• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.6
• /
• pp.323-331
• /
• 2013

An extreme learning machine (ELM) is an efficient learning algorithm that is based on the generalized single, hidden-layer feed-forward networks (SLFNs), which perform well in classification applications. Many studies have demonstrated its superiority over the existing classical algorithms: support vector machine (SVM) and BP neural network. This paper presents a novel face recognition approach based on a multi-class project extreme learning machine (MPELM) classifier and 2D Gabor transform. First, all face image features were extracted using 2D Gabor filters, and the MPELM classifier was used to determine the final face classification. Two well-known face databases (CMU-PIE and ORL) were used to evaluate the performance. The experimental results showed that the MPELM-based method outperformed the ELM-based method as well as other methods.

• Journal of the Korean Society of Industry Convergence
• /
• v.11 no.3
• /
• pp.121-125
• /
• 2008

Commutator which plays the major role in switching electric currents from AC to DC is composed of copper and molding compound. The longevity of the DC motors are mostly hampered by the improper machining of the parts. Smooth surface will be mandatory to create the proper air gap of the commutator. In this thesis the selection of the proper materials and tools, the design and analysis of machine structure and the final test procedures have been investigated to achieve the smooth cut surface of the commutators. The performance and the product of the newly manufactured machine has been compared with those of the existing one. And the test result shows the new sawing machine has better overall efficiency and durability.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.4
• /
• pp.207-218
• /
• 2019

The purpose of this study is to develop a model that can systematically study the whole learning process of machine learning. Since the existing model describes the learning process with minimum coding, it can learn the progress of machine learning sequentially through the new model, and can visualize each process using the tensor flow. The new model used all of the existing model algorithms and confirmed the importance of the variables that affect the target variable, survival. The used to classification training data into training and verification, and to evaluate the performance of the model with test data. As a result of the final analysis, the ensemble techniques is the all tutorial model showed high performance, and the maximum performance of the model was improved by maximum 5.2% when compared with the existing model using. In future research, it is necessary to construct an environment in which machine learning can be learned regardless of the data preprocessing method and OS that can learn a model that is better than the existing performance.

• International Journal of Advanced Culture Technology
• /
• v.12 no.1
• /
• pp.242-248
• /
• 2024

Contemporary societal and environmental transformations coincide with the emergence of novel mental health challenges. anxiety disorder, a chronic and highly debilitating illness, presents with diverse clinical manifestations. Epidemiological investigations indicate a global prevalence of 5%, with an additional 10% exhibiting subclinical symptoms. Notably, 9% of adolescents demonstrate clinical features. Untreated, anxiety disorder exerts profound detrimental effects on individuals, families, and the broader community. Therefore, it is very meaningful to predict anxiety disorder through machine learning algorithm analysis model. The main research content of this paper is the analysis of the prediction model of anxiety disorder by machine learning algorithms. The research purpose of machine learning algorithms is to use computers to simulate human learning activities. It is a method to locate existing knowledge, acquire new knowledge, continuously improve performance, and achieve self-improvement by learning computers. This article analyzes the relevant theories and characteristics of machine learning algorithms and integrates them into anxiety disorder prediction analysis. The final results of the study show that the AUC of the artificial neural network model is the largest, reaching 0.8255, indicating that it is better than the other two models in prediction accuracy. In terms of running time, the time of the three models is less than 1 second, which is within the acceptable range.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.6
• /
• pp.96-102
• /
• 2000

The finishing process for dies and molds is an important process because it has influence on final quality of products. And it is difficult to automatize finishing process so that the process has depended on expert's skill until now. However, recently a study on development of die automatic finishing machine has been progressed, and actually this machine is applied to fabrication of die. But the research about tooling system is not enough and finishing tool must have high machining efficiency and adaptability of curved surface. So, this study investigated the application of conductive elastic tool which is composed of metal-resin bonded pellet and elastic backing material. The metal-resin bonded pellet is used to finish the surface by conventional mechanical grinding or electro-chemial grinding method. And elastic backing material is used to follow the curved surface. So conductive elastic tool has long lifetime, uniform removal rate and adaptability of curved surface.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.04a
• /
• pp.215-222
• /
• 2003

The new square electro-magnetic chuck, which is using for the clamping devices on a grinding machine, is developed in this study to improve the convenience of grinding works. The various kinds of structures are recommended to find the most adequate magnetic characteristics through the analytical approach using finite element methods. The analyzed results are retrofitted to solve the drawbacks of previous models step by step by considering the magnetic fields, strength and distribution of drag force, and thermal deformations of chuck. such as high parallelism and flatness. Finally the best recommended models is designed to satisfy the KS specifications required for the commercial magnetic chuck. The prototype chuck with this dimensions and structures is manufactured. For this final model, the experimental verifications are investigated whether the KS specifications are satisfied.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.7 no.2
• /
• pp.29-39
• /
• 1998

A conversational programming system for turning processes was studied to enhance the user friendliness of a NC Lathe by adopting man-machine interface functions through Delphi programming tool under the Windows 95 environment. Functions of tool collision checking were developed through zone limitation algorithms. Final shape of workpiece was generated by means of tree structure algorithm. Shop floor programming performance was incorporated in the developed CAM module. In order to increase flexibility of the man-machine interface, graphic based programming tools have been developed. A NC turning machine equipped with an open architecture PCNC was used as a test bed of the system. Performance of the system was verified through case studies.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.18 no.2
• /
• pp.207-213
• /
• 2009

The bundling process is the final step in vegetable manufacturing, however, the process is a little difficult to be automatized, because vegetable has the physical properties of roughness, softness, and fragility etc. In this paper, we proposed an automatic bundling mechanism for vegetable based on the heat melt sticking. The proposed mechanism consists of three modules, one module is the moving part for aligning of the vegetable shape and adjusting of the vegetable tension, second module is the arm driving part for the vegetable binding and the band roll releasing, and third module is band joining, band cutting, and band feeding part for the vegetable binding continuously. Through this research, Using the SMO(SimDesigner Motion) module, we optimize condition of mechanical movement of the bundling mechanism. This bundling system designed in order to binding 288 bundle/hour.

• Korean Journal of Computational Design and Engineering
• /
• v.10 no.5
• /
• pp.365-374
• /
• 2005

Most of people who are engaged in research and development find it difficult to solve the engineering problems creatively due to the lack of ideas. TRIZ is one of the emerging problem solving techniques that leads us to a very useful and clear solution. TRIZ consists of several tools such as ideal final result (IFR), physical and technical contradictions, 40 invention principles, resource, effect, etc. However, many designers think that TRIZ is hard to be applied to a design problem since there are several tools in TRIZ. Machine designers may want to see which tool is more effective than others. Thus, this paper provides sample solutions of a design problem: holder design for the bottle etching machine by applying several TRIZ tools. Difficulties in applying TRIZ to a design problem are discussed.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.14 no.6
• /
• pp.8-15
• /
• 2005

The new square electro-magnetic chuck, which can be used for the clamping devices on a grinding machine, is developed in this study to improve the convenience of grinding works. The various kinds of structures are recommended to find the most adequate magnetic characteristics through the analytical approach using finite element methods. The analyzed results are retrofitted to solve the drawbacks of previous models step by step by considering the magnetic fields, strength and distribution of drag force, and thermal deformations of chuck such as high parallelism and flatness. Finally the best recommended models is designed to satisfy the KS specifications required fur the commercial magnetic chuck. The prototype chuck with this dimensions and structures is manufactured. For this final model, the experimental verifications are investigated whether the KS specifications are satisfied.