检索结果-内蒙古大学图书馆

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Jananipriya, R. Ramya, P. Mahendra Engineering College Department of Computer Science and Engineering Namakkal India

ISBN: (纸本)9798331529246

It is quite challenging to monitor goods quality or security issues due to the intricacy of a tracking system, particularly for the fundamental farming food supply chains that contribute to making up everyday feeds of individuals. There are a number of significant issues with the current agricultural food tracking systems, including a large number of subjects, challenging interactions brought on by lengthy logistics phases, and user and centrally managed distrust of data. The traceability issue in agricultural food tracking systems is successfully resolved by the development of blockchain technology. In order to reduce the requirement for central organizations and departments and enhance the dependability, safety, and authenticity of records of transactions, this work suggests a structure based on smart contracts and consortiums to monitor and document the process of agricultural food tracking system, implement transparency and accessibility, and dismantle data centers between businesses. Farmers simultaneously store file hashes in smart contracts and record environmental and agricultural development information in the InterPlanetary File System (IPFS), which improves the safety of information and mitigates the issue of blockchain storage overflow. The proposed system demonstrated superior performance with reduced delay in response (0.035) and increased transmission speed (265), reception speed (305) and processing power (17.65) compared to Ethereum and Hyperledger Fabric. © 2025 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Deep kernelized dimensionality reducer for multi-modality heterogeneous data

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第8期15卷 3255-3272页

作者： Shikalgar, Arifa Sonavane, Shefali Department of Computer Science and Engineering Annasaheb Dange College of Engineering Maharashtra Ashta416301 India Department of Information Technologies Walchand College of Engineering Sangli Maharashtra Sangli416415 India

Data mining applications use high-dimensional datasets, but still, a large number of extents causes the well-known ‘Curse of Dimensionality,' which leads to worse accuracy of machine learning classifiers due to the fact that most unimportant and unnecessary dimensions are included in the dataset. Many approaches are employed to handle critical dimension datasets, but their accuracy suffers as a result. As a consequence, to deal with high-dimensional datasets, a hybrid Deep Kernelized Stacked De-Noising Auto encoder based on feature learning was proposed (DKSDA). Because of the layered property, the DKSDA can manage vast amounts of heterogeneous data and performs knowledge-based reduction by taking into account many qualities. It will examine all the multimodalities and all hidden potential modalities using two fine-tuning stages, the input has random noise along with feature vectors, and a stack of de-noising auto-encoders is generated. This SDA processing decreases the prediction error caused by the lack of analysis of concealed objects among the multimodalities. In addition, to handle a huge set of data, a new layer of Spatial Pyramid Pooling (SPP) is introduced along with the structure of Convolutional Neural Network (CNN) by decreasing or removing the remaining sections other than the key characteristic with structural knowledge using kernel function. The recent studies revealed that the DKSDA proposed has an average accuracy of about 97.57% with a dimensionality reduction of 12%. By enhancing the classification accuracy and processing complexity, pre-training reduces dimensionality. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

An Interactive Augmented Reality Application for Agriculture using Unity 17

An Interactive Augmented Reality Application for Agriculture...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Maasthi, Manasvi J. Vidyavardhaka College of Engineering Department of Computer Science and Engineering Mysuru India

ISBN: (纸本)9798331531195

Augmented reality is defined as a 3D computer generated imagery that is embedded into the real world. There are numerous areas in which augmented reality can be applied, including: education, medical care, entertainment, & so on. Unlike VR, AR does not require the use of a HMD (Head Mounted Device);a projection can be performed on a mobile phone making it affordable. Most farmers are facing problems today, for instance, loss of crops. In this Paper an application has been created aimed at enabling farmers to know important things like when to grow certain crops and what to use to assist in soil fertility, through the development of augmented reality applications using Unity and Vuforia. That way, the farmers will have an idea of what other crops they should be able to grow during the other season. So that they will not be undergoing any kind of loss. © 2025 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

