Digital Library
Vol. 20, No. 5, Oct. 2024
-
Chunling Jin, Jingjing Liu, Li Gong, Yang Su
Vol. 20, No. 5, pp. 574-587, Oct. 2024
https://doi.org/10.3745/JIPS.04.0319
Keywords: Diversion Tunnel, Entropy Weight Method, Grey relational analysis, Matter-Element Extension Model, Risk Assessment
Show / Hide AbstractIn order to accurately predict the level of landslide and water surge risks during the construction phase of the diversion tunnel, a scientific and reasonable assessment of the tunnel construction safety risks was carried out by combining game theory and the matter-element expansion method. Considering the various predisposing indexes of the tunnel, an index system containing 24 indexes was constructed by combining relevant codes and references. GRA and EWM are used to assign subjective and objective weights to the indexes respectively, and game theory is used to determine the weights comprehensively. The GRA-EWM-MEE model was established based on the matter-element extension method and validated with tunnel 7# as an example. The results show that the correlation degrees of each section of the tunnel are: 0.086, 0.069, 0.033, 0.035, and 0.077, all of them belong to class II (moderate risk), which is consistent with the results of the variable fuzzy set evaluation and engineering risk assessment report. Therefore, it is feasible to apply the model to tunnel construction risk assessment, which can provide new ideas for the safety risk assessment of similar diversion tunnels. -
Jiao-Hong Qiang, Gao Yang, Ding-Wan Ning
Vol. 20, No. 5, pp. 588-601, Oct. 2024
https://doi.org/10.3745/JIPS.03.0201
Keywords: Environmental Resource Monitoring, Privacy Protection, Remote-Sensing Network, trust evaluation
Show / Hide AbstractHigh-resolution remote-sensing-network technology has the advantages of low cost, accuracy, and real-time performance in green city environmental resource investigation and management. However, in the “Internet of everything,” open, complex, and resource-intensive edge computing causes problems, such as equipment security issues and data leakage. Thus, the establishment of an effective trust evaluation mechanism has become an important research topic. In this study, the identity trust and behavioral trust of edge devices were combined, and a model was developed for evaluating the dynamic trust of edge devices. Through simulation analysis, the identity verification program has the advantages of good security performance and low bandwidth occupation, which increases the success rate of interaction with a device and enhances its data information security and privacy protection capabilities. Steps for the identity authentication process were identified, a trust evaluation mechanism was devised, and a privacy protection model was developed. Different indices were calculated to monitor environmental resources. -
Xin Feng, Haifeng Gong, Guohang Qiu, Kaiqun Hu
Vol. 20, No. 5, pp. 602-616, Oct. 2024
https://doi.org/10.3745/JIPS.04.0321
Keywords: Adaptive Sparse Representation, Image fusion, low-rank representation, Non-subsampled Shearlet Transform
Show / Hide AbstractTraditional multifucus image fusion often requires the inclusion of edge features, blurred details, and noise pollution when perturbed by noise. To address these problems, this study proposes a method for fusing noisy multifucus images using adaptive sparse and low-rank representations. The proposed method first decomposes the image into high- and low-frequency subband coefficients using a non-subsampled shearlet transform. Subsequently, the high-frequency energy components are fused and denoised using a low-rank representation. The corresponding fusion rules are then set using an adaptive sparse representation to fuse the low-frequency subband coefficients. The final fusion result is obtained by reconstructing the fused high- and low-frequency subband coefficients. Experimental results show that the proposed method outperforms traditional methods in terms of both subjective performance and objective indicators, making it a compelling fusion method for noisy multifucus images. -
Xia Hou, Zhiwei Li
Vol. 20, No. 5, pp. 617-626, Oct. 2024
https://doi.org/10.3745/JIPS.02.0218
Keywords: ROI, Stiffness, SVD, Taking Fabric, wavelet transform
Show / Hide AbstractTo address the issues of high cost and low accuracy in the manual detection method, an improved singular value decomposition (SVD)-based fabric defect detection method was proposed in this study. The method first performed noise reduction by wavelet transform; then the image was segmented. Finally, SVD was applied to remove background texture information and improve detection accuracy. The results for the detection of different types of fabric defects showed that the improved SVD method for stiffness detection of fabrics was highly efficient and accurate. The computational complexity, data redundancy and detection results of different sub-image sizes of pixels were all significant. The area under the curve (AUC) value of the star and check fabric was inferior to the defect fabric. The method is highly accurate for different fabric types and can be subsequently applied to the detection of stiffness in apparel fabrics, providing a reference for textile manufacturing production. -
