http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Khowaja, Sunder Ali,Prabono, Aria Ghora,Setiawan, Feri,Yahya, Bernardo Nugroho,Lee, Seok-Lyong Elsevier 2018 COMPUTER NETWORKS - Vol.145 No.-
<P><B>Abstract</B></P> <P>Healthcare industry is gaining a lot of attention due to its technological advancement and the miniaturization in the form of wearable sensors. IoT-driven healthcare industry has mainly focused on the integration of sensors rather than the integration of services and people. Nonetheless, the framework for IoT-driven healthcare applications are significantly lacking. In addition, the use of semantics for ontological reasoning and the integration of mobile applications into a single framework have also been ignored in many existing studies. This work presents the implementation of Healthcare Internet of Things, Services, and People (HIoTSP) framework using wearable sensor technology. It is designed to achieve the low-cost (consumer devices), the easiness to use (interface), and the pervasiveness (wearable sensors) for healthcare monitoring along with the integration of services and agents like doctors or caregivers. The proposed framework provides the functionalities for data acquisition from wearable sensors, contextual activity recognition, automatic selection of services and applications, user interface, and value-added services such as alert generation, recommendations, and visualization. We used the publicly available dataset, PAMAP2 which is a physical activity monitoring dataset, for deriving the contextual activity. Fall and stress detection services are implemented as case studies for validating the realization of the proposed framework. Experimental analysis shows that we achieve, 87.16% accuracy for low-level contextual activities and 84.06%–86.36% for high-level contextual activities, respectively. We also achieved 91.68% and 82.93% accuracies for fall and stress detection services, respectively. The result is quite satisfactory, considering that all these services have been implemented using pervasive devices with the low-sampling rate. The real-time applicability of the proposed framework is validated by performing the response time analysis for both the services. We also provide suggestions to cope with the scalability and security issues using the HIoTSP framework and we intend to implement those suggestions in our future work.</P>
Automated RULA for a sequence of activities based on sensor data
WENNY FRANCISKA SENJAYA,FRANS PRATHAMA,FERI SETIAWAN,ARIA GHORA PRABONO,BERNARDO NUGROHO YAHYA,SEOK- LYONG LEE 대한산업공학회 2020 대한산업공학회 추계학술대회논문집 Vol.2020 No.11
Work-related Musculoskeletal Disorders (WMSDs) are a common concern in the manufacturing industry and are induced by postural load requirements of job tasks that affect to neck, trunk, and upper extremities. Ergonomics assessment, such as Rapid Upper Limb Assessment (RULA), can help industries to prevent and evaluate the risk of WMSDs. However, the experts perform RULA with manual observation which is a tedious and complex task. A few works have attempted to work on automatic RULA with focusing on single activity. This work aims to propose a framework of automated ergonomics assessment on the sequence of assembly activities from time-series sensor data collected from the body tracking sensor and hand motion sensor. The grand score is categorized into two, activity-level and final grand score. Both categories are evaluated by mode-based analysis and mean-based analysis. The analysis results show that the mean-based analysis is more representative than mode-based analysis. Most of our subjects have RULA final grand score of 6, these indicate that we need further investigation and change the layout of the workspace immediately to increase work productivity.
Process Discovery on Assembly Process using Multimodal Human Activity Recognition
차형주,박현우,Wenny Franciska Senjaya,Feri Setiawan,Aria Ghora Prabono,Frans Prathama,이석룡 대한산업공학회 2019 대한산업공학회 추계학술대회논문집 Vol.2019 No.11
HAR(Human Activity Recognition) is a research area that aims to recognize human activities from a series of observations. While many works dealt with vision-based HAR, this work focuses on sensor-based HAR. This study attempts to build a system architecture to recognize human activities and behaviors in a workplace environment using multimodal sensor. Multimodal sensors of assembly sequence process are being used to collect the body skeleton, hand tracking motion and upper limb motion data. The synchronization among those devices is done by using PAA(Piecewise Aggregate Approximation) with HTTP requests. Acquired dataset using above techniques was then used to form a classification model, using feature extraction and two types of classifier; i.e. Random Forest(83.44% accuracy score) and Ensemble Classifier(62.58% with 0.0667 Hamming loss). The activity recognized by the classification was used for process discovery based on fuzzy-miner algorithm. Finally, the constructed process model was compared to the original process model designed according to the working procedure.