检索结果-内蒙古大学图书馆

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Natarajan, Yuvaraj Afra, J. Buvani Sankari, V. Gayathri, V. Malingan, Navaneeth KPR Institute of Engineering and Technology Department of Computer Science Engineering Coimbatore India Nunnari Labs Private Limited Coimbatore India

ISBN: (纸本)9798350327533

The rapid urbanization and burgeoning populations in cities worldwide have led to an increased demand for efficient and sustainable urban transit systems. In India, the pace of growth in the two-wheeler fleet is 30 times greater than the rate of growth in the population. The chance of mortality is 3.5 times higher for riders who don't wear helmets than for those who do. In view of this, developed an AI-based model for object detection to guarantee public safety and enable real-time monitoring of traffic law violations. The system uses a camera to capture images of bikes carrying three or more people who are not wearing helmets as well as to recognize the license plates of bikes. A CNN Transit model for traffic networks have been proposed. The model utilizes the Yolov5 backbone layer, which is fine-tuned by increasing hyperparameters. This results in the accuracy of 86 % and a significant reduction in training time, which enhances the model's performance. By addition of PANet and FPN to the Yolov5 Neck layer has improved the detection of far and tiny objects in traffic and roadways. This study emphasizes the potential of AI-ML technology to address urban transportation difficulties and foster a culture of safety by detecting objects. © 2024 IEEE.

关键词： Convolutional Neural Network (CNN) Transit Feature Pyramid Network (FPN) Object Detection Path Aggregation Network (PANet) Traffic law Violations Yolo v5

来源：评论

学校读者我要写书评

暂无评论

Exploring Twitter Sentiments for Predicting Match Outcomes in the Game of Cricket 2

Exploring Twitter Sentiments for Predicting Match Outcomes i...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Sharma, Karan Hota, Lopamudra Tikkiwal, Vinay Anand Kumar, Arun Department of Computer Science and Engineering National Institute of Technology Rourkela769008 India Department of Electronics and Communication Engineering Jaypee Institute of Information Technology Noida201304 India

In recent years, social media platforms such as Twitter have become popular among fans to discuss and share their opinions about the matches. This research aims to contribute to the growing body of knowledge on utilizing the sentiments expressed through messages on social media platforms to predict outcomes of matches in the sport of cricket. This research work provides insights into the effectiveness of sentiment analysis techniques in forecasting match outcomes, which can be beneficial to cricket fans, and cricket analysts. In this work, sentiment analysis is carried out based on models developed using various machine-learning techniques. The work also explores the impact of different features, such as the number of tweets collected, the timing of tweets, and the sentiment analysis techniques on the accuracy of the prediction. The results of this study have implications for cricket fans, sports analysts, and the broader field of predictive analytics. © 2024 Elsevier B.V.. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

DCHR: Dynamic Cluster Head Replacement Algorithm for Energy Optimization in Wireless Sensor Network 13

DCHR: Dynamic Cluster Head Replacement Algorithm for Energy ...

引用

13th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2024

作者： Kapoor, Abhishek Priyanka Bhadoria, Robin Singh National Institute of Technology Hamirpur Department of Computer Science and Engineering Himachal Pradesh 177005 India

ISBN: (纸本)9798350305463

One of the major aspects for sensing solutions across diverse applications, is the demand associated with better lifetime of sensor nodes. This can be resolved using energy optimization of these nodes in Wireless Sensor Network (WSN). The energy consumption level for certain nodes may not be the same and therefore, it may die earlier than its expectation. In WSN, the critical challenge lies in efficiently managing the finite energy resources of sensor nodes to ensure prolonged network operation and transmission success. In this paper, we present a dynamic cluster head replacement algorithm (DCHR) that calculates a threshold value in determining the number of rounds for a particular sensor as active cluster head (CH). This depends on the remaining energy left with the battery of that particular node. This algorithm helps in reduction of energy consumption during next replacement of CH and ultimately results in overall lifetime of WSN. © 2024 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Detection using Deep Learning 2

Breast Cancer Detection using Deep Learning

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Afaq, Shajal Singh, Nanhay Netaji Subhas Institute of Technology Department of Computer Science and Engineering New Delhi110031 India

