Research Briefs on Information and Communication Technology Evolution

Predicting Optimum Lockdown Pattern of Epidemic Spread Using AI Techniques

Tue, 10 Jan 2023 00:00:00 +0000

Recent COVID-19 has revealed that we are still unable to find a sustainable approach to combat such infections in order to maintain a stable economy and minimize death rates. COVID-19 vaccine is available but when COVID-19 first arrived, restricting movement was the only option to control the spread, yet, one of its consequences is an economic crisis. This paper proposes predicting optimum lockdown patterns of epidemic spread using AI techniques (MESA ABM) which will help to balance economic fall and death rates while conducting vaccine research. We created a computergenerated environment to replicate a pandemic, such as the initial wave of COVID-19. The model was created using the SIR (Susceptible, Infected, Recovered) hypothesis for disease propagation and implemented using the Mesa, which is an agent-based modeling framework. Using this model, we develop an optimum lockdown pattern using agents (entities that act like humans). Our model produces optimal movement restrictions by randomly putting lockdowns ranging from one to a hundred days using given conditions. Additionally, we carry out several assessments and offer the justification for the action.

Implementation of an Evacuee Support System for Distributed Evacuation by Visualizing the Congestion Status of Evacuation Shelter

Tomoyuki Ishida, Ryosuke Nitama — Sat, 25 Mar 2023 00:00:00 +0000

We implemented an evacuee support system in this study. This system consists of evacuee’s safety information registration, evacuation shelter management, and evacuation shelter congestion status visualization systems. By implementing these three systems, a disaster response headquarters can manage the evacuees at each evacuation shelter accurately and quickly. Additionally, residents who are considering evacuating to evacuation shelters can browse the visualized congestion status of each evacuation shelter and move to vacant evacuation shelters. We evaluated the operability, readability, functionality, necessity, effectiveness, the applicability of the entire system, effectiveness and operability of the safety information registration system, readability and effectiveness of the evacuation shelter congestion status visualization system, and functionality and effectiveness of the evacuation shelter management system. We conducted evaluation experiments on 30 subjects and obtained a high evaluation in each evaluation item.

Estimate House Price Using Machine Learning

Rishita Gadde, Md Amiruzzaman, Richard Burns, Md. Rajibul Islam, Rizal Mohd Nor — Tue, 02 May 2023 00:00:00 +0000

The House Price Index (HPI) is commonly used to estimate the changes in housing prices. The sale price of the house is correlated with many other factors like geographical location, size of the house, age of the house, the area and population of the neighborhood etc. There has been a considerably large number of datasets released in the literature of various locations to explore the correlation of the sale price of houses with their corresponding features. However, all the features don’t affect the sale price in equal proportion. Some features strongly correlate with each other and, while some features don’t carry any importance or are probably redundant. As a result, to explore various impacts of features on sales prices, we performed a detailed data analysis on the original house dataset. This report also comprehensively validates multiple steps of data analysis with supporting statistics and visualizations to provide an optimistic result of various features and their impact on the sales price of houses.

Analysis of Business Processes with Automatic Detection of KPI Thresholds and Process Discovery Based on Trace Variants

Taro Takei, Hiroki Horita — Tue, 05 Sep 2023 00:00:00 +0000

One effective way to analyze an event log of a complex business process is to filter the event log by a KPI threshold and then use an analysis algorithm. Event logs filtered by KPI thresholds are simpler and easier to understand than the original business process. KPI thresholds have conventionally had to be set through a trial-and-error process, but existing research has proposed an automatic KPI threshold detection method that reduces the time and effort required to search for a threshold value. In the existing method, an event log is first divided by an arbitrary number k, and a business process model is generated for the divided event log using a process discovery algorithm. By repeatedly aggregating similar business process models, it is possible to analyze how the business process models differ according to KPI values. However, the existing method requires trial-and-error to determine the value of k because the detection threshold and business process model vary depending on the value of k, which is time-consuming. Therefore, this paper proposes a method to automatically detect KPI thresholds by dividing event logs based on trace variants. Experimental results show that the business process models detected by the proposed method are simpler and the threshold detection time is significantly reduced.

Implementation of a Marker Type Augmented Reality-based Free Music Trial Listening Application at Physical Music Stores

