Applied Sciences

Editorial

Jump to: Research

3 pages, 158 KiB

Open AccessEditorial

Actionable Pattern-Driven Analytics and Prediction

by Jerry Chun-Wei Lin and Chun-Hao Chen

Appl. Sci. 2021, 11(16), 7529; https://doi.org/10.3390/app11167529 - 17 Aug 2021

Viewed by 929

Abstract

Pattern-driven analytics and mining has received a lot of attention in the last two decades, because information discovered in data can be used to support decision and strategy making [...] Full article

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)

Research

Jump to: Editorial

14 pages, 3049 KiB

Open AccessArticle

Driver Behavior Analysis via Two-Stream Deep Convolutional Neural Network

by Ju-Chin Chen, Chien-Yi Lee, Peng-Yu Huang and Cheng-Rong Lin

Appl. Sci. 2020, 10(6), 1908; https://doi.org/10.3390/app10061908 - 11 Mar 2020

Cited by 25 | Viewed by 4306

Abstract

According to the World Health Organization global status report on road safety, traffic accidents are the eighth leading cause of death in the world, and nearly one-fifth of the traffic accidents were cause by driver distractions. Inspired by the famous two-stream convolutional neural [...] Read more.

According to the World Health Organization global status report on road safety, traffic accidents are the eighth leading cause of death in the world, and nearly one-fifth of the traffic accidents were cause by driver distractions. Inspired by the famous two-stream convolutional neural network (CNN) model, we propose a driver behavior analysis system using one spatial stream ConvNet to extract the spatial features and one temporal stream ConvNet to capture the driver’s motion information. Instead of using three-dimensional (3D) ConvNet, which would suffer from large parameters and the lack of a pre-trained model, two-dimensional (2D) ConvNet is used to construct the spatial and temporal ConvNet streams, and they were pre-trained by the large-scale ImageNet. In addition, in order to integrate different modalities, the feature-level fusion methodology was applied, and a fusion network was designed to integrate the spatial and temporal features for further classification. Moreover, a self-compiled dataset of 10 actions in the vehicle was established. According to the experimental results, the proposed system can increase the accuracy rate by nearly 30% compared to the two-stream CNN model with a score-level fusion. Full article

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)

► Show Figures

Figure 1

21 pages, 5520 KiB

Open AccessArticle

Person Search via Deep Integrated Networks

by Ju-Chin Chen, Cheng-Feng Wu, Chun-Huei Chen and Cheng-Rong Lin

Appl. Sci. 2020, 10(1), 188; https://doi.org/10.3390/app10010188 - 25 Dec 2019

Cited by 2 | Viewed by 1958

Abstract

This study proposes an integrated deep network consisting of a detection and identification module for person search. Person search is a very challenging problem because of the large appearance variation caused by occlusion, background clutter, pose variations, etc., and it is still an [...] Read more.

This study proposes an integrated deep network consisting of a detection and identification module for person search. Person search is a very challenging problem because of the large appearance variation caused by occlusion, background clutter, pose variations, etc., and it is still an active research issue in the academic and industrial fields. Although various studies have been proposed, following the protocols of the person re-identification (ReID) benchmarks, most existing works take cropped pedestrian images either from manual labelling or a perfect detection assumption. However, for person search, manual processing is unavailable in practical applications, thereby causing a gap between the ReID problem setting and practical applications. One fact is also ignored: an imperfect auto-detected bounding box or misalignment is inevitable. We design herein a framework for the practical surveillance scenarios in which the scene images are captured. For person search, detection is a necessary step before ReID, and previous studies have shown that the precision of detection results has an influence on person ReID. The detection module based on the Faster R-CNN is used to detect persons in a scene image. For identifying and extracting discriminative features, a multi-class CNN network is trained with the auto-detected bounding boxes from the detection module, instead of the manually cropped data. The distance metric is then learned from the discriminative features output by the identification module. According to the experimental results of the test performed in the scene images, the multi-class CNN network for the identification module can provide a 62.7% accuracy rate, which is higher than that for the two-class CNN network. Full article

