• Journal of Software Assessment and Valuation
• /
• v.15 no.1
• /
• pp.63-70
• /
• 2019

These days, as Interest in Image recognition with deep learning is increasing, there has been a lot of research in image recognition using deep learning. In this study, we propose a system for classifying rocks through rock images of 18 types of rock(6 types of igneous, 6 types of metamorphic, 6 types of sedimentary rock) which are addressed in the high school curriculum, using CNN model based on Tensorflow, deep learning open source framework. As a result, we developed a classifier to distinguish rocks by learning the images of rocks and confirmed the classification performance of rock classifier. Finally, through the mobile application implemented, students can use the application as a learning tool in classroom or on-site experience.

• The Journal of Korea Robotics Society
• /
• v.16 no.3
• /
• pp.270-275
• /
• 2021

Most of the initial forms of cooperative robots were intended to repeat simple tasks in a given space. So, they showed no significant difference from industrial robots. However, research for improving worker's productivity and supplementing human's limited working hours is expanding. Also, there have been active attempts to use it as a service robot by applying AI technology. In line with these social changes, we produced a mobile manipulator that can improve the worker's efficiency and completely replace one person. First, we combined cooperative robot with mobile robot. Second, we applied speech recognition technology and deep learning based object detection. Finally, we integrated all the systems by ROS (robot operating system). This system can communicate with workers by voice and drive autonomously and perform the Pick & Place task.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.5
• /
• pp.53-63
• /
• 2019

To provide a hand gesture interface through deep learning in mobile environments, research on the light-weighting of networks is essential for high recognition rates while at the same time preventing degradation of execution speed. This paper proposes a method of real-time recognition of written characters in the air using a finger on mobile devices through the light-weighting of deep-learning model. Based on the SSD (Single Shot Detector), which is an object detection model that utilizes MobileNet as a feature extractor, it detects index finger and generates a result text image by following fingertip path. Then, the image is sent to the server to recognize the characters based on the learned OCR model. To verify our method, 12 users tested 1,000 words using a GALAXY S10+ and recognized their finger with an average accuracy of 88.6%, indicating that recognized text was printed within 124 ms and could be used in real-time. Results of this research can be used to send simple text messages, memos, and air signatures using a finger in mobile environments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4572-4586
• /
• 2019

Mobile Edge Computing (MEC) and Information-Centric Networking (ICN) are essential network architectures for the future Internet. The advantages of MEC and ICN such as computation and storage capabilities at the edge of the network, in-network caching and named-data communication paradigm can greatly improve the quality of video streaming applications. However, the packet loss in wireless network environments still affects the video streaming performance and the existing loss recovery approaches in ICN does not exploit the capabilities of MEC. This paper proposes a Deep Learning based Loss Recovery Mechanism (DL-LRM) for video streaming over MEC based ICN. Different with existing approaches, the Forward Error Correction (FEC) packets are generated at the edge of the network, which dramatically reduces the workload of core network and backhaul. By monitoring network states, our proposed DL-LRM controls the FEC request rate by deep reinforcement learning algorithm. Considering the characteristics of video streaming and MEC, in this paper we develop content caching detection and fast retransmission algorithm to effectively utilize resources of MEC. Experimental results demonstrate that the DL-LRM is able to adaptively adjust and control the FEC request rate and achieve better video quality than the existing approaches.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.570-590
• /
• 2024

Breast cancer ranks among the most prevalent forms of malignancy and foremost cause of death by cancer worldwide. It is not preventable. Early and precise detection is the only remedy for lowering the rate of mortality and improving the probability of survival for victims. In contrast to present procedures, thermography aids in the early diagnosis of cancer and thereby saves lives. But the accuracy experiences detrimental impact by low sensitivity for small and deep tumours and the subjectivity by physicians in interpreting the images. Employing deep learning approaches for cancer detection can enhance the efficacy. This study explored the utilization of thermography in early identification of breast cancer with the use of a publicly released dataset known as the DMR-IR dataset. For this purpose, we employed a novel approach that entails the utilization of a pre-trained MobileNetV2 model and fine tuning it through transfer learning techniques. We created three models using MobileNetV2: one was a baseline transfer learning model with weights trained from ImageNet dataset, the second was a fine-tuned model with an adaptive learning rate, and the third utilized early stopping with callbacks during fine-tuning. The results showed that the proposed methods achieved average accuracy rates of 85.15%, 95.19%, and 98.69%, respectively, with various performance indicators such as precision, sensitivity and specificity also being investigated.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.306-308
• /
• 2018

This paper proposes a variant malicious code detection algorithm in a mobile environment using a deep learning algorithm. In order to solve the problem of malicious code detection method based on Android, we have proved high detection rate through signature based malicious code detection method and realtime malicious file detection algorithm using machine learning method.

