Search

Despite recent progress of numerical air quality models, accurate prediction of fine particulate matter (PM2.5) is still challenging because of uncertainties in physical and chemical parameterizations, meteorological data, and emission inventory databases. Recent advances in artificial neural networks can be used to overcome limitations in numerical air quality models. In this study, a deep neural network (DNN) model was developed for a 3 d forecasting of 6 h average PM2.5 concentrations: the day of prediction (D+0), 1 d after prediction (D+1), and 2 d after prediction (D+2). The DNN model was evaluated against the currently operational Community Multiscale Air Quality (CMAQ) modeling system in South Korea. Our study demonstrated that the DNN model outperformed the CMAQ modeling results. The DNN model provided better forecasting skills by reducing the root-mean-squared error (RMSE) by 4.1, 2.2, and 3.0 µg m−3 for the 3 consecutive days, respectively, compared with the CMAQ. Also, the false-alarm rate (FAR) decreased by 16.9 %p (D+0), 7.5 %p (D+1), and 7.6 %p (D+2), indicating that the DNN model substantially mitigated the overprediction of the CMAQ in high PM2.5 concentrations. These results showed that the DNN model outperformed the CMAQ model when it was simultaneously trained by using the observation and forecasting data from the numerical air quality models. Notably, the forecasting data provided more benefits to the DNN modeling results as the forecasting days increased. Our results suggest that our data-driven machine learning approach can be a useful tool for air quality forecasting when it is implemented with air quality models together by reducing model-oriented systematic biases.

This study aims to develop a deep neural network (DNN) model as an artificial neural network (ANN) for the prediction of 6-hour average fine particulate matter (PM2.5) concentrations for a three-day period—the day of prediction (D+0), one day after prediction (D+1) and two days after prediction (D+2)—using observation data and forecast data obtained via numerical models. The performance of the DNN model was comparatively evaluated against that of the currently operational Community Multiscale Air Quality (CMAQ) modelling system for air quality forecasting in South Korea. In addition, the effect on predictive performance of the DNN model on using different training data was analyzed. For the D+0 forecast, the DNN model performance was superior to that of the CMAQ model, and there was no significant dependence on the training data. For the D+1 and D+2 forecasts, the DNN model that used the observation and forecast data (DNN-ALL) outperformed the CMAQ model. The root-mean-squared error (RMSE) of DNN-ALL was lower than that of the CMAQ model by 2.2 μgm−3, and 3.0 μgm−3 for the D+1 and D+2 forecasts, respectively, because the overprediction of higher concentrations was curtailed. An IOA increase of 0.46 for D+1 prediction and 0.59 for the D+2 prediction was observed in case of the DNN-ALL model compared to the IOA of the DNN model that used only observation data (DNN-OBS). In additionally, An RMSE decrease of 7.2 μgm−3 for the D+1 prediction and 6.3 μgm−3 for the D+2 prediction was observed in case of the DNN-ALL model, compared to the RMSE of DNN-OBS, indicating that the inclusion of forecast data in the training data greatly affected the DNN model performance. Considering the prediction of the 6-hour average PM2.5 concentration, the 8.8 μgm−3 RMSE of the DNN-ALL model was 2.7 μgm−3 lower than that of the CMAQ model, indicating the superior prediction performance of the former. These results suggest that the DNN model could be utilized as a better-performing air quality forecasting model than the CMAQ, and that observation data plays an important role in determining the prediction performance of the DNN model for D+0 forecasting, while prediction data does the same for D+1 and D+2 forecasting. The use of the proposed DNN model as a forecasting model may result in a reduction in the economic losses caused by pollution-mitigation policies and aid better protection of public health.

In many bandwidth-critical environments, including vehicle-to-vehicle and vehicle-to-infrastructure communications, implicit certificates such as elliptic curve Qu-Vanstone (ECQV) are frequently employed as a means to reduce the bandwidth requirement of digital signatures. In these environments, however, certain recipients such as roadside units need to verify signatures for multiple messages within considerably short time periods. In this paper, we propose two efficient methods of reducing the computational costs of signature verification when multiple digital signatures are provided together with the ECQV implicit certificates. The first method achieves this by sharing the intermediate results that are computed when public keys are extracted from ECQV certificates. The second guarantees a further speed improvement by merging the public key extraction processes into a batch signature verification process. We also present an algorithm that adaptively chooses the best verification method for the given signatures in real time. Our experimental results show that the proposed methods allow for a signature verification that is five times faster than existing methods.

