检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Smart information systems and Technologies, SIST 2023

作者： Turken, Gulzat Naizabayeva, Lyazat Satymbekov, Maxatbek Abdiakhmetova, Zukhra Al-Farabi Kazakh National University Department of Computer Science Almaty Kazakhstan International Information Technology University Department of Information System Almaty Kazakhstan

ISBN: (纸本)9798350335040

The data warehouse is based on the development of relational databases, parallel processing and distributed processing technologies, as well as online analytical processing technologies. SAP BW is widely used in many enterprise data warehouses. It can issue reports of enterprises at the group level, manage the group's business operations, help find the laws and trends behind the performance of corporations and ultimately provide decision-making support for decision makers of enterprises. Therefore, how to use the SAP BW model architecture to better realize enterprise data warehouses is one of the hot topics in the data warehouse industry today. For a large corporation, its branches and subsidiaries have deployed multiple sets of enterprise data warehouses. At the same time, because there are multiple sets of data warehouse systems, when the data model needs to be modified at the group level, the data model of the branch also needs to be modified accordingly, and the flexibility of maintenance is poor. Finally, every time the corporation needs to upgrade the version of the data warehouse, it needs to maintain and upgrade the version of the data warehouse of each branch and the maintenance cost is high. Therefore, how to integrate multiple sets of data warehouses distributed in various subsidiaries into a corporation enterprise data warehouse by designing the model hierarchy, so as to ensure the reliability of data, enhance the flexibility of model modification and reduce the cost of data warehouse. This paper completes the design of an enterprise data warehouse of a large corporation, which can be used for the summary and collation of data from multiple branches such as finance and sales of a corporation, effectively improving the efficiency of data utilization and ensuring the authenticity of data. At the same time, through hierarchical design, the problems of poor flexibility in model modification and high system maintenance costs are solved. © 2023 IEEE.

关键词： Data warehouses

来源：评论

学校读者我要写书评

暂无评论

Blockchain Security Using Q-Pragmatic-Sensitive Feature Analysis to Preserve Privacy 3

Blockchain Security Using Q-Pragmatic-Sensitive Feature Anal...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Punithavathi, S. Jeyalaksshmi, S. Vels Institute Of Science Technology & Advanced Studies Department Of Computer Science Chennai India School Of Computing Science Vels Institute Of Science Technology & Advanced Studies Department Of Information Technology Chennai India

ISBN: (纸本)9798350318609

Healthcare data contains large amounts of personal information and is privacy sensitive. The healthcare sector needs privacy protection to keep private and sensitive information safe from unauthorized access. Security problems are raised by fundamental sharing difficulties involving personal information setting to securely forecast sensitive medical data using blockchain technology to address this issue. To solve the problem issue, propose a quasi-sensitive identification of blockchain security using tried-and-true partition fold padding encryption (PFPE) to improve the security of healthcare transactions. The Q-Pragmatic-Sensitive Feature Analysis (QPSFA) determines the terms related to sensitive privacy features. Finally, the Provable Fold Padding Encryption, and the authentication procedure is completed by using an Access Verification-based role to verify it. To ensure that, in a blockchain, the private data are cleansed and placed into data blocks. This suggests that the proposed system outperforms high accuracy up to 90%, as well security up to 94 % high insecurity compared to previous approaches regarding sensitivity and specificity rate performance and prediction accuracy. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Transforming Public Service: AI Chatbot Integration in SI-PEKA Mobile App Development 2

Transforming Public Service: AI Chatbot Integration in SI-PE...

引用

2nd International Symposium on information technology and Digital Innovation, ISITDI 2024

作者： Oksama, Muhammad Haikel Marsal, Arif Hamzah, Muhammad Luthfi Syaifullah Rozanda, Nesdi Evrilyan Universitas Islam Negeri Sultan Syarif Kasim Faculty of Science and Technology Department of Information System Pekanbaru Indonesia

