Digital Library

Vol. 18, No. 4, Aug. 2022  Cover

1. Life Prediction of Hydraulic Concrete Based on Grey Residual Markov Model
   Li Gong, Xuelei Gong, Ying Liang, Bingzong Zhang, Yiqun Yang
   Vol. 18, No. 4, pp. 457-469, Aug. 2022  
   https://doi.org/10.3745/JIPS.04.0247
   Details Full Text PubReader
   Keywords: Durability, Grey Residuals, Hydraulic Concrete, Lifespan Prediction, Markov
   Show / Hide Abstract

   Hydraulic concrete buildings in the northwest of China are often subject to the combined effects of lowtemperature frost damage, during drying and wetting cycles, and salt erosion, so the study of concrete deterioration prediction is of major importance. The prediction model of the relative dynamic elastic modulus (RDEM) of four different kinds of modified concrete under the special environment in the northwest of China was established using Grey residual Markov theory. Based on the available test data, modified values of the dynamic elastic modulus were obtained based on the Grey GM(1,1) model and the residual GM(1,1) model, combined with the Markov sign correction, and the dynamic elastic modulus of concrete was predicted. The computational analysis showed that the maximum relative error of the corrected dynamic elastic modulus was significantly reduced, from 1.599% to 0.270% for the BS2 group. The analysis error showed that the model was more adjusted to the concrete mixed with fly ash and mineral powder, and its calculation error was significantly lower than that of the rest of the groups. The analysis of the data for each group proved that the model could predict the loss of dynamic elastic modulus of the deterioration of the concrete effectively, as well as the number of cycles when the concrete reached the damaged state.


2. Mukbang’s Foodcasting beyond Korea’s Borders: A Study Focusing on OTT Platforms
   Jia Lim
   Vol. 18, No. 4, pp. 470-479, Aug. 2022  
   https://doi.org/10.3745/JIPS.02.0176
   Details Full Text PubReader
   Keywords: Acculturation and Reception Theory, ASMR, Global Food Culture, Mukbang
   Show / Hide Abstract

   Mukbang is a type of foodcasting where a host records or streams their eating rituals for audience consumption in live format. With origins in South Korea via the online broadcast genre found on Afreeca TV in the mid- 2000s, the phenomenon has since found global popularity. Its development as a full-fledged genre is based on a communication culture that invites people to a meal rather than to talk to one another; viewers watch in silence as a host consumes a copious number of dishes from Korean gastronomy to fast food to other ethnic cuisine on display. An invitation to eat means the beginning of a public relationship that quickly turns to a private shared experience. This study analyzes several Mukbang video postings and makes use of Linden’s culture approach model to provide a view toward a number of cross-cultural connections by Koreans and non-Korean audiences. Prior to the study, 10 Korean eating shows were selected and used as standard models. Korean Mukbang mainly consists of eating behavior and ASMR, with very few storytelling or narrative devices utilized by its creators. For this reason, eating shows make a very private connection. In other ways, this paper shows how 28 Mukbangrelated YouTube contents selected by Ranker were evolving and examined through notions of acculturation and reception theory.


3. Tobacco Retail License Recognition Based on Dual Attention Mechanism
   Yuxiang Shan, Qin Ren, Cheng Wang, Xiuhui Wang
   Vol. 18, No. 4, pp. 480-488, Aug. 2022  
   https://doi.org/10.3745/JIPS.02.0177
   Details Full Text PubReader
   Keywords: Attention Mechanism, Image recognition, Robot Process Automation (RPA)
   Show / Hide Abstract

   Images of tobacco retail licenses have complex unstructured characteristics, which is an urgent technical problem in the robot process automation of tobacco marketing. In this paper, a novel recognition approach using a double attention mechanism is presented to realize the automatic recognition and information extraction from such images. First, we utilized a DenseNet network to extract the license information from the input tobacco retail license data. Second, bi-directional long short-term memory was used for coding and decoding using a continuous decoder integrating dual attention to realize the recognition and information extraction of tobacco retail license images without segmentation. Finally, several performance experiments were conducted using a largescale dataset of tobacco retail licenses. The experimental results show that the proposed approach achieves a correction accuracy of 98.36% on the ZY-LQ dataset, outperforming most existing methods.


