检索结果-内蒙古大学图书馆

Autotrack: a framework for query-based vehicle tracking and retrieval from CCTV footages using machine learning at the edge

引用

International Journal of information technology (Singapore) 2023年第7期15卷 3827-3837页

作者： Sreedhar, Sreela Philip, Abin Oommen Sreeja, M.U. Department of Computer Science and Engineering Toc H Institute of Science and Technology Ernakulam India Department of Electronics Cochin University of Science and Technology Kochi India Department of Computer Science and Engineering-Cybersecurity Indian Institute of Information Technology Kottayam (IIIT Kottayam) Kottayam India

Automobile theft and hit and run incidents have become ever rampant than before urging the need for automated tracking systems. However, prompt detection of the vehicle involved in incident and recovery of the stolen vehicle is crucial as these are immediately forged to reduce the chances of getting caught. Hence, the proposed model puts forth a query-based framework to intelligently detect and track vehicles from CCTV surveillance footages using queries involving custom input features such as model, make, colour and license plate number. The model uses a combination of techniques for detecting the vehicle make and model, tracking vehicle, and for identifying the license plate number based on You Only Look Once (YOLO), Kalman filters, and Tesseract respectively. Further, the model performs vehicle detection and tracking from multiple surveillance videos which can ensure that the suspicious vehicle which is reported of either theft, license plate forgery or any unusual activity like hit and run cases is located immediately. The detection model is trained and deployed on edge device integrated to CCTVs and hence overcoming the drawbacks associated with a centralized system. The performance of the proposed vehicle detection model compared to baseline models on the basis of popular classification metrics precision, recall and f1-score proves the superiority of the proposed model compared to the existing ones. Additional experimental analysis of the entire framework further establishes the relevance of the combination of selected input features as well as emphasizes the significance of query-based models over its generic counterparts. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Edge computing Kalman filter Object detection Tracking Vehicle detection YOLO

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning for Heterogeneous Residential Load Forecasting

引用

Big Data Mining and Analytics 2023年第4期6卷 421-432页

作者： Xiaodong Qu Chengcheng Guan Gang Xie Zhiyi Tian Keshav Sood Chaoli Sun Lei Cui the Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Taiyuan University of Science and TechnologyTaiyuan 030024China the Faculty of Engineering and Information Technology University of Technology SydneyUltimo 2007Australia the Centre for Cyber Security Research and Innovation Deakin UniversityMelbourne 3125Australia the School of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan 030024China

Accurate load forecasting is critical for electricity production,transmission,and *** learning(DL)model has replaced other classical models as the most popular prediction ***,the deep prediction model requires users to provide a large amount of private electricity consumption data,which has potential privacy *** nodes can federally train a global model through aggregation using federated learning(FL).As a novel distributed machine learning(ML)technique,it only exchanges model parameters without sharing raw ***,existing forecasting methods based on FL still face challenges from data heterogeneity and privacy ***,we propose a user-level load forecasting system based on personalized federated learning(PFL)to address these *** obtained personalized model outperforms the global model on local ***,we introduce a novel differential privacy(DP)algorithm in the proposed system to provide an additional privacy *** on the principle of generative adversarial network(GAN),the algorithm achieves the balance between privacy and prediction accuracy throughout the *** perform simulation experiments on the real-world dataset and the experimental results show that the proposed system can comply with the requirement for accuracy and privacy in real load forecasting scenarios.

