the application and deploy them appropriately to fog or cloud nodes to curtail the overall cost of the *** extensive simulation is conducted to assess the performance of the proposed approach compared to other state-of-the-art *** results demonstrate that GA-FSA approach is superior to the other approaches with respect to task guarantee ratio(TGR)and total cost.

关键词： Placement mechanism application module placement fog computing cloud computing genetic algorithm flamingo search algorithm

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：