Improving Archival Records and Service of Traditional Korean Performing Arts in a Semantic Web Environment

Purpose:This research project aims to organize the archival information of traditional Korean performing arts in a semantic web environment.Key requirements,which the archival records manager should consider for publishing and distribution of gugak performing archival information in a semantic web environment,are presented in the perspective of linked data.Design/methodology/approach:This study analyzes the metadata provided by the National Gugak Center’s Gugak Archive,the search and browse menus of Gugak Archive’s website and K-PAAN,the performing arts portal site.Findings:The importance of consistency,continuity,and systematicity—crucial qualities in traditional record management practices—is undiminished in a semantic web environment.However,a semantic web environment also requires new tools such as web identifiers(URIs),data models(RDF),and link information(interlinking).Research limitations:The scope of this study does not include practical implementation strategies for the archival records management system and website services.The suggestions also do not discuss issues related to copyright or policy coordination between related organizations.Practical implications:The findings of this study can assist records managers in converting a traditional performing arts information archive into a semantic web environment-based online archival service and system.This can also be useful for collaboration with record managers who are unfamiliar with relational or triple database system.Originality/value:This study analyzed the metadata of the Gugak Archive and its online services to present practical requirements for managing and disseminating gugak performing arts information in a semantic web environment.In the application of the semantic web services’principles and methods to an Gugak Archive,this study can contribute to the improvement of information organization and services in the field of Korean traditional music.

Classification of 3D Film Patterns with Deep Learning

Researches on pattern recognition have been tremendously performed in various fields because of its wide use in both machines and human beings. Previously, traditional methods used to study pattern recognition problems were not strong enough to recognize patterns accurately as compared to optimization algorithms. In this study, we employ both traditional based methods to detect the edges of each pattern in an image and apply convolutional neural networks to classify the right and wrong pattern of the cropped part of an image from the raw image. The results indicate that edge detection methods were not able to detect clearly the patterns due to low quality of the raw image while CNN was able to classify the patterns at an accuracy of 84% within 1.5 s for 10 epochs.

Novel Sensing Hole Recovery with Expanded Relay Node Capability

The occurrence of‘sensing holes’not only hinders seamless data col-lection but also leads to misinterpretation of information in certain areas under extensive data analysis.In order to overcome this,various sensor relocation stra-tegies have been proposed,but the existing relocation strategies revealed pro-blems such as the ping-pong,shaded area,network disconnection,etc.This paper conducted research on relocation protocols in a distributed environment that is very suitable for real-world situations and efficiently recovering the problem of sensing holes.First,a simulation was performed on the distribution of the shaded area for data collection,which is a problem with the existing representative relo-cation protocol.After that,a data collection capability was newly added to the relay node,which had been in charge of only communication between cluster zones so far,and with this additional functionality,the performance of the revised sensor relocation algorithm was dramatically improved to overcome the existing problems.In addition,the performance and validity of the proposed algorithm were verified through various simulations.

Parallel Iterative FEM Solver with Initial Guess for Frequency Domain Electromagnetic Analysis

The finite element method is a key player in computational electromag-netics for designing RF(Radio Frequency)components such as waveguides.The frequency-domain analysis is fundamental to identify the characteristics of the components.For the conventional frequency-domain electromagnetic analysis using FEM(Finite Element Method),the system matrix is complex-numbered as well as indefinite.The iterative solvers can be faster than the direct solver when the solver convergence is guaranteed and done in a few steps.However,such complex-numbered and indefinite systems are hard to exploit the merit of the iterative solver.It is also hard to benefit from matrix factorization techniques due to varying system matrix parts according to frequency.Overall,it is hard to adopt conventional iterative solvers even though the system matrix is sparse.A new parallel iterative FEM solver for frequency domain analysis is implemented for inhomogeneous waveguide structures in this paper.In this implementation,the previous solution of the iterative solver of Matlab(Matrix Laboratory)employ-ing the preconditioner is used for the initial guess for the next step’s solution process.The overlapped parallel stage using Matlab’s Parallel Computing Toolbox is also proposed to alleviate the cold starting,which ruins the convergence of early steps in each parallel stage.Numerical experiments based on waveguide structures have demonstrated the accuracy and efficiency of the proposed scheme.

