• International journal of advanced smart convergence
• /
• v.9 no.1
• /
• pp.193-201
• /
• 2020

The main objective of this study is to investigate the impact of additional modalities on the performance of emotion recognition using speech, facial expression and physiological measurements. In order to compare different approaches, we designed a feature-based recognition system as a benchmark which carries out linear supervised classification followed by the leave-one-out cross-validation. For the classification of four emotions, it turned out that bimodal fusion in our experiment improves recognition accuracy of unimodal approach, while the performance of trimodal fusion varies strongly depending on the individual. Furthermore, we experienced extremely high disparity between single class recognition rates, while we could not observe a best performing single modality in our experiment. Based on these observations, we developed a novel fusion method, called parametric decision fusion (PDF), which lies in building emotion-specific classifiers and exploits advantage of a parametrized decision process. By using the PDF scheme we achieved 16% improvement in accuracy of subject-dependent recognition and 10% for subject-independent recognition compared to the best unimodal results.

• International journal of advanced smart convergence
• /
• v.2 no.1
• /
• pp.24-26
• /
• 2013

In the process of a mobile network evolution to the All-IP, it is inevitable to experience a transient period embracing both circuit and packet based data traffics. At the stage of those hybrid networks, it is important to build them in an efficient manner in terms of resource utilization which is closely related to the overall system operation cost. Especially, the multimedia telephony is one of the essential services in the advanced packet based mobile networks. In this paper an effective method of system operation is proposed for building up the multimedia telephony service while the legacy network co-exists. The proposed solution is based on the careful investigation of the usage pattern of the multimedia services in the evolving networks. This method is also expected to be a useful guideline for the network resource planning.

• International journal of advanced smart convergence
• /
• v.10 no.4
• /
• pp.263-272
• /
• 2021

At a time when securing driving safety is the most important in the development and commercialization of autonomous vehicles, AI and big data-based algorithms are being studied to enhance and optimize the recognition and detection performance of various static and dynamic vehicles. However, there are many research cases to recognize it as the same vehicle by utilizing the unique advantages of radar and cameras, but they do not use deep learning image processing technology or detect only short distances as the same target due to radar performance problems. Radars can recognize vehicles without errors in situations such as night and fog, but it is not accurate even if the type of object is determined through RCS values, so accurate classification of the object through images such as cameras is required. Therefore, we propose a fusion-based vehicle recognition method that configures data sets that can be collected by radar device and camera device, calculates errors in the data sets, and recognizes them as the same target.

• International journal of advanced smart convergence
• /
• v.8 no.3
• /
• pp.177-183
• /
• 2019

We intend to improve the sustainability of rural villages by investigating the element technologies and platforms necessary for building smart villages. There are so many investment smart city platforms and solutions in many cities. but there are relatively few investments in rural or small cities. This situation can not only increase the urban problem due to the increase of population to the city, but also deepen the digital gap of citizens. So far, studies on smart village have been investigated in fragments. We will examine the cases applied to smart village as a whole and study the open smart village platform that analyzes the overall data storage and management of the village after the smart village was finally established. First, we will look at the overseas trends of smart village and second, we will study the smart village platform that efficiently manages smart village through the technology necessary for smart village.

• International journal of advanced smart convergence
• /
• v.8 no.2
• /
• pp.94-101
• /
• 2019

Building a stable knowledge base is an important issue in the application of knowledge engineering. In this paper, we present an algorithm for detecting and locating discrepancies in the line of the reasoning process especially when discrepancies occur on belief values. This includes backtracking the rule firing from a goal node of the rule network. Retracting a belief function allows the current belief state to move back to another belief state without the rule firing. It also gives an estimate, called contribution measure, of how much the rule has an impact on the current belief state. Examining the measure leads the expert to locate the possible cause of problem in the rule. For non-monotonic reasoning, the belief retraction method moves the belief state back to the previous state. A tracing algorithm is presented to identify and locate the cause of problem. This also gives repair suggestions for rule refinement.

• International journal of advanced smart convergence
• /
• v.8 no.2
• /
• pp.218-226
• /
• 2019

The use of Information and Communication Technologies (ICT) is the key to operate a change from the traditional manual reading of water meters and sensors to an automated system where high frequency data is remotely collected and analyzed in real time, one of the main components of a Smart Water Grid. The recent boom of ICT offers a wide range of both wired and wireless technologies to achieve this objective. We review and present in this article the most widely recognized technologies and protocols along with their respective advantages, drawbacks and applicability range which can be Home Area Network (HAN), Building Area Network (BAN) or Local/Neighborhood Area Network (LAN/NAN). We also present our findings and we give recommendations on the application of ICT in Smart Water Grids and future work needed.

• International journal of advanced smart convergence
• /
• v.9 no.4
• /
• pp.149-155
• /
• 2020

In the software industry of Korean Small and Medium-sized Enterprise(SME)s, the development process is often not mature. This may lead to failures in quality control and output management. As a result, the quality of the software can be degraded. To solve the problem, the software visualization technique, which is from the National IT Industry Promotion Agency Software Engineering Center can be applied. We have experienced with mentoring not only the visualization of software development process, but also various visualization process of SMEs. However, the existing software visualization method was difficult to install environment and its time cost was high. This paper proposes a software visualization environment through a cloud service along with a case of building a software visualization environment. We expect that this method will make it easier to build a visualization environment and improve the quality of SME software.

• International journal of advanced smart convergence
• /
• v.10 no.1
• /
• pp.184-196
• /
• 2021

This study, in order to evaluate the safety of evacuation by comparing and analyzing the RSET according to the slope change of the ramp, which is a vertical evacuation route in case of fire in a high school building, Evacuation simulation was run the Pathfinder program changed the slope of the ramp to 10°, 15°, and 20° for each male students and female students. In the case of female students, it was analyzed that when the final RSET slope was 15°, 25.7 seconds were shorter than when 10°, and 4.2 seconds were shorter than when 20°. Male students also found that when the final RSET slope was 15°, 23.8 seconds were shorter than when 10°, and 5.4 seconds shorter than when 20°. It was analyzed that even if the number of participants was increased and the evacuation simulation was executed, the safety of evacuation could be improved when the slope of the slope is 15° as the RSET when the slope of the slope is 15° is shorter than that of 10° and 20°.

• International journal of advanced smart convergence
• /
• v.12 no.1
• /
• pp.9-17
• /
• 2023

Recently, IoT technology has been widely used in many industries. Also research on integrating IoT technology with IoT sensors is actively underway. One of the important challenges in IoT is to support low-latency communication. With the development of communication networks and protocols, a variety of protocols are being used, and their performance is improving. In this paper, we compare the performance and analyze the characteristics of some of the major communication protocols in IoT application, namely MQTT, HTTP, and HTTPS. IoT sensors acquired data by connecting an Arduino equipped with ESP8266 and a temperature and humidity sensor (DHT11). The server measured the performance by building servers for each protocol using AWS EC2. We analyzed the packets transmitted between the Arduino and the server during the data transmission. We measured the amount of data and transfer time. The measurement results showed that MQTT had the lowest data transmission time and data amount among the three protocols.

• International journal of advanced smart convergence
• /
• v.11 no.4
• /
• pp.10-19
• /
• 2022

AI-based Network Intrusion Detection Systems (AI-NIDS) detect network attacks using machine learning and deep learning models. Recently, unsupervised AI-NIDS methods are getting more attention since there is no need for labeling, which is crucial for building practical NIDS systems. This paper aims to test the impact of designing autoencoder models that can be applied to unsupervised an AI-NIDS in real network systems. We collected security events of legacy network security system and carried out an experiment. We report the results and discuss the findings.