In recent years, artificial intelligence (AI) services have become one of the most essential parts to extend human
capabilities in various fields such as face recognition for security, weather prediction, and so on. Various
learning algorithms for existing AI services are utilized, such as classification, regression, and deep learning, to
increase accuracy and efficiency for humans. Nonetheless, these services face many challenges such as fake news
spread on social media, stock selection, and volatility delay in stock prediction systems and inaccurate moviebased
recommendation systems. In this paper, various algorithms are presented to mitigate these issues in
different systems and services. Convolutional neural network algorithms are used for detecting fake news in
Korean language with a Word-Embedded model. It is based on k-clique and data mining and increased
accuracy in personalized recommendation-based services stock selection and volatility delay in stock
prediction. Other algorithms like multi-level fusion processing address problems of lack of real-time database.
In view of the deficiencies of existing weighted similarity indexes, a hierarchical clustering method initializeexpand-
merge (IEM) is proposed based on the similarity of common neighbors for community discovery in
weighted networks. Firstly, the similarity of the node pair is defined based on the attributes of their common
neighbors. Secondly, the most closely related nodes are fast clustered according to their similarity to form initial
communities and expand the communities. Finally, communities are merged through maximizing the
modularity so as to optimize division results. Experiments are carried out on many weighted networks, which
have verified the effectiveness of the proposed algorithm. And results show that IEM is superior to weighted
common neighbor (CN), weighted Adamic-Adar (AA) and weighted resources allocation (RA) when using
the weighted modularity as evaluation index. Moreover, the proposed algorithm can achieve more reasonable
community division for weighted networks compared with cluster-recluster-merge-algorithm (CRMA)
Signal complexity is one point of view to analyze the biological signal. It arises as a result of the physiological
signal produced by biological systems. Signal complexity can be used as a method in extracting the feature for
a biological signal to differentiate a pathological signal from a normal signal. In this research, Hjorth
descriptors, one of the signal complexity measurement techniques, were measured on signal sub-band as the
features for lung sounds classification. Lung sound signal was decomposed using two wavelet analyses: discrete
wavelet transform (DWT) and wavelet packet decomposition (WPD). Meanwhile, multi-layer perceptron and
N-fold cross-validation were used in the classification stage. Using DWT, the highest accuracy was obtained at
97.98%, while using WPD, the highest one was found at 98.99%. This result was found better than the multiscale
Hjorth descriptor as in previous studies.
Camera calibration is an important part of machine vision and close-range photogrammetry. Since current
calibration methods fail to obtain ideal internal and external camera parameters with limited computing
resources on mobile terminals efficiently, this paper proposes an improved fast camera calibration method for
mobile terminals. Based on traditional camera calibration method, the new method introduces two-order radial
distortion and tangential distortion models to establish the camera model with nonlinear distortion items.
Meanwhile, the nonlinear least square L-M algorithm is used to optimize parameters iteration, the new method
can quickly obtain high-precise internal and external camera parameters. The experimental results show that
the new method improves the efficiency and precision of camera calibration. Terminals simulation experiment
on PC indicates that the time consuming of parameter iteration reduced from 0.220 seconds to 0.063 seconds
(0.234 seconds on mobile terminals) and the average reprojection error reduced from 0.25 pixel to 0.15 pixel.
Therefore, the new method is an ideal mobile terminals camera calibration method which can expand the
application range of 3D reconstruction and close-range photogrammetry technology on mobile terminals.
In this paper, we present an ontology-based approach to labeling influential topics of scientific articles. First, to
look for influential topics from scientific article, topic modeling is performed, and then social network analysis
is applied to the selected topic models. Abstracts of research papers related to data mining published over the
20 years from 1995 to 2015 are collected and analyzed in this research. Second, to interpret and to explain
selected influential topics, the UniDM ontology is constructed from Wikipedia and serves as concept
hierarchies of topic models. Our experimental results show that the subjects of data management and queries
are identified in the most interrelated topic among other topics, which is followed by that of recommender
systems and text mining. Also, the subjects of recommender systems and context-aware systems belong to the
most influential topic, and the subject of k-nearest neighbor classifier belongs to the closest topic to other topics.
The proposed framework provides a general model for interpreting topics in topic models, which plays an
important role in overcoming ambiguous and arbitrary interpretation of topics in topic modeling.
Non-local means (NLM) algorithm is an effective and successful denoising method, but it is computationally
heavy. To deal with this obstacle, we propose a novel NLM algorithm with fuzzy metric (FM-NLM) for image
denoising in this paper. A new feature metric of visual features with fuzzy metric is utilized to measure the
similarity between image pixels in the presence of Gaussian noise. Similarity measures of luminance and
structure information are calculated using a fuzzy metric. A smooth kernel is constructed with the proposed
fuzzy metric instead of the Gaussian weighted L2 norm kernel. The fuzzy metric and smooth kernel
computationally simplify the NLM algorithm and avoid the filter parameters. Meanwhile, the proposed FMNLM
using visual structure preferably preserves the original undistorted image structures. The performance of
the improved method is visually and quantitatively comparable with or better than that of the current state-ofthe-
art NLM-based denoising algorithms.
