• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.771-780
• /
• 2024

In this study, we implemented a real-time pest detection and prediction system for a strawberry farm using a computer vision model based on the YOLOv5 architecture and an Isolation Forest Classifier. The model performance evaluation showed that the YOLOv5 model achieved a mean average precision (mAP 0.5) of 78.7%, an accuracy of 92.8%, a recall of 90.0%, and an F1-score of 76%, indicating high predictive performance. This system was designed to be applicable not only to strawberry farms but also to other crops and various environments. Based on data collected from a tomato farm, a new AI model was trained, resulting in a prediction accuracy of over 85% for major diseases such as late blight and yellow leaf curl virus. Compared to the previous model, this represented an improvement of more than 10% in prediction accuracy.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.344-347
• /
• 2014

A human resource/labor management is a management activity to achieve the goal of an employee. To do this, it is required to measure the time of diligence/indolence effectively. However, existing diligence/indolence systems have the problems which require high costs for building the systems and have many unnecessary functions for small business or self-employed business. In this paper, we design and implement the diligence/indolence system using a smart phone of an employee. To measure the data of the diligence/indolence, the implemented system exploits the MAC addresses of both a smart phone and a access point of WiFi.

• Journal of Broadcast Engineering
• /
• v.21 no.3
• /
• pp.298-306
• /
• 2016

With the advent of Internet of Things (IoT) technology that allows the communications between things and devices over the Internet, a lot of researches on the IoT services, such as smart home or healthcare, have been progressed. In the existing machine-to-machine (M2M) communications, however, since the underlying link-layer technologies, such as Bluetooth or ZigBee, do not use the Internet Protocol (IP) communication, those technologies are not suitable to provide the IoT services. Accordingly, this paper discusses how to provide the Internet services in the M2M communication, and propose an implementation of the Constrained Application Protocol (CoAP) over 6LoWPAN for providing IoT services in the BLE networks. Based on the implementation, we compared the performance between HTTP and CoAP for IoT communications. From the experimental results, we can see that the CoAP protocol gives better performance than the HTTP protocol with two times higher throughput, 21% faster transmission time, and 22% smaller amount of generated packets.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.10
• /
• pp.2143-2148
• /
• 2011

In general, existed kiosk using touch-screen based kiosk system has been used by only single user, so that multiple users to access this kiosk need to provide a lot of waiting time and maintenance costs. To solve this problem, the framework design based on Bluetooth profile for kiosk servers is presented. The proposed kiosk system can be more efficiently used in theater, train station, bank, government, and public offices by using Bluetooth module and AP in mobile system such as smart phone.

• BMB Reports
• /
• v.53 no.7
• /
• pp.379-384
• /
• 2020

Exposure to Ultraviolet (UV) light induces photoaging of skin, leading to wrinkles and sunburn. The perennial herb Humulus japonicus, widely distributed in Asia, is known to have anti-inflammatory, antimicrobial, and antioxidant effects. However, the physiological activities of isolated compounds from H. japonicus have rarely been investigated. This study focused on the isolation of active compounds from H. japonicus and the evaluation of their effects on photoaging in UVB-irradiated human fibroblast (Hs68) cells. When the extract and four fractions of H. japonicus were treated respectively in UVB-irradiated Hs68 cells to investigate anti-photoaging effects, the ethyl acetate (EtOAc) fraction showed the strongest inhibitory effect on MMP1 secretion. From EtOAc fraction, we isolated luteolin-8-C-glucoside (1), apigenin-8-C-glucoside (2), and luteolin-7-O-glucoside (3). These compounds suppressed UVB-induced MMP-1 production by inhibiting the phosphorylation of the mitogen-activated protein kinases (MAPKs) and activator protein-1 (AP-1). When the antioxidant activity of the compounds were estimated by conducting western blot, calculating the bond dissociation energies of the O-H bond (BDE) at different grade, and measuring radical scavenging activity, we found luteolin-8-C-glucoside (1) showed the strongest activity on the suppression of UVB-induced photoaging. These results demonstrate the inhibitory effect of three flavone glycosides derived from H. japonicus on MMP-1 production, MAPK and AP-1 signaling, and oxidative stress; this could prove useful in suppressing UVB induced photoaging.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.2
• /
• pp.176-184
• /
• 2011

