检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Chandu, P. Siddardha, P. Priyadharshini, K. Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9798331527549

Monkeypox detection is essential for effective public health management and controlling its spread. Timely detection enables early intervention in outbreaks, reducing transmission risk. This project presents an innovative framework that enhances monkeypox detection and classification using deep learning and an interactive chatbot. It employs the VGG16 convolutional neural network (CNN) for accurate classification of monkeypox from medical images, utilizing performance metrics like precision, recall, and F1 score for reliability. Additionally, the system includes a neural network-based chatbot that provides interactive assistance, answers user questions, offers symptom information, and guides users through the diagnostic process. This chatbot improves user engagement and accessibility, linking clinical diagnostics with patient interaction. Built on the Flask framework, the system ensures a smooth, user-friendly interface for both image classification and chatbot functionalities. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Modified Deep Learning Framework for Leaf Disease Detection in Millet Crops

A Modified Deep Learning Framework for Leaf Disease Detectio...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Mohan, R. Raj Sukumar, V. John Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur India

ISBN: (纸本)9798331509828

Climate change is causing a rapid increase in millet crop disease, which poses a threat to food security. The technology behind this is deep learning, which is advanced and efficient and plays a crucial role in the classification of images, such as healthy and diseased crop leaves. Utilizing a web server program makes data upload automatic and enables rapid image processing and interpretation of crop images for disease diagnosis. We conduct the present work using a deep learning approach based on the AlexNet model to classify diseased and healthy millet crop leaves. We use a publicly available dataset with pictures of the two types of leaves and add to AlexNet by using its convolutional neural network (CNN) architecture to pull out features and tell leaf pictures apart based on how they look. Our approach consists of training the model after applying preprocessing steps to the images and testing it to detect whether the leaves are healthy or diseased. The results demonstrate that we can apply this deep learning-centered approach to tackle the issue of plant leaf disease detection on a large scale, enabling farmers to implement the necessary control measures promptly. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Detection using Histopathological Images 4

Breast Cancer Detection using Histopathological Images

引用

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

作者： Gaikwad, Vrishin Srivastava, Yash Kanchana, M. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur India

ISBN: (纸本)9798331523923

Breast cancer remains a major global health problem, and accurate and timely diagnosis of the disease is critical for improved survival rates. While traditional diagnosis methods like mammography and biopsy are well established, they are usually plagued by high false-positive rates and failure to discriminate between subtle histopathological patterns. Deep learning has made significant progress in medical image classification over the last few years, and Convolutional Neural Networks (CNNs) like ResNet and DenseNet have been demonstrating promising results. However, single models are not without their weaknesses, including vanishing gradients in deeper networks and poor feature propagation. To address these challenges, we introduce an ensemble model of DenseNet and ResNet architectures for breast cancer classification using histopathological images of the BreaKHis dataset. DenseNet offers improved feature propagation through densely connected layers, while ResNet solves the degradation issue via residual connections. Our ensemble model leverages the complementary strengths of the two architectures to offer improved feature extraction and classification accuracy. Experimental results show that the proposed ensemble model achieved an accuracy of 97.5%, outperforming the performance of the single DenseNet model (96.3%) and the single ResNet model (86.1%). This study demonstrates the potential of deep learning ensembles in improving the accuracy of breast cancer diagnosis and reducing misclassification in histopathological examination. © 2025 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Web-Based Framework for Evaluating Clustering Algorithms Across Multiple Datasets

Web-Based Framework for Evaluating Clustering Algorithms Acr...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Tiwari, Gyanendar Kumar Singh, Kshitij Dorathi Jayaseeli, J.D. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur India

ISBN: (纸本)9798331509828

This research study develops a web-based framework to compare clustering algorithms based on multiple datasets, assess the performance of algorithmic based on dataset characteristics and clustering objectives. The framework designed to support such widely used algorithms such as KM, DBSCAN and Hierarchical Clustering, offers visual and quantitative analysis for performance comparison. This platform was designed to make it easier for users to try out various algorithms and different parameter settings and thus, help them to choose the best clustering methods for a range of data types. This work impacts that greater understanding of how effective clustering is based on different data structures and application contexts by providing a useful framework for data driven research and analysis. © 2025 IEEE.

