检索结果-内蒙古大学图书馆

Deep learning model for plant-leaf disease detection in precision agriculture

International Journal of Intelligent Systems Technologies and Applications 2023年第1期21卷 72-91页

作者： Bajpai, Chandrabhanu Sahu, Ramnarayan Naik, K. Jairam Department of Computer Science and Engineering National Institute of Technology Raipur Chhattisgarh Raipur India

Crop disease in the agricultural is the main factor limiting yield and food quality. It requires timely diagnosis of crop illnesses for the better economy developing country. Manual crop illness assessment is limited due to lesser accuracy and restricted accessibility. It is very difficult to accurately identify and classify plant diseases due to corrupt in the data samples, lesser intensity of foreground and background, and the extreme similarity between unhealthy and healthy leaves in terms of colouring and size of crop leaves. Hence the employments of automated and computerised optimisations are needed. To identify plant leaf diseases, a DNSVM classification strategy fusing DenseNet-201 with support vector machine (SVM) is proposed in this work. Plant-Village dataset that provides good-variations, colour-differences, differences in orientation and size-of-leaves. Sugarcane plants-leaves were used for performance analysis of proposed model and obtained 97.78% of classification accuracy over the existing DenseNet-121-based classifier model (94%). © 2023 Inderscience Enterprises Ltd.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Kookaburra Optimization Algorithm and Feature Aggregated Region based Differential network for Colon Cancer Detection from Histopathological Images 8

Kookaburra Optimization Algorithm and Feature Aggregated Reg...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Gowthamy, J. Ramesh, S.S. Subashka Rm Institute of Science and Technology Amapuram Department of Computer Science and Engineering Chennai India Srm Institute of Science and Technology Ramapuram Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350376425

Colon cancer is a significant health concern, ranking as the third leading cause of cancer-related deaths in men and the second in women. Early detection is crucial in reducing the incidence and mortality rates associated with this malignancy. This paper introduces a novel Feature Aggregated Region-based Differential Network (FA-RDNet) designed for the accurate classification of colon cancer from histopathological images. Our approach leverages Multiple Instance Learning (MIL) to effectively handle large datasets structured as bags of instances, addressing the limitations of conventional MIL techniques. A key innovation of our work is the integration of an adaptive feature enhancement module that bilaterally updates multi-level deep features, allowing for efficient extraction of both low-level details and high-level semantic information. Furthermore, we introduce the Kookaburra Optimization Algorithm (KOA) to fine-tune the parameters of FA-RDNet, utilizing a unique two-phase mathematical modeling process inspired by the hunting behaviors of kookaburras. This enhances the model's optimization and classification accuracy. The effectiveness of our proposed system is validated using the publicly available LC25000 dataset, where it achieved a remarkable accuracy of 94.42%, outperforming existing state-of-the-art methods in colon cancer detection. The high computational efficiency and accuracy of FA-RDNet highlight its potential for practical applications in clinical settings, marking a significant advancement in the field of medical image analysis. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Multi Attribute Case Based Privacy-preserving for Healthcare Transactional Data Using Cryptography

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 2029-2042页

作者： K.Saranya K.Premalatha Department of Computer Science and Engineering Bannari Amman Institute of TechnologySathyamangalam638401India

Medical data mining has become an essential task in healthcare sector to secure the personal and medical data of patients using privacy *** this background,several authentication and accessibility issues emerge with an inten-tion to protect the sensitive details of the patients over getting published in open *** solve this problem,Multi Attribute Case based Privacy Preservation(MACPP)technique is proposed in this study to enhance the security of privacy-preserving *** information can be any attribute information which is categorized as sensitive logs in a patient’s *** semantic relation between transactional patient records and access rights is estimated based on the mean average value to distinguish sensitive and non-sensitive *** addition to this,crypto hidden policy is also applied here to encrypt the sensitive data through symmetric standard key log veriﬁcation that protects the personalized sensitive ***,linear integrity veriﬁcation provides authentication rights to verify the data,improves the performance of privacy preserving techni-que against intruders and assures high security in healthcare setting.

关键词： Privacy-preserving crypto policy medical data mining integrity and veriﬁcation personalized records cryptography

来源：评论

学校读者我要写书评

暂无评论

PUPC-GANs: A Novel Image Conversion Model using Modified CycleGANs in Healthcare

引用

Recent Advances in computer science and Communications 2023年第7期16卷 66-73页

作者： Taneja, Shweta Suri, Bhawna Kumar, Aman Chowdhry, Ashish Kumar, Harsh Dwivedi, Kautuk Department Computer Science & Engineering Bhagwan Parshuram Institute of Technology GGSIPU Delhi India

