• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1989-2011
• /
• 2019

Vehicle detection based on aerial images is an interesting and challenging research topic. Most of the traditional vehicle detection methods are based on the sliding window search algorithm, but these methods are not sufficient for the extraction of object features, and accompanied with heavy computational costs. Recent studies have shown that convolutional neural network algorithm has made a significant progress in computer vision, especially Faster R-CNN. However, this algorithm mainly detects objects in natural scenes, it is not suitable for detecting small object in aerial view. In this paper, an accurate and effective vehicle detection algorithm based on Faster R-CNN is proposed. Our method fuse a hyperactive feature map network with Eltwise model and Concat model, which is more conducive to the extraction of small object features. Moreover, setting suitable anchor boxes based on the size of the object is used in our model, which also effectively improves the performance of the detection. We evaluate the detection performance of our method on the Munich dataset and our collected dataset, with improvements in accuracy and effectivity compared with other methods. Our model achieves 82.2% in recall rate and 90.2% accuracy rate on Munich dataset, which has increased by 2.5 and 1.3 percentage points respectively over the state-of-the-art methods.

• 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.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.7B
• /
• pp.550-556
• /
• 2008

Swam intelligence refers that a large group of simple and unsophisticated entities work together to achieve complex and significant tasks. Researches using such swarm intelligence has been performed in the network routing area. Expecially, it has been well known that routing in mobile ad-hoc networks whose features are dynamic topology and routing based on the local information is one of the applications of swarm intelligence. In this paper, we propose an ant-based routing method for MANET. The proposed method sets its goals to reduce overheads by managing ants efficiently, and to reduce route set up time. The results obtained from simulations proved that the proposed method provides shorter path set-up time and end-to-end delay and less overhead while providing comparable packet delivery ratio.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.528-529
• /
• 2023

Due to vast points and irregular structure, labeling full points in large-scale point clouds is highly tedious and time-consuming. To resolve this issue, we propose a novel point-based transformer network in weakly-supervised semantic segmentation, which only needs 0.1% point annotations. Our network introduces general local features, representing global factors from different neighborhoods based on their order positions. Then, we share query point weights to local features through point attention to reinforce impacts, which are essential in determining sparse point labels. Geometric encoding is introduced to balance query point impact and remind point position during training. As a result, one point in specific local areas can obtain global features from corresponding ones in other neighborhoods and reinforce from its query points. Experimental results on benchmark large-scale point clouds demonstrate our proposed network's state-of-the-art performance.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.9
• /
• pp.1146-1151
• /
• 2018

Recently, researches on the intelligence of electric power facilities have been trying to apply artificial intelligence techniques as computer platforms have improved. In particular, faults occurring in substation should be able to quickly identify possible faults and minimize power fault recovery time. This paper presents fault location technique for 154kV substation using neural network. We constructed a training matrix based on the operating conditions of the circuit breaker and IED to identify the fault location of each component of the target 154kV substation, such as line, bus, and transformer. After performing the training to identify the fault location by the neural network using Weka software, the performance of fault location discrimination of the designed neural network was confirmed.

• Smart Structures and Systems
• /
• v.32 no.3
• /
• pp.179-193
• /
• 2023

This study explores an alternative to the existing centralized process for data anomaly detection in modern Internet of Things (IoT)-based structural health monitoring (SHM) systems. An edge intelligence framework is proposed for the early detection and classification of various data anomalies facilitating quality enhancement of acquired data before transmitting to a central system. State-of-the-art deep neural network pruning techniques are investigated and compared aiming to significantly reduce the network size so that it can run efficiently on resource-constrained edge devices such as wireless smart sensors. Further, depthwise separable convolution (DSC) is invoked, the integration of which with advanced structural pruning methods exhibited superior compression capability. Last but not least, quantization-aware training (QAT) is adopted for faster processing and lower memory and power consumption. The proposed edge intelligence framework will eventually lead to reduced network overload and latency. This will enable intelligent self-adaptation strategies to be employed to timely deal with a faulty sensor, minimizing the wasteful use of power, memory, and other resources in wireless smart sensors, increasing efficiency, and reducing maintenance costs for modern smart SHM systems. This study presents a theoretical foundation for the proposed framework, the validation of which through actual field trials is a scope for future work.