关键词： clustering algorithms DBSCAN Hierarchical Clustering K-Means Web-based framework

来源：评论

学校读者我要写书评

暂无评论

Application of CNN Based Deep Learning Algorithm for Herbal Plant Leaf Detection

Application of CNN Based Deep Learning Algorithm for Herbal ...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Pongiannan, R.K. Das, Sagardeep Purbia, Rudra Prakash Brindha, R. Jame, S. Lourde Shiju Kumar, P.S. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur India

ISBN: (纸本)9798331509828

The medicinal plant market faces challenges due to inefficiencies and a lack of transparency. In this paper, a total of 10GB dataset with 10,000 entries, including 15 attributes such as plant name, region, price, and high-resolution images capture seasonal and geographical variations. Designed for precise plant identification and market forecasting, the dataset also contains metadata and historical data on prices and demand trends. Deep learning models, including recurrent neural networks (RNN) and convolutional neural networks (CNNs), are employed for accurate plant identification. Time series analysis is used to forecast market patterns. Data optimization techniques are applied to ensure real-time insights, allowing farmers and traders to make informed decisions. This system aims to enhance market transparency and improve the decision-making process in the medicinal plant industry. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

ETBench: Characterizing Hybrid Vision Transformer Workloads Across Edge Devices

引用

IEEE Transactions on Computers 2025年第6期74卷 1857-1871页

作者： Zhou, Yingkun Tian, Zhengshuyuan Yang, Wenhao Zhang, Tingting Ye, Jinpeng Han, Chenji Liu, Tianyi Zhang, Fuxin Institute of Computing Technology CAS State Key Lab of Processors Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Loongson Technology Company Ltd. Beijing100095 China Institute of Computing Technology CAS Beijing100190 China University of Texas at San Antonio San AntonioTX78249 United States

Lightweight Convolution and Vision Transformer hybrid models have increasingly dominated the frontiers of deep learning (DL) on edge devices;however, to the best of our knowledge, no prior work has provided comprehensive evaluation on hybrid models’ performance and analyzed their characteristics by diving deep into the edge ecosystem with diversified modern DL inference engines and heterogeneous hardware. This paper proposes a comprehensive open-source benchmark suite, ETBench, to allow power-efficiency, performance and accuracy assessment for state-of-the-art (SOTA) hybrid models across 11 most widely-used DL engines deployed on diverse edge devices. After building ETBench that satisfies 6 design requirements proposed in our work, we conduct extensive experiments on 14 devices including 19 CPUs, 11 GPUs and 5 NPUs, and obtain benchmark results from all deployment scenarios (combinations of models, quantization formats, software engines, and hardware platforms). Valuable observations and insightful implications are finally summarized. For example, within current DL engines, the INT8 quantization is significantly underperformed in terms of accuracy and speed against FP16 for hybrid models. Overall, ETBench serves as a collaborative platform that assists model architects in better evaluating their models and makes it possible for future co-optimizations of DL engines and hardware accelerators. © 1968-2012 IEEE.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Optimizing Image Retrieval in Cloud Servers with TN-AGW: A Secure and Efficient Approach

引用

Journal of The Institution of Engineers (India): Series B 2025年第2期106卷 459-473页

作者： Ponnuviji, N.P. Nirmala, G. Kokila, M. L. Sworna Priyadharshini, S. Indra Department of Computer Science and Engineering RMK College of Engineering and Technology Puduvoyal Thiruvallur India Department of Computer Science and Engineering RMD Engineering College Chennai India Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nādu Kattankulathur Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

The increasing use of cloud-based image storage and retrieval systems has made ensuring security and efficiency crucial. The security enhancement of image retrieval and image archival in cloud computing has received considerable attention in transmitting data and ensuring data confidentiality among cloud servers and users. Various traditional image retrieval techniques regarding security have developed in recent years but they do not apply to large-scale environments. This paper introduces a new approach called Triple network-based adaptive grey wolf (TN-AGW) to address these challenges. The TN-AGW framework combines the adaptability of the Grey Wolf Optimization (GWO) algorithm with the resilience of Triple Network (TN) to enhance image retrieval in cloud servers while maintaining robust security measures. By using adaptive mechanisms, TN-AGW dynamically adjusts its parameters to improve the efficiency of image retrieval processes, reducing latency and utilization of resources. However, the image retrieval process is efficiently performed by a triple network and the parameters employed in the network are optimized by Adaptive Grey Wolf (AGW) optimization. Imputation of missing values, Min–Max normalization, and Z-score standardization processes are used to preprocess the images. The image extraction process is undertaken by a modified convolutional neural network (MCNN) approach. Moreover, input images are taken from datasets such as the Landsat 8 dataset and the Moderate Resolution Imaging Spectroradiometer (MODIS) dataset is employed for image retrieval. Further, the performance such as accuracy, precision, recall, specificity, F1-score, and false alarm rate (FAR) is evaluated, the value of accuracy reaches 98.1%, the precision of 97.2%, recall of 96.1%, and specificity of 917.2% respectively. Also, the convergence speed is enhanced in this TN-AGW approach. Therefore, the proposed TN-AGW approach achieves greater efficiency in image retrieving than other existing

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Detecting a suitable path method for assisted localization techniques in transmission of data over wireless sensor networks

引用

International Journal of Information technology (Singapore) 2025年第4期17卷 2235-2242页

作者： Navaneethan, S. Arun, A. Department of Networking & Communications School of Computing SRM Institute of Science and Technology SRM Nagar Tamilnadu KattanKulathur 603203 India Department of Networking & Communications School of Computing Faculty of Engineering & Technology SRM Institute of Science and Technology Tamilnadu KattanKulathur 603203 India

