检索结果-内蒙古大学图书馆

Ensuring safety of vehicular cyber physical systems using machine learning and MQTT

International Journal of Vehicle Information and Communication Systems 2025年第2期10卷 165-183页

作者： Bagga, Neha Kalra, Sheetal Kaur, Parminder Department of Computer Science Guru Nanak Dev University Punjab Amritsar India School of Computer Science Engineering Lovely Professional University Punjab Phagwara India Department of Computer Science and Engineering G.N.D.U. Regional Campus Punjab Jalandhar India

One of the pressing concerns for emerging nations is maintenance of roads, including identification and repair of pavement distress. Previous research has focused on pothole detection and lane identification, with the distress details being shared with drivers via database or an Android application. However, this approach is battery-intensive for sensors in smart vehicles and requires a regular internet connection. To address these issues, we have proposed a model trained using Python and TensorFlow to identify road distress and steep curves with an accuracy of 85.2% and 83.1%, respectively. The simulation uses Geocoder to capture the geographical coordinates of the distress, and the collected data is transferred to other CPS devices in cars using MQTT which outperforms databases and Android applications in terms of efficiency, sensor load, and internet connectivity. Drivers receive alerts within 10 seconds, allowing them to make informed decisions which helps prevent accidents and fatalities on the road. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Highway accidents

来源：评论

学校读者我要写书评

暂无评论

An Imperceptible Adversarial Attack Against 3D Object Detectors in Autonomous Driving

引用

IEEE Internet of Things Journal 2025年第12期12卷 21404-21414页

作者： Wang, Yizhou Wu, Libing Jin, Jiong Wang, Enshu Zhang, Zhuangzhuang Zhao, Yu Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan430072 China Swinburne University of Technology School of Engineering MelbourneVIC3122 Australia Wuhan University School of Cyber Science and Engineering Wuhan430072 China City University of Hong Kong Department of Computer Science Hong Kong Hong Kong

As LiDAR-based 3D object detection gains attention, existing research on point cloud adversarial attacks has exposed vulnerabilities in 3D neural network models, which can further impact the reliability of perception systems in autonomous driving. However, current adversarial attacks primarily focus on the point cloud classification tasks, while detection tasks are more challenging to attack because they involve the localization of multiple targets and the sparse distribution of objects. Existing methods often implement attacks by adding global perturbations to the point clouds, which results in poor attack performance and lack of imperceptibility. In this paper, we investigate the robustness of 3D object detectors against adversarial examples. We propose a novel imperceptible attack method to generate 3D adversarial point clouds. First, we introduce the saliency map for the point clouds, assigning the unique value to each point to measure its importance to the model's discrimination results. These salient points are then aggregated and adaptively matched to different attack areas corresponding to different targets. Next, we design an optimization-based attack algorithm to generate adversarial point clouds, which are supervised by a dual-loss function consisting of the detection loss to ensure attack effectiveness and the distance loss to limit gap with the original point cloud. Finally, we conducted experiments on two real-world datasets, the KITTI and Waymo Open datasets, to evaluate the proposed attack method. Extensive experiments demonstrate that our attack method achieves average attack success rates of 83.07% and 77.11% on two datasets against seven 3D object detectors with minimal perturbations. Additionally, the generated adversarial point clouds exhibit strong transferability across multiple mainstream detectors. © 2025 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Exploring Machine Learning Algorithms for Job Recommendation: A Focus on Career Development 15

Exploring Machine Learning Algorithms for Job Recommendation...

