• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1868-1887
• /
• 2024

Recommendation systems research is a subfield of information retrieval, as these systems recommend appropriate items to users during their visits. Appropriate recommendation results will help users save time searching while increasing productivity at work, travel, or shopping. The problem becomes more difficult when the items are geographical locations on the ground, as they are associated with a wealth of contextual information, such as geographical location, opening time, and sequence of related locations. Furthermore, on social networking platforms that allow users to check in or express interest when visiting a specific location, their friends receive this signal by spreading the word on that online social network. Consideration should be given to relationship data extracted from online social networking platforms, as well as their impact on the geolocation recommendation process. In this study, we compare the similarity of geographic locations based on their distance on the ground and their correlation with users who have checked in at those locations. When calculating feature embeddings for users and locations, social relationships are also considered as attention signals. The similarity value between location and correlation between users will be exploited in the overall architecture of the recommendation model, which will employ graph convolution networks to generate recommendations with high precision and recall. The proposed model is implemented and executed on popular datasets, then compared to baseline models to assess its overall effectiveness.

• Clinical Endoscopy
• /
• v.55 no.1
• /
• pp.22-32
• /
• 2022

Radiotherapy (RT) is a treatment modality that uses high-energy rays or radioactive agents to generate ionizing radiation against rapidly dividing cells. The main objective of using radiation in cancer therapy is to impair or halt the division of the tumor cells. Over the past few decades, advancements in technology, the introduction of newer methods of RT, and a better understanding of the pathophysiology of cancers have enabled physicians to deliver doses of radiation that match the exact dimensions of the tumor for greater efficacy, with minimal exposure of the surrounding tissues. However, RT has numerous complications, the most common being radiation proctitis (RP). It is characterized by damage to the rectal epithelium by secondary ionizing radiation. Based on the onset of signs and symptoms, post-radiotherapy RP can be classified as acute or chronic, each with varying levels of severity and complication rates. The treatment options available for RP are limited, with most of the data on treatment available from case reports or small studies. Here, we describe the types of RT used in modern-day medicine and radiation-mediated tissue injury. We have primarily focused on the classification, epidemiology, pathogenesis, clinical features, treatment strategies, complications, and prognosis of RP.

• Korean Journal of Agricultural Science
• /
• v.49 no.4
• /
• pp.837-845
• /
• 2022

In this study, tomato maturity was estimated based on deep learning for a harvesting robot. Tomato images were obtained using a RGB camera installed on a monitoring robot, which was developed previously, and the samples were cropped to 128 × 128 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the mean-variance loss was used to learn implicitly the distribution of the data features by class. In the test stage, the tomato maturity was estimated as a continuous index, which has a range of 0 to 1, by calculating the expected class value. The results show that the F1-score of the classification was approximately 0.94, and the performance was similar to that of a deep learning-based classification task in the agriculture field. In addition, it was possible to estimate the distribution in each maturity stage. From the results, it was found that our approach can not only classify the discrete maturation stages of the tomatoes but also can estimate the continuous maturity.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1297-1298
• /
• 2024

This research is centered on the adoption and evolution of Building Information Modeling Execution Plans (BEPs) and Employer's Information Requirements (EIRs) within the Japanese construction sector. Presently, these pivotal documents have not been comprehensively integrated into the Japanese industry, lacking a uniform standard. Addressing this gap, our study investigates the development of an automated system designed to generate optimal BEPs and EIRs, informed by project summaries and survey data. The system's development leverages insights from successful international BEP and EIR models, adapting these to align with the specific requirements of Japanese construction projects. It is tailored to facilitate key processes, including the assessment of BIM-capable personnel and the elucidation of BIM objectives within these projects. The objective of this research is to formulate actionable guidelines and tools that advance the implementation and effectiveness of BIM in Japan. By streamlining the generation of BEPs and EIRs, the system is expected to enrich BIM comprehension and application in the national construction landscape. This initiative not only serves the immediate needs of the local industry but also harmonizes global BIM methodologies with Japanese practices. In sum, this study contributes significantly to the refinement of BIM practices in Japan, promoting a more knowledgeable and efficient approach to construction project management.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.658-664
• /
• 2024

The importance of 3D city models for sustainable urban development and management is underscored, but existing models often overlook indoor spaces and attribute information. This issue can be tackled with BIM models, though the conventional method requires accurate and extensive information, incurring considerable time and cost in data collection and processing. To overcome these limitations, this study proposes a method to automatically generate BIM models that include indoor spaces using street view images. The proposed method uses YOLOv5 to identify façade elements and DBSCAN to normalize façade layouts, facilitating the generation of detailed BIM models with a parametric algorithm. To validate the method, a case study of a building in Korea was conducted. The results showed that indoor spaces similar to the actual building were generated, with an error rate of object quantities between 8.46% and 9.03%. This study is anticipated to contribute to the efficient generation of 3D city models that incorporate indoor spaces.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.714-721
• /
• 2024

