No abstract available.
Proceeding Downloads
A Comparison of Deep Learning Methods for Vision-based Fire Detection in Surveillance System
Fire detection by analyzing video and images from surveillance cameras is increasingly being used as an early warning system. Fire detection using video surveillance as input is much more efficient than fire sensors because of the broader coverage area ...
Design and deployment of a customer journey management system: the CJMA approach
- Nam Nguyen Chan,
- Duc Loc Nguyen Vo,
- Cuong Pham-Nguyen,
- Thang Le Dinh,
- Nguyen Anh Khoa Dam,
- Thanh Thoa Pham Thi,
- My Hang Vu Thi
Customer journey management has been recently in high demand across organizations as a means of better understanding customer behavior, predicting user needs, and enhancing customer experience to achieve their business goals. Therefore, there is an ...
Analysis of geometrical features of 3D model based on the surface curvature of a set of point cloud
In this paper, we present a method to analyze features of an unstructured 3D set of points. The method proposed consists in two main stages: 1) From the 3D point input data set, apply an algorithm of sparsity based on octree to subdivide the data ...
Electricity theft Detection in Power Grid with a Hybrid Convolutional Neural Network - Support Vector Machine Model
The losses of the power grid can be divided into two main categories, which are technical and non-technical losses. Non-technical losses, also called commercial losses, are mainly caused by electrical theft. To help utility companies discover the doubts ...
Day-ahead electricity load forecasting based on hybrid model of EEMD and Bidirectional LSTM
Load forecasting has always played a particularly important role in the power industry. In this article, we proposed a hybrid model based on Ensemble Empirical Mode Decomposition (EEMD) and Bidirectional Long Short-Term memory (Bi-LSTM). The original ...
Formalization of Business Processes and Business Rules Model using Colored Petri Nets
Business process modeling is becoming more popular as a way to improve system design and analysis efficiency and quality. As enterprise business processes get more complex and there are more modeling languages, the ability to validate the process model ...
Efficient Complex Valued Neural Network with Fourier Transform on Image Denoising
Denoising has become one of the main topics of study in the Computer Vision domain, since it is useful not only for media applications but also for other domains in Computer Vision. Recently, Complex valued neural networks have shown some capabilities ...
A Testbed Implementation of a Biometric Identity-Based Encryption for IoMT-enabled Healthcare System
Historically, health data was stored locally on the hospital’s server as patient health records, and we had to rely on the planned check-up during doctor’s visits. Now, we can monitor health continuously and in real-time. Remote healthcare monitoring ...
Semi-Decentralized Model for Drone Collaboration on Secure Measurement of Positions
The importance of drone use is increasing in all fields due to several characteristics and advantages they provide, such as saving lives, quality imaging, and being easily controllable. In addition, Unmanned Aerial Vehicle (UAV) prices are going to ...
Data Preservation System using BoCA: Blockchain-of-Custody Application
The recent growth in popularity of blockchains has been primarily fueled by their support of cryptocurrencies and smart contracts. However, a blockchain is primarily a distributed, trustworthy ledger and one of its greatest features is its ability to ...
A Hybrid Deep Learning Approach for Advanced Persistent Threat Attack Detection
Advanced Persistent Threat (APT) attack is one of the most common and costly destructive attacks on the target system. This attack has become a challenge for companies, governments, and organizations’ information security systems. In recent years, ...
Personal health records: Blockchain-based identity management and data ownership
Data privacy and security preservation are essential issues in the public sector and, particularly, in the health and medical sectors. Patients often lose their data and medical history if they must move between hospitals. In these cases, other health ...
An integrated smart wheelchair model: IW Smart Wheelchair with Embedded Smart Home, Navigation and Obstacle Avoidance Systems
A smart wheelchair refers to a Powered Wheelchair (PW) with computers, sensors, and assistive technology attached. Our research is concerned with a Smart Wheelchair with sensing capability, designed to provide global accessibility. This paralyzing ...
Malicious URL Detection Using Streaming Feature Selection
Malicious uniform resource locators (URLs) are one of the most critical cybersecurity challenges. Attackers are constantly working on new ways to generate malicious URLs. Attackers also constantly update the methods they use to trick systems that detect ...