关键词： load forecasting personalized federated learning differential privacy

来源：评论

学校读者我要写书评

暂无评论

Automated Driving License Testing system 4

Automated Driving License Testing System

引用

4th International Conference on Power, Energy, Control and Transmission systems, ICPECTS 2024

作者： Rachel, Sheeba Sanjay Krishna, B. Saranya, A. Yashika, R. Sri Sairam Engineering College Department of Information Technology Chennai India Sri Sairam Institute of Technology Department of Computer Science Chennai India

ISBN: (纸本)9798331508845

The Automated Driving License Test system (ADLTS) is a cutting-edge project that aims to automate and enhance the process of evaluating candidates for driving licenses. It uses a combination of sensors and algorithms to objectively assess an applicant's driving skills and provide instant results on their performance. The ADLTS is a forward-looking approach to modernizing driving license testing in an era of evolving automotive *** applicants are fingerprinted with fingerprint sensor to ensure that no one else can impersonate them. This application and authentication process is handled by software application. The testing procedure is monitored by three sensors: a proximity sensor, an RPM sensor, and a human face identification system powered by OpenCV, a Machine Learning Library. Proximity sensor is used to monitor the distance between the vehicle and the external objects, while the RPM sensor is used to determine if the vehicle is turned on thereby monitoring the status of the engine. The Face Detection sensor monitors the presence of candidates in the vehicle. Violations of these testing procedures result in license rejection. The license is approved once the car is successfully parked without violating the *** sensors and the software system are integrated with a user-friendly UI to form a comprehensive model. This automated system improves safety, consistency, and cost efficiency in the licensing process, reducing the reliance on human evaluators and the risk of accidents during testing. © 2024 IEEE.

关键词： Proximity sensors

来源：评论

学校读者我要写书评

暂无评论

The Smart and Secured Communication Using Applied Cryptography Algorithms 5th

The Smart and Secured Communication Using Applied Cryptograp...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Agarwal, Trapty Jebakumari, S. Adlin Hemlata Ayesha, Amreen Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science and Information Technology Jain University Karnataka Bangalore India Department of Computer Science & Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Manduwala Dehradun Navgaon India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India

ISBN: (纸本)9789819780426

This paper describes the implementation of a at ease communication device the usage of an implemented cryptography algorithm. The gadget is designed to provide comfy statistics and voice communique between endpoints using techniques consisting of encryption and digital signature. The applied cryptography set of rules includes primary components, the symmetric and the uneven algorithms. The symmetric algorithms, along with AES and DES, are used for statistics encryption, even as the uneven algorithms, which include RSA and DSA, are used for virtual signature. The proposed gadget additionally focuses on security of physical places to defend the important thing exchange by means of the use of physical access control measures which include biometric identification. The system additionally employs advanced safety strategies together with message authentication codes and protection protocols like SSL/TLS. The device is examined for robustness and safety using real communique experiments. The results confirm that the proposed machine is cozy and green in supplying comfortable communication among endpoints. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

Towards Smart Farming: Simulation Framework to Exploit Network Connectivity for End-to-End Data Transmission 14

Towards Smart Farming: Simulation Framework to Exploit Netwo...

引用

14th International Conference on Software, Knowledge, information Management and Applications, SKIMA 2022

作者： Huo, Dongyang Ravana, Sri Devi Malik, Asad Waqar Rahman, Anis Ur Ahmedy, Ismail University of Malaya Faculty of Computer Science & Information Technology Department of Information Systems Kuala Lumpur Malaysia Department of Computing Islamabad Pakistan University of Malaya Faculty of Computer Science & Information Technology Department of Computer Systems & Technology Kuala Lumpur Malaysia

ISBN: (纸本)9781665493345

Traditional agriculture is highly dependent on human participation and experience. Therefore, it is not possible to guarantee crop yield and quality while expanding the production scale. In recent years, based on the continuous development and innovation of IoT and ICT technologies, the concept of smart farming has started to receive the attention of researchers and farmers. However, many existing smart agriculture applications and research are conducted under controlled environments such as greenhouse farming, vertical farming, and hydroponic farming, etc. Few studies have shifted attention to large-scale arable agriculture, thus neglecting the scalability of the system. This work presents a simulation stack (digital mapping) in which the results of running the simulation model in a large-scale class of real-world scenarios are used to enhance the further performance of the proposed farming system in large-scale scenarios. © 2022 IEEE.