With the wide spread of Social Network Services (SNS), fake news—which is a way of disguising false information
as legitimate media—has become a big social issue. This paper proposes a deep learning architecture for
detecting fake news that is written in Korean. Previous works proposed appropriate fake news detection models
for English, but Korean has two issues that cannot apply existing models: Korean can be expressed in shorter
sentences than English even with the same meaning; therefore, it is difficult to operate a deep neural network
because of the feature scarcity for deep learning. Difficulty in semantic analysis due to morpheme ambiguity.
We worked to resolve these issues by implementing a system using various convolutional neural network-based
deep learning architectures and “Fasttext” which is a word-embedding model learned by syllable unit. After
training and testing its implementation, we could achieve meaningful accuracy for classification of the body
and context discrepancies, but the accuracy was low for classification of the headline and body discrepancies.
Characteristics of fruit tree canopies are important target information for adjusting the pesticide application
rate in variable rate spraying in orchards. Therefore, the target detection of the canopy characteristics is very
important. In this study, a canopy volume measurement method for peach trees was presented and a variable
rate spraying system based on canopy volume measurement was developed using the ultrasonic sensing, one of
the most effective target detection method. Ten ultrasonic sensors and two flow control units were mounted on
the orchard air-assisted sprayer. The ultrasonic sensors were used to detect the canopy diameters and the flow
controls were used to modify the flow rate of the nozzles in real time. Two treatments were established: a
constant application rate of 300 Lha-1 was set as the control treatment for the comparison with the variable rate
application at a 0.095 Lm-3 canopy. The tracer deposition at different parts of peach trees and the tracer losses
to the ground (between rows and within rows) were analyzed in detail under constant rate and variable rate
application. The results showed that there were no significant differences between two treatments in the liquid
distribution and the capability to reach the inner parts of the crop canopies.
Today, most approaches used in the recommendation system provide correct data prediction similar to the data
that users need. The method that researchers are paying attention and apply as a model in the recommendation
system is the communities’ detection in the big social network. The outputted result of this approach is effective
in improving the exactness. Therefore, in this paper, the personalized movie recommendation system that
combines data mining for the k-clique method is proposed as the best exactness data to the users. The proposed
approach was compared with the existing approaches like k-clique, collaborative filtering, and collaborative
filtering using k-nearest neighbor. The outputted result guarantees that the proposed method gives significant
exactness data compared to the existing approach. In the experiment, the MovieLens data were used as practice
and test data.
In recent years, the problem of data drifted of the smart grid due to manual operation has been widely studied
by researchers in the related domain areas. It has become an important research topic to effectively and reliably
find the reasonable data needed in the Supervisory Control and Data Acquisition (SCADA) system has become
an important research topic. This paper analyzes the data composition of the smart grid, and explains the power
model in two smart grid applications, followed by an analysis on the application of each parameter in densitybased
spatial clustering of applications with noise (DBSCAN) algorithm. Then a comparison is carried out for
the processing effects of the boxplot method, probability weight analysis method and DBSCAN clustering
algorithm on the big data driven power grid. According to the comparison results, the performance of the
DBSCAN algorithm outperforming other methods in processing effect. The experimental verification shows
that the DBSCAN clustering algorithm can effectively screen the power grid data, thereby significantly
improving the accuracy and reliability of the calculation result of the main grid’s theoretical line loss.
This study proposes a deep neural network model based on an encoder–decoder structure for visual dialogs.
Ongoing linguistic understanding of the dialog history and context is important to generate correct answers to
questions in visual dialogs followed by questions and answers regarding images. Nevertheless, in many cases, a
visual understanding that can identify scenes or object attributes contained in images is beneficial. Hence, in
the proposed model, by employing a separate person detector and an attribute recognizer in addition to visual
features extracted from the entire input image at the encoding stage using a convolutional neural network, we
emphasize attributes, such as gender, age, and dress concept of the people in the corresponding image and use
them to generate answers. The results of the experiments conducted using VisDial v0.9, a large benchmark
dataset, confirmed that the proposed model performed well.
We design an ingenious view-pooling method named learning-based multiple pooling fusion (LMPF), and
apply it to multi-view convolutional neural network (MVCNN) for 3D model classification or retrieval. By this
means, multi-view feature maps projected from a 3D model can be compiled as a simple and effective feature
descriptor. The LMPF method fuses the max pooling method and the mean pooling method by learning a set
of optimal weights. Compared with the hand-crafted approaches such as max pooling and mean pooling, the
LMPF method can decrease the information loss effectively because of its “learning” ability. Experiments on
ModelNet40 dataset and McGill dataset are presented and the results verify that LMPF can outperform those
previous methods to a great extent.
Recently, artificial intelligence techniques have been widely used in the computer science field, such as the
Internet of Things, big data, cloud computing, and mobile computing. In particular, resource management is
of utmost importance for maintaining the quality of services, service-level agreements, and the availability of
the system. In this paper, we review and analyze various ways to meet the requirements of cloud resource
management based on artificial intelligence. We divide cloud resource management techniques based on
artificial intelligence into three categories: fog computing systems, edge-cloud systems, and intelligent cloud
computing systems. The aim of the paper is to propose an intelligent resource management scheme that
manages mobile resources by monitoring devices' statuses and predicting their future stability based on one of
the artificial intelligence techniques. We explore how our proposed resource management scheme can be
extended to various cloud-based systems.