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)

► Show Figures

Figure 1

26 pages, 10355 KiB

Open AccessArticle

On Ontology-Based Tourist Knowledge Representation and Recommendation

by Mao-Yuan Pai, Ding-Chau Wang, Tz-Heng Hsu, Guan-Yu Lin and Chao-Chun Chen

Appl. Sci. 2019, 9(23), 5097; https://doi.org/10.3390/app9235097 - 25 Nov 2019

Cited by 6 | Viewed by 3373

Abstract

In the rapid development of the information technology age, many travelers search for travel articles through the Internet. These travel articles include the experience and knowledge of traveler, which can be used as a reference for tourism planning and attraction selection. At present, [...] Read more.

In the rapid development of the information technology age, many travelers search for travel articles through the Internet. These travel articles include the experience and knowledge of traveler, which can be used as a reference for tourism planning and attraction selection. At present, the most travel experience and knowledge is available in online travel reviews (OTR). OTR and eWOM (electronic word-of-mouth) contain a lot of knowledge of consumers and travelers. Many travelers often look for OTR content through virtual communities, blogs, and search engine, but the search results often cause information overload problems. In addition, through virtual communities, blogs, and search engines, an OTR search still requires using keywords. However, most travelers cannot know the name of the attraction; therefore, travelers cannot use the correct keywords to search. That causes travelers to be unable to get enough information from OTR and unable to make the best travel plan. Therefore, this study focuses on the ontology-based tourist knowledge representation and recommendation method. And the study is to search for popular attractions from the OTR content and construct a tourist knowledge structure for these travelers. When the tourists do not need to know the keywords of the popular attraction name, they just need to get their current location; and then ORT content will recommend the next attraction to the traveler, which helps the traveler make the correct travel decision. The evaluation result showed that the method proposed in this study can help the travelers to quickly make the travel decision and is better than the traditional searching methods. Full article

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)

► Show Figures

Figure 1

16 pages, 1529 KiB

Open AccessArticle

An Intelligent Course Decision Assistant by Mining and Filtering Learners’ Personality Patterns

by Ja-Hwung Su, Yi-Wen Liao and Liang-Ni Chen

Appl. Sci. 2019, 9(21), 4665; https://doi.org/10.3390/app9214665 - 01 Nov 2019

Cited by 5 | Viewed by 2058

Abstract

For a student, determining how to choose from a set of courses is an important issue prior to learning. An appropriate learning guide can direct students toward an area of interest. The learning results produced by the student in this case are superior [...] Read more.

For a student, determining how to choose from a set of courses is an important issue prior to learning. An appropriate learning guide can direct students toward an area of interest. The learning results produced by the student in this case are superior due to their strong interest in the subject matter. Although a number of methods have been proposed to address this issue, the effectiveness remains unsatisfactory. To this end, we created an effective system, called the personality-driven course decision assistant, to help students determine the courses they should select by mining and filtering learners’ personality patterns. For learner pattern mining, the relationships between the students’ learning results and the referred personalities are discovered to provide the learners with valuable information before learning. For filtering learner personality patterns, students with similar personality patterns are filtered to predict the potential learning results. Through the actual system, a number of subjective and objective evaluations were conducted, and the evaluation results reveal that the proposed system is highly effective and reliable. Full article

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)

► Show Figures

Figure 1

12 pages, 1587 KiB

Open AccessEditor’s ChoiceArticle

Improving Electric Energy Consumption Prediction Using CNN and Bi-LSTM

by Tuong Le, Minh Thanh Vo, Bay Vo, Eenjun Hwang, Seungmin Rho and Sung Wook Baik

Appl. Sci. 2019, 9(20), 4237; https://doi.org/10.3390/app9204237 - 10 Oct 2019

Cited by 164 | Viewed by 10852

Abstract

The electric energy consumption prediction (EECP) is an essential and complex task in intelligent power management system. EECP plays a significant role in drawing up a national energy development policy. Therefore, this study proposes an Electric Energy Consumption Prediction model utilizing the combination [...] Read more.