U-YOLOv3: A Model Focused on Underwater Object Detection

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第6期49卷 87-102页

作者： Sarkar, Pratima De, Sourav Gurung, Sandeep Department of Computer Science and Engineering Sikkim Manipal Institute of Technology Majhitar India Sikkim Manipal University Gangtok India Department of Computer Science and Engineering Techno International New Town Newtown Kolkata India Department of Computer Science and Engineering Cooch Behar Government Engineering College Vill-Harinchowrah West Bengal Cooch Behar736170 India

Underwater image enhancement and object detection has great potential for studying underwater environments. It has been utilized in various domains, including image-based underwater monitoring and Autonomous Underwater Vehicle (AUV)-driven applications such as underwater terrain surveying. It has been observed that underwater images are not clear due to several factors such as low light, the presence of small particles, different levels of refraction of light, etc. Extracting high-quality features from these images to detect objects is a significant challenging task. To mitigate this challenge, MIRNet and the modified version of YOLOv3 namely Underwater-YOLOv3 (U-YOLOv3) is proposed. The MIRNet is a deep learning-based technology for enhancing underwater images. while using YOLOv3 for underwater object detection it lacks in detection of very small objects and huge-size objects. To address this problem proper anchor box size, quality feature aggregation technique, and during object classification image resizing is required. The proposed U-YOLOv3 has three unique features that help to work with the above specified issue like accurate anchor box determination using the K-means++ clustering algorithm, introduced Spatial Pyramid Pooling (SPP) layer during feature extraction which helps in feature aggregation, and added downsampling and upsampling to improve the detection rate of very large and very small size objects. The size of the anchor box is crucial in detecting objects of different sizes, SPP helps in aggregation of features, while down and upsampling changes sizes of objects during object detection. Precision, recall, F1-score and mAP are used as assessment metrics to assess proposed work. The proposed work compared with SSD, Tiny-YOLO, YOLOv2, YOLOv3, YOLOv4, YOLOv5, KPE-YOLOv5, YOLOv7, YOLOv8 and YOLOv9 single stage object detectors. The experiment on the Brackish and Trash ICRA19 datasets shows that our proposed method enhances the mean average precision for b

关键词： Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

Integrated Hydroponics Automation System Utilizing IoT for Enhanced Plant Growth 3

Integrated Hydroponics Automation System Utilizing IoT for E...

引用

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

作者： Nilahni, N. Sivasakthi, P. Kavitha, P. Madhumathi, S.M. Sakthi Lakshmi Priya, C. Saranyavaishalini, V.G. Department of Computer Science and Engineering PSR Engineering College Sivakasi India

ISBN: (纸本)9798331527549

Growing plants in nutrition solution with any growing medium or roots dipped in distilled water is Hydroponics. Hydroponics, the practice of growing plants in a nutrient-rich solution without soil, offers significant advantages such as higher yield, reduced water usage, and efficient resource management compared to traditional farming. However, existing hydroponic systems often require separate monitoring and control platforms for different setups, such as Wick and Drip systems, increasing complexity and cost. This paper proposes a Combined Hydroponics Automation System utilizing IoT, integrating both Wick and Drip systems into a single, unified platform. The system employs Nodemcu ESP8266 to monitor key parameters such as pH, humidity, moisture, and water levels, with data transmitted to a cloud platform for real-time access and control. The unified approach reduces development and operational costs while simplifying the monitoring process. The outcome demonstrates improved efficiency in plant management, with streamlined data visualization, remote control, and optimized resource allocation, making it a cost-effective solution for urban and resource-limited farming environments. © 2025 IEEE.

关键词： Hydroponics

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Detection Using Deep Learning 7th

Skin Cancer Detection Using Deep Learning

引用

7th International Conference on Communication, Device and Networking, ICCDN 2024

作者： Rakshit, Pranati Ghosh, Arundhati Chakraborty, Chirag Paul, Joydeep Das, Dinika Department of Computer Science and Engineering JIS College of Engineering Kalyani India