4. Analysis of Security Vulnerabilities for IoT Devices
   Hee-Hyun Kim and Jinho Yoo
   Vol. 18, No. 4, pp. 489-499, Aug. 2022  
   https://doi.org/10.3745/JIPS.03.0178
   Details Full Text PubReader
   Keywords: CVE Vulnerability, CVSS, IoT device, Security Vulnerabilities
   Show / Hide Abstract

   Recently, the number of Internet of Things (IoT) devices has been increasing exponentially. These IoT devices are directly connected to the internet to exchange information. IoT devices are becoming smaller and lighter. However, security measures are not taken in a timely manner compared to the security vulnerabilities of IoT devices. This is often the case when the security patches cannot be applied to the device because the security patches are not adequately applied or there is no patch function. Thus, security vulnerabilities continue to exist, and security incidents continue to increase. In this study, we classified and analyzed the most common security vulnerabilities for IoT devices and identify the essential vulnerabilities of IoT devices that should be considered for security when producing IoT devices. This paper will contribute to reducing the occurrence of security vulnerabilities in companies that produce IoT devices. Additionally, companies can identify vulnerabilities that frequently occur in IoT devices and take preemptive measures.


5. Evaluation Method of College English Education Effect Based on Improved Decision Tree Algorithm
   Fang Dou
   Vol. 18, No. 4, pp. 500-509, Aug. 2022  
   https://doi.org/10.3745/JIPS.04.0248
   Details Full Text PubReader
   Keywords: Association Rules, Characteristic Interval Value, English Education, Improved Decision Tree, Incremental Algorithm
   Show / Hide Abstract

   With the rapid development of educational informatization, teaching methods become diversified characteristics, but a large number of information data restrict the evaluation on teaching subject and object in terms of the effect of English education. Therefore, this study adopts the concept of incremental learning and eigenvalue interval algorithm to improve the weighted decision tree, and builds an English education effect evaluation model based on association rules. According to the results, the average accuracy of information classification of the improved decision tree algorithm is 96.18%, the classification error rate can be as low as 0.02%, and the anti-fitting performance is good. The classification error rate between the improved decision tree algorithm and the original decision tree does not exceed 1%. The proposed educational evaluation method can effectively provide early warning of academic situation analysis, and improve the teachers’ professional skills in an accelerated manner and perfect the education system.


6. Fuzzy Neural Network Active Disturbance Rejection Control for Two-Wheeled Self-Balanced Robot
   Chao Wang, Xiao Jianliang, Cheng Zhang
   Vol. 18, No. 4, pp. 510-523, Aug. 2022  
   https://doi.org/10.3745/JIPS.01.0089
   Details Full Text PubReader
   Keywords: ADRC, Compensate Dynamically, ESO, FNN, Nonlinear PD Control Rate, TWSBR
   Show / Hide Abstract

   Considering the problems of poor control effect, weak disturbance rejection ability and adaptive ability of twowheeled self-balanced robot (TWSBR) systems on undulating roads, this paper proposes a fuzzy neural network active disturbance rejection controller (FNNADRC), that is based on fuzzy neural network (FNN) for online correction of active disturbance rejection controller (ADRC)’s nonlinear control rate. Firstly, the dynamic model of the TWSBR is established and decoupled, the extended state observer (ESO) is used to compensate dynamically and linearize the upright and displacement subsystems. Then, the nonlinear PD control rate and FNN are designed, and the FNN is used to modify the control parameters of the nonlinear PD control rate in real time. Finally, the proposed control strategy is simulated and compared with the traditional ADRC and fuzzy active disturbance rejection controller (FADRC). The simulation results show that the control effect of the proposed control strategy is slightly better than ADRC and FADRC.