Hopping-Aware Cluster Header Capability for Sensor Relocation in Mobile IoT Networks

Mobile sensor nodes such as hopping sensors are of critical importance in data collection.However,the occurrence of sensing holes is unavoidable due to the energy limitation of the nodes.Thus,it is evident that the relocation of mobile sensors is the most desirable method to recover the sensing holes.The previous research conducted by the authors so far demonstrated the most realistic hopping sensor relocation scheme,which is suitable for the distributed environment.In previous studies,the cluster header plays an essential role in detecting the sensing hole and requesting the neighboring cluster to recover the sensing hole that occurred in the sensor node.However,the limitations of the cluster header in the previously proposed relocation protocol are not fully considered.Because the cluster header jumps more frequently than non-header nodes,its energy con-sumption is relatively high compared to other nodes.Therefore,it is most likely to lead to header node failure and can lead to data loss on the network.In this paper,the jumping ability and energy consumption of the cluster header are seriously considered.Additional ability to replace cluster headers in case of failure is also implemented.Simulation results show that the data collection time can be further increased,which demonstrates the validity of the proposed algorithms.

Dragonfly Interaction Algorithm for Optimization of Queuing Delay in Industrial Wireless Networks

In industrial wireless networks,data transmitted from source to destination are highly repetitive.This often leads to the queuing of the data,and poor management of the queued data results in excessive delays,increased energy consumption,and packet loss.Therefore,a nature-inspired-based Dragonfly Interaction Optimization Algorithm(DMOA)is proposed for optimization of the queue delay in industrial wireless networks.The term“interaction”herein used is the characterization of the“flying movement”of the dragonfly towards damselflies(female dragonflies)for mating.As a result,interaction is represented as the flow of transmitted data packets,or traffic,from the source to the base station.This includes each and every feature of dragonfly movement as well as awareness of the rival dragonflies,predators,and damselflies for the desired optimization of the queue delay.These features are juxtaposed as noise and interference,which are further used in the calculation of industrial wireless metrics:latency,error rate(reliability),throughput,energy efficiency,and fairness for the optimization of the queue delay.Statistical analysis,convergence analysis,the Wilcoxon test,the Friedman test,and the classical as well as the 2014 IEEE Congress of Evolutionary Computation(CEC)on the benchmark functions are also used for the evaluation of DMOA in terms of its robustness and efficiency.The results demonstrate the robustness of the proposed algorithm for both classical and benchmarking functions of the IEEE CEC 2014.Furthermore,the accuracy and efficacy of DMOA were demonstrated by means of the convergence rate,Wilcoxon testing,and ANOVA.Moreover,fairness using Jain’s index in queue delay optimization in terms of throughput and latency,along with computational complexity,is also evaluated and compared with other algorithms.Simulation results show that DMOA exceeds other bio-inspired optimization algorithms in terms of fairness in queue delay management and average packet loss.The proposed algorithm is also evaluated for the conflicting objectives at Pareto Front,and its analysis reveals that DMOA finds a compromising solution between the objectives,thereby optimizing queue delay.In addition,DMOA on the Pareto front delivers much greater performance when it comes to optimizing the queuing delay for industry wireless networks.

