• Journal of the Korea Safety Management & Science
• /
• v.23 no.4
• /
• pp.93-104
• /
• 2021

In this paper, we propose a method for diagnosing overload and working load of collaborative robots through performance analysis of machine learning algorithms. To this end, an experiment was conducted to perform pick & place operation while changing the payload weight of a cooperative robot with a payload capacity of 10 kg. In this experiment, motor torque, position, and speed data generated from the robot controller were collected, and as a result of t-test and f-test, different characteristics were found for each weight based on a payload of 10 kg. In addition, to predict overload and working load from the collected data, machine learning algorithms such as Neural Network, Decision Tree, Random Forest, and Gradient Boosting models were used for experiments. As a result of the experiment, the neural network with more than 99.6% of explanatory power showed the best performance in prediction and classification. The practical contribution of the proposed study is that it suggests a method to collect data required for analysis from the robot without attaching additional sensors to the collaborative robot and the usefulness of a machine learning algorithm for diagnosing robot overload and working load.

• International Journal of Human Ecology
• /
• v.10 no.1
• /
• pp.1-11
• /
• 2009

The effect of learning orientation on company innovation and innovation capability are explored based on survey data collected from 154 small and medium-sized manufacturing firms. The theoretical links between learning orientation and company innovation as well as innovation capability are investigated in four research models that compare textile and non-textile manufacturing firms. Learning orientation has a significant effect on company innovation and innovation capability in the model test. However, some of the three segmented factors (commitment to learning, shared vision, and open-mindedness) of learning orientation had no significant effect on company innovation and innovation capability. Company innovation and innovation capability of textile manufacturing firms are predicted by the commitment to learning and shared vision, whereas those of non-textile firms were determined by shared vision and open-mindedness. Differences show that firms may need to put weight on some distinctive aspects of learning orientation according to the business categories in order to enhance company innovation.

• Journal of Advanced Marine Engineering and Technology
• /
• v.21 no.1
• /
• pp.66-70
• /
• 1997

In this paper a new learning algorithm for curvature smoothing and improved generalization for multi-layer neural networks is proposed. To enhance the generalization ability a constraint term of hidden neuron activations is added to the conventional output error, which gives the curvature smoothing characteristics to multi-layer neural networks. When the total cost consisted of the output error and hidden error is minimized by gradient-descent methods, the additional descent term gives not only the Hebbian learning but also the synaptic weight decay. Therefore it incorporates error back-propagation, Hebbian, and weight decay, and additional computational requirements to the standard error back-propagation is negligible. From the computer simulation of the time series prediction with Santafe competition data it is shown that the proposed learning algorithm gives much better generalization performance.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.39-51
• /
• 2022

Image-based gender classification and age estimation of human are classic problems in computer vision. Most of researches in this field focus just only one task of either gender classification or age estimation and most of the reported methods for each task focus on accuracy performance and are not computationally light. Thus, running both tasks together simultaneously on low cost mobile or embedded systems with limited cpu processing speed and memory capacity are practically prohibited. In this paper, we propose a novel light-weight gender classification and age estimation method based on ensemble multitasking deep learning with light-weight processing neural network architecture, which processes both gender classification and age estimation simultaneously and in real-time even for embedded systems. Through experiments over various well-known datasets, it is shown that the proposed method performs comparably to the state-of-the-art gender classification and/or age estimation methods with respect to accuracy and runs fast enough (average 14fps) on a Jestson Nano embedded board.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.441-452
• /
• 2021

Federated learning provides an efficient integrated model for distributed data, allowing the local training of different data. Meanwhile, the goal of multi-task learning is to simultaneously establish models for multiple related tasks, and to obtain the underlying main structure. However, traditional federated multi-task learning models not only have strict requirements for the data distribution, but also demand large amounts of calculation and have slow convergence, which hindered their promotion in many fields. In our work, we apply the rank constraint on weight vectors of the multi-task learning model to adaptively adjust the task's similarity learning, according to the distribution of federal node data. The proposed model has a general framework for solving optimal solutions, which can be used to deal with various data types. Experiments show that our model has achieved the best results in different dataset. Notably, our model can still obtain stable results in datasets with large distribution differences. In addition, compared with traditional federated multi-task learning models, our algorithm is able to converge on a local optimal solution within limited training iterations.