关键词： Hydroponics

来源：评论

学校读者我要写书评

暂无评论

Simultaneous segmentation and classification of colon cancer polyp images using a dual branch multi-task learning network

引用

Mathematical Biosciences and Engineering 2024年第2期21卷 2024-2049页

作者： Li, Chenqian Liu, Jun Tang, Jinshan School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan430065 China Department of Health Administration and Policy College of Public Health George Mason University FairfaxVA22030 United States

Accurate classification and segmentation of polyps are two important tasks in the diagnosis and treatment of colorectal cancers. Existing models perform segmentation and classification separately and do not fully make use of the correlation between the two tasks. Furthermore, polyps exhibit random regions and varying shapes and sizes, and they often share similar boundaries and backgrounds. However, existing models fail to consider these factors and thus are not robust because of their inherent limitations. To address these issues, we developed a multi-task network that performs both segmentation and classification simultaneously and can cope with the aforementioned factors effectively. Our proposed network possesses a dual-branch structure, comprising a transformer branch and a convolutional neural network (CNN) branch. This approach enhances local details within the global representation, improving both local feature awareness and global contextual understanding, thus contributing to the improved preservation of polyp-related information. Additionally, we have designed a feature interaction module (FIM) aimed at bridging the semantic gap between the two branches and facilitating the integration of diverse semantic information from both branches. This integration enables the full capture of global context information and local details related to polyps. To prevent the loss of edge detail information crucial for polyp identification, we have introduced a reverse attention boundary enhancement (RABE) module to gradually enhance edge structures and detailed information within polyp regions. Finally, we conducted extensive experiments on five publicly available datasets to evaluate the performance of our method in both polyp segmentation and classification tasks. The experimental results confirm that our proposed method outperforms other state-of-the-art methods. ©2024 the Author(s), licensee AIMS Press.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Mode Collapse Alleviation of Reinforcement Learning-based GANs in Drug Design

Mode Collapse Alleviation of Reinforcement Learning-based GA...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Jiang, Zongli Wang, Zhenbo Zhang, Jinli Wub, Man Li, Chen Yamanishi, Yoshihiro Beijing University of Technology Faculty of Information Technology China Keio University Department of Information and Computer Science Japan Nagoya University Graduate School of Informatics Japan

ISBN: (纸本)9798350337488

De novo drug design is a challenging task that involves understanding the principles of chemistry, chemical properties, and the rules that govern molecular interactions. Deep learning-based generative models, such as MolGAN, offer a promising approach for generating new molecules with the desired chemical properties from molecular graphs. Such models often combine a discrete generative adversarial network (GAN) and reinforcement learning (RL) to produce highly valid and novel molecules. However, the severe mode collapse problem leads to low performance. This study aims to alleviate and investigate the effect of multiple factors on mode collapse. We conducted experiments on different sampling methods, training epochs, and datasets of various volumes and evaluated the experimental results using performance metrics such as validity, uniqueness, novelty, and diversity. The experimental results demonstrate that noise sampling distributions, training epochs, and training data volumes affect performance. The experimental results provide a direction for mitigating the mode collapse problem for RL-based discrete GANs. © 2023 IEEE.

关键词： Generative adversarial networks (GANs) Mode collapse Molecular generation Reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Enhancement of Standard Classifier Performance by Resolving Class Imbalance Issue Using Smote-Variants Over Multiple Medical Datasets

引用

SN computer science 2025年第3期6卷 1-30页

作者： Kumar, Vinod Kumar, Ravi Kant Singh, Sunil Kumar School of Computer Applications and Information Technology Galgotias University Uttar Pradesh Greater Noida India Department of Computer Science and Engineering SRM University AP Andhra Pradesh Guntur India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India karnataka Bengaluru India