SDN Based DDos Mitigating Approach Using Traffic Entropy for IoT Network

The Internet of Things(IoT)has been widely adopted in various domains including smart cities,healthcare,smart factories,etc.In the last few years,the fitness industry has been reshaped by the introduction of smart fitness solutions for individuals as well as fitness gyms.The IoT fitness devices collect trainee data that is being used for various decision-making.However,it will face numerous security and privacy issues towards its realization.This work focuses on IoT security,especially DoS/DDoS attacks.In this paper,we have proposed a novel blockchain-enabled protocol(BEP)that uses the notion of a self-exposing node(SEN)approach for securing fitness IoT applications.The blockchain and SDN architectures are employed to enhance IoT security by a highly preventive security monitoring,analysis and response system.The proposed approach helps in detecting the DoS/DDoS attacks on the IoT fitness system and then mitigating the attacks.The BEP is used for handling Blockchain-related activities and SEN could be a sensor or actuator node within the fitness IoT system.SEN provides information about the inbound and outbound traffic to the BEP which is used to analyze the DoS/DDoS attacks on the fitness IoT system.The SENcalculates the inbound and outbound traffic features’entropies and transmits them to the Blockchain in the form of transaction blocks.The BEP picks the whole mined blocks’transactions and transfers them to the SDN controller node.The controller node correlates the entropies data of SENs and decides about the DoS or DDoS attack.So,there are two decision points,one is SEN,and another is the controller.To evaluate the performance of our proposed system,several experiments are performed and results concerning the entropy values and attack detection rate are obtained.The proposed approach has outperformed the other two approaches concerning the attack detection rate by an increase of 11%and 18%against Approach 1 and Approach 2 respectively.

Complex Problems Solution as a Service Based on Predictive Optimization and Tasks Orchestration in Smart Cities

Smart cities have different contradicting goals having no apparent solution.The selection of the appropriate solution,which is considered the best compromise among the candidates,is known as complex problem-solving.Smart city administrators face different problems of complex nature,such as optimal energy trading in microgrids and optimal comfort index in smart homes,to mention a few.This paper proposes a novel architecture to offer complex problem solutions as a service(CPSaaS)based on predictive model optimization and optimal task orchestration to offer solutions to different problems in a smart city.Predictive model optimization uses a machine learning module and optimization objective to compute the given problem’s solutions.The task orchestration module helps decompose the complex problem in small tasks and deploy them on real-world physical sensors and actuators.The proposed architecture is hierarchical and modular,making it robust against faults and easy to maintain.The proposed architecture’s evaluation results highlight its strengths in fault tolerance,accuracy,and processing speed.

DISTINIT:Data poISoning atTacks dectectIon usiNg optIized jaCcard disTance

Machine Learning(ML)systems often involve a re-training process to make better predictions and classifications.This re-training process creates a loophole and poses a security threat for ML systems.Adversaries leverage this loophole and design data poisoning attacks against ML systems.Data poisoning attacks are a type of attack in which an adversary manipulates the training dataset to degrade the ML system’s performance.Data poisoning attacks are challenging to detect,and even more difficult to respond to,particularly in the Internet of Things(IoT)environment.To address this problem,we proposed DISTINIT,the first proactive data poisoning attack detection framework using distancemeasures.We found that Jaccard Distance(JD)can be used in the DISTINIT(among other distance measures)and we finally improved the JD to attain an Optimized JD(OJD)with lower time and space complexity.Our security analysis shows that the DISTINIT is secure against data poisoning attacks by considering key features of adversarial attacks.We conclude that the proposed OJD-based DISTINIT is effective and efficient against data poisoning attacks where in-time detection is critical for IoT applications with large volumes of streaming data.

Simply Fine-Tuned Deep Learning-Based Classification for Breast Cancer with Mammograms

A lump growing in the breast may be referred to as a breast mass related to the tumor.However,not all tumors are cancerous or malignant.Breast masses can cause discomfort and pain,depending on the size and texture of the breast.With an appropriate diagnosis,non-cancerous breast masses can be diagnosed earlier to prevent their cultivation from being malignant.With the development of the artificial neural network,the deep discriminative model,such as a convolutional neural network,may evaluate the breast lesion to distinguish benign and malignant cancers frommammogram breast masses images.This work accomplished breastmasses classification relative to benign and malignant cancers using a digital database for screening mammography image datasets.A residual neural network 50(ResNet50)model along with an adaptive gradient algorithm,adaptive moment estimation,and stochastic gradient descent optimizers,as well as data augmentations and fine-tuning methods,were implemented.In addition,a learning rate scheduler and 5-fold cross-validation were applied with 60 training procedures to determine the best models.The results of training accuracy,p-value,test accuracy,area under the curve,sensitivity,precision,F1-score,specificity,and kappa for adaptive gradient algorithm 25%,75%,100%,and stochastic gradient descent 100%fine-tunings indicate that the classifier is feasible for categorizing breast cancer into benign and malignant from the mammographic breast masses images.