Stock price is characterized as being mutable, non-linear and stochastic. These key characteristics are known to
have a direct influence on the stock markets globally. Given that the stock price data often contain both linear
and non-linear patterns, no single model can be adequate in modelling and predicting time series data. The
autoregressive integrated moving average (ARIMA) model cannot deal with non-linear relationships, however,
it provides an accurate and effective way to process autocorrelation and non-stationary data in time series
forecasting. On the other hand, the neural network provides an effective prediction of non-linear sequences. As
a result, in this study, we used a hybrid ARIMA and neural network model to forecast the monthly closing price
of the Shanghai composite index and Shenzhen component index.
Developing methods to search over an encrypted database (EDB) have received a lot of attention in the last few
years. Among them, order-revealing encryption (OREnc) and order-preserving encryption (OPEnc) are the
core parts in the case of range queries. Recently, some ideally-secure OPEnc schemes whose ciphertexts reveal
no additional information beyond the order of the underlying plaintexts have been proposed. However, these
schemes either require a large round complexity or a large persistent client-side storage of size O(n) where n
denotes the number of encrypted items stored in EDB. In this work, we propose a new construction of an
efficient OPEnc scheme based on an OREnc scheme. Security of our construction inherits the security of the
underlying OREnc scheme. Moreover, we also show that the construction of a non-interactive ideally-secure
OPEnc scheme with a constant client-side storage is theoretically possible from our construction.
This study proposes a novel video traffic flow detection method based on machine vision technology. The threeframe
difference method, which is one kind of a motion evaluation method, is used to establish initial
background image, and then a statistical scoring strategy is chosen to update background image in real time.
Finally, the background difference method is used for detecting the moving objects. Meanwhile, a simple but
effective shadow elimination method is introduced to improve the accuracy of the detection for moving objects.
Furthermore, the study also proposes a vehicle matching and tracking strategy by combining characteristics,
such as vehicle’s location information, color information and fractal dimension information. Experimental
results show that this detection method could quickly and effectively detect various traffic flow parameters,
laying a solid foundation for enhancing the degree of automation for traffic management.
This paper presents a two-dimensional attention-based long short-memory (2D-ALSTM) model for stock
index prediction, incorporating input attention and temporal attention mechanisms for weighting of important
stocks and important time steps, respectively. The proposed model is designed to overcome the long-term
dependency, stock selection, and stock volatility delay problems that negatively affect existing models. The 2DALSTM
model is validated in a comparative experiment involving the two attention-based models multi-input
LSTM (MI-LSTM) and dual-stage attention-based recurrent neural network (DARNN), with real stock data
being used for training and evaluation. The model achieves superior performance compared to MI-LSTM and
DARNN for stock index prediction on a KOSPI100 dataset.
As current algorithms unable to perform effective fusion processing of unknown complex radar signals lacking
database, and the result is unstable, this paper presents a multi-level fusion processing algorithm for complex
radar signals based on evidence theory as a solution to this problem. Specifically, the real-time database is
initially established, accompanied by similarity model based on parameter type, and then similarity matrix is
calculated. D-S evidence theory is subsequently applied to exercise fusion processing on the similarity of
parameters concerning each signal and the trust value concerning target framework of each signal in order. The
signals are ultimately combined and perfected. The results of simulation experiment reveal that the proposed
algorithm can exert favorable effect on the fusion of unknown complex radar signals, with higher efficiency and
less time, maintaining stable processing even of considerable samples.
Recently, concomitant with a surge in numbers of Internet of Things (IoT) devices with various sensors, mobile
crowdsensing (MCS) has provided a new business model for IoT. For example, a person can share road traffic
pictures taken with their smartphone via a cloud computing system and the MCS data can provide benefits to
other consumers. In this service model, to encourage people to actively engage in sensing activities and to
voluntarily share their sensing data, providing appropriate incentives is very important. However, the sensing
data from personal devices can be sensitive to privacy, and thus the privacy issue can suppress data sharing.
Therefore, the development of an appropriate privacy protection system is essential for successful MCS. In this
study, we address this problem due to the conflicting objectives of privacy preservation and incentive payment.
We propose a privacy-preserving mechanism that protects identity and location privacy of sensing users
through an on-demand incentive payment and group signatures methods. Subsequently, we apply the proposed
mechanism to one example of MCS—an intelligent parking system—and demonstrate the feasibility and
efficiency of our mechanism through emulation.
The 2nd Journal of Information Processing Systems Awards
"Block-VN: A Distributed Blockchain Based Vehicular Network Architecture in Smart City"
Pradip Kumar Sharma, Seo Yeon Moon and Jong Hyuk Park (Seoul National University of Science and Technology, Korea)
Publication (Corresponding Author)
Chengyou Wang (Shangdong University, China)