Naho Kuriya, Momoka Hagihara, Tomoyuki Ishida — Mon, 09 Oct 2023 00:00:00 +0000

The way we listen to music has undergone major changes—from cassette tapes and records to com- pact disks (CDs) and digital music that includes subscription-based online streaming and download- able sound sources. However, despite the popularity of digital music, CDs continue to be used as a means of listening to music due to the following reasons: the sense of safety felt upon holding the actual product and the collection factor for people interested in building personal collections. However, since the COVID-19 pandemic occurred in 2019, amid growing anxiety and turmoil about contact with “people” and “things,” users have become sensitive to the use of auditioning machines at CD shops. Therefore, we have developed a music trial listening application that uses augmented reality (AR) technology to enable people who visit CD shops to listen to the music of artists they are interested in without any physical contact with the auditioning machines. Users can feel the com- mitment of the artist by actually holding the CD jacket in their hands via AR; they can also view various types of information about the artist by recognizing the image on the CD jacket by using our AR technology-based developed application. Our proposed application consists of the “Listening Mode,” which provides the music trial listening function, and “AR Mode,” which provides the artist information presentation function. Further, we conducted an evaluation experiment with 30 sub- jects to evaluate the operability, readability, functionality, relevance, effectiveness, applicability, and safety of our developed application compared to the CD auditioning machine. The experiment results showed highly positive user evaluations regarding most of the abovementioned tested attributes. The user evaluations also showed that there is room for improvement regarding the operability of the AR objects generated via the application. In future studies, we aim to focus on the improvement of the application’s operability and enrichment of its contents, for example, we plan to add the “background playback function” and “administrator content registration function” to the existing functions of the applications.

A Comprehensive Review of the Recent Advancement in Integrating Deep Learning with Geographic Information Systems

Asif Raihan — Mon, 16 Oct 2023 00:00:00 +0000

The integration of deep learning (DL) techniques with geographical information system (GIS) offers a promising avenue for gaining novel insights into environmental phenomena by using the capabilities of spatial, temporal, and spectral resolutions, as well as data integration. The integration of these two technologies can result in the development of a highly efficient system for assessing environmental conditions by analyzing the interplay between texture, size, pattern, and process. This viewpoint has gained appeal across various academic disciplines. GIS heavily relies on processors, especially for tasks such as 3D computations, map rendering, and route calculation. In contrast, DL has the capability to efficiently analyze vast quantities of data. DL has garnered significant attention in recent times due to its potential for delivering a wide range of promising outcomes. Moreover, there is clear evidence of the increasing utilization of deep learning techniques across various fields, including GIS. The objective of this study is to provide an overview of the application of DL techniques in the field of GIS. This paper presents a concise review of the fundamental DL ideas that are pertinent to GIS, with a focus on the most current research findings. The present study investigates the various uses and technology of remote sensing in diverse domains, including mapping, hydrological modeling, disaster management, and transportation route planning. This study offers insights into contemporary framework approaches and proposes avenues for further research.

IoT Security Implementation using Machine Learning

Fri, 20 Oct 2023 00:00:00 +0000

This paper focuses on the implementation of machine learning algorithms to improve security in the Internet of Things (IoT) environment. IoT is becoming an essential part of our daily lives, and security is a significant concern in this domain. Traditional security measures are not enough to protect IoT systems from the increasing number of cyber-attacks. Machine learning algorithms can provide a better and more effective approach to detecting and mitigating security threats in IoT systems. This paper discusses various machine learning techniques such as supervised learning, unsupervised learning, and deep learning, and how they can be applied to improve security in IoT systems. The paper also explores the challenges and opportunities of using machine learning in IoT security and provides recommendations for future research. Overall, this paper provides a comprehensive overview of the role of machine learning in IoT security implementation and highlights the need for further research in this area.

An Overview of the Implications of Artificial Intelligence (AI) in Sixth Generation (6G) Communication Network

Asif Raihan — Thu, 02 Nov 2023 00:00:00 +0000

The 6G communication network is anticipated to be a cutting-edge next-generation communication network that will enhance the value of the intelligent Internet of Things (IoT). The emergence of many domains within artificial intelligence (AI) has paved the way for significant opportunities in the development of 6G technology. These opportunities include the enhancement of human intelligence, the integration of various devices and systems through the Internet of Everything (IoE), improvements in the quality of experiences, and enhancements in the overall quality of life. The integration of AI and 6G networking technology is anticipated to bring about a transformative shift, transitioning from a focus on interconnected devices to a paradigm centered around interconnected intelligent systems. This article provides an overview of the extent to which AI is poised to revolutionize 6G networking technologies. This study is primarily concerned with the implementation of appropriate applications that address human needs and challenges. Furthermore, this research highlights the significance of technology that has the potential to provide value for emerging technologies.

An Improved Semi-Supervised Gaussian Mixture Model (I-SGMM)

