• Title/Summary/Keyword: Machine Learning

Search Result 5,605, Processing Time 0.038 seconds

Personal Information Detection and Blurring Cloud Services Based on Machine Learning (머신러닝에 기반을 둔 사진 속 개인정보 검출 및 블러링 클라우드 서비스)

  • Kim, Min-jeong;Lee, Soo-young;Lee, Jiyoung;Ham, Na-youn
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2019.05a
    • /
    • pp.152-155
    • /
    • 2019
  • 클라우드가 대중화되어 많은 모바일 유저들이 자동 백업 기능을 사용하면서 민감한 개인정보가 포함된 사진들이 무분별하게 클라우드에 업로드 되고 있다. 개인정보를 포함한 클라우드가 악의적으로 해킹 될 시, 사진에 포함된 지문, 자동차 번호판, 카드 번호 등이 유출됨에 따라 대량의 개인정보가 유출될 가능성이 크다. 이에 따라 적절한 기준에 맞게 사진 속 개인 정보 유출을 막을 수 있는 기술의 필요성이 대두되고 있다. 현재의 클라우드 시스템의 문제를 해결하고자 본 연구는 모바일 기기에서 클라우드 서버로 사진을 백업하는 과정에서 영역 검출과 블러링의 과정을 제안하고 있다. 클라우드 업로드 과정에서 사진 속의 개인 정보를 검출한 뒤 이를 블러링하여 클라우드에 저장함으로써 악의적인 접근이 행해지더라도 개인정보의 유출을 방지할 수 있다. 머신러닝과 computer vision library등을 이용하여 이미지 내에 민감한 정보를 포함하고 있는 영역을 학습된 모델을 통해 검출한 뒤, OpenCV를 이용하여 블러링처리를 진행한다 사진 속에 포함될 수 있는 생체정보인 지문은 손 영역을 검출한 뒤, 해당 영역을 블러링을 하여 업로드하고 카드번호나 자동차 번호판이 포함된 사진은 영역을 블러링한 뒤, 암호화하여 업로드 된다. 후에 필요에 따라 본인인증을 거친 후 일정기간 열람을 허용하지만 사용되지 않을 경우 삭제되도록 한다. 개인정보 유출로 인한 피해가 꾸준히 증가하고 있는 지금, 사진 속의 개인 정보를 보호하는 기술은 안전한 통신과 더불어 클라우드의 사용을 더 편리하게 할 수 있을 것으로 기대된다.

Artificial Intelligence Technology Trends and IBM Watson References in the Medical Field (인공지능 왓슨 기술과 보건의료의 적용)

  • Lee, Kang Yoon;Kim, Junhewk
    • Korean Medical Education Review
    • /
    • v.18 no.2
    • /
    • pp.51-57
    • /
    • 2016
  • This literature review explores artificial intelligence (AI) technology trends and IBM Watson health and medical references. This study explains how healthcare will be changed by the evolution of AI technology, and also summarizes key technologies in AI, specifically the technology of IBM Watson. We look at this issue from the perspective of 'information overload,' in that medical literature doubles every three years, with approximately 700,000 new scientific articles being published every year, in addition to the explosion of patient data. Estimates are also forecasting a shortage of oncologists, with the demand expected to grow by 42%. Due to this projected shortage, physicians won't likely be able to explore the best treatment options for patients in clinical trials. This issue can be addressed by the AI Watson motivation to solve healthcare industry issues. In addition, the Watson Oncology solution is reviewed from the end user interface point of view. This study also investigates global company platform business to explain how AI and machine learning technology are expanding in the market with use cases. It emphasizes ecosystem partner business models that can support startup and venture businesses including healthcare models. Finally, we identify a need for healthcare company partnerships to be reviewed from the aspect of solution transformation. AI and Watson will change a lot in the healthcare business. This study addresses what we need to prepare for AI, Cognitive Era those are understanding of AI innovation, Cloud Platform business, the importance of data sets, and needs for further enhancement in our knowledge base.