• ETRI Journal
• /
• v.45 no.2
• /
• pp.318-328
• /
• 2023

Recently, embedded systems, such as mobile platforms, have multiple processing units that can operate in parallel, such as centralized processing units (CPUs) and neural processing units (NPUs). We can use deep-learning compilers to generate machine code optimized for these embedded systems from a deep neural network (DNN). However, the deep-learning compilers proposed so far generate codes that sequentially execute DNN operators on a single processing unit or parallel codes for graphic processing units (GPUs). In this study, we propose PartitionTuner, an operator scheduler for deep-learning compilers that supports multiple heterogeneous PUs including CPUs and NPUs. PartitionTuner can generate an operator-scheduling plan that uses all available PUs simultaneously to minimize overall DNN inference time. Operator scheduling is based on the analysis of DNN architecture and the performance profiles of individual and group operators measured on heterogeneous processing units. By the experiments for seven DNNs, PartitionTuner generates scheduling plans that perform 5.03% better than a static type-based operator-scheduling technique for SqueezeNet. In addition, PartitionTuner outperforms recent profiling-based operator-scheduling techniques for ResNet50, ResNet18, and SqueezeNet by 7.18%, 5.36%, and 2.73%, respectively.

• Journal of Semiconductor Engineering
• /
• v.2 no.2
• /
• pp.130-135
• /
• 2021

Recently, deep neural networks (DNNs) are actively used for action control so that an autonomous system, such as the robot, can perform human-like behaviors and operations. Unlike recognition tasks, the real-time operation is essential in action control, and it is too slow to use remote learning on a server communicating through a network. New learning techniques, such as reinforcement learning (RL), are needed to determine and select the correct robot behavior locally. In this paper, we propose an energy-efficient DNN processor with a LUT-based processing engine and near-zero skipper. A CNN-based facial emotion recognition and an RNN-based emotional dialogue generation model is integrated for natural HRI system and tested with the proposed processor. It supports 1b to 16b variable weight bit precision with and 57.6% and 28.5% lower energy consumption than conventional MAC arithmetic units for 1b and 16b weight precision. Also, the near-zero skipper reduces 36% of MAC operation and consumes 28% lower energy consumption for facial emotion recognition tasks. Implemented in 65nm CMOS process, the proposed processor occupies 1784×1784 um2 areas and dissipates 0.28 mW and 34.4 mW at 1fps and 30fps facial emotion recognition tasks.

• Journal of Information Processing Systems
• /
• v.18 no.2
• /
• pp.197-207
• /
• 2022

The applications and user interfaces (UIs) of smart mobile devices are constantly diversifying. For example, deep learning can be an innovative solution to classify widgets in screen images for increasing convenience. To this end, the present research leverages captured images and the ReDraw dataset to write deep learning datasets for image classification purposes. First, as the validation for datasets using ResNet50 and EfficientNet, the experiments show that the dataset composed in this study is helpful for classification according to a widget's functionality. An implementation for widget detection and classification on RetinaNet and EfficientNet is then executed. Finally, the research suggests the Widg-C and Widg-D datasets-a deep learning dataset for identifying the widgets of smart devices-and implementing them for use with representative convolutional neural network models.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.3
• /
• pp.346-354
• /
• 2024

Deep learning models require high computing power due to a substantial amount of computation. It is difficult to use them in devices with limited computing environments, such as coastal surveillance equipments. In this study, a lightweight model is constructed by analyzing the weight changes of the convolutional layers during the training process based on MobileNet and then pruning the layers that affects the model less. The performance comparison results show that the lightweight model maintains performance while reducing computational load, parameters, model size, and data processing speed. As a result of this study, an effective pruning method for constructing lightweight deep learning models and the possibility of using equipment resources efficiently through lightweight models in limited computing environments such as coastal surveillance equipments are presented.