Blockchain-based E-commerce for the COVID-19 economic crisis
The beginning of 2020 is associated with the emergence and spread of the COVID-19 disease. The characteristics of this virus, such as high transmission power and lack of definitive treatment have caused problems in all aspects of organizational ...
Developing a stable house price estimator using regression analysis
Buying a house of their own is a goal of most people, regardless of where they come from and their purchasing power. In order to help people realize this goal within their means, regression techniques such as Multiple linear, Ridge and Lasso regressions ...
Two routers network architecture and scheduling algorithms under packet category classification constraint
The sending and exchanging of data have become essential in the current revolution of industry 4.0 and digital transformation and all aspects of life. Ensuring the security of transmitted data continues to be a critical issue due to the fast advancement ...
A Survey on Deep Learning and Machine Learning for COVID-19 Detection
Coronaviruses are a type of virus that can cause a variety of disorders and exist in different types. COVID-19 is derived from a special type of a respiratory illness caused by the SARS-CoV-2 virus, discovered in 2019. Approximately two years ago, COVID-...
Towards Achieving the 2030 Vision, the Case study of Automating the Food Production Services during the Hajj Season and Quality Control Using the Blockchain Technology
Improving the services provided for the pilgrims is one of the Saudi Arabian government priorities, as well as for each person who works in the agencies of serving them. Food providing is considered one of the main services for the pilgrims. The current ...
Developing an Automatic COVID-19 Diagnostic Care System Using Machine Learning
The newly detected Coronavirus pneumonia, dubbed COVID-19, is highly contagious and pathogenic. To combat this disease, the diagnostic step is mostly carried out utilizing the RT-PCR technique on nasopharyngeal and throat samples with sensitivity values ...
Enhancing Customer Relationship Management Using Association Rule Mining and the Evolutionary Algorithm
Firms are forced to come up with innovative approaches to compete in today’s difficult global market circumstances. The churning of the customer is one of the issues that arise when a company’s customers stop buying from or interacting with them. In ...
The Impact of Quantum Computing on Security in Emerging Technologies
Quantum computing is rapidly shifting from high-tech lab to mainstream commercial use in the next few years, representing the next breakthrough in modern ICT. It is motivated by quantum computer's ability to perform computational tasks with efficiencies ...
An Efficient DeFi-based Data Warehousing Approach in Supply Chain Finance
In today’s world, industries are looking to improve their productivity through effective logistics and supply chain management. The efficiency of the supply chain in dealing with the huge volumes of data plays a key role in the overall performance of ...
IoT-Blockchain in Remote Patient Monitoring
Internet of Things (IoT) and Blockchain technologies have been utilized heavily in diverse domains, including remote patient monitoring (RPM). Expeditious development of wearable IoT medical devices with a variety of functionality, real-time sensory ...
Machine Learning for Botnet Detection: An Optimized Feature Selection Approach
Technological advancements have been evolving for so long, particularly Internet of Things (IoT) technology that has seen an increase in the number of connected devices surpass non IoT connections. It has unlocked a lot of potential across different ...
Deep learning Arabic printed document knowledge extraction
This paper presents how to utilize deep learning to extract knowledge from Arabic printed document images. The fundamental goal of deep learning is automatically extracting significant features from images, eliminating the need for a classic feature ...
Effect of Variability of Orders in an Auction-based Local Energy Market
To achieve a community pool towards net-zero carbon, this study explores the variability of submitted bids and offers in an auction-based local energy market (LEM). As these variables are correlated with the economic and environmental benefit of the ...
Comparative Analysis of Hybrid Deep Learning Frameworks for Energy Forecasting
As energy forecasting is paramount to efficient grid planning, this work presents a comparative analysis of different hybrid deep learning frameworks for energy forecasting in applications such as energy consumption and trading. Specifically, we ...
Web Scraper Application for Extracting Scientific Journals Data
Searching for certain subjects of articles that are disseminated throughout scientific journals would be a time-consuming task, as it would necessitate scouring many digital libraries or journal websites. This process can be performed efficiently by ...