Leakage detection and management in water distribution systems

  • Sangroula, Uchit;Gnawali, Kapil;Koo, KangMin;Han, KukHeon;Yum, KyungTaek
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2019.05a
    • /
    • pp.160-160
    • /
    • 2019
  • Water is a limited source that needs to be properly managed and distributed to the ever-growing population of the world. Rapid urbanization and development have increased the overall water demand of the world drastically. However, there is loss of billions of liters of water every year due to leakages in water distribution systems. Such water loss means significant financial loss for the utilities as well. World bank estimates a loss of $14 billion annually from wasted water. To address these issues and for the development of efficient and reliable leakage management techniques, high efforts have been made by the researchers and engineers. Over the past decade, various techniques and technologies have been developed for leakage management and leak detection. These include ideas such as pressure management in water distribution networks, use of Advanced Metering Infrastructure, use of machine learning algorithms, etc. For leakage detection, techniques such as acoustic technique, and in recent yeats transient test-based techniques have become popular. Smart Water Grid uses two-way real time network monitoring by utilizing sensors and devices in the water distribution system. Hence, valuable real time data of the water distribution network can be collected. Best results and outcomes may be produced by proper utilization of the collected data in unison with advanced detection and management techniques. Long term reduction in Non Revenue Water can be achieved by detecting, localizing and repairing leakages as quickly and as efficiently as possible. However, there are still numerous challenges to be met and future research works to be conducted in this field.

  • PDF

Optimization of Alumina Tape Casting Process for Building Big Data (빅데이터 구축을 위한 알루미나 테이프 캐스팅 공정 최적화)

  • Kim, Dong Ha;Kim, Shi Yeon;Lee, Joo Sung;Yeo, Dong-Hun;Shin, Hyo-Soon;Yoon, Sang-Ok
    • Journal of the Korean Institute of Electrical and Electronic Material Engineers
    • /
    • v.32 no.6
    • /
    • pp.483-489
    • /
    • 2019
  • For machine learning techniques, a large amount of high-quality material property data should be accumulated. In this study, several data for an alumina tape casting process were produced with the variables of slurry viscosity, gap size, and coating speed. The alumina tapes were manufactured in the range of 1,000~6,000 cps for slurry viscosity, $300{\sim}1,000{\mu}m$ for gap size, and 0.5~2.0 m/min for coating speed. As a result, the lower the viscosity, coating speed, and gap size, the more pore-free tapes could be manufactured. The viscosity of the slurry limited the minimum thickness of the tape. Green sheets with high packing density were manufactured from the slurry of 100~6,000 cps slurry viscosity, coating speed of 0.5 m/min, and a $300{\sim}500{\mu}m$ gap size.

EXCUTE REAL-TIME PROCESSING IN RTOS ON 8BIT MCU WITH TEMP AND HUMIDITY SENSOR

  • Kim, Ki-Su;Lee, Jong-Chan
    • Journal of the Korea Society of Computer and Information
    • /
    • v.24 no.11
    • /
    • pp.21-27
    • /
    • 2019
  • Recently, embedded systems have been introduced in various fields such as smart factories, industrial drones, and medical robots. Since sensor data collection and IoT functions for machine learning and big data processing are essential in embedded systems, it is essential to port the operating system that is suitable for the function requirements. However, in embedded systems, it is necessary to separate the hard real-time system, which must process within a fixed time according to service characteristics, and the flexible real-time system, which is more flexible in processing time. It is difficult to port the operating system to a low-performance embedded device such as 8BIT MCU to perform simultaneous real-time. When porting a real-time OS (RTOS) to a low-specification MCU and performing a number of tasks, the performance of the real-time and general processing greatly deteriorates, causing a problem of re-designing the hardware and software if a hard real-time system is required for an operating system ported to a low-performance MCU such as an 8BIT MCU. Research on the technology that can process real-time processing system requirements on RTOS (ported in low-performance MCU) is needed.