ISBN: (纸本)9798350389241

The rapid advancement of Artificial Intelligence (AI) and its integration into chatbot applications have opened new opportunities for enhancing government administration and public services. However, developing and maintaining chatbots poses significant challenges due to the necessity of proficiency in machine learning and natural language processing, distinguishing it from conventional software development. To address these challenges, this paper introduces SI-PEKA, an innovative public service mobile application featuring the intelligent chatbot, Tanya Jaksa, integrated with advanced AI technology. By leveraging the GPT-4 assistant, facilitated by the OpenAI Platform API, SI-PEKA overcomes these development hurdles, ensuring precise and accurate responses without requiring extensive expertise in AI from developers. Currently, public service delivery at the Public Prosecutor's Office in Pekanbaru is conducted manually. SI-PEKA revolutionizes this process by offering AI-driven legal consultations, thereby enhancing efficiency and convenience for the public. This paper details the development, implementation, and testing of SI-PEKA, highlighting its transformative potential in public service delivery. The development process includes system analysis and design, application implementation, chatbot integration, testing, and iterative improvement. The application underwent rigorous Blackbox testing, achieving a 100% acceptance rate. Results indicate that SI-PEKA functions effectively, providing accurate responses to user queries and demonstrating its efficacy in addressing user needs. This study underscores SI-PEKA's role in driving innovation and adapting to the rapid advancements in AI technology to meet evolving user requirements. © 2024 IEEE.

关键词： Acceptance tests

来源：评论

学校读者我要写书评

暂无评论

A Novel QoS Interval Prediction Method for Web Services Based on Random Walk 4

A Novel QoS Interval Prediction Method for Web Services Base...

引用

4th International Conference on computers and Artificial Intelligence technology, CAIT 2023

作者： Zhang, Tingting Wang, Shiya Tang, Mingdong Nie, Jun Faculty of Computer Guangdong University of Science and Technology Dongguan China Guangdong University of Foreign Studies Faculty of Information Science and Technology Guangzhou China

ISBN: (纸本)9798350326710

The quality of service (QoS) of a candidate service plays a decisive role in Web service recommendation. How to accurately predict the QoS value of a service for specific users is a recent research hotspot. Previous work has focused on using a single value (i.e., a pip value) to predict the QoS of a web service. However, in reality, the QoS value of a web service is often uncertain and varies depending on the user's location, network status, and service load. Using intervals to estimate the QoS value of a web service may be more in line with the needs and realities of the user. Based on the fact that the QoS of a web service is often affected by the location of users and services, some research efforts suggest that additional user or service location information can be used to better address the data sparsity problem. On the other hand, the sparseness of the user's service call data makes the location-aware approach take into account the QoS experience of neighbors who are not very close or similar, which may reduce the prediction accuracy. In order to find a good balance, we propose a random walk-based QoS interval prediction method for Web services, which effectively combines location awareness and collaborative filtering methods. To evaluate the performance of our proposed method, we conducted a series of comprehensive experiments on a real web service dataset. The experimental results showed that our proposed random walk method achieved a better balance between confidence and accuracy compared to other collaborative filtering methods in service recommendation. Similarly, considering the dynamic changes in web service QoS, adopting interval based QoS prediction methods is more convincing than previous methods that predict precise QoS point values. © 2023 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Enhancing Convergence Efficiency in Federated Learning Models 25

Enhancing Convergence Efficiency in Federated Learning Model...

引用

25th International Arab Conference on information technology, ACIT 2024

作者： Samara, Ghassan Elhilo, Ala'Mazen Aljaidi, Mohammad Alamleh, Amneh Al-Mousa, Mohammad Rasmi Batyha, Radwan Alazaidah, Raed Bani-Bakr, Alaa Elrashidi, Ali Zarqa University Faculty of It Department of Computer Science Zarqa Jordan Zarqa University Faculty of Information Technology Zarqa Jordan Zarqa University Faculty of Information Technology Department of Data Science and Ai Zarqa Jordan Zarqa University Department of Cybersecurity Zarqa Jordan Applied Science Private University Faculty of Information Technology Amman Jordan Zarqa University Faculty of It Department of Cyber Security Zarqa Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia

ISBN: (纸本)9798331540012

This study evaluates federated learning models' performance compared to centralized models using the MNIST and CIFAR-10 datasets. Four models were tested: two Federated Learning models and two centralized models. The evaluation focused on accuracy, training rounds, and CO2 emissions, to optimize convergence and reducing energy consumption while maintaining strong model performance. The results showed that Federated learning models outperformed centralized models, with the Federated Learning MNIST model achieving 98.79% accuracy compared to 87.93% for the centralized model. Also, the accuracy of the Federated Learning CIFAR-10 model achieved 91.20% accuracy, exceeding the centralized model's 90.14%. The most accuracy improvements happened in the early training rounds. An adjusted hill-climbing technique was used to the centralized models, decreasing the number of iterations and CO2 emissions without significantly reducing accuracy. © 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

Machine Learning Approaches for Quality Control in Pulp Packaging Manufacturers 20

Machine Learning Approaches for Quality Control in Pulp Pack...