The electric energy consumption prediction (EECP) is an essential and complex task in intelligent power management system. EECP plays a significant role in drawing up a national energy development policy. Therefore, this study proposes an Electric Energy Consumption Prediction model utilizing the combination of Convolutional Neural Network (CNN) and Bi-directional Long Short-Term Memory (Bi-LSTM) that is named EECP-CBL model to predict electric energy consumption. In this framework, two CNNs in the first module extract the important information from several variables in the individual household electric power consumption (IHEPC) dataset. Then, Bi-LSTM module with two Bi-LSTM layers uses the above information as well as the trends of time series in two directions including the forward and backward states to make predictions. The obtained values in the Bi-LSTM module will be passed to the last module that consists of two fully connected layers for finally predicting the electric energy consumption in the future. The experiments were conducted to compare the prediction performances of the proposed model and the state-of-the-art models for the IHEPC dataset with several variants. The experimental results indicate that EECP-CBL framework outperforms the state-of-the-art approaches in terms of several performance metrics for electric energy consumption prediction on several variations of IHEPC dataset in real-time, short-term, medium-term and long-term timespans. Full article

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)

► Show Figures

Figure 1

26 pages, 17818 KiB

Open AccessArticle

Deep-Learning-Based Defective Bean Inspection with GAN-Structured Automated Labeled Data Augmentation in Coffee Industry

by Yung-Chien Chou, Cheng-Ju Kuo, Tzu-Ting Chen, Gwo-Jiun Horng, Mao-Yuan Pai, Mu-En Wu, Yu-Chuan Lin, Min-Hsiung Hung, Wei-Tsung Su, Yi-Chung Chen, Ding-Chau Wang and Chao-Chun Chen

Appl. Sci. 2019, 9(19), 4166; https://doi.org/10.3390/app9194166 - 04 Oct 2019

Cited by 30 | Viewed by 10970

Abstract

In the production process from green beans to coffee bean packages, the defective bean removal (or in short, defect removal) is one of most labor-consuming stages, and many companies investigate the automation of this stage for minimizing human efforts. In this paper, we [...] Read more.

In the production process from green beans to coffee bean packages, the defective bean removal (or in short, defect removal) is one of most labor-consuming stages, and many companies investigate the automation of this stage for minimizing human efforts. In this paper, we propose a deep-learning-based defective bean inspection scheme (DL-DBIS), together with a GAN (generative-adversarial network)-structured automated labeled data augmentation method (GALDAM) for enhancing the proposed scheme, so that the automation degree of bean removal with robotic arms can be further improved for coffee industries. The proposed scheme is aimed at providing an effective model to a deep-learning-based object detection module for accurately identifying defects among dense beans. The proposed GALDAM can be used to greatly reduce labor costs, since the data labeling is the most labor-intensive work in this sort of solutions. Our proposed scheme brings two main impacts to intelligent agriculture. First, our proposed scheme is can be easily adopted by industries as human effort in labeling coffee beans are minimized. The users can easily customize their own defective bean model without spending a great amount of time on labeling small and dense objects. Second, our scheme can inspect all classes of defective beans categorized by the SCAA (Specialty Coffee Association of America) at the same time and can be easily extended if more classes of defective beans are added. These two advantages increase the degree of automation in the coffee industry. The prototype of the proposed scheme was developed for studying integrated tests. Testing results of a case study reveal that the proposed scheme can efficiently and effectively generate models for identifying defective beans with accuracy and precision values up to

80 %

. Full article

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)

► Show Figures

Figure 1

15 pages, 2588 KiB

Open AccessArticle

An Intelligent Event-Sentiment-Based Daily Foreign Exchange Rate Forecasting System

by Muhammad Yasir, Mehr Yahya Durrani, Sitara Afzal, Muazzam Maqsood, Farhan Aadil, Irfan Mehmood and Seungmin Rho

Appl. Sci. 2019, 9(15), 2980; https://doi.org/10.3390/app9152980 - 25 Jul 2019

Cited by 31 | Viewed by 4992

Abstract

Financial time series analysis is an important research area that can predict various economic indicators such as the foreign currency exchange rate. In this paper, a deep-learning-based model is proposed to forecast the foreign exchange rate. Since the currency market is volatile and [...] Read more.