ISBN: (纸本)9798350368109

Breast cancer is a leading cause of morbidity for women all over the world, BC, or breast cancer, affects many women globally. It ranks fourth in fatality among colon, brain, and cervical malignancies. New BC cases are predicted to rise 70% in the following two decades. Thus, early identification and accurate breast cancer diagnosis improve prognosis and long-term survival. Machine learning methods like "Support Vector Machines"(SVM) and Nearest Neighbor have shown promising but limited efficacy in recognizing BC. This study introduced a "Convolutional Neural Network"(CNN) model of utilizing deep neural networks to diagnose BC using the Wisconsin BC database. The research demonstrates the application of DL technology for diagnosing BC using the Kaggle Dataset. The research method involves data acquisition, data preprocessing and using the dataset to train the CNN model and assess its performance using four key metrics: precision, recall, accuracy, and F-measure. CNN model accuracy is 95.57%, precision is 97.70%, recall is 98.64%, and F-measure is 98.14%. This approach outperforms standard models, proving its effectiveness in detecting BC. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

MetaIClone: A Robust Iris Clone Detection Mechanism for the Metaverse

MetaIClone: A Robust Iris Clone Detection Mechanism for the ...

引用

2024 IEEE International Conference on Modeling, Simulation and Intelligent Computing, MoSICom 2024

作者： Verma, Palak Kaur, Harkeerat Indian Institute of Technology Jammu Department of Computer Science and Engineering Jammu and Kashmir181221 India

ISBN: (纸本)9798331533311

Recent advancements in artificial intelligence have paved the way for the metaverse to become an imminent reality. Within this virtual world, people can buy and sell virtual assets, meet up with friends, purchase goods, and attend event, all while using biometric traits for secure and seamless authentication. Iris recognition has become a highly prevalent method for human authentication due to its robustness and effectiveness. Despite its widespread use, these systems are vulnerable to various security threats, particularly when attackers use biometric replicas to impersonate legitimate users-commonly known as biometric cloning. To counteract such cloning attempts, an anti-cloning subsystem is incorporated with the sensor, enabling intelligent differentiation between genuine and clone iris traits. In this research, we present MetaIClone, a hybrid iris clone detection (ICD) system designed for secure identification within the metaverse. MetaIClone integrates the powerful features of two handcrafted feature extractors namely histogram of oriented gradient (HoG) and binary statistical image feature (BSIF), with the extracted feature vectors subsequently classified using two distinct support vector machines (SVMs). The final decision is achieved through score-level fusion with a fine-tuned MobileNet V2 model. We evaluated MetaIClone using benchmark datasets, including iris liveness detection Notre Dame 2017 (LivDet ND17) and Notre Dame cosmetic lenses dataset 2015 (NDCLD-15). Additionally, we introduced a digital clone generation technique using a generative adversarial network (GAN) model and tested the system on this novel dataset. MetaIClone excels in known attack scenarios, achieving an average classification error rate (ACER) of 0. 0 2%, and performs well in unseen attack scenarios with an ACER of 0. 0 5%, delivering competitive results in crossdatabase evaluations. Overall, MetaIClone outperforms other ICD models, offering superior accuracy with high computational

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Detection Using CNN Based Model 2

Lung Cancer Detection Using CNN Based Model

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Chaudhary, Prince Nitin Kumar, Prince Rana, Naman Garg, Payal Gl Bajaj Institute of Technology and Management Department of Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798350371055

Lung cancer can be fatal, but early diagnosis and treatment can save lives. Doctors use x-ray imaging to detect lung cancer, but it can be hard to distinguish cancerous cells from normal ones. computer-aided diagnosis can help doctors make accurate decisions. This research evaluates different computer-aided methods, analyzes the best one, identifies its flaws and limitations, and suggests a model with enhancements. The methods were ranked and compared based on their detection accuracy, and their flaws and limitations were examined. Some methods have low accuracy, while others have high accuracy, but not higher than 90%. The research aims to achieve an accuracy of 91 % or more © 2024 IEEE.

关键词： CNN Lung Cancer ResNet50 VGG16

来源：评论

学校读者我要写书评

暂无评论

A Cyber Physical Security for Electrical Vehicles using Deep learning

A Cyber Physical Security for Electrical Vehicles using Deep...

引用

2024 IEEE International Conference on Automation and Computation, AUTOCOM 2024

作者： Sonker, Sanjay Kumar Raina, Vibha Kaw Sagar, Bharat Bhushan Bansal, Ramesh C. Birla Institute of Technology - Mesra Computer Science and Engineering Ranchi India Harcourt Butler Technical University Computer Science and Engineering Kanpur India University of Sharjah Electrical Engineering Sharjah United Arab Emirates

ISBN: (纸本)9798350382723

In this paper, Fog-based IoT-enabled Electrical vehicles connected with smart grid systems and propose a reference model that integrates fog computing concepts for electrical vehicles connected with smart grids. Due to its distributed nature, fog computing allows to capture the real data. fog computing capable to improve security with latency minimization between electric vehicles to cloud, and provide reliability in smart grid applications such as electric vehicles' energy management and security. In addition, we explain the security challenges and attacks and existing solutions. our proposed method CNN+LSTM Algorithms on a publicly CICIDS-2017 dataset demonstrated its high performance. We achieved an impressive accuracy rate of 99.86%. © 2024 IEEE.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

