• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.41 no.3
• /
• pp.277-288
• /
• 2021

Building information modeling (BIM) element to industry foundation classes (IFC) entity mappings need to be checked to ensure the semantic integrity of BIM models. Existing studies have demonstrated that machine learning algorithms trained on geometric features are able to classify BIM elements, thereby enabling the checking of these mappings. However, reliance on geometry is limited, especially for elements with similar geometric features. This study investigated the employment of relational data between elements, with the assumption that such additions provide higher classification performance. Neural structured learning, a novel approach for combining structured graph data as features to machine learning input, was used to realize the experiment. Results demonstrated that a significant improvement was attained when trained and tested on eight BIM element types with their relational semantics explicitly represented.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.850-858
• /
• 2022

To deploy Gate Recurrent Units (GRU) on resource-constrained embedded devices, this paper presents a reconfigurable FPGA-based GRU accelerator that enables structured compression. Firstly, a dense GRU model is significantly reduced in size by hybrid quantization and structured top-k pruning. Secondly, the energy consumption on external memory access is greatly reduced by the proposed reuse computing pattern. Finally, the accelerator can handle a structured sparse model that benefits from the algorithm-hardware co-design workflows. Moreover, inference tasks can be flexibly performed using all functional dimensions, sequence length, and number of layers. Implemented on the Intel DE1-SoC FPGA, the proposed accelerator achieves 45.01 GOPs in a structured sparse GRU network without batching. Compared to the implementation of CPU and GPU, low-cost FPGA accelerator achieves 57 and 30x improvements in latency, 300 and 23.44x improvements in energy efficiency, respectively. Thus, the proposed accelerator is utilized as an early study of real-time embedded applications, demonstrating the potential for further development in the future.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.169-179
• /
• 2021

Consumers' food consumption behavior is likely to be affected not only by structured data such as consumer panel data but also by unstructured data such as mass media and social media. In this study, a deep learning-based consumption prediction model is generated and verified for the fusion data set linking structured data and unstructured data related to food consumption. The results of the study showed that model accuracy was improved when combining structured data and unstructured data. In addition, unstructured data were found to improve model predictability. As a result of using the SHAP technique to identify the importance of variables, it was found that variables related to blog and video data were on the top list and had a positive correlation with the amount of paprika purchased. In addition, according to the experimental results, it was confirmed that the machine learning model showed higher accuracy than the deep learning model and could be an efficient alternative to the existing time series analysis modeling.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.1263-1268
• /
• 2011

Rail infrastructure manager and operators shall establish emergency response plans. Emergency Response Planning Activities expanded coincidence events should be modeled. Identify the emergency response organization for the purpose of knowledge is required. In other words, control concepts and skills needed core elements. Structured analysis & design technic methodology is Compared with other modeling techniques through a simple graphical model is visualized. The information contained in a model real problems that considering the state of the system activities, so that knowledge acquired in situations where the modeling becomes possible. In this paper, using structured analysis techniques, infrastructure deployment model of the proposed features. In addition to emergency response planning in the 1960s in Germany, Karl Petrie (Carl Petri) devised various means of modeling the situation presents a Petri net model.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.08a
• /
• pp.417-417
• /
• 2012

For desired optical properties of QDs, it is very important to reduce the presence of defects on their surfaces. Passivation of surface defects using larger band gap materials is the most effective way. Some groups successfully synthesized Cd based multi-shell structured quantum dots and improved its optical properties. However, its productivity has limit because of the amounts of glass ware and space. In this research, we try to synthesize Cd based multi-shell structured nanocrystal quantum dots to overcome demerits of conventional batch synthetic method. This reactor composed pump, SUS reaction part (3.2 mm stainless steel and furnace) and batch mixer. We successively synthesized CdSe/CdS/ZnS quantum dot at this reactor in one step.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2008.04a
• /
• pp.435-441
• /
• 2008

Building Information Modelings(BIM) are more complex than typically required for early phase of the design process of a building. Construction projects have many participants from various disciplines involved throughout the entire process. Therefore the success of the project greatly depend on the efficiency of decision-making using the information generated from each process stage. This research utilized an ontology to provide an underlying structure of objects and relationships of a building. The OWL is introduced as a main vehicle to encode the information and knowledge about the building structures and spaces. A case study was conducted to develop a structured representation of an ontology where the relationships among the necessary components in the stage of preliminary design were to be automatically utilized to plan on the sizes of each room in a building and structured thoroughly with a simple structured representation.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.184-187
• /
• 2002

Two-dimensional (2-D) X-ray computerized tomography (CT) equipments are widely used in industrial and medical fields, and nowadays studies on reconstruction algorithm for 3-D cone-beam acquisition systems are active for better utilization. The authors recent-By have proposed a fast reconstruction aigorithm using tree-structured filter bank for 2-D C1, and shown the algorithm is applicable to an approximate reconstruction of 3-D CT. For exact 3-D CT reconstruction, however, we have to backproject 1-D signal into 3-D space. This paper proposes a fast implementation method for this back-projection by use of tree-structured filter bank. and shows the proposed method works approximately 700 times faster than the direct one with almost same reconstruction image quality.

• Preventive Nutrition and Food Science
• /
• v.8 no.3
• /
• pp.219-224
• /
• 2003

Structured lipid (SL) produced from soybean oil was enriched with conjugated linoleic acid (CLA). The SL had 21.9 mol % CLA isomers incorporated into SL-soybean after the 24-h reaction. Removal of tocopherols (73～84% loss from original soybean oil) was observed in the SL. Electronic nose can discriminate the aroma of SL-soybean from that of soybean oil. Many oxidative volatiles including pentenal, octenal, 2,4-decandienal, and nonenal were found in SL-soybean. Electronic nose, which is valuable for composite aroma analysis, can provide flavor information together with GC-MS that is useful for qualitative or quantitative analysis of each odor compound in SL.

• The Mathematical Education
• /
• v.51 no.2
• /
• pp.95-114
• /
• 2012

This study examines the use of ill-structured problem to help the 4th graders' problem solving and reasoning. It appears that children with good understanding of problem situation tend to accept the situation as itself rather than just as texts and produce various results with extraction of meaningful variables from situation. In addition, children with better understanding of problem situation show AR (algorithmic reasoning) and CR (creative reasoning) while children with poor understanding of problem situation show just AR (algorithmic reasoning) on their reasoning type.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.12
• /
• pp.1068-1076
• /
• 2005

In order to increase the autonomous navigation capability of a mobile robot, it is very crucial to develop a method for the robot to be able to recognize a priori hon structured environmental characteristics. This paper proposes an ultrasonic sensor based real-time method for recognizing a priori known structured indoor environmental characteristics like a wall and comer Unlike the methods reported in the literature the information obtained from the sensor can be processed in real-time by extended Kalman filter to update estimations of the position and orientation of robot with respect to known environmental characteristics.