7. TOD: Trash Object Detection Dataset
   Min-Seok Jo, Seong-Soo Han, Chang-Sung Jeong
   Vol. 18, No. 4, pp. 524-534, Aug. 2022  
   https://doi.org/10.3745/JIPS.02.0178
   Details Full Text PubReader
   Keywords: dataset, Deep Learning, recognition, Trash Detection
   Show / Hide Abstract

   In this paper, we produce Trash Object Detection (TOD) dataset to solve trash detection problems. A wellorganized dataset of sufficient size is essential to train object detection models and apply them to specific tasks. However, existing trash datasets have only a few hundred images, which are not sufficient to train deep neural networks. Most datasets are classification datasets that simply classify categories without location information. In addition, existing datasets differ from the actual guidelines for separating and discharging recyclables because the category definition is primarily the shape of the object. To address these issues, we build and experiment with trash datasets larger than conventional trash datasets and have more than twice the resolution. It was intended for general household goods. And annotated based on guidelines for separating and discharging recyclables from the Ministry of Environment. Our dataset has 10 categories, and around 33K objects were annotated for around 5K images with 1280×720 resolution. The dataset, as well as the pre-trained models, have been released at https://github.com/jms0923/tod.


8. Burmese Sentiment Analysis Based on Transfer Learning
   Cunli Mao, Zhibo Man, Zhengtao Yu, Xia Wu, Haoyuan Liang
   Vol. 18, No. 4, pp. 535-548, Aug. 2022  
   https://doi.org/10.3745/JIPS.04.0249
   Details Full Text PubReader
   Keywords: Burmese, Cross-Lingual, sentiment analysis, Transfer Learning
   Show / Hide Abstract

   Using a rich resource language to classify sentiments in a language with few resources is a popular subject of research in natural language processing. Burmese is a low-resource language. In light of the scarcity of labeled training data for sentiment classification in Burmese, in this study, we propose a method of transfer learning for sentiment analysis of a language that uses the feature transfer technique on sentiments in English. This method generates a cross-language word-embedding representation of Burmese vocabulary to map Burmese text to the semantic space of English text. A model to classify sentiments in English is then pre-trained using a convolutional neural network and an attention mechanism, where the network shares the model for sentiment analysis of English. The parameters of the network layer are used to learn the cross-language features of the sentiments, which are then transferred to the model to classify sentiments in Burmese. Finally, the model was tuned using the labeled Burmese data. The results of the experiments show that the proposed method can significantly improve the classification of sentiments in Burmese compared to a model trained using only a Burmese corpus.


9. Bi-directional Maximal Matching Algorithm to Segment Khmer Words in Sentence
   Makara Mao, Sony Peng, Yixuan Yang, Doo-Soon Park
   Vol. 18, No. 4, pp. 549-561, Aug. 2022  
   https://doi.org/10.3745/JIPS.04.0250
   Details Full Text PubReader
   Keywords: Bi-directional Maximal Matching, Khmer Language, Natural Language Processing, Word Corpus, Word Segmentation
   Show / Hide Abstract

   In the Khmer writing system, the Khmer script is the official letter of Cambodia, written from left to right without a space separator; it is complicated and requires more analysis studies. Without clear standard guidelines, a space separator in the Khmer language is used inconsistently and informally to separate words in sentences. Therefore, a segmented method should be discussed with the combination of the future Khmer natural language processing (NLP) to define the appropriate rule for Khmer sentences. The critical process in NLP with the capability of extensive data language analysis necessitates applying in this scenario. One of the essential components in Khmer language processing is how to split the word into a series of sentences and count the words used in the sentences. Currently, Microsoft Word cannot count Khmer words correctly. So, this study presents a systematic library to segment Khmer phrases using the bi-directional maximal matching (BiMM) method to address these problematic constraints. In the BiMM algorithm, the paper focuses on the Bidirectional implementation of forward maximal matching (FMM) and backward maximal matching (BMM) to improve word segmentation accuracy. A digital or prefix tree of data structure algorithm, also known as a trie, enhances the segmentation accuracy procedure by finding the children of each word parent node. The accuracy of BiMM is higher than using FMM or BMM independently; moreover, the proposed approach improves dictionary structures and reduces the number of errors. The result of this study can reduce the error by 8.57% compared to FMM and BFF algorithms with 94,807 Khmer words.