The rapidly increasing expansion of distributed energy resources (DER), such as renewable energy systems and energy storage systems into the electric power system and the integration of advanced information and communication technologies enable DER owners to participate in the electricity market for grid services. For more efficient and reliable power system operation, the concept of peer-to-peer (P2P) energy trading has recently been proposed. The adoption of blockchain technology in P2P energy trading has been considered to be the most promising solution enabling secure smart contracts between prosumers and users. However, privacy concerns arise because the sensitive data and transaction records of the participants, i.e., the prosumers and the distribution system operator (DSO), become available to the blockchain nodes. Many efforts have been made to resolve this issue. A recent breakthrough in a P2P energy trading system on an Ethereum blockchain is that all bid values are encrypted using functional encryption and peer matching for trading is performed securely on these encrypted bids. Their protocol is based on a method that encodes integers to vectors and an algorithm that securely compares the ciphertexts of these vectors. However, the comparison method is not very efficient in terms of the range of possible bid values because the amount of computation grows linearly according to the size of this range. This paper addresses this challenge by proposing a new bid encoding algorithm called dual binary encoding, which dramatically reduces the amount of computation as it is only proportional to the square of the logarithm of the size of the encoding range. Moreover, we propose a practical mechanism for rebidding the remaining amount caused when the amounts from the two matching peers are not equal. Finally, the feasibility of the proposed method is evaluated by using a virtual energy trade testbed and a private Ethereum blockchain platform.

Advanced smart grid technologies enable energy prosumers to trade surplus energy from their distributed renewable energy sources with other peer prosumers through peer-to-peer (P2P) energy trading. In many previous works, P2P energy trading was facilitated by blockchain technology through blockchain’s distributive nature and capacity to run smart contracts. However, the feature that all the data and transactions on a blockchain are visible to all blockchain nodes may significantly threaten the privacy of the parties participating in P2P energy trading. There are many previous works that have attempted to mitigate this problem. However, all these works focused on the anonymity of participants but did not protect the data and transactions. To address this issue, we propose a P2P energy trading system on a blockchain where all bids are encrypted and peer matching is performed on the encrypted bids by a functional encryption-based smart contract. The system guarantees that the information encoded in the encrypted bids is protected, but the peer matching transactions are performed by the nodes in a publicly verifiable manner through smart contracts. We verify the feasibility of the proposed system by implementing a prototype composed of smart meters, a distribution system operator (DSO) server, and private Ethereum blockchain.

The development of smart meters that can frequently measure and report power consumption has enabledelectricity providers to offer various time-varying rates, including time-of-use and real-time pricing plans. High-resolution power consumption data, however, raise serious privacy concerns because sensitive information regarding an individual’s lifestyle can be revealed by analyzing these data. Although extensive research has been conducted to address these privacy concerns, previous approaches have reduced the quality of measured data. In this paper, we propose a new privacy-preserving electricity billing method that does not sacrifice data quality for privacy. The proposed method is based on the novel use of functional encryption. Experimental results on a prototype system using a real-world smart meter device and data prove the feasibility of the proposed method.

Fast growth of smartphone technology and advent of Fintech enabled smartphones to deal with more sensitive information. Although many devices applying biometric technology are released as a step for protecting sensitive information securely, there can be potential vulnerabilities if security is not considered at the design stage of a biometric system. By analyzing the potential vulnerabilities, we classify threats in biometric system design process on smartphones and we propose the design requirements for solving these problems. In addition, we propose a framework for secure biometric system design on smartphone by synthesizing the design requirements.Keywords:Biometrics, Smartphone Security, System Design Requirement, Framework 스마트폰 상의 안전한 바이오인식 시스템 설계를 위한 프레임워크 임 종 혁 † ⋅권 희 용 †† ⋅이 문 규 ††† 요 약 최근 스마트폰 기술의 빠른 발전과 핀테크의 등장으로 스마트폰은 더욱 많은 민감한 정보를 다루게 되었다. 이 같은 민감한 정보를 안전하게 보호하는 수단으로 바이오인식 기술이 적용된 다양한 기기들이 출시되고 있으나, 바이오인식 시스템 설계 시 보안을 고려하지 않을 경우 잠재적인 취약점이 존재할 수 있다. 이에 본 논문에서는 잠재적인 취약점의 분석을 통해 스마트폰 상의 바이오인식 시스템 설계 과정에서 주의할 점을 분류하고, 이를 해결하기 위한 설계 요구사항을 제시한다. 또한, 설계 요구사항을 종합하여 안전한 스마트폰 바이오인식 시스템 설계를 위한 프레임워크를 제시한다.키워드:바이오인식, 스마트폰 보안, 시스템 설계 요구사항, 프레임워크