引用

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

作者： Pallavi, M.S. Sumukha, M. Sumukh, M.R. Hegde, Vinayak Amrita Vishwa Vidyapeetham School of Computing Department of Computer Science Mysuru India

ISBN: (纸本)9798350370249

The education system plays a pivotal role in shaping individuals' careers. In addressing the challenge of recommending suitable jobs for students who are nearing the graduation, our research focuses on developing a job recommendation system leveraging machine learning (ML) algorithms. This study assesses the effectiveness of ML algorithms in categorizing jobs into sectors such as 'IT Sector', 'Teaching Sector', 'Bank Sector' and 'Business Sector'. Various parameters, including SSLC marks, PUC marks, communication skills, aptitude, and proficiency in subjects like networks, DBMS, data structures, operating systems, and programming skills, are considered. By conducting correlation analysis and employing dimensionality reduction techniques, we identify the most relevant attributes for job prediction. Three ML algorithms - Cat (categorical) Boost, Ada Boost (adaptive Boost), and XG (extra gradient) Boost - are compared for their predictive performance. A 70-30 training-testing model was employed to evaluate the performance of each model. Evaluation metrics such as accuracy, F1-score, precision, and recall were used to determine the best-performing model. Cross-validation techniques are applied to detect underfitting or overfitting. Among the three ML algorithms examined, Cat Boost emerges as the most effective, achieving a 94.7% accuracy rate in predicting job sectors. Consequently, Cat Boost is selected to build the predictive model. © 2024 IEEE.

关键词： Ada Boost Cat Boost Data Mining Student Job Recommendation XG-Boost

来源：评论

学校读者我要写书评

暂无评论

Calligraphy Alphabet Perception Using Artificial Intelligence 9

Calligraphy Alphabet Perception Using Artificial Intelligenc...

引用

9th International Conference on science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Venkatesh, S. Jeevitha, D. Gnanaselvi, J. Anitha Srm Institute of Science And Technology Department of Data Science And Business Systems School of Computing Chennai Kattankulathur India Jeppiaar Engineering College Department of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350365092

The human brain has a simple time analyzing and processing images. The brain is able to rapidly deconstruct and distinguish an image's various components when the eye perceives it. With the Convolutional Neural Network (CNN) as its foundation, this research suggests deep learning conceptual models. When the algorithms are compared, it becomes clear that CNN-based classification of handwritten alphabets performs better than other algorithms in terms of accuracy. The Manual Net, Alex Net, and LeNet Architectures are among the CNN algorithms employed in this research. The convulational layer, max pooling, flattening, feature assortment, rectifier lined unit, and completely linked softmaxx layers are each components of the aforementioned designs. The proposed network is tested using an image dataset comprising 530 training photos and 2756 testing images. The top precision and cost-efficient model will be used in the Django context to build a handler line for supplying the appeal to be recognized and obtaining the productivity outcome of recognized appeal. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Paddy Leaf Disease Detection Using Fine-Tuned EfficientNetB4 Convolutional Neural Network 15

Paddy Leaf Disease Detection Using Fine-Tuned EfficientNetB4...

引用

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

作者： Siddartha, Thota Reddiar, Nallamilli Eswar Venkata Vikranth, Pilla Veera Satya Sai Kumar, Teerdhala Singh, Rimjhim Padam Kumar, Priyanka Amrita Vishwa Vidyapeetham Amrita School of Computing Bengaluru Department of Computer Science and Engineering India University of Texas at San Antonio Texas Department of Computer Science United States

ISBN: (纸本)9798350370249

Agriculture remains the backbone of many countries since it acts as the main source of income and food. In this regard, different food crops are significant in the global economy, where rice occupies a very central position as one of the most important staple foods in many Asian countries. However, rice cultivation encounters various diseases at the different stage affecting either the quality or the rate of growth in the crop. Diagnosis of these diseases can be tiresome by applying traditional methods and use of naked eyes because symptoms of most diseases are often related. Therefore, the use of automated systems and the integration of such systems adds more realization to disease detection, hence informing the farmer to take appropriate measures on time to minimize crop or plant losses in order to yield quality produce. In the last several years different approaches utilizing image processing, machine learning, and deep learning algorithms have been investigated by researchers to create effective automatic systems. Therefore, this paper aims at optimizing several of the existing highly accurate deep learning-based state-of-Art Convolutional neural networks for the early detection of different rice crop diseases, also known as paddy leaf diseases. This work also pointed out a comparative assessment of the utilized techniques through precision, accuracy, recall, and F1-score metrics with a fine-Tuned EfficientNetB4 model with an optimum F1-score of approximately 99.7%. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Tire Imprint Identification and Classification using VGG19 1