As modern megalopolises become more complex and huge, convenience and safety of citizens are main components for a welfare state. In order to make safe society, telemetrics technology, which remotely measures the information of target system using electronic devices, is an essential component. In general, telemetrics technology consists of USN (ubiquitous sensor network) based on a wireless network, smart sensor, and SoC (system on chip). In the smart sensor technology, the following two problems should be overcome. Firstly, because it is very difficult for transducer manufacturers to develop smart sensors that support all the existing network protocols, the smart sensor must be independent of the type of networking protocols. Secondly, smart sensors should be modular so that a faulty sensor element can be replaced without replacing healthy communication element. To solve these problems, this paper investigates the feasibility of an IEEE 1451 based ZigBee smart sensor system. More specifically, a smart sensor for large network coverage has been developed using ZigBee for active telemetrics.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.4
• /
• pp.315-325
• /
• 2014

In ubiquitous environment, User's location information is very important to serve personalized service to user. Previous works consider only User's locations in the big buildings and assume APs are fixed. Normal home environment, However, is consists of small spaces. And the state of APs is highly fluid. Previous research has focused on indoor localization in the building where has stationary AP environment. However, in this paper, we propose as User's Location Predicting System that finds out a space where a user is located based on Wi-Fi Fingerprint approach in home environments. The results that conducted real home environments are using the system show more than 80% accuracy.

• International journal of advanced smart convergence
• /
• v.9 no.1
• /
• pp.202-208
• /
• 2020

Body balance necessary for ordinary daily activities can be undermined by diverse causes. In this study, as a way to control such a problem, we have produced smart insole as a wearable device in the form of insole and developed analysis software evaluating body balance, which measures ground reaction force applied to each area of sole and Center of Pressure (COP). The software visualized changes in COP positions while a user was moving and average COP positions, and it is also capable of measuring the COP values in the Anterior-Posterior (AP) and Medial-Lateral (ML) areas of feet. Through gait analysis, it can analyze the time of walking, strides, speed, COP trajectory while walking, etc. In addition, we have developed training contents for body balance improvement designed in consideration of Y-Balance Test and Timed Up and Go (TUG) Test. They were established in virtual reality similar to daily living environment so that people can expect more effective training results regardless of places.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.22-29
• /
• 2022

Recently, with the development of mobile computing power, mobile-based VR and AR services are being developed. Due to network performance and computing power constraints, VR and AR services using large-capacity 3D content have limitations. A study on an efficient 3D content load method for a mobile device is required. The conventional method downloads all 3D content used for AR services at the same time. In this paper, we propose an active 3D content load according to the user's track. The proposed method is a partitioned 3D object load. Edge servers were installed for each area and connected through the MESH network. Partitioned load the required 3D object in the area referring to the user's location. The location is identified through the edge server information of the connected AP. The performance of the proposed method and the conventional method was compared. As a result of the comparison, the proposed method showed a stable Mobile AR Service. The results of this study, it is expected to contribute to the activation of edge server-based AR mobile services.

• Smart Media Journal
• /
• v.11 no.4
• /
• pp.46-55
• /
• 2022

It is very important to first detect and remove defective fruits with scratches or bruised areas in the automatic fruit quality screening system. This paper proposes a method of detecting defective areas in fruits using the latest artificial intelligence technology, the Yolo V4 deep learning model in order to overcome the limitations of the method of detecting fruit's defective areas using the existing image processing techniques. In this study, a total of 2,400 defective fruits, including 1,000 defective apples and 1,400 defective fruits with scratch or decayed areas, were learned using the Yolo V4 deep learning model and experiments were conducted to detect defective areas. As a result of the performance test, the precision of apples is 0.80, recall is 0.76, IoU is 69.92% and mAP is 65.27%. The precision of pears is 0.86, recall is 0.81, IoU is 70.54% and mAP is 68.75%. The method proposed in this study can dramatically improve the performance of the existing automatic fruit quality screening system by accurately selecting fruits with defective areas in real time rather than using the existing image processing techniques.