引用

20th International Joint Conference on computer science and Software Engineering, JCSSE 2023

作者： Ceesay, Rattana Boonchoo, Thapana Rattanatamrong, Prapaporn Thammasat University Faculty of Science and Technology Department of Computer Science Pathumthani Thailand

ISBN: (纸本)9798350300505

In molded pulp packaging manufacturing, defect detection and classification processes are critical to ensuring the products meet quality criteria. Yet most manufacturers still rely on human-based manual visual defect classification which can be inconsistent and labor intensive. In this research, we introduce the conjunction of machine vision hardware and machine learning to build a framework for an automated molded pulp packaging defect detection system. The framework consists of two modules. First, the image acquisition module setups appropriate hardware and configuration such t hat high-quality images can be acquired. The second is a machine learning module that constructs a deep learning model with hyper-parameter tuning to automatically detect the defects on the surface of molded pulp products. Our proposed model is based on deep learning model - the Xception architecture, which is recently developed and expected to be more robust on defect detection. In comparison with Traditional machine learning algorithms - SVM and Naive bayes have been widely used in the field of industrial detection. The oriented FAST and rotated BRIEF (ORB) and Bag-of-Visual-Word (BoVW) are implemented for pre-feature extraction. Since molded pulp packaging has obstacles on surface fluctuation by color, grain pulp fiber and non-repeating defect pattern, the Negative Monochrome (NGMC) image preprocessing is proposed to enhance the visibility of defects on the surface and reduce undesired features. The extracted features must be able to describe and distinguish images categories, which could be a limitation for traditional algorithms that required pre-feature extraction. The results demonstrate that the Xception model trained with NGMC images resolution 192x192 and learning rate 0.001 achieved more than 92.98% accuracy and best generalize across datasets from different production lots, which suggests that the robustness of our framework has the potential to be utilized in industrial applica

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Statistical Comparison ARIMA Order Performance In Stock Market 7

Statistical Comparison ARIMA Order Performance In Stock Mark...

引用

7th International Conference on information technology, InCIT 2023

作者： Deemee, Chanatip Ngampis, Kirati Noraset, Thanapon Thaipisutikul, Tipajin Sun, Min-Te Kitchat, Kotcharat Mahidol University Faculty of Information and Communication Technology Thailand National Central University Department of Computer Science and Information Engineering Taiwan

ISBN: (纸本)9798350358698

Stock market forecasting is important for financial decision-making and risk management. Among the various time series models, the Autoregressive (p) Integrated (d) Moving Average (q) (ARIMA) model has been widely adopted for its simplicity and effectiveness in capturing temporal patterns. However, selecting appropriate ARIMA orders remains a crucial and challenging task, impacting the accuracy of predictions. This paper presents a comprehensive statistical comparison of ARIMA order performance in the context of stock market forecasting. We examine the impact of different ARIMA model orders. Our study utilizes historic New York Stock Exchange (NYSE) stock price data. Our findings shed light on the complex interplay between ARIMA parameters and predictive accuracy, offering valuable insights for robust financial forecasting. © 2023 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Automated Generation of Multi-tenant Database systems Based upon system Design Diagrams 5th

Automated Generation of Multi-tenant Database Systems Based ...

引用

5th International Conference on information systems and Management science, ISMS 2022

作者： Camilleri, Rebecca Vella, Joseph G. Department of Computer Information Systems Faculty of Information and Communication Technology University of Malta Msida Malta

ISBN: (纸本)9783031311529

Energetic technological advancements in the past decade, have led to an exponential increase in the amount of data being stored. Consequently, the need for effective Database Management systems (DBMSs) which embody security considerations from the initial stages of database design is imperative in modern information systems development. This prerequisite is further accentuated by the recent transitioning from single tenant information systems to multi-tenant based on public cloud infrastructures. Within this context, this paper proposes a computer-Aided Software Engineering (CASE) tool capable of generating secure database related structures and processes. A comprehensive overview of a specific information system design is provided to the CASE tool by means of entity-relationship diagram, entity life history and dataflow diagram. Subsequently, crucial security controls targeted towards the protection of database objects are incorporated by means of discretionary and role-based access controls. Following the encoding of the system’s design data is adorned with the required security elements, the CASE tool performs an in-depth analysis that aids in the detection of potential security pitfalls. Provided that the database design enhanced with security elements is satisfactory, i.e., all checks conducted are successful, the CASE tool generates Structured Query Language (SQL) language constructs for well-known multi-tenant scenarios. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： information systems

