Sirindhorn International Institute of Technology

About: Sirindhorn International Institute of Technology is a based out in . It is known for research contribution in the topics: Supply chain & Combustion. The organization has 1048 authors who have published 1678 publications receiving 30067 citations.

Analysis of Optimal Sensor Positions for Activity Classification and Application on a Different Data Collection Scenario.

Abstract: This paper focuses on optimal sensor positioning for monitoring activities of daily living and investigates different combinations of features and models on different sensor positions, i.e., the side of the waist, front of the waist, chest, thigh, head, upper arm, wrist, and ankle. Nineteen features are extracted, and the feature importance is measured by using the Relief-F feature selection algorithm. Eight classification algorithms are evaluated on a dataset collected from young subjects and a dataset collected from elderly subjects, with two different experimental settings. To deal with different sampling rates, signals with a high data rate are down-sampled and a transformation matrix is used for aligning signals to the same coordinate system. The thigh, chest, side of the waist, and front of the waist are the best four sensor positions for the first dataset (young subjects), with average accuracy values greater than 96%. The best model obtained from the first dataset for the side of the waist is validated on the second dataset (elderly subjects). The most appropriate number of features for each sensor position is reported. The results provide a reference for building activity recognition models for different sensor positions, as well as for data acquired from different hardware platforms and subject groups.

Optimal sequencing of rotation angles for five-axis machining

Abstract: In this paper, we propose two new algorithms to correct the trajectories of the tool tip of a five-axis milling machine by adjusting the rotation angles in such a way that the kinematics error is reduced. The first algorithm is based on the shortest-path optimization with regards to feasible rotations of the inverse kinematics. The cost function is represented in terms of the total angle variation. We show that such an optimization increases the accuracy of machining and is the most appropriate in the case of a rough cut. The shortest-path procedure applies to either the entire set of trajectories or to only the most inappropriate undercuts inside the workpiece. In the latter case, the algorithm generates an interesting family of solutions characterized by smaller undercuts obtained at the expense of increased overcuts. The second algorithm also exploits the idea of the minimization of the angle variation. It is based on the uniform distribution of the cutter contact points with regards to the rotation angles. The method inserts additional tool positions by numerically finding a grid of points distributed uniformly in the angular space. We prove that the proposed algorithm in the neighborhood of stationary points requires 3-4 times fewer additional points than the conventional scheme. Also, if a maximum angular speed has been exceeded, the controller detects this event and reduces the angular speed. Our correction algorithms minimize the total angle variation, thus, reduc- ing the probability of such an event. Finally, the efficiency of the two algorithms has been verified by a five-axis machine MAHO600E at the CIM Lab of the Asian Institute of Technology of Thailand and HERMLE UWF920H at the CIM Lab of the Kasetsart University of Thailand.

Internal capabilities, external cooperation and proactive CSR on financial performance

Abstract: The impact of proactive corporate social responsibility on a firm’s financial performance has received considerable attention. Grounded in the knowledge-based view (KBV), we aimed to examine the im...