Sensors-Based Ambient Assistant Living via E-Monitoring Technology

Independent human living systems require smart,intelligent,and sustainable online monitoring so that an individual can be assisted timely.Apart from ambient assisted living,the task of monitoring human activities plays an important role in different fields including virtual reality,surveillance security,and human interaction with robots.Such systems have been developed in the past with the use of various wearable inertial sensors and depth cameras to capture the human actions.In this paper,we propose multiple methods such as random occupancy pattern,spatio temporal cloud,waypoint trajectory,Hilbert transform,Walsh Hadamard transform and bone pair descriptors to extract optimal features corresponding to different human actions.These features sets are then normalized using min-max normalization and optimized using the Fuzzy optimization method.Finally,the Masi entropy classifier is applied for action recognition and classification.Experiments have been performed on three challenging datasets,namely,UTDMHAD,50 Salad,and CMU-MMAC.During experimental evaluation,the proposed novel approach of recognizing human actions has achieved an accuracy rate of 90.1%with UTD-MHAD dataset,90.6%with 50 Salad dataset,and 89.5%with CMU-MMAC dataset.Hence experimental results validated the proposed system.

Recurrent Autoencoder Ensembles for Brake Operating Unit Anomaly Detection on Metro Vehicles

The anomaly detection of the brake operating unit (BOU) in thebrake systems on metro vehicle is critical for the safety and reliability ofthe trains. On the other hand, current periodic inspection and maintenanceare unable to detect anomalies in an early stage. Also, building an accurateand stable system for detecting anomalies is extremely difficult. Therefore,we present an efficient model that use an ensemble of recurrent autoencodersto accurately detect the BOU abnormalities of metro trains. This is the firstproposal to employ an ensemble deep learning technique to detect BOUabnormalities in metro train braking systems. One of the anomalous caseson metro vehicles is the case when the air cylinder (AC) pressures are less thanthe brake cylinder (BC) pressures in certain parts where the brake pressuresincrease before coming to a halt. Hence, in this work, we first extract the dataof BC and AC pressures. Then, the extracted data of BC and AC pressuresare divided into multiple subsequences that are used as an input for bothbi-directional long short-term memory (biLSTM) and bi-directional gatedrecurrent unit (biGRU) autoencoders. The biLSTM and biGRU autoencodersare trained using training dataset that only contains normal subsequences. Fordetecting abnormalities from test dataset which consists of abnormal subsequences, the mean absolute errors (MAEs) between original subsequences andreconstructed subsequences from both biLSTM and biGRU autoencoders arecalculated. As an ensemble step, the total error is calculated by averaging twoMAEs from biLSTM and biGRU autoencoders. The subsequence with totalerror greater than a pre-defined threshold value is considered an abnormality.We carried out the experiments using the BOU dataset on metro vehiclesin South Korea. Experimental results demonstrate that the ensemble modelshows better performance than other autoencoder-based models, which showsthe effectiveness of our ensemble model for detecting BOU anomalies onmetro trains.