来源：评论

学校读者我要写书评

暂无评论

Transforming Cybersecurity in the Digital Era: The Power of AI 2

Transforming Cybersecurity in the Digital Era: The Power of ...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Mahfuri, Mahmoud Ghwanmeh, Sameh Almajed, Rsha Alhasan, Waseem Salahat, Mohammed Lee, Jin Hie Ghazal, Taher M. International University For Science And Technology Computer And Information Technology Department Damascus Syria American University In The Emirates Department Of Computer Scienc Dubai United Arab Emirates School Of Computer Science And Informatics De Montfort University Dubai Dubai United Arab Emirates College Of Engineering And Technology University Of Science And Technology Of Fujairah Fujairah United Arab Emirates Miracle Clinic Seoul Korea Republic of Khalifa University Centre For Cyber Physical Systems Computer Science Department United Arab Emirates Center For Cyber Security Faculty Of Information Science And Technology Selangor Bangi43600 Malaysia

ISBN: (纸本)9798350394962

In the midst of the digital revolution of the 21st century, cybersecurity has come to be a primary social situation, requiring revolutionary and Innovative solution. To find the proper answer for this pressing demand, AI (AI) has developed as an innovative catalyst that has fundamentally transformed the cybersecurity landscape. The power of AI is exemplified by its ability to process and interpret large and heterogeneous cybersecurity data sets optimizing critical functions such as threat detection, asset prioritization, and vulnerability management beyond human capabilities swiftly and accurately. This transformation is redefining our cybersecurity approach. This paper presents a full exploration of AI's extreme influence on cybersecurity, delving deep into how AI tools not only enhance but often surpass human-mediated processes. By unraveling the intricacies of integrating AI into the realm of cybersecurity, we vividly illustrate AI's potential to anticipate, detect, and proactively mitigate cyber threats, empowering organizations to bolster their digital security. However, it's vital to recognize the essential difficulties of AI. We underline the critical necessity for non-stop human administration and involvement to confirm that cybersecurity processes are in proportion and powerful. Additionally, we mention the probable ethical concerns and underscore the importance of strong authority structures to accelerate accountable and transparent AI usage in cybersecurity. This paper elucidates how AI is revolutionizing cybersecurity techniques, contributing to a more secure and greater secure digital future. It additionally lays the base for current investigation and discourse on the role of AI in cybersecurity - a conversation of growing importance in our unexpectedly advancing digital age. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

PES-DAS: Privacy Enhancing Subset-Data Aggregation Scheme Leveraging Homomorphic Cryptosystem in Fog-Cloud Based IoT Applications

引用

SN computer science 2025年第3期6卷 1-16页

作者： Shukla, Prashant Pandey, Sudhakar Department of Information Technology National Institute of Technology Chhattisgarh Raipur 492010 India School of Computer Science Engineering and Technology Bennett University (The Times Group) Uttar Pradesh Greater Noida India

Fog computing is an emerging technology that many sectors and industries are currently investing in to establish their own real-time and low-latency environments. Unlike the traditional Internet of Things (IoT), the fog-based IoT systems offers improved performance efficiency and enhanced data security by providing local mechanisms for pre-processing, filtering, and forwarding of data. However, the incorporation of fog technologies into the IoT has specific challenges with security and privacy. This is because fog nodes are located at the edge of the network, that may lack full reliability and trustworthiness. This work presents a novel scheme called PHE-SDA for aggregating a subset of response data while preserving privacy. The proposed PHE-SDA scheme is specifically designed for scenarios involving Fog-Cloud based IoT systems. It enables end-users to calculate the total amount of data collected from a certain group of smart devices. The subset is determined through securely calculating the inner product to measure the similarity between the normalized feature vectors of the end user's request and the response from each IoT device. If the inner product surpasses the threshold specified by the user, the data from the IoT device will be securely incorporated into the aggregation process to produce the ultimate outcome. In order to successfully carry out privacy-enhancing subset data aggregation in the Fog-Cloud based IoT system, we employ the Paillier homomorphic cryptography technique to encrypt the user's desired feature vector, similarity threshold, data sensed by IoT device, and some intermediate results. This work is an innovative initiative to effectively address the problem of prioritizing privacy while aggregating subsets in fog-based IoT systems. Subsequently, this work presents a comprehensive analysis and assessment of the effectiveness of the proposed PHE-SDA scheme. The comprehensive evaluation and results indicate that our proposed PHE-SDA scheme succes

关键词： Aggregation scheme Fog-based IoT network Homomorphic encryption Privacy preserving Subset data

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：