|
|
|
Issues: Hệ thống và Thiết bị thông minh Vol 34.2 (05/2024)
|
1. Navistar – A universal Internet of Things Platform for Smart Systems
Hoang Van Hiep, Nguyen Dinh Thuan, Pham Ngoc Hung, Ta Hai Tung, La The Vinh*, Tran Duy Hien, Nguyen Van Giang, Phan Minh Tan, Tran Trung Dung
Recent years have seen a rapid development of artificial-intelligence-based (AI-based) internet of things (IoT) systems and applications like real-time object detection systems, face identification, AI-based cameras, etc. Many of these utilize a compact-form computing device based on system-on-chip (SoC) embedded modules from different providers like Qualcomm, Renesas, Quectel, etc. One of the most popular and easy-to-access platforms both practically and academically is the Raspberry Pi computing device and other PI-like devices such as: Orange Pi, Banana Pi, Jetson Nano, etc. However, we realize that the existing platforms strongly focus on the computation aspect, while other important features such as communication, location, ease of integration with high-level operating systems are lacking or poorly supported (through the use of so-called HAT). Therefore, in this work we propose a design of a multi-purpose IoT platform with full integration of computation module, IO ports, communications, location and high-level operating system (Android). We also utilize this IoT platform in a variety of applications including data collection, location-based services and biometric identification. Those sample applications will be presented in our work together with the algorithm and testing result to demonstrate the practical use of our platform.
Article Code:23073
# IoT, AI, single board computer, smart SoC
Page: 1-9
Field: Information and Communication Technology
|
2. VNeSafe: Machine Learning-Assisted System for Detecting Malicious URLs and Spam Calls
Van Tong, Dong Le Van, Quynh Anh Vu, Tuan Anh Ngo, Duc Tran*, Tri Duc Phung, Van Trong Nguyen
Spam calls and malicious Uniform Resource Locators (URLs) have become major concerns for Internet users. Phishing, spam, and drive-by-download attacks can be initiated by malicious URLs, while normal users may experience irritation from spam calls. To tackle the aforementioned issues, we provide VNeSafe, a machine learning-assisted system, in this paper. By leveraging user feedback, VNeSafe may identify a phone number that is spam. Particularly, it keeps track of how many times a phone subscriber has been reported as spam. When such a number is over a predetermined threshold, VNeSafe automatically adds the phone number to a blacklist and blocks it. Furthermore, VNeSafe uses a natural language processing technique named TF-IDF in order to extract good features from a URL. The Random Forest algorithm then makes use of these features to determine whether the URL is malicious or not. Our empirical research has demonstrated that Random Forest can offer a real-time detection with an F1-score of 0.9298. This algorithm is ready to be deployed in VNeSafe and used on a general mobile device.
Article Code:23074
# VNeSafe, malicious URL, spam call, Random Forest
Page: 10-17
Field: Information and Communication Technology
|
3. Extending Amdahl's and Gustafson Baris's Laws by Adding Communication Overheads
Pham Van Hai, Ho Khanh Lam, Dung Nguyen Hoang*
The extension of Amdahl's law and Gustafson-Barsis' law presented in this article provides insight into the relationship between communication costs and network topology in parallel computing. By considering communication latency in parallel computation execution time, these extensions can help researchers and developers optimize the interconnected network architecture of processing nodes and improve the performance of parallel computing systems. Today, parallel computer systems consisting of hundreds and thousands of processing nodes based on multiprocessor chip technology, high-speed optical transmission such as supercomputers are being researched, developed, and applied in many fields many areas. Although chip technology has progressed to the 3 nm process, the network architecture connecting processing nodes continues to be a problem that greatly affects the communication delay in the parallel computation time of the applications. In this paper, extensions of Amdahl's law and Gustafson-Barsis' law are presented with the addition of communication costs depending on the topology of the topology. These extensions provide insight into the relationship between communication costs and network topology in parallel computing. By considering communication latency in parallel computation execution time, these extensions can help researchers and developers optimize the interconnected network architecture of processing nodes and improve the performance of parallel computing systems.
Article Code:23037
# Extensions of Amdahl’Law, Gustafson-Barsis, interconnection network topology, supercomputer, communication overhead, speedup.
Page: 18-26
Field: Information and Communication Technology
|
4. Research on the Application of Visible Light Communication in IoT System Configuration
Nam Hoang Nguyen*, Tung Huu Duong
The growing need for seamless connectivity on the Internet of Things (IoT) paradigm has fueled the development of innovative technologies. This research deeply focuses on the integration of Visible Light Communications (VLC) to configure the WSN nodes in an IoT system. VLC, an emerging technology that uses visible light to transmit data, is not limited in frequency and maximizes security in wireless data transmission. Furthermore, due to the use of light-emitting diodes (LEDs) in almost every aspect of our daily lives, VLC is providing massive connectivity for various types of large-scale IoT communications, from machine to machine, vehicle to infrastructure, infrastructure-to-vehicle, chip-to-chip as well as device to device. This article presents an investigation of the multifaceted applications of VLC, especially its role in configuring Wi-Fi connectivity for smart devices and their location in the system within the IoT framework. In addition to conventional data transmission capabilities, VLC has emerged as a key technology for transmitting configuration data and location data, thereby supporting an accurate positioning system. This study shows the effective interaction between VLC and IoT, shedding light on the applications of VLC in IoT systems, especially in smart building...