In the era of machine learning we are solving the classification problems by training the labeled classes. But sometimes due to insufficient data in some of the training classes, the system training is inadequate for these minority classes. In this case the output for the classes obtained from the less amount of trained data are miserably inappropriate and biased towards the classes having more data. This problem is known as a class imbalance problem. In such cases, standard classifiers tend to be overpowered by the expansive classes and disregard the little ones. As a result, the performance of machine learning and the deep learning algorithms are also reducing and sometimes highly unacceptable too, mainly if it is related to crucial data like medical and health related. Though various researchers provided some methods to solve this problem but mostly they are problem specific and suitable with the specific classifier only. To find a generalized and effective solution to this problem, we have applied various smote variants for solving the imbalanced factors in dataset and finally improved the performance of the various machine learning and deep learning algorithms. We have experimented and analyzed the effects of SMOTE variants on various machine learning techniques over six standard medical datasets. We have found that SMOTE variants are very effective, and they improve the standard performance measures (Accuracy, Precision, Recall and F1-Score). Additionally, based on our research, it is feasible to determine which smote variation works best with machine learning methods and datasets. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Class imbalanced Classifiers Machine learning Medical datasets Smote variants

来源：评论

学校读者我要写书评

暂无评论

Detecting the Abuse of Cloud Services for C&C Infrastructure Through Dynamic Analysis and Machine Learning

Detecting the Abuse of Cloud Services for C&C Infrastructure...

引用

2024 International Symposium on Networks, computers and Communications, ISNCC 2024

作者： Al Lelah, Turki Theodorakopoulos, George Javed, Amir Anthi, Eirini Schaol of Computer Science and Informatics Cardiff University Cardiff United Kingdom Jubail Industrial College Department of Computer Science and Information Technology Jubail Saudi Arabia

ISBN: (纸本)9798350364910

Cybercriminals increasingly abuse cloud and legitimate services (CLS) as covert command and control (C&C) infrastructure to orchestrate malicious operations and evade detection. This paper addresses the critical challenge of detecting such abuse of cloud platforms. We introduce a detection system that integrates dynamic analysis with Machine Learning (ML) to accurately distinguish between benign and malicious interactions with cloud services. By utilising a comprehensive data set from VirusTotal, the system uses advanced feature extraction techniques from both host behaviour and network traffic, using Cuckoo and Triage sandboxes to extract behaviors, to develop a detection model. The results demonstrate that the model achieves nearly 98% accuracy in identifying cloud service abuse, substantially outperforming previous efforts. Furthermore, we evaluate the model's robustness against adversarial attacks that aim to decrease accuracy by manipulating the feature values. Comparative evaluations show that our method maintains a higher detection accuracy under attack compared to related systems. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Cross-Industry Standard Process For Data Mining (CRISP-DM) For Discovering Association Rules in Graduate Tracer Study Data of Islamic Higher Education Institution 11

Cross-Industry Standard Process For Data Mining (CRISP-DM) F...

引用

11th International Conference on Cyber and IT Service Management, CITSM 2023

作者： Lathifah, Ari Arham, Zainul Hasanati, Nidaul Zulfiandri Nurmiati, Evy Uin Syarif Hidayatullah Science and Technology Faculty Information System Department Jakarta Indonesia

ISBN: (纸本)9798350305968

The Career Development Center (CDC) at UIN Syarif Hidayatullah Jakarta faces challenges when designing development programs for its diverse graduate groups, including those employed, pursuing further studies, or engaged in entrepreneurship. The complexity of tracer study data hampers the identification of prevailing association patterns. This study aims to uncover these patterns within UIN Syarif Hidayatullah Jakarta's tracer study data, aiding the CDC in enhancing career services and target mapping for diverse graduates. The research follows the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology, using the FP-Growth algorithm. Tracer study data from 2021 UIN Syarif Hidayatullah Jakarta graduates (1355 records) is reduced to 925 records for analysis using RapidMiner and Microsoft Excel. The findings reveal association patterns for graduates categorized by employment status, educational pursuits, entrepreneurship endeavors, and advanced graduates not employed. This research offers a structured approach to navigate tracer study data complexities and proposes an action plan for enhancing UIN Syarif Hidayatullah Jakarta Career Center services based on these patterns, providing a systematic guide to address the tracer study data complexity. © 2023 IEEE.

关键词： Data mining

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：