최근 세포 영상에 대한 자동 분석이 의료 영상 분야에서 활발히 연구되고 있다이러한 세포 영상의 분석 결과는 의사의 진단 근거로 이용되기 때문에 높은 정확성이 요구되는데특히세포의 외곽선은 세포의 정보를 분석하는데 있어 매우 중요한 영향을 미친다이에 다양한 외곽선 추적 알고리즘 들이 연구되어 왔다외곽선 추적 알고리즘 은 경계선 추적 알고리즘 이라고도 하며영상에서 특정한 물체의 외곽선을 추적하는 알고리즘이다외곽선 추적을 이용하여 배경 영상으로부터 물체를 분리할 수 있으며물체의 외곽선 길이를 알 수 있으므로 물체의 크기와 모양을 추정할 수 있다또한 외곽선을 구성하는 픽셀들의 방향 정보에 따라 물체의 선분 정보와 방향 변화 정보를 알 수 있으므로 물체의 특징 점을 찾아내는 경우에도 매우 유용하고물체를 영상에 표현하거나 묘사할 경우에도 이용된다 외곽선 추적 알고리즘으로는 대상 영상을 관심영역과 비관심 영역으로 분류하고체인코드를 생성하여 경계선을 추출하는 방식의 간단한 경계선 추적자 알고리즘 ! 과 의 비일관성 문제를 개선한 수정된 간단한 경계선 추적자 알고리즘" # $ 방향성을 이용하여 외곽선을 추적해 나가는 방사형 탐색 알고리즘 % 과 & '( 알고리즘 ) 등이 있다이 알고리즘들은 매우 간단하여 적용이 용이한 장점이 있으나응용 영역에 따라 유효하지 않은 경우가 존재하며순차적으로 알고리즘이 수행되기 때문에 영상의 크기가 증가하면실행속도가 늦어질 수 있다특히의료영상과 같은 고용량의 데이터가 사용

In this paper, we conduct sensitivity analysis of parameters used for inverse modeling in order to estimate the PM10 emissions from the 16 areas in East Asia accurately. Parameters used in sensitivity analysis are R, the observational error covariance matrix, and B, a priori (background) error covariance matrix. In previous studies, it was used with the predetermined parameter empirically. Such a method, however, has difficulties in estimating an accurate emissions. Therefore, an automatically determining method for the most suitable value of R and B with an error measurement criteria and posteriori emissions accuracy is required. We determined the parameters through a sensitivity analysis, and improved the accuracy of posteriori emissions estimation. Inverse modeling methods used in the emissions estimation are pseudo inverse, NNLS (Nonnegative Least Square), and BA(Bayesian Approach). Pseudo inverse has a small error, but has negative values of emissions. In order to resolve the problem, NNLS is used. It has a unrealistic emissions, too. The problems are resolved with BA(Bayesian Approach). We showed the effectiveness and the accuracy of three methods through case studies.

In this paper, air pollutant tracing models using perception neural network(PNN) and non-negative least square(NNLS) are proposed. When the measured values of the air pollution and the contribution concentration of each source by chemical transport modeling are given, they estimate and trace the amount of the air pollutants emission from each source. Two kinds of emissions data are used in the experiments : CH4 and N2O of Geumgo-dong landfill greenhouse gas, and PM10 of 17 areas in Northeast Asia and eight regions of the Korean Peninsula. Emission values were calculated using pseudo inverse method, PNN and NNLS. Pseudo inverse method could be used for the model, but it may have negative emission values. In order to deal with the problem, we used the PNN and NNLS methods. As a result, the estimation using the NNLS is closer to the measured values than that using PNN. The proposed tracing models have better utilization and generalization than those of conventional pseudo inverse model. It could be used more efficiently for air quality management and air pollution reduction.

In this paper, we propose a new 3D PUI(Physical User Interface) system in which the index fingertip points and moves a mouse position on a given monitor screen. There are two 3D PUI schemes to control smart devices like smart TVs remotely, the relative pointing one and the absolute pointing one. The former has a problem in that it does not match the human perception process, and the latter requires excessive movement of the body. We combined the relative one and the absolute one, and develop a new intuitive and user-friendly pointing method, 3D PUI. It requires an establishment of a pyramid shape visible area (view volume) to point a mouse position on a screen with the dominant eye. In order to maintain the real-time view volume, however, it requires large computation depending on the movement of the dominant eye. We optimized the computation of the view volume in which it determines the internal and external position on the screen. In addition, Kalman filter is applied with tracing of the mouse pointer position to stabilize the trembling of the pointer and offers the user ease of use.