RNN-LSTM Based Soil Moisture Estimation Using Terra MODIS NDVI and LST (Terra MODIS NDVI 및 LST 자료와 RNN-LSTM을 활용한 토양수분 산정)

  • Jang, Wonjin;Lee, Yonggwan;Lee, Jiwan;Kim, Seongjoon
    • Journal of The Korean Society of Agricultural Engineers
    • /
    • v.61 no.6
    • /
    • pp.123-132
    • /
    • 2019
  • This study is to estimate the spatial soil moisture using Terra MODIS (Moderate Resolution Imaging Spectroradiometer) satellite data and machine learning technique. Using the 3 years (2015~2017) data of MODIS 16 days composite NDVI (Normalized Difference Vegetation Index) and daily Land Surface Temperature (LST), ground measured precipitation and sunshine hour of KMA (Korea Meteorological Administration), the RDA (Rural Development Administration) 10 cm~30 cm average TDR (Time Domain Reflectometry) measured soil moisture at 78 locations was tested. For daily analysis, the missing values of MODIS LST by clouds were interpolated by conditional merging method using KMA surface temperature observation data, and the 16 days NDVI was linearly interpolated to 1 day interval. By applying the RNN-LSTM (Recurrent Neural Network-Long Short Term Memory) artificial neural network model, 70% of the total period was trained and the rest 30% period was verified. The results showed that the coefficient of determination ($R^2$), Root Mean Square Error (RMSE), and Nash-Sutcliffe Efficiency were 0.78, 2.76%, and 0.75 respectively. In average, the clay soil moisture was estimated well comparing with the other soil types of silt, loam, and sand. This is because the clay has the intrinsic physical property for having narrow range of soil moisture variation between field capacity and wilting point.

A Study on Rotational Alignment Algorithm for Improving Character Recognition (문자 인식 향상을 위한 회전 정렬 알고리즘에 관한 연구)

  • Jin, Go-Whan
    • Journal of the Korea Convergence Society
    • /
    • v.10 no.11
    • /
    • pp.79-84
    • /
    • 2019
  • Video image based technology is being used in various fields with continuous development. The demand for vision system technology that analyzes and discriminates image objects acquired through cameras is rapidly increasing. Image processing is one of the core technologies of vision systems, and is used for defect inspection in the semiconductor manufacturing field, object recognition inspection such as the number of tire surfaces and symbols. In addition, research into license plate recognition is ongoing, and it is necessary to recognize objects quickly and accurately. In this paper, propose a recognition model through the rotational alignment of objects after checking the angle value of the tilt of the object in the input video image for the recognition of inclined objects such as numbers or symbols marked on the surface. The proposed model can perform object recognition of the rotationally sorted image after extracting the object region and calculating the angle of the object based on the contour algorithm. The proposed model extracts the object region based on the contour algorithm, calculates the angle of the object, and then performs object recognition on the rotationally aligned image. In future research, it is necessary to study template matching through machine learning.

Modeling and Selecting Optimal Features for Machine Learning Based Detections of Android Malwares (머신러닝 기반 안드로이드 모바일 악성 앱의 최적 특징점 선정 및 모델링 방안 제안)

  • Lee, Kye Woong;Oh, Seung Taek;Yoon, Young
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.8 no.11
    • /
    • pp.427-432
    • /
    • 2019
  • In this paper, we propose three approaches to modeling Android malware. The first method involves human security experts for meticulously selecting feature sets. With the second approach, we choose 300 features with the highest importance among the top 99% features in terms of occurrence rate. The third approach is to combine multiple models and identify malware through weighted voting. In addition, we applied a novel method of eliminating permission information which used to be regarded as a critical factor for distinguishing malware. With our carefully generated feature sets and the weighted voting by the ensemble algorithm, we were able to reach the highest malware detection accuracy of 97.8%. We also verified that discarding the permission information lead to the improvement in terms of false positive and false negative rates.

