REV Journal on Electronics and Communications
Not a member yet
230 research outputs found
Sort by
Beam Size Optimization for High-Altitude Platforms to Ground Links in FSO Communications
Get PDFFree-space optical (FSO) communication has been used in practice mainly for short-distance transmission because it requires light of sight (LoS) between the transmitter and receiver. For long-distance communication, to avoid terrestrial obstacles, high-altitude platforms (HAPs) flying at stratosphere are used to carry intermediate FSO transceivers which relay data through several hops from the source to the destination stations. A HAP can communicate with a large ground area if its FSO transceiver projects a wide beam onto the ground. However, an excessively large beam makes the FSO transceiver consume a lot of energy. This study investigates the problem of finding individual optimal beam sizes for FSO transceivers on HAPs so that the total cost of the HAP network, including the amortization, energy, and maintenance costs, is minimized. An optimization algorithm was proposed and implemented. The simulation results show the network designed by the algorithm achieves a nearly optimal number of HAPs, leading to a low network cost
An efficient approach to measure the difficulty degree of practical programming exercises based on student performances
Get PDFThis study examines the generality of easy to hard practice questions in programming subjects. One of the most important contributions is to propose four new formulas for determining the difficulty degree of questions. These formulas aim to describe different aspects of difficulty degree from the learner's perspective instead of the instructor's subjective opinions. Then, we used clustering technique to group the questions into three easy, medium and difficult degrees. The results will be the baseline to consider the generality of the exercise sets according to each topic. The proposed solution is then tested on the data set that includes the results of the two subjects: Programming Fundamentals, Data Structures and Algorithms from Ho Chi Minh City University of Technology. The most important result is to suggest the instructors complete various degrees according to each topic for better evaluating student's performance
PGN-LM Model and Forcing-Seq2Seq Model: Multiple Automatic Models of Title Generation for Natural Text using Deep Learning
Get PDFIn the current era, the amount of information from the Internet in general and the electronic press in particular has increased rapidly and has extremely useful information value in all aspects of life, many popular users have posted several high-quality writings as casual blogs, notes or reviews. Some of them are even selected by editors to be published in professional venues. However, the original posts often come without titles, which are needed to be manually added by the editing teams. This task would be done automatically, with the recent advancement of AI techniques, especially deep learning. Even though auto-title can be considered as a specific case of text summarization, this job poses some major different requirements. Basically, a title is generally short but it needs to capture major content while still maintaining the writing style of the original document. To fulfill those constraints, we introduce PGN-LM Model, an architecture evolved from the Pointer Generator Network, with the ability to solve Out-of-Vocabulary problems that traditional Seq2Seq models cannot handle, and at the same time combined with language modeling techniques. In addition, we also introduce a model called Forcing-Seq2Seq Model, an enhanced Seq2Seq architecture, in which the classical TF-IDF scores are incorporated with Named Entity Recognition method to identify the major keywords of the original texts. To enforce the appearance of those keywords in the generated titles, the specific Teacher Forcing mechanism combined with the language model technique are employed. We have tested our approaches with real datasets and obtained promising initial results, on both metrics of machine and human perspectives
Neighborhood search for solving personal scheduling problem in available time windows with split-min and deadline constraints
Get PDFThe scheduling of individual jobs with certain constraints so that efficiency is a matter of concern. Jobs have deadlines to complete, can be broken down but not too small, and will be scheduled into some available time windows. The goal of the problem is to find a solution so that all jobs are completed as soon as possible. This problem is proved to be a strongly -hard problem. The implementation of the proposed MILP model using a CPLEX solver was also conducted to determine the optimal solution for the small-size dataset. For large-size dataset, heuristic algorithms are recommended such as First Come First Served (FCFS), Earliest Deadline (EDL), and neighborhood search including Stochastic Hill Climbing (SHC), Random Restart Hill Climbing (RRHC), Simulated Annealing (SA) to determine a good solution in an acceptable time. Experimental results will present in detail the performance among the groups of exact, heuristic, and neighborhood search methods
Enhancing Security and Robustness for SDN-Enabled Cloud Networks
Get PDFSoftware-Defined Networking is an emerging network architecture which promises to solve the limitations associated with current cloud computing systems based on traditional network. The main idea behind SDN is to separate control plane from networking devices, thereby providing a centralized control layer integrable to cloud-based infrastructure. The integration of SDN and Cloud Computing brings an immense benefits to network deployment and management, however, this model still faces many critical challenges with regards to availability, scalability and security. In this study, we present a security and robustness SDN-Enabled Cloud model using OpenStack and OpenDaylight. In particular, we design and implement a security clustering-based SDN Controller for monitoring and managing cloud networking, and a hardware platform to accelerate packet processing in virtual switches. We evaluate our proposed model on a practical cloud testbed consisting of several physical and virtual nodes. The experiment results show that the SDN controller cluster significantly improve robustness for the network even in case of being attacked by abnormal network traffic; while the hardware-accelerated switches can be operated in highperformance and well-adapted to the cloud environment
Unbiased Pairwise Approach toward Learning-to-Rank: An Empirical Study
Get PDFWith the bloom of information technology in recent decades, people are constantly being exposed to a huge amount of information. Learning-to-rank comes out as one of the solutions to ease out the mentioned obstacle by trying to rearrange objects according to their degrees of importance or relevance. This solution usually applies machine learning techniques to construct ranking models in information retrieval systems. The aim of this study is to explore and experiment the existing learning-to-rank approaches with real-life logs data. The study also includes estimating and minimizing the bias noise found in the click-through data of the recorded logs. Evaluation results have presented the advantage and disadvantage of the experimented approaches in realistic settings
Generating Website Codes from Images
Get PDFBrainstorm website layout ideas usually start with everyone giving out their mockups, and all the team members will discuss to finalize the layout of the user interface. Once a vision of that mockup is accepted, it is given to the designer to sketch it digitally on computer software (i.e., Photoshop, Figma, Sketch). When the designer completes, the developer based on the final design to code the UI/UX of the website. As we can see, the process requires three stages, which can be time-consuming. Therefore, if anyone has an idea for the professional website layout, they can visualize it by drawing on sketches. However, it can be impossible for them to make a usable website without designers and website developers. Due to that reason, our primary goal in this paper is to help individuals transform their hand-drawn sketch images into a website that can be deployed. To achieve that goal, we present two approaches: classical computer vision techniques and the other using a deep learning model to detect the sketch and execute the conversion. Furthermore, our evaluation shows that deep learning is the most promising direction. Still, classical techniques also improve the model’s input data by applying it in the pre-processing image
Two-Phase Defect Detection Using Clustering and Classification Methods
Get PDFAutonomous fault management of network and distributed systems is a challenging research problem and attracts many research activities. Solving this problem heavily depends on expertise knowledge and supporting tools for monitoring and detecting defects automatically. Recent research activities have focused on machine learning techniques that scrutinize system output data for mining abnormal events and detecting defects. This paper proposes a two-phase defect detection for network and distributed systems using log messages clustering and classification. The approach takes advantage of K-means clustering method to obtain abnormal messages and random forest method to detect the relationship of the abnormal messages and the existing defects. Several experiments have evaluated the performance of this approach using the log message data of Hadoop Distributed File System (HDFS) and the bug report data of Bug Tracking System (BTS). Evaluation results have disclosed some remarks with lessons learned