Financial time series analysis is an important research area that can predict various economic indicators such as the foreign currency exchange rate. In this paper, a deep-learning-based model is proposed to forecast the foreign exchange rate. Since the currency market is volatile and susceptible to ongoing social and political events, the proposed model incorporates event sentiments to accurately predict the exchange rate. Moreover, as the currency market is heavily dependent upon highly volatile factors such as gold and crude oil prices, we considered these sensitive factors for exchange rate forecasting. The validity of the model is tested over three currency exchange rates, which are Pak Rupee to US dollar (PKR/USD), British pound sterling to US dollar (GBP/USD), and Hong Kong Dollar to US dollar (HKD/USD). The study also shows the importance of incorporating investor sentiment of local and foreign macro-level events for accurate forecasting of the exchange rate. We processed approximately 5.9 million tweets to extract major events’ sentiment. The results show that this deep-learning-based model is a better predictor of foreign currency exchange rate in comparison with statistical techniques normally employed for prediction. The results present evidence that the exchange rate of all the three countries is more exposed to events happening in the US. Full article

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)

► Show Figures

Figure 1

12 pages, 2895 KiB

Open AccessArticle

Personalized Online Live Video Streaming Using Softmax-Based Multinomial Classification

by Kyeongseon Kim, Dohyun Kwon, Joongheon Kim and Aziz Mohaisen

Appl. Sci. 2019, 9(11), 2297; https://doi.org/10.3390/app9112297 - 04 Jun 2019

Cited by 1 | Viewed by 2332

Abstract

As the demand for over-the-top and online streaming services exponentially increases, many techniques for Quality of Experience (QoE) provisioning have been studied. Users can take actions (e.g., skipping) while streaming a video. Therefore, we should consider the viewing pattern of users rather than [...] Read more.

As the demand for over-the-top and online streaming services exponentially increases, many techniques for Quality of Experience (QoE) provisioning have been studied. Users can take actions (e.g., skipping) while streaming a video. Therefore, we should consider the viewing pattern of users rather than the network condition or video quality. In this context, we propose a proactive content-loading algorithm for improving per-user personalized preferences using multinomial softmax classification. Based on experimental results, the proposed algorithm has a personalized per-user content waiting time that is significantly lower than that of competing algorithms. Full article

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)

► Show Figures

Figure 1

13 pages, 2419 KiB

Open AccessArticle

MISFP-Growth: Hadoop-Based Frequent Pattern Mining with Multiple Item Support

by Chen-Shu Wang and Jui-Yen Chang

Appl. Sci. 2019, 9(10), 2075; https://doi.org/10.3390/app9102075 - 20 May 2019

Cited by 14 | Viewed by 3211

Abstract

In practice, single item support cannot comprehensively address the complexity of items in large datasets. In this study, we propose a big data analytics framework (named Multiple Item Support Frequent Patterns, MISFP-growth algorithm) that uses Hadoop-based parallel computing to achieve high-efficiency mining of [...] Read more.

In practice, single item support cannot comprehensively address the complexity of items in large datasets. In this study, we propose a big data analytics framework (named Multiple Item Support Frequent Patterns, MISFP-growth algorithm) that uses Hadoop-based parallel computing to achieve high-efficiency mining of itemsets with multiple item supports (MIS). The proposed architecture consists of two phases. First, in the counting support phase, a Hadoop MapReduce architecture is employed to determine the support for each item. Next, in the analytics phase, sub-transaction blocks are generated according to MIS and the MISFP-growth algorithm identifies the frequency of patterns. To facilitate decision makers in setting MIS, we also propose the concept of classification of item (COI), which classifies items of higher homogeneity into the same class, by which the items inherit class support as their item support. Three experiments were implemented to validate the proposed Hadoop-based MISFP-growth algorithm. The experimental results show approximately 38% reduction in the execution time on parallel architectures. The proposed MISFP-growth algorithm can be implemented on the distributed computing framework. Furthermore, according to the experimental results, the enhanced performance of the proposed algorithm indicates that it could have big data analytics applications. Full article

