检索结果-内蒙古大学图书馆

11th International Conference on Electrical engineering, computer Science and informatics, EECSI 2024

作者： Mulyati Stiawan, Deris Widhiarso, Wijang Budiarto, Rahmat Multi Data Palembang University & Faculty of Engineering Universitas Sriwijaya Department of Information System Palembang Indonesia Sriwijaya University Faculty of Computer Science Palembang Indonesia Multi Data Palembang University Department of Informatics Palembang Indonesia College of Computer Science & IT Albaha University Saudi Arabia

ISBN: (纸本)9798350355314

Effective and efficient cyber incident handling is crucial for maintaining the security of information systems and organizational data. This research aims to develop a priority-based cyber incident handling method by adopting the NIST 2.0 framework and utilizing machine learning classification algorithms. This method enables organizations to quickly and accurately identify and respond to incidents based on threat levels and impact, focusing resources on the most critical incidents. The research employs the Support Vector Machine (SVM) classification algorithm to determine incident priorities. The study is still developing for handling cyber incidents, followed by testing and evaluating the system prototype within organizations. Initial results indicate that the priority-based approach using the SVM classification algorithm achieves a True Positive (TP) Rate of 0.999 and a False Positive (FP) Rate of 0.008, with a correlation of 98.88%, resulting in excellent performance in identifying positive cases and a low error rate. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

A computer Vision System to Classify the Quality of Central Sulawesi Cocoa Beans Using Convolutional Neural Networks (CNN) 3

A Computer Vision System to Classify the Quality of Central ...

引用

3rd International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2023

作者： Angreni, Dwi Shinta Anshori, Yusuf Wirdayanti Arifin, Suci Ramadhani Humaira, Fitrah Maharani Universitas Tadulako Faculty of Engineering Departement of Information Technology Palu Indonesia Universitas Dipa Makassar Departement of Informatics Engineering Makassar Indonesia Politeknik Elektronika Negeri Surabaya Departemen of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350394559

The cocoa industry serves as a vital economic pillar, holding a pivotal role in the daily lives of farmers in Central Sulawesi. However, a prevailing challenge for cocoa cultivators in this region resides in the inherently subjective nature of cocoa bean quality assessment, often necessitating the involvement of a substantial human workforce. Addressing this challenge requires the implementation of computer vision technology capable of autonomously grading cocoa bean quality. Such a system not only expedites the evaluation process but also enhances the precision and consistency in determining the quality of the beans. The study employed Convolutional Neural Networks (CNN) methodology to analyze images of cocoa beans sourced from Central Sulawesi farmers. The research demonstrated a remarkable accuracy of 94.66%, accompanied by a minimal loss of 0.1195. The model demonstrates strong performance on both training and validation sets, indicating effective learning of relevant patterns. Consistent accuracy and loss trends across epochs signify stable training without notable overfitting or underfitting. The minimal gap between training and validation metrics reflects the model's effective generalization to unseen data. This technological integration promises to revolutionize cacao quality assessment, offering a sophisticated and efficient solution for the benefit of Central Sulawesi's cacao farming community. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Creating Robust and Secure Decentralized Autonomous Organizations (DAOs) for the Metaverse Using Blockchain Technology 6th

Creating Robust and Secure Decentralized Autonomous Organiza...

引用

6th International Conference on Recent Innovations in Computing, ICRIC 2023

作者： Goyal, S.B. Rajawat, Anand Singh Shaari, Rosnizah Bt Verma, Chaman Singh, Pradeep Kumar City University Petaling Jaya Malaysia School of Computer Sciences and Engineering Sandip University Nashik India City University Petaling Jaya46100 Malaysia Department of Media and Educational Informatics Faculty of Informatics Eötvös Loránd University Budapest1053 Hungary Department of Computer Science and Engineering Central University of Jammu Jammu India

ISBN: (纸本)9789819778614

This paper presents an all-encompassing exploration on the conception and implementation of sturdy and impregnable decentralized autonomous organizations (DAOs) custom-made for the Metaverse, capitalizing on the capabilities of blockchain technology. The Metaverse, an incorporation of virtual shared space, is evolving at a rapid pace, necessitating governance structures that are decentralized, transparent, efficient, and impervious to points of failure. DAOs, governed by smart contracts and consensus mechanisms, offer a promising resolution to this exigency. To commence by scrutinizing the distinctive prerequisites of the Metaverse milieu, encompassing scalability, interoperability, and user involvement. Subsequently, we delve into the framework of DAOs, accentuating blockchain’s essential role in ensuring security, transparency, and decentralized governance. Our approach involves a stratified method to DAO design, amalgamating blockchain’s immutable ledger, smart contract functionality, and advanced cryptographic techniques to safeguard against potential hazards and susceptibilities that are specific to the Metaverse. To propose innovative mechanisms for decentralized decision-making, asset management, and dispute resolution within DAOs, ensuring consonance with the dynamic and engrossing essence of the Metaverse. Moreover, to tackle the obstacles of incorporating DAOs with existing Metaverse platforms, with a focus on interoperability between distinct blockchain protocols and virtual domains. Our proposed model encompasses a collection of exemplary practices for DAO deployment in the Metaverse, ensuring adaptability and resilience. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserved learning from non-i.i.d data in fog-assisted IoT:A federated learning approach

引用

Digital Communications and Networks 2024年第2期10卷 404-415页

作者： Mohamed Abdel-Basset Hossam Hawash Nour Moustafa Imran Razzak Mohamed Abd Elfattah Faculty of Computers and Informatics Zagazig UniversityZagazigSharqiyah44519Egypt School of Engineering and Information Technology University of New South Wales@ADFACanberraACT2600Australia Deakin University Geelong Waurn Ponds CampusAustralia Computer Science Department Misr Higher Institute for Commerce and ComputersMansoura35511Egypt

With the prevalence of the Internet of Things(IoT)systems,smart cities comprise complex networks,including sensors,actuators,appliances,and cyber *** complexity and heterogeneity of smart cities have become vulnerable to sophisticated cyber-attacks,especially privacy-related attacks such as inference and data poisoning *** Learning(FL)has been regarded as a hopeful method to enable distributed learning with privacypreserved intelligence in IoT *** though the significance of developing privacy-preserving FL has drawn as a great research interest,the current research only concentrates on FL with independent identically distributed(i.i.d)data and few studies have addressed the non-i.i.d *** is known to be vulnerable to Generative Adversarial Network(GAN)attacks,where an adversary can presume to act as a contributor participating in the training process to acquire the private data of other *** paper proposes an innovative Privacy Protection-based Federated Deep Learning(PP-FDL)framework,which accomplishes data protection against privacy-related GAN attacks,along with high classification rates from non-i.i.d ***-FDL is designed to enable fog nodes to cooperate to train the FDL model in a way that ensures contributors have no access to the data of each other,where class probabilities are protected utilizing a private identifier generated for each *** PP-FDL framework is evaluated for image classification using simple convolutional networks which are trained using MNIST and CIFAR-10 *** empirical results have revealed that PF-DFL can achieve data protection and the framework outperforms the other three state-of-the-art models with 3%–8%as accuracy improvements.

关键词： Privacy preservation Federated learning Deep learning Fog computing Smart cities

来源：评论

学校读者我要写书评

暂无评论

Stress Detection Using EEG Signals: A SVM-Based Classification and Feature Selection Approach

Stress Detection Using EEG Signals: A SVM-Based Classificati...

引用

Electrical Power, Electronics, Communications, Controls and informatics Seminar (EECCIS)

作者： Fi Imanur Sifaunnufus Fitra Abdurrachman Bachtiar Barlian Henryranu Prasetio Department of Computer Engineering Faculty of Computer Science Brawijaya University Malang Indonesia Department of Informatics Engineering Faculty of Computer Science Brawijaya University Malang Indonesia

ISBN: (数字)9798350379914

ISBN: (纸本)9798350379921

Stress is a problem with various adverse effects, such as mental disorders and suicide. With these problems arising, a stress detection system is needed as an initial examination of the level of stress experienced. Generally, stress detection is done with a stress test at a hospital. However, medical examinations done in the hospital require high costs. Another alternative to examine stress levels is by using a biosignal electroencephalogram (EEG), which provides more objective and accurate results. In addition, there is a need to develop a portable device that can be used to detect stress. This study tries to detect stress levels using EEG Signals. The data used in this study is primary data that simulates several stress-level activities. In total, 55 subjects participated in this stress detection research. The received signal goes through preprocessing to clean it from noise and artifacts. The data will be extracted using Power Spectral Density (PSD) into power value for each signal frequency. The preprocessed input signals are then classified into indications of stress levels. This study uses Random Forest, SVM, and Decision Tree. The model is stored on a portable system with Raspberry Pi as the main component. EEG signals are taken using electrodes on Muse 2 and sent to the system. The classification model generates predicted stress levels and is displayed on a 16×2 LCD. SVM as the best model test result achieved a testing accuracy of 1, and an average computation time of 0.92.

关键词： Support vector machines Seminars Accuracy Hospitals Computational modeling Human factors Brain modeling Electroencephalography Random forests Testing

来源：评论

学校读者我要写书评

暂无评论

Internal Validity Index for Fuzzy Clustering Based on Relative Uncertainty

引用

computers, Materials & Continua 2022年第8期72卷 2909-2926页

作者： Refik Tanju Sirmen Burak Berk Üstündag Graduate School of Science Engineering&Technology Istanbul Technical UniversityIstanbul34469Turkey Faculty of Computer&Informatics Istanbul Technical UniversityIstanbul34469Turkey

Unsupervised clustering and clustering validity are used as essential instruments of data *** clustering being realized under uncertainty,validity indices do not deliver any quantitative evaluation of the uncertainties in the suggested ***,validity measures may be biased towards the underlying clustering ***,neglecting a confidence requirement may result in *** the absence of an error estimate or a confidence parameter,probable clustering errors are forwarded to the later stages of the ***,having an uncertainty margin of the projected labeling can be very fruitful for many applications such as machine ***,the validity issue was approached through estimation of the uncertainty and a novel low complexity index proposed for fuzzy *** involves only uni-dimensional membership weights,regardless of the data dimension,stipulates no specific distribution,and is independent of the underlying similarity *** tests and comparisons returned that it can reliably estimate the optimum number of partitions under different data distributions,besides behaving more robust to over ***,in the comparative correlation analysis between true clustering error rates and some known internal validity indices,the suggested index exhibited the highest strong *** relationship has been also proven stable through additional statistical acceptance *** the provided relative uncertainty measure can be used as a probable error estimate in the clustering as ***,it is the only method known that can exclusively identify data points in dubiety and is adjustable according to the required confidence level.

关键词： Machine learning data science clustering validity fuzzy clustering uncertainty intelligent systems data analytics

来源：评论

学校读者我要写书评

暂无评论

A Neutrosophic based C-Means Approach for Improving Breast Cancer Clustering Performance

引用

Neutrosophic Sets and Systems 2023年 53卷 317-330页

作者： Abdelhafeez, Ahmed Mohamed, Hoda K Maher, Ali Abdelmonem, Ahmed Faculty of Information Systems and Computer Science October 6th University Cairo12585 Egypt Faculty of Engineering Ain shams University Cairo11566 Egypt Military Technical College Cairo18711 Egypt Faculty of computers and informatics Zagazig University Zagazig11544 Egypt

Breast cancer is among the most prevalent cancers, and early detection is crucial to successful treatment. One of the most crucial phases of breast cancer treatment is a correct diagnosis. Numerous studies exist about breast cancer classification in the literature. However, analyzing the cancer dataset in the context of clusterability for unsupervised modeling is rare. This work analyzes pointedly the breast cancer dataset clusterability via applying the widely used c-means clustering algorithm and its evolved versions fuzzy and neutrosophic ones. An in-depth comparative study is conducted utilizing a set of quantitative and qualitative clustering efficiency metrics. The study's outcomes divulge the presented neutrosophic c-means clustering superiority in segregating similar breast cancer instances into clusters © 2023, Neutrosophic Sets and *** Rights Reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

MobileDNN: Leveraging the Potential of Hybrid MobileNetV2-DNN for Advanced Image Analysis

MobileDNN: Leveraging the Potential of Hybrid MobileNetV2-DN...

引用

2024 International Conference on Science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Ogundokun, Roseline Oluwaseun Maskeliunas, Rytis Damasevicius, Robertas Adebiyi, Marion Olubunmi Landmark University Department of Computer Science Omu Aran Nigeria Kaunas University of Technology Department of Multimedia Engineering Lithuania Kaunas University of Technology Faculty of Informatics Kaunas Lithuania