Introduction: Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) both have their areas of specialty in the medical imaging world. MRI is considered to be a safer modality as it exploits the magnetic properties of the hydrogen nucleus. Whereas a CT scan uses multiple X-rays, which is known to contribute to carcinogenesis and is associated with affecting the patient's health. Methods: In scenarios, such as radiation therapy, where both MRI and CT are required for medical treatment, a unique approach to getting both scans would be to obtain MRI and generate a CT scan from it. Current deep learning methods for MRI to CT synthesis purely use either paired data or unpaired data. Models trained with paired data suffer due to a lack of availability of well-aligned data. Results: Training with unpaired data might generate visually realistic images, although it still does not guarantee good accuracy. To overcome this, we proposed a new model called PUPC-GANs (Paired Unpaired CycleGANs), based on CycleGANs (Cycle-Consistent Adversarial Net-works). Conclusion: This model is capable of learning transformations utilizing both paired and unpaired data. To support this, a paired loss is introduced. Comparing MAE, MSE, NRMSE, PSNR, and SSIM metrics, PUPC-GANs outperform CycleGANs. © 2023 Bentham science Publishers.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

DeepFakeGuard: Safeguarding Digital Platforms Against Fake Profiles Using AI 4

DeepFakeGuard: Safeguarding Digital Platforms Against Fake P...

引用

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

作者： Swarna Sudha, M. Manjula, S. Bharathi, Indira Krishnasamy, Valarmathi Vijayalakshmi, K. Ramco Institute of Technology Department of Computer Science and Engineering Rajapalayam India School of Computer Science and Engineering Vellore Institute of Technology Chennai India PSR Engineering College Department of Electronics and Communication Engineering Sivakasi India

ISBN: (纸本)9798331523923

This research introduces DeepFakeGuard, a hybrid deep learning framework designed to detect fake profiles on social media platforms, addressing the growing threat of fraudulent accounts online. DeepFakeGuard integrates multiple data modalities, including textual, visual, behavioral, and network features, to accurately classify profiles as real or fake. Leveraging advanced deep learning models such as BERT for textual analysis, ResNet for image processing, and LSTM for modeling behavioral patterns, DeepFakeGuard provides a comprehensive and robust solution for identifying fake profiles across diverse platforms. The framework processes a rich set of profile characteristics, including account information, posting behavior, post sentiment, and network relationships, ensuring a multi-dimensional analysis of social media accounts. The hybrid architecture of DeepFakeGuard merges outputs from individual sub-models, which are then processed through dense layers for final classification using a sigmoid activation function. This multi-faceted approach significantly enhances detection accuracy, precision, and recall compared to traditional methods. The framework is highly scalable and adaptable to various social media platforms, offering a versatile tool for strengthening online security. With strong performance metrics, including high classification accuracy, DeepFakeGuard demonstrates its potential for real-world applications in mitigating the risks associated with fake profiles. By fostering secure and trustworthy social media environments, this research contributes to the ongoing fight against fraudulent accounts, paving the way for safer online interactions. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Reconstruction probability-based anomaly detection using variational auto-encoders

引用

International Journal of computers and Applications 2023年第3期45卷 231-237页

作者： Iqbal, Touseef Qureshi, Shaima Department of Computer Science and Engineering National Institute of Technology Jammu and Kashmir Srinagar India

Anomaly detection is a method of categorizing unexpected data points or events in a dataset. Variational Auto-Encoders (VAEs) have proved to handle complex problems in a variety of disciplines. We propose a technique for detecting anomalies based on the reconstruction probability of VAEs. The proposed method trains VAEs on three different datasets. The reconstruction probability is a much more principled and realistic anomaly score than the reconstruction error utilized by auto-encoders and other data compression methods because of the theoretical background and by including the concept of variability. The paper describes recent deep learning models for anomaly detection, as well as a comparison to other methodologies. Variational auto-encoders are trained on three different datasets, in an unsupervised setup to classify the anomalies, based on reconstruction probability. Further, the in-depth study of anomaly detection techniques is presented in this paper. The data are reconstructed using the VAEs generative characteristics to investigate the root cause of the anomalies. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT ECO System - Smart Parking System

Enhancing IoT ECO System - Smart Parking System

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Avinash, S. Muthukrishnan, S. Aishwarya, R. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331529833