• The Journal of the Korea Contents Association
• /
• v.12 no.9
• /
• pp.9-15
• /
• 2012

A conventional event sentence extraction research doesn't learn the 3W features in the learning step and applies the rule on whether the 3W feature exists in the extraction step. This paper presents a sentence weight based event sentence extraction method that calculates the weight of the 3W features in the learning step and applies the weight of the 3W features in the extraction step. In the experimental result, we show that top 30% features by the $TF{\times}IDF$ weighting method is good in the feature filtering. In the real estate domain of the public issue, the performance of sentence weight based event sentence extraction method is improved by who and when of 3W features. Moreover, In the real estate domain of the public issue, the sentence weight based event sentence extraction method is better than the other machine learning based extraction method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.2
• /
• pp.81-86
• /
• 2016

Term weighting is a popular technique that effectively weighs the term features to improve accuracy in document classification. While several successful term weighting algorithms have been suggested, none of them appears to perform well consistently across different data domains. In this paper we propose several reasonable methods to combine different term weight vectors to yield a robust document classifier that performs consistently well on diverse datasets. Specifically we suggest two approaches: i) learning a single weight vector that lies in a convex hull of the base vectors while minimizing the class prediction loss, and ii) a mini-max classifier that aims for robustness of the individual weight vectors by minimizing the loss of the worst-performing strategy among the base vectors. We provide efficient solution methods for these optimization problems. The effectiveness and robustness of the proposed approaches are demonstrated on several benchmark document datasets, significantly outperforming the existing term weighting methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.2
• /
• pp.143-148
• /
• 2012

This paper proposes a new method to improve performance of AdaBoost by using a distance weight function to increase the accuracy of its machine learning processes. The proposed distance weight algorithm improves classification in areas where the original binary classifier is weak. This paper derives the new algorithm's optimal solution, and it demonstrates how classifier accuracy can be improved using the proposed Distance Sensitive AdaBoost in a simulation experiment of pedestrian detection.

• The Mathematical Education
• /
• v.47 no.2
• /
• pp.221-224
• /
• 2008

The article shows that the concept 'weight' and the concept 'heaviness' give rise to different abstractions in the sense of Piaget and that these two concepts are differentiated by set-theoretic devices. The failure of differentiation of these two concepts 'weight' and the 'heaviness' can cause the failure of learning of the difference between reflective abstraction and empirical reflective abstraction. To explain the Piagetian abstrcation in a classroom, the author suggests to use the concept 'color' instead of the concept 'weigtht'.

• Journal of Korean Physical Therapy Science
• /
• v.9 no.1
• /
• pp.53-59
• /
• 2002

This study is research for effect of the involved lower limb weight bearing training on symmetrical weight supporting rate improvement by practicing involved lower limb weight bearing training of three weeks period to improve standing equilibrium problem with asymmetric weight supporting rate of hemiplegia. In result of the study, it has shown that P-value incase of involved supporting rate is lower than level of significance $\alpha$<.05 and mean improvement rate of experienced group is higher in comparison with controlled group and experienced group. In changing quantity of involved maximum supporting rate, P-value is .26 and higher than level of significance $\alpha$<.05, and so it did not show significant difference statistically. But in case of experienced group between pre and post-test, involved side supporting rate and involved side maximum supporting rate showed significant improvement in all. In comparison of relative characteristic training effect difference, it was shown that train-learning effect on case of 40-60 years old, hemorrhagic patient and standard body bun of patient is valuable, which showed significant improvement in case of paralytic side and disease period, it did not show significant difference on excercise learning effect in two above cases. In the above result, we can say that continuous weight bearing training on the involved lower limb for three weeks period help improve the involved side supporting rate of hemiplegia. Accordingly, the weight bearing training on the involved lower limb is training method that patient can easily train with simple guidance of therapists, without being special expensive equipment. Furthermore it can be helpful to establish home therapeutic plan for hemiplegia through education of a patron.