Classification of diabetic macular edema severity using deep learning technique

引用

Research on Biomedical engineering 2022年第3期38卷 977-987页

作者： Kumar, Amit Tewari, Anand Shanker Singh, Jyoti Prakash Department of Computer Science & Engineering National Institute of Technology Patna Patna India

Purpose: Diabetic macular edema (DME) is a kind of hard exudates lesion seen near the diabetic macular region of the retina. DME causes visual loss and may result in complete blindness;early identification and treatment may be able to cure this. Identification of DME at an early stage is a challenging and error-prone task. To address this issue, the article presents a methodology that uses the notion of transfer learning to identify cases of DME from retinal fundus images. Methods: A pre-trained DenseNet121 is used in this technique to extract the useful set of feature vectors from the fundus images, which are then fed into a few additional fully connected layers and then into the classification layer to classify DME instances. A total of 577 fundus training images from 3 DME classes were used to train the proposed model, and 103 fundus testing images were used to verify the proposed model for classifying them into one of the three DME cases. Results: The suggested model is trained and tested on the Indian Diabetic Retinopathy Image Dataset (IDRiD). With the test images, the results demonstrate that the proposed model outperformed the state-of-the-art models presented in "Diabetic Retinopathy – Segmentation and Grading Challenge" held at ISBI-2018 with an accuracy of 86.4%. Conclusion: The proposed model diagnoses DME at an early stage for timely treatment and helps to reduce the workload of ophthalmologists. © 2022, The Author(s), under exclusive licence to The Brazilian Society of Biomedical engineering.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

Smart Agricultural Greenhouse System: A Context-Aware Application

Smart Agricultural Greenhouse System: A Context-Aware Applic...

引用

International Conference on Machine Learning and Big Data Analytics, ICMLBDA 2023

作者： Swain, Sujata Niyogi, Rajdeep School of Computer Engineering Kalinga Institute of Industrial Technology Bhubaneswar India Department of Computer Science IIT Roorkee Roorkee India

ISBN: (纸本)9783031513374

Smart applications are getting more powerful and cheaper cost due to the advancement in sensor technology. In this chapter, we have considered a smart greenhouse application. The important parameters of the smart greenhouse are to control light, temperature, humidity, and water. Greenhouse can provide a favourable growth environment for plants. This smart greenhouse system is a context-aware application. When the context changes in the environment, the application automatically adapts it and does the changes seamlessly without user intervention. In this chapter, we propose a model for the smart greenhouse system. The proposed model can adapt to context changes such as temperature rises, and it automatically turns on the AC seamlessly. The proposed model is based on the machine learning approach. The model maintains the greenhouse temperature, humidity, and sunlight duration in the suitable ranges of the plant. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Context Greenhouse Machine learning NLP Sensors Web service

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Collaborative Filtering: A Deep Neural Network Approach for Accurate and Diverse Recommendations 2

Cross-Domain Collaborative Filtering: A Deep Neural Network ...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Goel, Chirag Sinha, Bam Bahadur Department of Computer Science and Engineering Indian Institute of Information Technology Jharkhand Ranchi834010 India

The rapid proliferation of data and the intricate nature of user behavior in the online realm have presented new hurdles for recommendation systems, which aim to suggest pertinent items to users. Among the notable challenges, ensuring the provision of accurate recommendations across diverse domains stands out. This research paper proposes an innovative solution to tackle this challenge by developing a cross-domain recommendation system that leverages the collaborative filtering technique to generate precise and varied recommendations spanning multiple domains. The system gathers user behavior and item attribute data from various domains and employs a collaborative filtering algorithm integrated with a deep neural network. The model makes use of a Neural Network with CReLU activation along with the embeddings of the user and the item followed by concealed layers. The output layer employs tanh activation to guarantee that recommendations fall within [-1, 1]. Adam optimizer, MSE loss, and an accuracy metric are utilised in training. This architecture captures user-item interactions effectively, resulting in precise personalised recommendations resulting an accuracy of 96.5% - 97.5%. To validate the effectiveness of the model, extensive evaluations are conducted on real-world datasets encompassing movies and books. The results demonstrate that the proposed system outperforms state-of-the-art recommendation systems in terms of accuracy, as measured by precision(89%), recall(90%), and AUC(0.74) scores. Furthermore, the system exhibits robust performance even in scenarios characterized by cold-start problems and data sparsity. © 2024 Elsevier B.V.. All rights reserved.

关键词： Collaborative filtering

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：