Abdinabiev Aslan Safarovich, Jisung Kim, Byungjeong Lee
Vol. 20, No. 5, pp. 627-639, Oct. 2024
https://doi.org/10.3745/JIPS.04.0320
Keywords: Automated Program Repair, Machine Learning, Multi-Chunk Bugs, Patch Optimization
Show / Hide AbstractAutomated program repair techniques leveraging deep learning have shown remarkable performances in bug repair. These techniques commonly employ pre-trained neural machine translation (NMT) models to generate patches for a buggy part of the source code. However, when dealing with multiple buggy code chunks in various locations, current methods face challenges in effectively selecting and combining these patches for optimal repair. This paper identifies limitations within one of the existing methods used for optimizing patches related to multiple buggy code chunks and proposes an enhanced patch optimization technique to address these shortcomings. The primary aim of this study is to improve the process of selecting and combining patches generated for groups of buggy chunks. Through experiments conducted on a dataset, this paper demonstrates the efficacy of the proposed patch optimization technique, showcasing its potential to enhance the overall bug repair process. This study highlights the importance of patch optimization in bug repair by addressing limitations and enhancing the repair process. -
Yiqin Wang, Yunyun Dong
Vol. 20, No. 5, pp. 640-653, Oct. 2024
https://doi.org/10.3745/JIPS.01.0108
Keywords: channel attention, DeepLabv3+, Feature Fusion Module, Remote-Sensing Images, Semantic segmentation
Show / Hide AbstractCurrent methods for semantic segmentation of remote-sensing images, especially for irregular and small targets, often result in low precision and incomplete feature extraction. To address this issue, an improved semantic segmentation method was developed utilizing DeepLabv3+. First, DeepLabv3+ is combined with the proposed feature fusion module to make full use of the complementary information of low- and high-level features. Second, the channel attention module helps extract effective features while suppressing irrelevant features, thereby enabling the extraction of more meaningful global information from high-level features. Finally, rich spatial information is selected using guided spatial attention, which improves the accuracy of edge segmentation of target objects. The results of the comparison show that the mean F1 score (MF1) and overall accuracy (OA) of the proposed method on the ISPRS Potsdam dataset are 89.81% and 88.45%, respectively. The MF1 of the proposed method is 89.90% and the OA is 89.14% for the UAVid dataset, which are higher than those of the other comparison algorithms. The proposed method exhibits superior semantic segmentation capabilities for remote-sensing images. -
Guizhen Shi, Na Li
Vol. 20, No. 5, pp. 654-662, Oct. 2024
https://doi.org/10.3745/JIPS.03.0202
Keywords: Food safety, Internet of Things, Neural Networks, Safety Testing
Show / Hide AbstractIn order to make it more convenient and fast for people to obtain the production information of dairy food and consume dairy food with confidence, a dairy food safety testing system based on the Internet of Things (IoT) is proposed in the study. Firstly, an ISM-AHP-RBF neural network-based risk assessment method for dairy products is proposed, and then the design of an IoT-based dairy milk production method is proposed using the information transmission and data collection functions of the IoT. The performance of the model is validated by comparing it with traditional neural network models. The results show that the ISM-AHP-RBF neural network can quickly iterate to a stable state and converge better than the other two traditional models; the results of risk prediction and assessment of milk components using the model are close to the real values and can accurately predict the riskier components, thus ensuring the food safety of dairy products. -
Changguo Li, Fuquan Zhu
Vol. 20, No. 5, pp. 663-674, Oct. 2024
https://doi.org/10.3745/JIPS.02.0219
Keywords: Causal Neighborhood, Hyperspectral Image, Lossless compression, Variable Forgetting Factor Recursive Least Squares
Show / Hide AbstractForgetting factor recursive least squares (FFRLS) is an effective lossless compression technique for hyperspectral images. However, the forgetting factor of the FFRLS algorithm is a predetermined fixed value that cannot be adjusted in real time, which can affect prediction accuracy. To address this problem, a new lossless compression method for hyperspectral images using variable forgetting factor recursive least squares was developed. The impact of the forgetting factor on the FFRLS algorithm was analyzed, and a forgetting factor adjustment function was constructed using the average of the posterior prediction residuals in a causal neighborhood as a variable to adjust the forgetting factor dynamically. The performance of this algorithm was verified using NASA's AIRS and CCSDS's 2006 AVIRIS images with minimum average bit rates of 3.66 and 4.07 bits per pixel, respectively. The experimental results show that the proposed algorithm improves prediction accuracy compared with the algorithm with a fixed forgetting factor and achieves better compression performance. -