ISBN: (纸本)9789819764648

Skin cancer is characterized by the uncontrolled proliferation of abnormal cells in the outermost skin layer, the epidermis, due to unrepaired DNA damage leading to mutations. These mutations cause rapid multiplication of skin cells, forming malignant tumors. The primary types of skin cancer include basal cell carcinoma (BCC), squamous cell carcinoma (SCC), melanoma, and Merkel cell carcinoma (MCC). Melanoma of the skin ranks as the 17th most common cancer worldwide, with more than 150,000 new cases reported in 2020. Early detection and treatment of melanoma can significantly impact patient outcomes. The present work aims to detect melanoma skin cancer in its early stages using image processing through computer Vision and deep learning methodologies. The culmination of this effort is an Android application designed to facilitate self-diagnosis for users, offering timely alerts on when to consult a medical professional. Hospitals can also utilize the application to prioritize patient care based on their risk percentages, benefiting both patients and healthcare providers. The study delves into relevant research papers published in esteemed journals related to skin cancer diagnosis. Deep learning methods are proposed to assist dermatologists in achieving early and accurate diagnoses. While specialists can provide accurate diagnoses, the development of automated systems becomes crucial to efficiently diagnose diseases, saving lives and reducing healthcare and financial burdens. Machine learning (ML) emerges as a valuable tool in this context. The article focuses on the fundamentals of ML and its potential in aiding skin cancer diagnosis. The objective is to conduct a comparative study between the DenseNet-121, ResNet-50, and CNN-RF models. The study reveals that DenseNet-121 outperformed with a testing accuracy of 83%, surpassing ResNet- 50, which achieved 81% testing accuracy. This comparative analysis contributes to the ongoing research and development in the field of

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Detection Using Deep Learning 10

Skin Cancer Detection Using Deep Learning

引用

10th International Conference on Electrical Energy Systems, ICEES 2024

作者： Mahalakshmi, A. Padmavathy, C. Priya, N. Priyanka, G. Babu, Lidiya Archana, B. Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India Hindusthan College of Engineering and Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350353778

Skin cancer is a significant global health concern that requires early detection and accurate diagnosis for effective treatment. Traditionally, dermatologists with specialized training have been responsible for diagnosing skin cancer. However, the emergence of deep learning models, particularly Convolutional Neural Networks (CNNs), offers a promising approach for utilizing dermatoscopic images in the early identification and categorization of skin cancer. The HAM10000 dataset, comprising a vast library of high-quality dermatoscopic images displaying a variety of skin lesions, significantly contributes to advancing skin cancer diagnosis. This research leverages the HAM10000 dataset to develop and evaluate a CNN model tailored for accurate skin cancer classification. The suggested CNN model is an advanced deep learning architecture adept at image classification tasks, particularly in recognizing various forms of skin cancer. It consists of multiple layers of dense neural networks, pooling, and convolution designed to extract detailed characteristics from skin lesion images. To ensure comprehensive representation of various skin lesions and maximize performance, the training dataset is extensively oversampled. This oversampling technique enhances the model's ability to generalize across different lesion types, thereby improving classification accuracy. Furthermore, the Adam optimizer refines the model's learning process by effectively adjusting its parameters during training, leading to increased accuracy. By training the model for more than one hundred epochs with a batch size of 323, it learns intricate patterns and distinguishing features within skin lesion photos, which enhances its ability to classify skin cancer accurately. These advancements in deep learning-based skin cancer categorization represent a significant step towards leveraging artificial intelligence to improve early diagnosis and detection. Such innovations have the potential to support medical profe

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Approach for Automatic Melanoma Diagnosis: Integrating Convolutional Neural Networks with Vision Transformers 4

A Hybrid Deep Learning Approach for Automatic Melanoma Diagn...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Priyanka, G. Mahalakshmi, A. Priya, N. Sivaranjani, N. Archana, B. Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India Hindusthan college of Engineering and Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529635