QI-BRiCE: Quality Index for Bleeding Regions in Capsule Endoscopy Videos

With the advent in services such as telemedicine and telesurgery,provision of continuous quality monitoring for these services has become a challenge for the network operators.Quality standards for provision of such services are application specic as medical imagery is quite different than general purpose images and videos.This paper presents a novel full reference objective video quality metric that focuses on estimating the quality of wireless capsule endoscopy(WCE)videos containing bleeding regions.Bleeding regions in gastrointestinal tract have been focused in this research,as bleeding is one of the major reasons behind several diseases within the tract.The method jointly estimates the diagnostic as well as perceptual quality of WCE videos,and accurately predicts the quality,which is in high correlation with the subjective differential mean opinion scores(DMOS).The proposed combines motion quality estimates,bleeding regions’quality estimates based on support vector machine(SVM)and perceptual quality estimates using the pristine and impaired WCE videos.Our method Quality Index for Bleeding Regions in Capsule Endoscopy(QI-BRiCE)videos is one of its kind and the results show high correlation in terms of Pearson’s linear correlation coefcient(PLCC)and Spearman’s rank order correlation coefcient(SROCC).An F-test is also provided in the results section to prove the statistical signicance of our proposed method.

DWPT-Based Sub-Band Analysis for FaultDetection of Rolling Element Bearings

To early detect symptoms of defective rolling element bearings, this paper introduces discrete wavelet packet transform （DWPT）-based sub-band analysis. The objective of this analysis is to explore the impacts of multiple sub-band signals by 4-level DWPTusing proper Daubechies mother wavelet on a 2.5-second acoustic emission signal. In particular, the DWPT-based sub-bandanalysis determines the most informative sub-band signal involving intrinsic information about bearing defects among theaforementioned multiple sub-band signals based on the ratio of spectral magnitudes at harmonics of the bearing＇s characteristicfrequency to those around the harmonics. This paper also verifies the efficacy of the DWPT-based sub-band analysis for seededbearing defects （i.e., a crack on the inner race, the outer race, or a roller）.

A probabilistic model of quantum states for classical data security

The phenomenal progress of quantum information theory over the last decade has substantially broadened the potential to simulate the superposition of states for exponential speedup of quantum algorithms over their classical peers.Therefore,the conventional and modern cryptographic standards(encryption and authentication)are susceptible to Shor’s and Grover’s algorithms on quantum computers.The significant improvement in technology permits consummate levels of data protection by encoding classical data into small quantum states that can only be utilized once by leveraging the capabilities of quantum-assisted classical computations.Considering the frequent data breaches and increasingly stringent privacy legislation,we introduce a hybrid quantum-classical model to transform classical data into unclonable states,and we experimentally demonstrate perfect state transfer to exemplify the classical data.To alleviate implementation complexity,we propose an arbitrary quantum signature scheme that does not require the establishment of entangled states to authenticate users in order to transmit and receive arbitrated states to retrieve classical data.The consequences of the probabilistic model indicate that the quantum-assisted classical framework substantially enhances the performance and security of digital data,and paves the way toward real-world applications.

Joint Non-Orthogonal Multiple Access (NOMA) & Walsh-Hadamard Transform: Enhancing the Receiver Performance

Non-orthogonal multiple access(NOMA) is a new access method to achieve high performance gains in terms of capacity and throughput, so it is currently under consideration as one of the candidates for fifth generation(5 G) technologies. NOMA utilizes power domain in order to superimpose signals of multiple users in a single transmitted signal. This creates a lot of interference at the receive side. Although the use of successive interference cancellation(SIC) technique reduces the interference, but to further improve the receiver performance, in this paper, we have proposed a joint Walsh-Hadamard transform(WHT) and NOMA approach for achieving better performance gains than the conventional NOMA. WHT is a well-known code used in communication systems and is used as an orthogonal variable spreading factor(OVSF) in communication systems. Application of WHT to NOMA results in low bit error rate(BER) and high throughput performance for both low and high channel gain users. Further, it also reduces peak to average power ratio(PAPR) of the user signal. The results are discussed in terms of comparison between the conventionalNOMA and the proposed technique, which shows that it offers high performance gains in terms of low BER at different SNR levels, reduced PAPR, high user throughput performance and better spectral efficiency.