In many Wireless Sensor Networks (WSNs) applications, the relevant sensor node’s location information is essential in determining where the event or situation occurs. Therefore, localization is one of the critical challenges in WSNs. Mobile Anchor Node Assisted Localization (MANAL) is one of the promising solutions for the localization of statically deployed sensors. The main problem in MANAL is that the path planning of the Mobile Anchor Node (MAN) should be done in a way that the localization error in the network will be minimal and that all unknown nodes in the network are covered. In this paper, a new path planning approach called Nested Hexagons Curves (NH-exCurves) is proposed for MANAL. NH-exCurves guarantees that it will receive messages from at least three non-collinear anchors to locate all unknown nodes in the network. The proposed model is compared to six different path planning schemes using Accuracy Priority Trilateration (APT) under different evaluation criteria. In these comparisons, first of all, localization errors of the models are compared using some statistical concepts. Secondly, the variation of the localization error according to parameters such as resolution (R) and the standard deviation of noise (σ) are observed. The simulation results present the superiority of the proposed work over existing path planning models used in this study. © Bharati Vidyapeeth's institute of Computer Applications and Management 2025.

关键词： Accuracy priority trilateration (APT) Localization Mobile anchor node assisted localization (MANAL) Static path planning Wireless sensor networks (WSNs)

来源：评论

学校读者我要写书评

暂无评论

Drone-based Aerial Surveillance and Real-Time Hazardous Gas Leakage Detection System with Power BI Dashboard Integration for Enhanced Environmental Safety 6

Drone-based Aerial Surveillance and Real-Time Hazardous Gas ...

引用

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

作者： Ramesh, Krithick Balaji Saran, S. Department of Computing Technologies SRM Institute of Science & Technology Chennai India SRM Institute of Science & Technology Chennai India

ISBN: (纸本)9798331522667

This paper focuses on an embedded system for air quality control and hazardous gas detection using multiple sensors to trigger real-time danger alerts. The system employs and integrates gas sensors MQ-2, MQ-3, and MQ-9, temperature, and humidity sensors for assessing many combustible gases including methane, carbon monoxide alcohol smoke and even fire. These sensors send signals to an embedded microcontroller which controls air and environmental quality for the circumferential range. Apart from the gas sensors, a fire sensor has been integrated within the system, improving its efficiency in ascertaining cases of fire outbreak in the presence of gas leakages. In addition to this, Power BI works with the system for sensor monitoring and data visualization through the sensors being connected online. The dashboard shows the most important parameters such as the level of gas leakage and the type of gas involved, the temperature of the surroundings, and the humidity. Power BI supports how to visualize what is going on at that time to monitor environmental conditions, how bad is the gas leakage, and make quick decisions. The dashboard also helps in looking out for risks by showing past trends of data and carrying out market predictions. The integration of multi-sensor systems with a drone is intensified to outstretch the boundaries even further where remote monitoring of industrial sites, areas that have been hit by disasters, and even of cities, is possible. The drone equipped with the embedded system provides the real time gas leak detection temperature, humidity monitoring and fire threat assessment in environments where the human presence is quite dangerous. This system is also easy, cheap and provides an admirable solution for environmental monitoring on a day to day basis for the sake of public safety, reduction in the response rates to dangerous situations and the encouragement of smart city designs. The research in this study focused on both stationary and mobile w

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Enhanced Indoor Pathfinding Navigation in Multistoried Buildings Using a Hybrid of RRT-Connect and Dijkstra's Algorithm

Enhanced Indoor Pathfinding Navigation in Multistoried Build...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Ramamoorthy, S. Yadav, Abhishek Pal, Subha Bal School of Computing Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Tamil Nadu Chennai603203 India

ISBN: (纸本)9798331509828

This paper presents a hybrid approach to enhance indoor pathfinding and navigation within complex multistory environments by integrating RRT-Connect and Dijkstra's algorithm. The objective is to address the limitations of traditional algorithms like Dijkstra and A*, which struggle with computational inefficiency and adaptability in dynamic, high-dimensional spaces. The proposed solution leverages the rapid path generation capabilities of RRT-Connect, combined with Dijkstra's algorithm for refining and optimizing the final route to ensure accuracy and optimality. To further improve efficiency, parallel processing techniques utilizing multi-threaded CPU operations are incorporated, enabling real-time computation even in dynamic environments. Additionally, a frontend visualization system is developed using React, which provides users with real-time rendering of path nodes on multistory floor plan images, enhancing usability and system interactivity. Experimental findings reveal that the hybrid approach achieves a significant reduction in computation time - up to 25% compared to traditional methods - while maintaining high pathfinding accuracy. This novel combination of rapid exploration, optimal path refinement, and real-time visualization offers a robust and scalable solution for navigating complex multistory environments, making it a significant advancement in the field of indoor navigation. © 2025 IEEE.

关键词： Visualization

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：