JunHyeok Go, Nammee Moon
Vol. 20, No. 5, pp. 675-683, Oct. 2024
https://doi.org/10.3745/JIPS.01.0109
Keywords: Convolutional Neural Network (CNN), Image Similarity, Large Waste
Show / Hide AbstractLarge-scale waste similarity analysis is crucial for automating waste management on a large scale. It involves confirming the match between waste discharged from homes and that collected by agencies, which is essential for a stable automated system. This paper compares feature extraction methods for similarity measurement, including the scale-invariant feature transform (SIFT) algorithm with added HSV color features, convolutional neural network-based encoders, and a modified 6-channel (6CH) ResNet for end-to-end learning. The results demonstrate that the 6CH ResNet achieves up to 4.9% higher accuracy than both the basic SIFT method and encoders, as well as the SIFT algorithm with HSV color features. Implementing the 6CH ResNet in automated waste management systems can enhance object similarity measurement while using fewer computing resources. -
Xiaowei Hai, Shenglan He, Chanchan Zhao
Vol. 20, No. 5, pp. 684-695, Oct. 2024
https://doi.org/10.3745/JIPS.04.0323
Keywords: Agricultural Enterprises, Collaboration Strategy, Digital Transformation, evolutionary game, Local government
Show / Hide AbstractLocal governments play an important role in the digital transformation of agricultural enterprises. An effective government–enterprise collaboration strategy can enable the successful digitalization of agricultural enterprises. However, efficient collaboration between the local government of a place and agricultural enterprises is difficult to achieve because of the complexity of influencing factors, evolutionary processes, and stability strategies. To address this issue, we propose a government–enterprise collaboration strategy based on evolutionary game theory. First, we build an evolutionary game model based on local governments' guidance behavior and agricultural enterprises' digital transformation decision-making. Second, we analyze the evolutionary stability strategy of the local government and agricultural enterprises using the Jacobian matrix. The influence of related parameters on strategy evolution is also discussed. Third, we use numerical simulation to verify the effectiveness of the proposed model. Finally, some managerial implications are proposed for local governments to promote the digital transformation of agricultural enterprises. -
Sheng Miao, Guoqing Ni, Lan Chen, Ruolan Mu, Yansu Qi, Chao Liu
Vol. 20, No. 5, pp. 696-708, Oct. 2024
https://doi.org/10.3745/JIPS.04.0322
Keywords: Agglomeration and Hierarchical Clustering, Natural Language Processing, Text Mining, Wetland Evaluation
Show / Hide AbstractWetlands are one of the important ecosystems on Earth, with necessary functions such as regulating climate, providing water, purifying water quality, and protecting biodiversity. At present, wetland health assessment has become a major direction in wetland research, and optimizing wetland assessment is of great significance for global sustainable development. However, most wetland assessments do not have agreed upon indicators and standards. In recent years, many achievements have been made in wetland health research. Therefore, the aim of this study is to use data mining techniques to explore and evaluate the main factors in relation to wetlands. This article uses 100 wetland health papers on Web of Science as the corpus, proposes an indicator extraction method based on natural language processing and text mining technology, explores the interrelationships between the extracted indicators, establishes a wetland indicator evaluation system to evaluate the wetland health status, and explores new ideas for wetland health evaluation. -
Meiqin Zheng
Vol. 20, No. 5, pp. 709-717, Oct. 2024
https://doi.org/10.3745/JIPS.02.0220
Keywords: Artificial intelligence, Educational Technology Application, Mental Health Nursing Education, Statistical Model, Teaching Effect
Show / Hide AbstractWith the rapid development of artificial intelligence (AI) technology, its widespread use in various industries, especially in education, has triggered an in-depth exploration of the role of AI in specific fields. Mental health nursing education, as a technology-sensitive and rapidly responsive field, is particularly important for research on the use of AI technology in order to enhance educational effectiveness and efficiency. Based on an in-depth analysis of existing educational models, this study explores how AI technology can revolutionize mental health nursing education, and comprehensively analyses the actual potential of AI technology in enhancing the quality of mental health nursing education through questionnaires, experimental design and the construction and application of statistical models.
Indexing
All publications of JIPS are indexed in ESCI (a new Web of Science index of Thomson Reuters), SCOPUS, DOI, DBLP, EI COMPENDEX, EBSCO, Google Scholar, and Crossref.
JIPS is also selected as the Journal for Accreditation by NRF (National Research Foundation of Korea).