引用

5th International Conference on computer and Communication Technologies, IC3T 2023

作者： Girish, Disha N. Priyanka, M. Department of Computer Science School of Computing Amrita Vishwa Vidyapeetham Mysore India

ISBN: (数字)9789819997046

ISBN: (纸本)9789819997039

In the fields of forensic research, the automobile industry, and consumer safety, classifying tire imprints is a crucial task. It involves identifying the brand or producer of a tire based on the imprints left on various surfaces. Tire impressions can be valuable evidence in criminal investigations, counterfeit identification, product quality control, and accident reconstruction. Here, we propose a deep learning approach using the VGG19 architecture for tire impression identification and classification. To begin, we collected tire impressions from various two- and four-wheeler MRF tire brands. Our dataset consists of 2693 photos divided into 22 classes, with 15 classes representing 2-wheelers and 7 classes representing 4-wheelers. We processed the images through denoising, normalization, and enhancement steps. We then employed a mask-based segmentation method to extract texture-based information from the tire impressions. This, combined with morphological data, resulted in a comprehensive set of features used in pattern recognition. These features include statistical measurements such as mean, entropy, correlation, contrast, and others. To accurately determine the tire brand, we utilized the Structural Similarity Index Matrix (SSIM) with a minimum similarity index value of 0.7. By comparing the SSIM values, we were able to match the tire impressions to the correct brand. We divided the dataset into 80% training data and 20% test data, which provided the best performance for our proposed technique. The accuracy achieved using this approach was 95.3%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Characterization of Exact One-Query Quantum Algorithms for Partial Boolean Functions

引用

Journal of computer science & Technology 2023年第6期38卷 1423-1430页

作者：叶泽坤李绿周 Institute of Quantum Computing and Computer Theory School of Computer Science and EngineeringSun Yat-sen UniversityGuangzhou 510006China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen UniversityGuangzhou 510006China

The query model(or black-box model)has attracted much attention from the communities of both classical and quantum ***,quantum advantages are revealed by presenting a quantum algorithm that has a better query complexity than its classical *** the history of quantum algorithms,the Deutsch algorithm and the Deutsch-Jozsa algorithm play a fundamental role and both are exact one-query quantum *** leads us to con-sider the problem:what functions can be computed by exact one-query quantum algorithms?This problem has been ad-dressed in the literature for total Boolean functions and symmetric partial Boolean functions,but is still open for general partial Boolean ***,in this paper,we continue to characterize the computational power of exact one-query quantum algorithms for general partial Boolean ***,we present several necessary and sufficient conditions for a partial Boolean function to be computed by exact one-query quantum ***,inspired by these conditions,we discover some new representative functions that can be computed by exact one-query quantum algorithms but have an essential difference from the already known ***,it is worth pointing out that before our work,the known func-tions that can be computed by exact one-query quantum algorithms are all symmetric functions and the quantum algo-rithm used is essentially the Deutsch-Jozsa algorithm,whereas the functions discovered in this paper are generally asym-metric and new algorithms to compute these functions are ***,this expands the class of functions that can be computed by exact one-query quantum algorithms.