• Journal of the Korean Society of Safety
• /
• v.38 no.1
• /
• pp.1-8
• /
• 2023

It is extremely important to design safety-guaranteed industrial processes because such process determine the ultimate outcomes of industrial activities, including worker safety. Application of artificial intelligence (AI) in industrial safety involves modeling industrial safety systems by using vast amounts of safety-related data, accident prediction, and accident prevention based on predictions. As a preliminary step toward realizing AI-based industrial safety in Korea, this study discusses neural network-based modeling of industrial safety systems. The input variables that are the most discriminatory relative to the output variables of industrial safety processes are selected using two information-theoretic measures, namely entropy and cross entropy. Normalized frequency and severity of industrial accidents are selected as the output variables. Our simulation results confirm the effectiveness of the proposed neural network model and, therefore, the feasibility of extending the model to include more input and output variables.

• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.27-33
• /
• 2023

Digitalization due to COVID-19 has rapidly developed artificial intelligence-based voice recognition technology. However, this technology causes unfair social problems, such as race and gender discrimination if datasets are biased against some groups, and degrades the reliability and security of artificial intelligence services. In this work, we compare and analyze accuracy-based unfairness in biased data environments using VGGNet (Visual Geometry Group Network), ResNet (Residual Neural Network), and MobileNet, which are representative CNN (Convolutional Neural Network) models of artificial intelligence. Experimental results show that ResNet34 showed the highest accuracy for women and men at 91% and 89.9%in Top1-accuracy, while ResNet18 showed the slightest accuracy difference between genders at 1.8%. The difference in accuracy between genders by model causes differences in service quality and unfair results between men and women when using the service.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1301-1306
• /
• 2018

Artificial intelligence is one of the key technologies of the Fourth Industrial Revolution. This paper introduces the diverse kinds of approaches to subjects that tackle diverse kinds of research fields such as model-based MS approach, deep neural network model, image edge detection approach, cross-layer optimization model, LSSVM approach, screen design approach, CPU-GPU hybrid approach and so on. The research on Superintelligence and superconnection for IoT and big data is also described such as 'superintelligence-based systems and infrastructures', 'superconnection-based IoT and big data systems', 'analysis of IoT-based data and big data', 'infrastructure design for IoT and big data', 'artificial intelligence applications', and 'superconnection-based IoT devices'.

• Korean Journal of Artificial Intelligence
• /
• v.6 no.2
• /
• pp.11-15
• /
• 2018

Breast cancer is one of the leading causes of cancer related death among women. So prediction of overall survival status is important into decided in adjuvant treatment. Deep belief network is a kind of artificial intelligence (AI). We intended to construct prediction model by deep belief network using associated clinicopathologic factors. 103881 cases were found in the Korean Breast Cancer Registry. After preprocessing of data, a total of 15733 cases were enrolled in this study. The median follow-up period was 82.4 months. In univariate analysis for overall survival (OS), the patients with advanced AJCC stage showed relatively high HR (HR=1.216 95% CI: 0.011-289.331, p=0.001). Based on results of univariate and multivariate analysis, input variables for learning model included 17 variables associated with overall survival rate. output was presented in one of two states: event or cencored. Individual sensitivity of training set and test set for predicting overall survival status were 89.6% and 91.2% respectively. And specificity of that were 49.4% and 48.9% respectively. So the accuracy of our study for predicting overall survival status was 82.78%. Prediction model based on Deep belief network appears to be effective in predicting overall survival status and, in particular, is expected to be applicable to decide on adjuvant treatment after surgical treatment.