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)

► Show Figures

Figure 1

13 pages, 1760 KiB

Open AccessArticle

A Distributed Algorithm for Fast Mining Frequent Patterns in Limited and Varying Network Bandwidth Environments

by Chun-Cheng Lin, Wei-Ching Li, Ju-Chin Chen, Wen-Yu Chung, Sheng-Hao Chung and Kawuu W. Lin

Appl. Sci. 2019, 9(9), 1859; https://doi.org/10.3390/app9091859 - 06 May 2019

Cited by 2 | Viewed by 3517

Abstract

Data mining is a set of methods used to mine hidden information from data. It mainly includes frequent pattern mining, sequential pattern mining, classification, and clustering. Frequent pattern mining is used to discover the correlation among various sets of items within large databases. [...] Read more.

Data mining is a set of methods used to mine hidden information from data. It mainly includes frequent pattern mining, sequential pattern mining, classification, and clustering. Frequent pattern mining is used to discover the correlation among various sets of items within large databases. The rapid upward trend in data size slows the mining of frequent patterns. Numerous studies have attempted to develop algorithms that operate in distributed computing environments to accelerate the mining process. FLR-mining (Fast, Load balancing and Resource efficient mining algorithm) is one of the fastest methods of mining with efficient consideration of load balancing and resources. FLR-mining can automatically determine the appropriate number of computing nodes. However, FLR-mining and existing methods assume that the network bandwidth is constant. In practical distributed and many-task computing systems, this assumption fails because there are packet collisions caused by many mining tasks that run in a simultaneous manner. Therefore, a method that can consider the varying network bandwidth is necessary. In this study, we propose a method that can rapidly mine frequent patterns under the varying network bandwidth. The proposed method can also determine the appropriate number of computing nodes to efficiently utilize computing resources and achieve load balancing. Through empirical evaluation, the proposed method is shown to deliver excellent performance in terms of execution efficiency and load balancing. Full article

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)

► Show Figures

Figure 1

15 pages, 602 KiB

Open AccessArticle

A Hybrid Crow Search Algorithm for Solving Permutation Flow Shop Scheduling Problems

by Ko-Wei Huang, Abba Suganda Girsang, Ze-Xue Wu and Yu-Wei Chuang

Appl. Sci. 2019, 9(7), 1353; https://doi.org/10.3390/app9071353 - 30 Mar 2019

Cited by 20 | Viewed by 3995

Abstract

The permutation flow shop scheduling problem (PFSP) is a renowned problem in the scheduling research community. It is an NP-hard combinatorial optimization problem that has useful real-world applications. In this problem, finding a useful algorithm to handle the massive amounts of jobs required [...] Read more.

The permutation flow shop scheduling problem (PFSP) is a renowned problem in the scheduling research community. It is an NP-hard combinatorial optimization problem that has useful real-world applications. In this problem, finding a useful algorithm to handle the massive amounts of jobs required to retrieve an actionable permutation order in a reasonable amount of time is important. The recently developed crow search algorithm (CSA) is a novel swarm-based metaheuristic algorithm originally proposed to solve mathematical optimization problems. In this paper, a hybrid CSA (HCSA) is proposed to minimize the makespans of PFSPs. First, to make the CSA suitable for solving the PFSP, the smallest position value rule is applied to convert continuous numbers into job sequences. Then, the HCSA uses a Nawaz–Enscore–Ham (NEH) technique to create a population with the required levels of quality and diversity. We apply a local search to enhance the quality of the solutions and avoid premature convergence; simulated annealing enhances the local search of a method based on a variable neighborhood search. Computational tests are used to evaluate the algorithm using PFSP benchmarks with job sizes between 20 and 500. The tests indicate that the performance of the proposed HCSA is significantly superior to that of other algorithms. Full article

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Actionable Pattern-Driven Analytics and Prediction

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (12 papers)

Editorial

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI