• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.99-103
• /
• 2023

NFT technology is mostly used to create digital drawings, characters, and items, and to simply buy and sell, but research and development to spread to various contents of NFT are somewhat marginal. Therefore, this study aims to solve the above-described problems. Depending on the exercise performance, it allows users to create and trade custom NFTs. In addition, it supports users to own customized digital works through exercise performance or to make money by trading them. Through it, the aim is to enhance users' positive interest in exercise and provide devices and methods for providing customized NFT creation and trading services that can help them develop exercise habits.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.129-133
• /
• 2023

Image compression is a fundamental technique in the field of digital image processing, which will help to decrease the storage space and to transmit the files efficiently. Recently many deep learning techniques have been proposed to promise results on image compression field. Since many image compression techniques have artifact problems, this paper has compared two deep learning approaches to verify their performance experimentally to solve the problems. One of the approaches is a deep autoencoder technique, and another is a deep convolutional neural network (CNN). For those results in the performance of peak signal-to-noise and root mean square error, this paper shows that deep autoencoder method has more advantages than deep CNN approach.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.128-132
• /
• 2023

Recently, with the development of deep learning technology, research on pedestrian attribute recognition technology using deep neural networks has been actively conducted. Existing pedestrian attribute recognition techniques can be obtained in such a way as global-based, regional-area-based, visual attention-based, sequential prediction-based, and newly designed loss function-based, depending on how pedestrian attributes are detected. It is known that the performance of these pedestrian attribute recognition technologies varies greatly depending on the type of backbone network that constitutes the deep neural networks model. Therefore, in this paper, several backbone networks are applied to the baseline pedestrian attribute recognition model and the performance changes of the model are analyzed. In this paper, the analysis is conducted using Resnet34, Resnet50, Resnet101, Swin-tiny, and Swinv2-tiny, which are representative backbone networks used in the fields of image classification, object detection, etc. Furthermore, this paper analyzes the change in time complexity when inferencing each backbone network using a CPU and a GPU.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.4
• /
• pp.172-178
• /
• 2023

With the expansion of metaverse content and hardware platforms, various interactions in the virtual world have been built, raising expectations for an increase in immersion which is a major element of the metaverse. However, among hardware platforms that increase virtual immersion elements, the typical HMD platform can be a barrier to new user inflows due to its high cost. Thus, this paper focused on improving virtual-to-real interactions by extracting motion data using relatively inexpensive webcam equipment in PC environments, utilizing Unity game engines, Photon unity network, multi-platform implementations, and Barracuda neural network inference libraries.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.142-148
• /
• 2023

In this paper, we identify performance issues in executing compute kernels from PolyBench, which includes compute kernels that are the core computational units of various data-intensive workloads, such as deep learning and data-intensive applications, on Processing-in-Memory (PIM) devices. Therefore, using our in-house simulator, we measured and compared the various performance metrics of workloads based on traditional out-of-order and in-order processors with Processing-in-Memory-based systems. As a result, the PIM-based system improves performance compared to other computing models due to the short-term data reuse characteristic of computational kernels from PolyBench. However, some kernels perform poorly in PIM-based systems without a multi-layer cache hierarchy due to some kernel's long-term data reuse characteristics. Hence, our evaluation and analysis results suggest that further research should consider dynamic and workload pattern adaptive approaches to overcome performance degradation from computational kernels with long-term data reuse characteristics and hidden data locality.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.73-77
• /
• 2023

As the DeFi market continues to expand, fraudulent activities using smart contracts have also increased. HoneyPot and Ponzi schemes are well-known frauds that exploit smart contracts. While several studies have demonstrated the potential to detect smart contracts implementing these scams, there has been a lack of research focusing on simultaneously detecting both types of fraud. This paper addresses this gap by harnessing artificial intelligence to conduct experiments for the detection of both HoneyPot and Ponzi schemes. The study employs the CNN (Convolutional Neural Network) model, commonly used for malware detection. To effectively utilize CNN, the bytecode of smart contracts is transformed into visual representations. The experimental results showcase a recall rate of 0.89 and an F1 score of 0.85, indicating promising detection capabilities.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.78-83
• /
• 2023

This paper proposes a lightweight trace-driven Processing-In-Memory (PIM) simulator, TP-Sim. TP-Sim is a General Purpose PIM (GP-PIM) simulator that evaluates various PIM system performance-related metrics. Based on instruction and memory traces extracted from the Intel Pin tool, TP-Sim can replay trace files for multiple models of PIM architectures to compare its performance. To verify the availability of TP-Sim, we estimated three different system configurations on the STREAM benchmark. Compared to the traditional Host CPU-only systems with conventional memory hierarchy, simple GP-PIM architecture achieved better performance; even the Host CPU has the same number of in-order cores. For further study, we also extend TP-Sim as a part of a heterogeneous system simulator that contains CPU, GPGPU, and PIM as its primary and co-processors.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.1
• /
• pp.19-24
• /
• 2024

It is not an exaggeration to say that a single fire causes a lot of damage, so fires are one of the disaster situations that must be alerted as soon as possible. Various technologies have been utilized so far because preventing and detecting fires can never be completely accomplished with individual human efforts. Recently, deep learning technology has been developed, and fire detection systems using object detection neural networks are being actively studied. In this paper, we propose a new fire detection system that improves the previously studied fire detection system. We train the YOLOv8 model using refined datasets through improved labeling methods, derive results, and demonstrate the superiority of the proposed system by comparing it with the results of previous studies.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.3
• /
• pp.135-139
• /
• 2024

Public datasets, which are freely available and often labeled, play a crucial role in training object detection models in computer vision. While public datasets are effective for developing general object detection models, they may not be ideal for specialized tasks. For specific object detection needs, it is more beneficial to create and use a dataset tailored to the target object. This paper proposes a method for extracting a target-specific dataset from public datasets to develop object detection models with superior performance for the target object. This approach not only improves detection accuracy, but also reduces training data requirements and complexity. We evaluate the performance of the proposed method using the latest object detection model YOLOv10.

• Journal of the Korea Computer Graphics Society
• /
• v.21 no.1
• /
• pp.1-11
• /
• 2015

Researchers have developed virtual reality environments to provide audience with more visually immersive experiences than previously possible. One of the most popular solutions to build the immersive VR space is a multi-projection technique. However, utilization of multiple projectors requires large spaces, expensive cost, and accurate geometry calibration among projectors. This paper presents a novel omnidirectional projection system with a single projector and a single spherical mirror.We newly designed the simple and intuitive calibration system to define the shape of environment and the relative position of mirror/projector. For successful image projection, our optimized omnidirectional image generation step solves image distortion produced by the spherical mirror and a calibration problem produced by unknown parameters such as the shape of environment and the relative position between the mirror and the projector. Additionally, the focus correction is performed to improve the quality of the projection. The experiment results show that our method can generate the optimized image given a normal panoramic image for omnidirectional projection in a rectangular space.