The forecasting system for Today`s and Tomorrow`s PM10 was developed based on the statistical model and the forecasting was performed at 9 AM to predict Today`s 24 hour average PM10 concentration and at 5 PM to predict Tomorrow`s 24 hour average PM10. The Today`s forecasting model was operated based on measured air quality and meteorological data while Tomorrow`s model was run by monitored data as well as the meteorological data calculated from the weather forecasting model such as MM5 (Mesoscale Meteorological Model version 5). The observed air quality data at ambient air quality monitoring stations as well as measured and forecasted meteorological data were reviewed to find the relationship with target PM10 concentrations by the regression analysis. The PM concentration, wind speed, precipitation rate, mixing height and dew-point deficit temperature were major variables to determine the level of PM10 and the wind direction at 500 hpa height was also a good indicator to identify the influence of long-range transport from other countries. The neural network, regression model, and decision tree method were used as the forecasting models to predict the class of a comprehensive air quality index and the final forecasting index was determined by the most frequent index among the three model`s predicted indexes. The accuracy, false alarm rate, and probability of detection in Tomorrow`s model were 72.4%, 0.0%, and 42.9% while those in Today`s model were 80.8%, 12.5%, and 77.8%, respectively. The statistical model had the limitation to predict the rapid changing PM10 concentration by long-range transport from the outside of Korea and in this case the chemical transport model would be an alternative method.

PM-10 is one of major air pollutants which affect on human health. Since PM-10 comes from various emission sources and its level of concentration is largely dependent on meteorological and geographical factors of the local region, the forecasting of PM-10 concentration is of great interest to protect daily human health. In this study, the dependent variables on PM-10 concentration were derived from the correlation analysis between PM-10 and meteorological as well as environmental factors based on the observations at the monitoring stations. Using the potential variables on the PM-10 level, the neural network model was developed and tested. The root mean square errors of the prediction in test runs were 0.064 to 0.077 and the test results implied that the system could be used in real forecasting within 10% error rates.

In this paper, we propose a scale and rotation invariant pattern recognition system using complex-log mapping (CLM) and translation invariant neural network (TINN). CLM is very useful for extracting scale and rotation invariant features. However, the results are given in a wrap-around translated form, which requires subsequent wrap-translation invariant recognition steps. This problem can be solved by using an augmented second order neural network (SONN). It requires, however, a connection complexity O(n/sup 2/) for input feature extraction which is too high to be implemented. The proposed method reduces the connection complexity to O(n*log(n)) by using TINN. Experimental results show that the recognition performance of the proposed method is almost the same as that of SONN while its network size is significantly reduced. >

This paper proposes an efficient scale and rotation invariant 2-D object recognition method using Complex-Log Mapping (CLM) and Translation Invariant Neural Network (TINN). CLM is known as very useful transform for extracting scale and rotation invariant features. However, the results are given in a wrap-around translated form, which requires subsequent wrap-translation invariant recognition steps. Recently, a new method using an augmented second order neural network (SONN) was introduced as a solution. It requires, however, a connection complexity O(n/sup 2/) for input feature extraction which is too high to be implemented. In this paper, we propose a method reducing the connection complexity to O(n*log(n)) by using TINN. Experimental results show that the recognition performance of the proposed method is almost the same as that of SONN while its network size is significantly reduced. >

For pt.I see ICNN'97, vol.2, p.1321-5 (1997). Call admission control (CAC) is a key technology of ATM network traffic control. It should be adaptable to the rapid and various changes of the ATM network environment. Conventional approach to the ATM CAC requires network analysis in detail in all cases. The optimal implementation is said to be very difficult. Therefore, a neural approach has been employed, but it does not meet the adaptability requirements. It requires additional learning data tables and learning phase during CAC operation. The authors compare the neural network CAC method based on sparse distributed memory (SDM) which they proposed in pt.I with a conventional neural CAC method. The performance of our method is as good as those of the previous neural approaches without additional learning table or learning phases. Our method, however, shows better adaptability to manage changes in ATM network.

We have proposed a neural network call admission control (CAC) method based on sparse distributed memory (SDM). CAC is a key technology of ATM network traffic control. It should be adaptable to the rapid and various changes of the ATM network environment. Conventional approaches to the ATM CAC require network analysis in detail in all cases. The optimal implementation is said to be very difficult. Therefore, neural approaches have recently been employed. However, it does not meet the adaptability requirements. We, thus, have proposed a method which is based on SDM as the neural network controller. Since SDM is a RAM-like associative memory, it has the property of good adaptability. It provides CAC with good adaptability to manage changes. Experimental results are as good as those of the previous neural approaches without additional analytical data, and without relearning from initial state.

Each content-based image retrieval (CBIR) method using color features includes its limitations to be applied to its own application areas. We analyze that the limitations are mostly due to the adoption of first-order or second-order relations among color features from a given image as its index. In this paper, we propose a new CBIR method based on a third-order color feature relations. This new method shows robustness in retrieving geometrically transformed images and can be applied in various areas.