The most lethal type of skin lesion is melanoma. The likelihood of survival for melanoma is significantly increased by early detection. Nevertheless, a number of characteristics, such as diminished contrast between the skin and abrasion and visual similarities between non-melanoma and melanoma, make it challenging to identify melanoma with accuracy. The novel melanoma recognition method described in this study consists of three primary phases: preprocessing, segmentation and classification. To maximize image quality and get the data ready for segmentation, the preprocessing step included denoising techniques, grayscale conversion, Gaussian thresholding, and Contrast Limited Adaptive Histogram Equalization (CLAHE). Three widely used edge detection algorithms-Canny, Sobel, and Prewitt-were applied to the segmentation process in order to identify lesion boundaries and extract features unique to melanoma. Performance criteria such as Root Mean Square Error (RMSE), Structural Similarity Index (SSIM), and Peak Signal-to-Noise Ratio (PSNR) were used to assess the accuracy of the segmentation. Based on the comparison analysis, Sobel was found to be the best algorithm for correctly identifying melanoma lesions. The outcomes showed how well the preprocessing methods worked to enhance image quality and how well the segmentation algorithms identified melanoma lesions. This research's subsequent phase will concentrate on classifying images using deep learning models. The segmented images are used to train deep learning model namely Convolutional Neural Networks with Vision Transformer. Superior performance is obtained in terms of accuracy, precision, recall, and F1 score when denoising, segmentation, and classification techniques are combined. This highlights the potential of deep learning and image processing fusion in improving skin disease recognition and performance of classification systems. © 2024 IEEE.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Helmet and Equipment Detection with Worker's Mobility Tracker In Mining Sector Using YOLOv8 & LSTM

Helmet and Equipment Detection with Worker's Mobility Tracke...

引用

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

作者： Ramyadevi, R. Keerthy, S. Catherina J, Sherin Joys Dhayanithi, T. Saveetha Engineering College Department of Computer Science and Engineering Kanchipuram India

ISBN: (纸本)9798331529833

Monitoring personal protective equipment and compliance with safety procedures for mining operations is essential to ensuring personnel safety. Nevertheless, sending humans underground is impractical, as mining conditions are fast-changing and dangerous. Most of the existing systems are still not able to detect helmets, PPE, and the worker mobility in real-time, which are two critical aspects of safety. To overcome these challenges, this project bases its approach on enhancing monitoring and security by integrating machine learning technologies. Using YOLOv8, a cutting-edge object detection model, the system enables workers' helmet and PPE detection in real-time. This work also uses Long Short-Term Memory (LSTM), a special type of RNN, to track the behavior of workers within and over time. By reading the frames at 10 millisecond intervals, the system detects movement deviations be it unsafe movements or fatigue induced deviations and provides proactive measures for safety. The devised method reaches an outstanding accuracy of 95.9%, combining YOLOv8 and LSTM, which reduces human error and improves safety at the workplace. This state-of-the-art solution is not only providing continuous monitoring but is also increasing operational efficiency, thereby transforming safety solutions in the mining space. © 2025 IEEE.

关键词： Protective clothing

来源：评论

学校读者我要写书评

暂无评论

Probe Attack Detection Using an Improved Intrusion Detection System

引用

computers, Materials & Continua 2023年第3期74卷 4769-4784页

作者： Abdulaziz Almazyad Laila Halman Alaa Alsaeed Department of Computer Engineering College of Computer ScienceKing Saud UniversityRiyadh11421Saudi Arabia

The novel SoftwareDefined Networking(SDN)architecture potentially resolves specific challenges arising from rapid internet growth of and the static nature of conventional networks to manage organizational business requirements with distinctive ***,such benefits lead to a more adverse environment entailing network breakdown,systems paralysis,and online banking fraudulence and *** one of the most common and dangerous threats in SDN,probe attack occurs when the attacker scans SDN devices to collect the necessary knowledge on system susceptibilities,which is thenmanipulated to undermine the entire ***,high performance,and real-time systems prove pivotal in successful goal attainment through feature selection to minimize computation time,optimize prediction performance,and provide a holistic understanding of machine learning *** the extension of astute machine learning algorithms into an Intrusion Detection System(IDS)through SDN has garnered much scholarly attention within the past decade,this study recommended an effective IDS under the Grey-wolf optimizer(GWO)and Light Gradient Boosting Machine(Light-GBM)classifier for probe attack *** InSDN dataset was employed to train and test the proposed IDS,which is deemed to be a novel benchmarking dataset in *** proposed IDS assessment demonstrated an optimized performance against that of peer IDSs in probe attack detection within *** results revealed that the proposed IDS outperforms the state-of-the-art IDSs,as it achieved 99.8%accuracy,99.7%recall,99.99%precision,and 99.8%F-measure.

关键词： GWO IDS InSDN LightGBM probe attack SDN

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：