• Journal of the Korea Society of Computer and Information
• /
• v.18 no.8
• /
• pp.105-111
• /
• 2013

This paper presents a virtual sensor system that is an effective method to test application software of smart sensors. The common way of testing sensor application is to build a test board, connect sensors to the board, and test sensor applications on the board with sensor's measurements as inputs. The problem of testing sensor application software with sensor's measurements as inputs is the restriction of test data. In other words, software testers cannot manipulate test data, because test data is generated by sensors. To solve this problem a virtual sensor system is presented in this paper. The virtual sensor system enables software testers to manipulate measurements of sensors. In the virtual sensor system, generation of virtual sensors comprises three stages - sensor selection, sensor characterization, and determination of output patterns. Sensor's measurements that can be manipulated through the virtual sensor system make the process of testing efficient. To show the usefulness of our virtual sensor system, it is applied to sensor applications in Android platform and the result of experiments is shown.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1244-1253
• /
• 2021

In this paper, we propose a method for predicting in advance whether pedestrians will enter the hazardous area after the current time using the pedestrian trajectory prediction method and an efficient simplification method of the trajectory prediction network. In addition, we propose a method to apply KD(Knowledge Distillation) to a small network for real-time operation in an embedded environment. Using the correlation between predicted future paths and hazard zones, we determined whether to enter or not, and applied efficient KD when learning small networks to minimize performance degradation. Experimentally, it was confirmed that the model applied with the simplification method proposed improved the speed by 37.49% compared to the existing model, but led to a slight decrease in accuracy. As a result of learning a small network with an initial accuracy of 91.43% using KD, It was confirmed that it has improved accuracy of 94.76%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.2
• /
• pp.365-375
• /
• 2019

A PLC (Programmable Logic Controller) is a highly-reliable industrial digital computer which supports real-time embedded control applications for safety-critical control systems. Real-time operating systems such as uC/OS have been used for PLCs and must meet real-time constraints. As PLCs have been widely used for industrial control systems and connected to the Internet, they have been becoming a main target of cyberattacks. In this paper, we propose an execution code sanitizer to enhance the security of PLC systems. The proposed sanitizer analyzes PLC programs developed by an IDE before downloading the program to a target PLC, and mitigates security vulnerabilities of the program. Our sanitizer can detect vulnerable function calls and illegal memory accesses in development of PLC programs using a database of vulnerable functions as well as the other database of code patterns related to pointer misuses. Based on these DBs, it detects and removes abnormal use patterns of pointer variables and existence of vulnerable functions shown in the call graph of the target executable code. We have implemented the proposed technique and verified its effectiveness through experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.55-62
• /
• 2019

Convolutional neural networks (CNNs) show high performance in the computer vision, but they require an enormous amount of operations, making them unsuitable for some resource- or energy-starving environments like the embedded environments. To overcome this problem, there have been much research on accelerators or pruning of CNNs. The previous pruning schemes have not considered the architecture of CNN accelerators, so the accelerators for the pruned CNNs have some inefficiency. This paper proposes a new pruning scheme, Conv-XP, which considers the architecture of CNN accelerators. In Conv-XP, the pruning is performed following the 'X' or '+' shape. The Conv-XP scheme induces a simple architecture of the CNN accelerators. The experimental results show that the Conv-XP scheme does not degrade the accuracy of CNNs, and that the accelerator area can be reduced by 12.8%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.2
• /
• pp.173-178
• /
• 2019

Recently, the types and amount of data generated, collected, and measured in IoT such as smart home, security, and factory are increasing. The technologies for IoT service include sensor devices to measure desired data, embedded software to control the devices such as signal processing, wireless network protocol to transmit and receive the measured data, and big data and AI-based analysis. In this paper, we focused on developing a gateway for interfacing heterogeneous sensor network protocols that are used in various IoT devices and propose a heterogeneous network interface IoT gateway. We utilized a OpenWrt-based wireless routers and used 6LoWAN stack for IP-based communication via BLE and IEEE 802.15.4 adapters. We developed a software to convert Z-Wave and LoRa packets into IP packet using our Python-based middleware. We expect the IoT gateway to be used as an effective device for collecting IoT big data.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.5
• /
• pp.959-968
• /
• 2019

In the agricultural industry, wireless sensor network technology has being applied by utilizing various sensors and embedded systems. In particular, a lot of researches are being conducted to diagnose diseases of crops early by using sensor network. There are some difficulties on traditional research how to diagnose crop diseases is not practical for agriculture. This paper proposes the algorithm which enables to investigate and analyze the crop leaf image taken by image camera and detect the infected area within the image. We applied the enhanced k-means clustering method to the images captured at horticulture facility and categorized the areas in the image. Then we used the edge detection and edge tracking scheme to decide whether the extracted areas are located in inside of leaf or not. The performance was evaluated using the images capturing tomato leaves. The results of performance evaluation shows that the proposed algorithm outperforms the traditional algorithms in terms of classification capability.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.93-98
• /
• 2021

Due to the development of deep learning and AI, the scale of the model has grown, and it has been integrated into other fields to blend into our lives. However, in environments with limited resources such as embedded devices, it is exist difficult to apply the model and problems such as power shortages. To solve this, lightweight methods such as clouding or offloading technologies, reducing the number of parameters in the model, or optimising calculations are proposed. In this paper, quantization of learned models is applied to ONNX models used in various framework interchange formats, neural network structure and inference performance are compared with existing models, and various module methods for quantization are analyzed. Experiments show that the size of weight parameter is compressed and the inference time is more optimized than before compared to the original model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1280-1287
• /
• 2020

This paper proposes a vision-based food recognition method for automated production of custom cakes. A small camera module mounted on a food art printer recognizes objects' shape and estimates their center points through image processing. Through the perspective transformation, the top-view image is obtained from the original image taken at an oblique position. The line and circular hough transformations are applied to recognize square and circular shapes respectively. In addition, the center of gravity of each figure are accurately detected in units of pixels. The test results show that the shape recognition rate is more than 98.75% under 180 ~ 250 lux of light and the positioning error rate is less than 0.87% under 50 ~ 120 lux. These values sufficiently meet the needs of the corresponding market. In addition, the processing delay is also less than 0.5 seconds per frame, so the proposed algorithm is suitable for commercial purpose.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.20 no.3
• /
• pp.113-120
• /
• 2010

Content security and privacy protection are important issues in emerging network-based video surveillance applications. Especially, satisfying both real-time constraint and energy efficiency with embedded system-based video sensors is challenging since the battery-operated sensors need to compress and protect video content in real-time. In this paper, we propose a multicore-based solution to compress and protect video surveillance data, and evaluate the effectiveness of the solution in terms of both real-time constraint and energy efficiency. Based on the experimental results with MPEG2/AES software, we confirm that the multicore-based solution can improve the energy efficiency of a singlecore-based solution by a factor of 30 under the real-time constraint.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.17-22
• /
• 2022

In this paper, we design a lightweight embedded device that can support intelligent edge computing, and show that the device quickly detects an object in an image input from a camera device in real time. The proposed system can be applied to environments without pre-installed infrastructure, such as an intelligent video control system for industrial sites or military areas, or video security systems mounted on autonomous vehicles such as drones. The On-Device AI(Artificial intelligence) technology is increasingly required for the widespread application of intelligent vision recognition systems. Computing offloading from an image data acquisition device to a nearby edge device enables fast service with less network and system resources than AI services performed in the cloud. In addition, it is expected to be safely applied to various industries as it can reduce the attack surface vulnerable to various hacking attacks and minimize the disclosure of sensitive data.