Article Code:24003
# Internet of Things (IoT), Light-Emitting Diodes (LEDs), Visible light communication (VLC), VLC-IoT communication
Page: 27-34
Field:
Electronics and Telecommunications
|
5. Development of a Smart Wearable Device for Fall and Slip Detection and Warning for the Elderly People
Thanh Huong Nguyen*, Viet Tung Nguyen
In the elderly, due to the degeneration of the muscles along with visual impairment, mobility becomes more difficult than in other ages. Upon moving, the elderly can be susceptible to several factors such as slips or obstacles which can cause unintended fall events and can lead to different degrees of injury, from minor trauma to more severe and even life-threatening injuries. In this work, the characteristics of movement and falling in the elderly are first studied, thereby finding thresholds for determining fall events for motion parameters to detect ahead of time the fall event. Therefore, necessary warnings can be promptly delivered to the users or caregivers, otherwise distress signal can be sent wirelessly to request assistance if the elderly is unable to stand up. This will help minimize the negative impact on the elderly caused by the fall event. The paper proposes to base the research on motion and fall features of the old people to build a wearable device which combines gyroscope accelerometer, a self-developed fall sensor and heart rate sensor for fall detection and warning. The device also employs parameter thresholds to detect forward and backward fall events as well as to provide accurate information about other familiar activities such as standing and sitting, lean forward, backward, left or right. The threshold-based method we used in determining the body states correctly identified the states: 93.33% steady state, 86.67% fallible state and 96.67% slip state. Moreover, the device can also achieve 90% accurate information about the user's heart rate.
Article Code:24002
# Elderly, fall, slip, detection, warning, sensor, wearable device
Page: 35-43
Field:
Electrical Engineering
|
6. Utilizing Layer-2 Blockchain and IPFS Innovations for Establishing a Robust System for Secure Document Signing and Management
Thinh Nguyen-Cong*, Ngoc C. Lê
Data holds immense significance within any information system. In traditional setups, data typically funnels into a central server for processing and storage, rendering the entire system reliant on this singular point. The ongoing digitalization trend, particularly accelerated by the global pandemic, has ushered in many transformative shifts in various operational aspects, including the validation, storage, and electronic signing of many documents. This surge in digital transactions has amplified both the data storage requirements and the volume of data traversing the Internet, thereby heightening the potential risks associated with fraud and document tampering. Consequently, an imperative need for a robust and secure document management system arises. Blockchain technology emerges as an innovative solution poised to address these challenges. In this study, we explore the compelling advantages that Blockchain technology offers to the realm of digital document storage, culminating in the development of a secure, web-based solution for document storage and processing.
Article Code:24001
# BC-DMS, blockchain, document management, polygon, security, IPFS, CP-ABE, Layer-2 blockchain
Page: 44-53
Field: Applied Mathematics and Informatics
|
7. Minimizing Flight Hours Losses by Utilizing Deep-Q Learning Techniques in Scheduling Aircraft Maintenance
Manh-Tuan Ha*, Minh-Hieu Nguyen, Quang-Hung Pham
Currently, there are insufficiently good or efficient tools or procedures for long-term scheduling of aviation maintenance activities in the world, and Vietnam specifically. Airlines are impacted by a variety of elements, including the quantity of aircraft they operate, their capacity, their personnel resources, their maintenance resources, and unforeseen and urgent occurrences that cause schedule disruptions. There are no fast, automatic solutions to the above-described problems existing in aviation today. The reinforcement learning method as described here could potentially be one answer to these problems. The idea is to plan in years running across a specified period such that the aircraft is brought as close as possible to the inspection deadline. From there, the airworthiness of the aircraft increases while the maintenance inspection decreases, reducing the cost of maintenance. Application optimization of the scheduling plan is done using the Deep Q-learning method. The results achieved by the Q-learning and Deep Q-learning algorithms are better in terms of computation times as compared to the other current techniques. The research results of the checks showed reinforcement learning potential in dealing with this problem, where the fly hours loss of planned inspections was reduced by using data from Vietnam Airlines. Computational experiments show that our methods adapt for different purposes and settings of reality. After teaching the model with these simulated conditions, they show how well an reinforcement learning application quickly arrives at lean repair plans.
Article Code:24006
# Aircraft maintenance, maintenance check scheduling, reinforcement learning, Q-learning, deep Q-learning
Page: 54-65
Field: Mechanical Engineering
|
8. Adaptive Fast Terminal Sliding Mode Control for Inverted Pendulum on Cart
Thi-Van-Anh Nguyen, Xuan-Hiep Nguyen, Quy-Thinh Dao*
This paper presents an innovative control strategy, the Adaptive Fast Terminal Sliding Mode Control (AFTSMC), designed for the stability control of an inverted pendulum on a cart. The proposed controller aims to stabilize the system within a finite time, leveraging the advantages of fast terminal sliding mode techniques. The system’s dynamic model is employed to derive the controller, utilizing an adaptive approach to accommodate uncertainties and disturbances. Simulations are conducted to validate the proposed AFTSMC, comparing its performance with an Adaptive Sliding Mode Controller under various scenarios. The results demonstrate the efficacy of the AFTSMC in achieving stable and precise control, making it a promising solution for the challenging dynamics of inverted pendulum systems.
Article Code:24011
# Sliding mode control, adaptive fast terminal sliding mode control, inverted pendulum
Page: 66-74
Field:
Electrical Engineering
|
 | Loading… |
|
|
|
|