Researching the phenomenon and answering research questions to generate an integrated management system to manage the post-disaster reconstruction phase calls for a well-created or structured framework for the research methodology plus a mixed method. Aim and Purpose: To produce an Integrated Management of Environmental, Occupational Health & Safety and Quality Management Systems, a Disaster Management framework for Post-Disaster Reconstruction Projects Management and Empirically Validate the Framework. Research methodology and mixed methods framework study activities are the following stages: Literature Review, Formulating Research Methodology and Mixed Methods, The Research Aim and Objectives, The Research Question Statements - Mixed Methods (Qualitative and Quantitative), Planning and Procedures for Participants and Service Users' Involvements, Designing of Questionnaires and Surveys Research Question, Using Mixed Method Design Data Collection and Analysis with NVIVO and Final Development of the Integrated Management System for Post-Disaster Construction Management Phase, Recommendation and Conclusion. OBJECTIVES: Explore the awareness and practice of environmental, occupational health, safety, and quality management systems, as well as disaster management practices for the post-disaster reconstruction phase and routine reconstruction. Furthermore, the mixed methods part addresses the research aim and objectives. Then, it facilitates the achievement of the research goals and contribution to the knowledge and development of an integrated management system for the post-disaster reconstruction management phase. The end addresses the significance of the research methodology and mixed methods framework developed.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.367-374
• /
• 2024

The detection and tracking of construction workers in building sites generate valuable data on unsafe behavior, work productivity, and construction progress. Many computer vision-based tracking approaches have been investigated and their capabilities for tracking construction workers have been tested. However, the dynamic nature of real-world construction environments, where workers wear similar outfits and move around in often cluttered and occluded regions, has severely limited the accuracy of these methods. Herein, to enhance the performance of vision-based tracking, a new framework is proposed which seamlessly integrates three computer vision components: detection, tracking, and re-identification (DTR). In DTR, a tracking algorithm continuously tracks identified workers using a detector and tracker in combination. Then, a re-identification model extracts visual features and utilizes them as appearance descriptors in subsequent frames during tracking. Empirical results demonstrate that the proposed method has excellent multi-object-tracking accuracy with better accuracy than an existing approach. The DTR framework can efficiently and accurately monitor workers, ensuring safer and more productive dynamic work environments.

• Structural Engineering and Mechanics
• /
• v.92 no.2
• /
• pp.163-172
• /
• 2024

This paper intends to analyze the nonlinear forced vibrations of functionally graded material (FGM) beams with initial geometrical defects in hygro-thermal ambiences. For this purpose, we assume that the correlation properties of the material alter along the thickness direction in succession and the surface of the beam is subjected to humid and thermal loads. Based on the Euler Bernoulli beam theory and geometrical non-linearity, we use the Hamiltonian principle to formulate a theoretical model with consideration of the hygrothermal effects. Galerkin's technique has been proposed for the control equations of discrete systems. The non-linear primary resonances are acquired by applying the modified Lindstedt-Poincare method (MLP). Verify the reliability of the data obtained through comparison with literature. The non-linear resonance response is reflected by amplitude-frequency response curves. The numerical results indicate that the resonances of FGM beams include three non-linear characteristics, namely hard springs, soft springs and soft-hard spring types. The response modalities of the structure may transform between those non-linear characteristics when material properties, spring coefficients, geometric defect values, temperature-humidity loads and even the external stimulus generate variations.

• Journal of the Korean GEO-environmental Society
• /
• v.25 no.11
• /
• pp.13-24
• /
• 2024

The propagation of elastic waves in soil is crucial in geotechnical and seismic engineering. Although soil is often assumed homogeneous, natural geomaterials like soil and rock possess inherent heterogeneity. This study uses FLAC 2D finite difference software to simulate wave propagation under different spatial variability parameters. Random field models and Monte Carlo methods were employed to generate random field data for soil parameters, reflecting the actual variability of soil. The study analyzes the effects of different correlation lengths, variability parameters, and saturation on the propagation characteristics of elastic waves, including wave velocity, amplitude attenuation, and waveform changes. Results show that wave propagation is most sensitive to elastic modulus variability, followed by porosity, while Poisson's ratio has minimal impact. Due to the variability of the elastic modulus, wave propagation time increases with increasing variability coefficient and correlation length. The peak amplitude decreases significantly, and the attenuation mean decreases while the variability of attenuation increases with increasing variability coefficient. Additionally, increasing soil saturation in heterogeneous soils leads to a decrease in wave velocity and an increase in attenuation. These findings contribute to a better understanding of elastic wave propagation in heterogeneous soils and improving design reliability.

• The Journal of Information Systems
• /
• v.33 no.3
• /
• pp.105-121
• /
• 2024

Purpose The purpose of this paper is to develop a method to improve topic representation by incorporating the TextRank technique in Bertopic-based topic modeling and additional indicators for determining the optimal number of topics. Design/methodology/approach In this paper, we propose a method to extract important documents from documents assigned to each topic of a topic model using the TextRank technique, and to calculate secondary diversity and generate topic representations based on the results. First, we integrate the TextRank algorithm into the Bertopic-based topic modeling process to set local secondary labels for each topic. The secondary labels of each topic are derived through extractive summarization based on the TextRank algorithm. Second, we improve the accuracy of selecting the optimal number of topics by calculating the secondary diversity index based on the extractive summary results of each topic. Third, we improve the efficiency by utilizing ChatGPT when deriving the labels of each topic. Findings As a result of performing case analysis and analysis evaluation using the proposed method, it was confirmed that topic representation based on TextRank results generated more accurate topic labels and that the secondary diversity index was a more effective index for determining the optimal number of topics.