ISBN: (纸本)9798350358155

computer vision systems designed for posture recognition could offer valuable solutions in the healthcare sector, improving healthy ageing and supporting elderly individuals in their daily routines. One area of interest is the automatic detection of falls, which has garnered attention from computer vision and pattern recognition communities. While many existing methods rely on wearable sensors, which demonstrate high accuracy in fall detection, some individuals may be reluctant to wear such devices. Consequently, alternative approaches, such as vision-based techniques, have been developed. The proposed method utilizes a vision-based system that employs a convolutional neural network (CNN) to recognize and categorize various postures (e.g., sitting, lying, standing) in each frame, if available. This approach begins by detecting the person in the frame, applying background subtraction for human body shape extraction, and associating each daily activity with the extracted shape. The proposed model achieved an accuracy of 93.75%, which shows an outstanding performance over existing models. Subsequently, it estimates bounding boxes encompassing the predicted person's body shape. Overall, the proposed technique shows promising results for indoor monitoring systems. © 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

Interactive Multimodal Learning: Towards Using Pedagogical Agents for Inclusive Education

Interactive Multimodal Learning: Towards Using Pedagogical A...

引用

2023 IEEE International Humanitarian Technology Conference, IHTC 2023

作者： Al Omoush, Muhammad H. Salih, Sumaia E. Kishore, Sameer Mehigan, Tracey Dublin City University Faculty of Engineering and Computing Dublin Ireland Dublin Ireland Middlesex University Department of Computer Engineering and Informatics Dubai United Arab Emirates

ISBN: (纸本)9798350314311

A pedagogical agent is an animated interface in an interactive online learning environment. Its role involves guiding users through instructions and participating in direct discussions. Numerous research studies underline the advantages of pedagogical agents in delivering instruction, tailoring learning experiences, and promoting inclusivity. The authors utilize machine learning techniques to develop an interactive multimodal application (combining visuals and audio) designed as a pedagogical agent. This application is intended to assist in teaching primary school students (aged 6 to 8) the recognition of colors and letters. Additionally, it incorporates voice interaction to assess their learning progress. The overarching objective of this pedagogical agent is to seamlessly integrate artificial intelligence (AI) into educational settings, thereby amplifying student engagement and motivation during the learning process. This paper will explore the journey of creating a machine learning-based application and its potential utility in supporting educators. Furthermore, the authors will investigate potential augmentations that could render the application more adept at aiding students with dyslexia. The paper will emphasize the significance of human-computer interaction (HCI), as it significantly shapes pedagogical agents' design and operational aspects. © 2023 IEEE.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Divide-and-train: A new approach to improve the predictive tasks of bike-sharing systems

引用

Mathematical Biosciences and engineering 2024年第7期21卷 6471-6492页

作者： Ali, Ahmed Salah, Ahmad Bekhit, Mahmoud Fathalla, Ahmed Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Higher Future Institute for Specialized Technological Studies Cairo3044 Egypt College of Computing and Information Sciences University of Technology and Applied Sciences Ad-Dhahirah Ibri Oman Zagazig University Department of Computer Science Faculty of Computers and Informatics Sharkeya Zagazig Egypt Sydney Australia Kaplan Business School Sydney Australia Department of Mathematics Faculty of Science Suez Canal University Ismailia Egypt

Bike-sharing systems (BSSs) have become commonplace in most cities worldwide as an important part of many smart cities. These systems generate a continuous amount of large data volumes. The effectiveness of these BSS systems depends on making decisions at the proper time. Thus, there is a vital need to build predictive models on the BSS data for the sake of improving the process of decision-making. The overwhelming majority of BSS users register before utilizing the service. Thus, several BSSs have prior knowledge of the user’s data, such as age, gender, and other relevant details. Several machine learning and deep learning models, for instance, are used to predict urban flows, trip duration, and other factors. The standard practice for these models is to train on the entire dataset to build a predictive model, whereas the biking patterns of various users are intuitively distinct. For instance, the user’s age influences the duration of a trip. This endeavor was motivated by the existence of distinct user patterns. In this work, we proposed divide-and-train, a new method for training predictive models on station-based BSS datasets by dividing the original datasets on the values of a given dataset attribute. Then, the proposed method was validated on different machine learning and deep learning models. All employed models were trained on both the complete and split datasets. The enhancements made to the evaluation metric were then reported. Results demonstrated that the proposed method outperformed the conventional training approach. Specifically, the root mean squared error (RMSE) and mean absolute error (MAE) metrics have shown improvements in both trip duration and distance prediction, with an average accuracy of 85% across the divided sub-datasets for the best performing model, i.e., random forest. © 2024 the Author(s).

关键词： Forecasting

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：