A Feature Set Selection Approach Based on Pearson Correlation Coefficient for Real Time Attack Detection (실시간 공격 탐지를 위한 Pearson 상관계수 기반 특징 집합 선택 방법)

  • Kang, Seung-Ho;Jeong, In-Seon;Lim, Hyeong-Seok
    • Convergence Security Journal
    • /
    • v.18 no.5_1
    • /
    • pp.59-66
    • /
    • 2018
  • The performance of a network intrusion detection system using the machine learning method depends heavily on the composition and the size of the feature set. The detection accuracy, such as the detection rate or the false positive rate, of the system relies on the feature composition. And the time it takes to train and detect depends on the size of the feature set. Therefore, in order to enable the system to detect intrusions in real-time, the feature set to beused should have a small size as well as an appropriate composition. In this paper, we show that the size of the feature set can be further reduced without decreasing the detection rate through using Pearson correlation coefficient between features along with the multi-objective genetic algorithm which was used to shorten the size of the feature set in previous work. For the evaluation of the proposed method, the experiments to classify 10 kinds of attacks and benign traffic are performed against NSL_KDD data set.

  • PDF

Development of hybrid activation function to improve accuracy of water elevation prediction algorithm (수위예측 알고리즘 정확도 향상을 위한 Hybrid 활성화 함수 개발)

  • Yoo, Hyung Ju;Lee, Seung Oh
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2019.05a
    • /
    • pp.363-363
    • /
    • 2019
  • 활성화 함수(activation function)는 기계학습(machine learning)의 학습과정에 비선형성을 도입하여 심층적인 학습을 용이하게 하고 예측의 정확도를 높이는 중요한 요소 중 하나이다(Roy et al., 2019). 일반적으로 기계학습에서 사용되고 있는 활성화 함수의 종류에는 계단 함수(step function), 시그모이드 함수(sigmoid 함수), 쌍곡 탄젠트 함수(hyperbolic tangent function), ReLU 함수(Rectified Linear Unit function) 등이 있으며, 예측의 정확도 향상을 위하여 다양한 형태의 활성화 함수가 제시되고 있다. 본 연구에서는 기계학습을 통하여 수위예측 시 정확도 향상을 위하여 Hybrid 활성화 함수를 제안하였다. 연구대상지는 조수간만의 영향을 받는 한강을 대상으로 선정하였으며, 2009년 ~ 2018년까지 10년간의 수문자료를 활용하였다. 수위예측 알고리즘은 Python 내 Tensorflow의 RNN (Recurrent Neural Networks) 모델을 이용하였으며, 강수량, 수위, 조위, 댐 방류량, 하천 유량의 수문자료를 학습시켜 3시간 및 6시간 후의 수위를 예측하였다. 예측정확도 향상을 위하여 입력 데이터는 정규화(Normalization)를 시켰으며, 민감도 분석을 통하여 신경망모델의 은닉층 개수, 학습률의 최적 값을 도출하였다. Hybrid 활성화 함수는 쌍곡 탄젠트 함수와 ReLU 함수를 혼합한 형태로 각각의 가중치($w_1,w_2,w_1+w_2=1$)를 변경하여 정확도를 평가하였다. 그 결과 가중치의 비($w_1/w_2$)에 따라서 예측 결과의 RMSE(Roote Mean Square Error)가 최소가 되고 NSE (Nash-Sutcliffe model Efficiency coefficient)가 최대가 되는 지점과 Peak 수위의 예측정확도가 최대가 되는 지점을 확인할 수 있었다. 본 연구는 현재 Data modeling을 통한 수위예측의 정확도 향상을 위해 기초가 되는 연구이나, 향후 다양한 형태의 활성화 함수를 제안하여 정확도를 향상시킨다면 예측 결과를 통하여 침수예보에 대한 의사결정이 가능할 것으로 기대된다.

  • PDF