Human Pose Estimation and Object Interaction for Sports Behaviour

In the new era of technology,daily human activities are becoming more challenging in terms of monitoring complex scenes and backgrounds.To understand the scenes and activities from human life logs,human-object interaction(HOI)is important in terms of visual relationship detection and human pose estimation.Activities understanding and interaction recognition between human and object along with the pose estimation and interaction modeling have been explained.Some existing algorithms and feature extraction procedures are complicated including accurate detection of rare human postures,occluded regions,and unsatisfactory detection of objects,especially small-sized objects.The existing HOI detection techniques are instancecentric(object-based)where interaction is predicted between all the pairs.Such estimation depends on appearance features and spatial information.Therefore,we propose a novel approach to demonstrate that the appearance features alone are not sufficient to predict the HOI.Furthermore,we detect the human body parts by using the Gaussian Matric Model(GMM)followed by object detection using YOLO.We predict the interaction points which directly classify the interaction and pair them with densely predicted HOI vectors by using the interaction algorithm.The interactions are linked with the human and object to predict the actions.The experiments have been performed on two benchmark HOI datasets demonstrating the proposed approach.

Deep Learning Approach for Cosmetic Product Detection and Classification

As the amount of online video content is increasing,consumers are becoming increasingly interested in various product names appearing in videos,particularly in cosmetic-product names in videos related to fashion,beauty,and style.Thus,the identification of such products by using image recognition technology may aid in the identification of current commercial trends.In this paper,we propose a two-stage deep-learning detection and classification method for cosmetic products.Specifically,variants of the YOLO network are used for detection,where the bounding box for each given input product is predicted and subsequently cropped for classification.We use four state-of-the-art classification networks,namely ResNet,InceptionResNetV2,DenseNet,and EfficientNet,and compare their performance.Furthermore,we employ dilated convolution in these networks to obtain better feature representations and improve performance.Extensive experiments demonstrate that YOLOv3 and its tiny version achieve higher speed and accuracy.Moreover,the dilated networks marginally outperform the base models,or achieve similar performance in the worst case.We conclude that the proposed method can effectively detect and classify cosmetic products.

Korean Morphological Analysis for Korean-Vietnamese Statistical Machine Translation

This paper describes the experiments with Korean-to-Vietnamese statistical machine translation(SMT). The fact that Korean is a morphologically complex language that does not have clear optimal word boundaries causes a major problem of translating into or from Korean. To solve this problem, we present a method to conduct a Korean morphological analysis by using a pre-analyzed partial word-phrase dictionary(PWD).Besides, we build a Korean-Vietnamese parallel corpus for training SMT models by collecting text from multilingual magazines. Then, we apply such a morphology analysis to Korean sentences that are included in the collected parallel corpus as a preprocessing step. The experiment results demonstrate a remarkable improvement of Korean-to-Vietnamese translation quality in term of bi-lingual evaluation understudy(BLEU).

Hybrid Renewable Energy Resources Management for Optimal Energy Operation in Nano-Grid

Renewable energy resources are deemed a potential energy production source due to their cost efficiency and harmless reaction to the environment,unlike non-renewable energy resources.However,they often fail to meet energy requirements in unfavorable weather conditions.The concept of Hybrid renewable energy resources addresses this issue by integrating both renewable and non-renewable energy resources to meet the required energy load.In this paper,an intelligent cost optimization algorithm is proposed to maximize the use of renewable energy resources and minimum utilization of non-renewable energy resources to meet the energy requirement for a nanogrid infrastructure.An actual data set comprising information about the load and demand of utility grids is used to evaluate the performance of the proposed nanogrid energy management system.The objective function is formulated to manage the nanogrid operation and implemented using a variant of Particle Swarm Optimization(PSO)named recurrent PSO(rPSO).Firstly,rPSO algorithm minimizes the installation cost for nanogrid.Thereafter,the proposed NEMS ensures cost efficiency for the post-installation period by providing a daily operational plan and optimizing renewable resources.State-of-the-art optimization models,including Genetic Algorithm(GA),bat and different Mathematical Programming Language(AMPL)solvers,are used to evaluate the model.The study’s outcomes suggest that the proposed work significantly reduces the use of diesel generators and fosters the use of renewable energy resources and beneficiates the eco-friendly environment.