The Smart Parking System is an innovative solution designed to tackle the challenges of parking in densely populated urban areas. By integrating advanced technologies such as RFID (Radio Frequency Identification) sensors, automated gate systems, and proximity sensors, the system delivers a streamlined and efficient parking experience. RFID technology automates entry and exit processes by recognizing vehicles equipped with RFID tags, reducing wait times and enhancing security through controlled access. Proximity sensors at each parking spot monitor occupancy in real-time, feeding data to a central management system that directs drivers to available spaces via digital signage or a mobile app. This real-time guidance decreases search time, reduces congestion, and improves overall parking organization. Designed with scalability and future-readiness, the system's central management unit can integrate additional features like payment processing, reservation systems, and predictive analytics powered by machine learning. This adaptability ensures the system remains relevant as technology advances and user needs evolve. The Smart Parking System also promotes sustainability by minimizing vehicle idling and carbon emissions, contributing to a reduced environmental impact. For users, the system offers a more convenient, secure, and efficient parking experience. For operators, it enhances operational efficiency, reduces manual labor, and provides valuable insights into parking patterns, aiding in pricing, expansion, and maintenance decisions. The system's modular design allows for cost-effective implementation, making it suitable for various facilities from small lots to large complexes. In summary, the Smart Parking System represents a forward-thinking approach to urban parking, combining technology, efficiency, and sustainability to improve urban living. © 2025 IEEE.

关键词： Proximity sensors

来源：评论

学校读者我要写书评

暂无评论

Automated Brain Tumor Detection and Classification in MRI Scans using a Deep Convolutional Neural Network and U-Net Architecture 6

Automated Brain Tumor Detection and Classification in MRI Sc...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Devadas, Prathima Mathivanan, G. Department of Computer science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9798331522667

Brain tumor identification and categorization serve a precarious role in early diagnosis and treatment planning. This study suggests a new deep learning (DL)-based structure for the automatic detection and categorization of brain cancers using medical imaging technologies. The framework uses a deep convolutional neural network (DCNN) with an exclusive segmentation technique, notably the U-Net architecture, to discrete tumor areas in magnetic resonance imaging (MRI) scans. The DCNN model, which contains multiple convolutional layers, is used for feature extraction, followed by fully connected layers for tumor classification. To increase segmentation accuracy, the U-Net model integrates both encoder-decoder structures and skip connections to capture fine-grained spatial details. The suggested algorithm is trained and evaluated on a large dataset of brain MRI images, achieving high accuracy, sensitivity, and specificity for both tumor detection and classification. Experimental results show that the model outclasses standard methods, providing a dependable and operative solution for the early detection and diagnosis of brain cancers, potentially aiding clinical decision-making processes. © 2025 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Cohesive Heartbeat Monitoring for Geolocation and Log Correlation in Campus Networks 15

Cohesive Heartbeat Monitoring for Geolocation and Log Correl...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Suganya, R. Shazil Nath, Hiran V. Vellore Institute of Technology Chennai Department of Computer Science and Engineering Chennai India Vellore Institute of Technology Chennai School of Computer Science and Engineering Chennai India National Institute of Technology Department of Computer Science and Engineering Kozhikode Calicut India

ISBN: (纸本)9798350370249

A campus network is made up of a dense interconnection of local area networks within a limited geographical area characterized by a centralized infrastructure that interconnects various facilities within an institution, providing communication and data exchange services to support organizational activities. In a campus network, relevant information about connected clients such as connection status, duration, and relative location has to be maintained and updated in real-time to facilitate availability, log correlation and monitoring capabilities. It is important to establish a multi-pronged system in place to combat security threats and potential data loss. In this paper, we examine several existing standard practices and identify the operational and functional bottlenecks associated with each implementation with respect to the campus network. The study underscores the critical need for robust and adaptive network architectures and practices to safeguard organizational communication and data integrity with emphasis on the dynamic landscape of campus environments. Finally, we propose a novel cohesive heartbeat monitoring system that leverages data from various sources to ensure connection availability and provide advanced logging capabilities. © 2024 IEEE.

关键词： 802.1X campus network heartbeat logging RADIUS SNMP

来源：评论

学校读者我要写书评

暂无评论

Novel Deep Learning Architecture for Automated Identification of Obstructive Sleep Apnea from Polysomnographic Data 2

Novel Deep Learning Architecture for Automated Identificatio...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Shabu, S.L. Jany Indhuja, V. Jeevitha, R. Refonaa, J. Dhamodaran, S. Poornima, D. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331505745

Sleep apnea disorder manifests as obstructive sleep apnea, which affects immense portions of society because it causes life-threatening health problems that include cardiovascular disease alongside diabetes and decreased productivity. The diagnosis of OSA through manual methods is both time demanding and expensive and contains a significant potential for human errors while requiring heavy resources. This research presents deep learning automation as the novel approach for automatic OSA detection through polysomnographic assessments. Our proposed system implements Genetics Algorithm optimized machine learning algorithms which include Logistic Regression, Support Vector Machines, Random Forests, Artificial Neural Networks and more. The analysis utilizes data from the Sleep Health and Lifestyle Dataset for preprocessing operations and features extraction that leads to better sleep disorder and stage classification accuracy. Through hyperparameter adjustment the Random Forest predictive model reached 95% F1 score which proved most effective for OSA detection. Through automation the classification process benefits from reliability with scalability and efficiency and produces better patient outcomes. © 2025 IEEE.

关键词： 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：