Bakare K.A, Torentikaza I.E — Sun, 12 Nov 2023 00:00:00 +0000

In the era of data-driven decision-making, the Gaussian Mixture Model (GMM) stands as a cornerstone in statistical modeling, particularly in clustering and density estimation. The Improved GMM presents a robust solution to a fundamental problem in clustering: the determination of the optimal number of clusters. Unlike its predecessor, it does not rely on a predetermined cluster count but employs model selection criteria, such as the Bayesian Information Criterion (BIC) or Akaike Information Criterion (AIC), to automatically identify the most suitable cluster count for the given data. This inherent adaptability is a hallmark of the Improved GMM, making it a versatile tool in a broad spectrum of applications, from market segmentation to image processing. Furthermore, the Improved GMM revolutionizes parameter estimation and model fitting. It leverages advanced optimization techniques, such as the Expectation-Maximization (EM) algorithm or variational inference, to achieve convergence to more favorable local optima. This results in precise and reliable parameter estimates, including cluster means, covariances, and component weights. The Improved GMM is particularly invaluable when dealing with data of varying complexities, non-standard data distributions, and clusters with differing shapes and orientations. It excels at capturing the nuanced relationships within the data, providing a powerful framework for understanding complex systems. One of the key differentiators of the Improved GMM is its accommodation of full covariance matrices for each component. This feature empowers the model to account for intricate interdependencies between variables, which is essential for modeling real-world data effectively. It is capable of handling data that exhibits non-spherical or irregular cluster shapes, a significant limitation of the traditional GMM.

PC-based User Continuous Authentication System Using the User's Finger Stroke Characteristics

Hyung-dong Lee, KiHyo Nam, Heewoong Lee, Mun-Kweon Jeong — Tue, 14 Nov 2023 00:00:00 +0000

Biometric technology, which performs continuous authentication based on user behavior, has been developed in various ways depending on the type of device, input device, and sensor. Research on continuous authentication technology in PC-based systems with few sensors installed is based on data from 3physical devices that extract and analyze features from keyboard and mouse input patterns. Among these, previous studies on continuous authentication through keyboard input performed continuous authentication using the key hold delay time that occurs when one key is pressed, the key interval delay time that occurs due to the interaction between fingers, and the key press delay time. did However, the keyboard-based continuous authentication model has limitations in increasing accuracy due to a small number of features. Therefore, in this paper, when a user inputs a sentence using a QWERTY keyboard in a PC system, the function is subdivided by reflecting the characteristics of each finger and used for continuous authentication. The features extracted by reflecting the characteristics of the finger were subdivided into a total of 151 latencies, and SVDD, decision tree, and CNN were used as continuous authentication models. Experimental data was collected through the user's input of randomly displayed sentences, and features were created based on this. User keystroke behavior was used to validate the continuous authentication model. Validation metrics included thresholds for classification accuracy (ACC), ROC curves, false rejection rate (FRR), equal error rate (EER), and false acceptance rate (FAR). As a result of the experiment, it was found that continuous authentication including the user's finger input pattern was superior to the existing method.

Large Language Model in SD-WAN Intelligent Operations and Maintenance

Yiyun Zhang — Tue, 19 Dec 2023 00:00:00 +0000

The integration of LLM (Large Language Model) into the intelligent operations and maintenance of SD-WAN (Software-Defined Wide Area Networks) is comprehensively explored. As the scale of the network continues to expand and its complexity increases, traditional operation and maintenance methods can no longer meet efficient and accurate requirements. Therefore, LLM technology was introduced, and the intelligent operation and maintenance of the data center network were realized by leveraging its powerful natural language processing capabilities. The importance and shortcomings of SD-WAN and the application scenarios of LLM in network operation and maintenance are first introduced, followed by an elaboration on how LLM can be used for network configuration, network optimization, network maintenance, and network security risk management. Through specific analysis, the significant effect of LLM in enhancing the efficiency and quality of operation and maintenance has been demonstrated. Finally, the advantages and challenges of employing LLM for intelligent network operation and maintenance are summarized, and future research directions are anticipated.

How to diagnose SS7 Protocol Vulnerability in Roaming Networks

Seongmin Park — Thu, 21 Dec 2023 00:00:00 +0000

As cellular networks spread to various operators in various countries, access to roaming networks by operators in other countries has become easier than before. As security attacks pretending to be roaming operators increased as the number of security attacks increased as the number of hours that were closed between trusted operators was gradually operated openly. By analyzing SS7 vulnerabilities in roaming networks and reenacting them through simulation, this study establishes a security threat scenario in a real commercial communication environment and builds a pre-simulation test environment that can identify and respond to the presence or absence of proactive measures through security analysis. The simulation test environment can be applied to the actual operational environment to reduce attack damage through pre-defense measures by preparing countermeasures against possible security attacks.

A study of Total Security Platform to Protect Autonomous Car and Intelligent Traffic System

Keon Yun, Myung Cheol Lim — Sat, 30 Dec 2023 00:00:00 +0000

Advancements in ultra-high-speed, low-latency 5G communication at 28GHz, pivotal for enabling autonomous driving, are currently under active development, heralding the imminent integration of this technology into our daily lives. The emergence of autonomous driving promises an array of services and enhanced comfort. However, the increasing proximity of autonomous driving to our societal fabric unveils a significant gap in security measures essential to shield self-driving cars and the interconnected intelligent transportation system from cyber threats. As autonomous vehicles transition from concept to service, the paramount importance of bolstering security measures becomes evident. Consequently, our focus centers on the development and research of security technologies aimed at robustly safeguarding against potential cyber attacks targeting the communication between infrastructure and vehicles.