10. Effect of Interactive Multimedia PE Teaching Based on the Simulated Annealing Algorithm
    Mingfeng Zhao
    Vol. 18, No. 4, pp. 562-574, Aug. 2022  
    https://doi.org/10.3745/JIPS.02.0181
    Details Full Text PubReader
    Keywords: Evaluation Model, Interactive Physical Education, Multimedia Interaction, simulated annealing algorithm, Teaching Effectiveness Assessment
    Show / Hide Abstract

    As traditional ways of evaluation prove to be ineffective in evaluating the effect of interactive multimedia physical education (PE) teaching, this study develops a new evaluation model based on the simulated annealing algorithm. After the evaluation subjects and the principle of the evaluation system are determined, different subjects are well chosen to constitute the evaluation system and given the weight. The backpropagation neural network has been improved through the simulated annealing algorithm, whose improvement indicates the completion of the evaluation model. Simulation results show that the evaluation model is highly efficient. Compared with traditional evaluation models, the proposed one enhances students’ performance in PE classes by 50%.


11. GAN-Based Local Lightness-Aware Enhancement Network for Underexposed Images
    Yong Chen, Meiyong Huang, Huanlin Liu, Jinliang Zhang, Kaixin Shao
    Vol. 18, No. 4, pp. 575-586, Aug. 2022  
    https://doi.org/10.3745/JIPS.02.0179
    Details Full Text PubReader
    Keywords: GAN, Local Lightness Attention Module, Local Lightness-Aware, Low-Light Image Enhancement, Multiple Discriminators
    Show / Hide Abstract

    Uneven light in real-world causes visual degradation for underexposed regions. For these regions, insufficient consideration during enhancement procedure will result in over-/under-exposure, loss of details and color distortion. Confronting such challenges, an unsupervised low-light image enhancement network is proposed in this paper based on the guidance of the unpaired low-/normal-light images. The key components in our network include super-resolution module (SRM), a GAN-based low-light image enhancement network (LLIEN), and denoising-scaling module (DSM). The SRM improves the resolution of the low-light input images before illumination enhancement. Such design philosophy improves the effectiveness of texture details preservation by operating in high-resolution space. Subsequently, local lightness attention module in LLIEN effectively distinguishes unevenly illuminated areas and puts emphasis on low-light areas, ensuring the spatial consistency of illumination for locally underexposed images. Then, multiple discriminators, i.e., global discriminator, local region discriminator, and color discriminator performs assessment from different perspectives to avoid over- /under-exposure and color distortion, which guides the network to generate images that in line with human aesthetic perception. Finally, the DSM performs noise removal and obtains high-quality enhanced images. Both qualitative and quantitative experiments demonstrate that our approach achieves favorable results, which indicates its superior capacity on illumination and texture details restoration.


12. Building Change Detection Using Deep Learning for Remote Sensing Images
    Chang Wang, Shijing Han, Wen Zhang, Shufeng Miao
    Vol. 18, No. 4, pp. 587-598, Aug. 2022  
    https://doi.org/10.3745/JIPS.02.0180
    Details Full Text PubReader
    Keywords: Deep neural network (DNN), Difference Image, Frequency-Domain Significance, fuzzy c-means
    Show / Hide Abstract

    To increase building change recognition accuracy, we present a deep learning-based building change detection using remote sensing images. In the proposed approach, by merging pixel-level and object-level information of multitemporal remote sensing images, we create the difference image (DI), and the frequency-domain significance technique is used to generate the DI saliency map. The fuzzy C-means clustering technique preclassifies the coarse change detection map by defining the DI saliency map threshold. We then extract the neighborhood features of the unchanged pixels and the changed (buildings) from pixel-level and object-level feature images, which are then used as valid deep neural network (DNN) training samples. The trained DNNs are then utilized to identify changes in DI. The suggested strategy was evaluated and compared to current detection methods using two datasets. The results suggest that our proposed technique can detect more building change information and improve change detection accuracy.