关键词： quantum computing quantum query complexity quantum algorithm

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Deep Learning Based Methods for Grading Papaya Fruit by Maturity Level 3

A Comparison of Deep Learning Based Methods for Grading Papa...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Bipin Nair, B.J. Rushab, D. Kruthik, S. School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science Mysuru India

ISBN: (纸本)9798331518592

Papaya is a tropical fruit with high nutritional value. Identifying the maturity level of papaya is important in fruit industries. However, doing this manually by humans is inefficient. To automate this process, we tested two deep-learning models for classifying papaya images into four categories: ripe, partially ripe, unripe, and decayed. Previous works are focused on the classification of papaya fruit maturity into unmatured (unripe), partially mature (partially ripe), and mature(ripe), we have extended this to one more class i.e. Decayed. This class inclusion plays a vital role in distinguishing the decayed fruits from healthy ones in real-world applications and also helps in preventing the distribution of compromised produce, thereby maintaining quality control in the food supply. The primary goal is to find the best-performing deep learning model for accurate classification, which is essential for applications in agriculture and the food industry for quality control and automated sorting. We tested well-known Deep learning models: DenseNet121 and InceptionV3. Both the trained models are evaluated on the dataset comprising 1809 images. Each model's performance is evaluated using a different validation set and its classification accuracy. Our experimental results shows that the InceptionV3 model performs with the highest accuracy at 99.37% at 90:10 train-test ratio with batch size 16 under 40 Epochs, demonstrating superior performance in distinguishing between the four categories of papaya images. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A study on artificial intelligence for monitoring smart environments

引用

Materials Today: Proceedings 2023年 80卷 2009-2013页

作者： D., Karthika Department of Computer Science School of Computing Science Vels Institute of Science Technology & Advanced Studies Tamil Nadu Chennai India

Wireless networking has made enormous improvements. These developments have brought about new paradigms of wireless networking and communications Environmental protection has been in recent years a more intelligent and linked system for all facets of a global city. With the rise in data gathering, machine learning (ML) approaches can be used to boost the knowledge and the skill of an application. As the numbers increase and technology develops, the number of available data increases. Smart collection and interpretation of these Big Data is the underground to the rising of smart Internet of Things IoT apps. This study discovers the diverse methods of machine learning that resolve data difficulties in smart cities. The discussion takes place on applications such as air quality, water pollution, radiation pollution, smart buildings, smart transport, etc., which pose genuine environmental challenges. Adequate monitoring is needed to ensure sustainable growth in the world by safeguarding a healthy society. The potential and challenges in particular the role of machine learning technology for the Internet of Things and Big Data Analytics. © 2021

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

RSSI-Based 3D Wireless Sensor Node Localization Using Hybrid T Cell Immune and Lotus Optimization

引用

computers, Materials & Continua 2024年第12期81卷 4833-4851页

作者： Weiwei Hu Kiran Sree Pokkuluri Rajesh Arunachalam Bander A.Jabr Yasser A.Ali Preethi Palanisamy School of Information Engineering Technology&MediaUniversity of HenanKaifeng475004China Department of Computer Science and Engineering Shri Vishnu Engineering College forWomenBhimavaram534202Andhra PradheshIndia Department of Electronics and Communication Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesThandalam602105ChennaiIndia Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Department of Computer Science and Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesThandalam602105ChennaiIndia

Wireless Sensor Network(WSNs)consists of a group of nodes that analyze the information from surrounding *** sensor nodes are responsible for accumulating and exchanging ***,node local-ization is the process of identifying the target node’s *** this research work,a Received Signal Strength Indicator(RSSI)-based optimal node localization approach is proposed to solve the complexities in the conventional node localization ***,the RSSI value is identified using the Deep Neural Network(DNN).The RSSI is conceded as the range-based method and it does not require special hardware for the node localization process,also it consumes a very minimal amount of cost for localizing the nodes in 3D *** position of the anchor nodes is fixed for detecting the location of the ***,the optimal position of the target node is identified using Hybrid T cell Immune with Lotus Effect Optimization algorithm(HTCI-LEO).During the node localization process,the average localization error is minimized,which is the objective of the optimal node *** the regular and irregular surfaces,this hybrid algorithm effectively performs the localization *** suggested hybrid algorithm converges very fast in the three-dimensional(3D)*** accuracy of the proposed node localization process is 94.25%.

关键词： Sensor node localization received signal strength indicator 3D wireless sensor network deep neural network average localization error and hybrid T cell immune with lotus effect optimization 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：