Search

Industries need a mechanism to monitor the workers' safety and to prevent Work-related Musculoskeletal Disorders (WMSDs). The development of ergonomics assessment tools helps the industry evaluate workplace design and worker posture. Many studies proposed the automated ergonomics assessment method to replace the manual; however, it only focused on calculating body angle and assessing the wrist section manually. This study aims to (a) propose a wrist kinematics measurement based on unobtrusive sensors, (b) detect potential WMSDs related to wrist posture, and (c) compare the wrist posture of subjects while performing assembly tasks to achieve a comprehensive and personalized ergonomic assessment. The wrist posture measurement is combined with the body posture measurement to provide a comprehensive ergonomics assessment based on RULA. Data were collected from subjects who performed the assembly process to evaluate our method. We compared the risk score assessed by the ergonomist and the risk score generated by our method. All body segments achieved more than an 80% similarity score, enhancing the scores for wrist position and wrist twist by 6.8% and 0.3%, respectively. A hypothesis analysis was conducted to evaluate the difference across the subjects. The results indicate that every subject performs tasks differently and has different potential risks regarding wrist posture. [ABSTRACT FROM AUTHOR]

Common approaches in the cross-domain sensor-based human activity recognition are based on the homogeneous domain adaptation which relies on the assumption that the training and testing data are of homogeneous feature space. In reality, such an assumption does not always hold. For example, although two devices may share common sensors, it is possible that each of them has its own specific sensors. In this case, the homogeneous domain adaptation approaches cannot be used directly. Although heterogeneous domain adaptation approaches have been proposed to handle such feature space heterogeneity, most of them require some label information in the target domain, which is often difficult to obtain. As a compromise, the hybrid domain adaptation has been recently proposed to address feature space heterogeneity. Instead of using the target domain label information, it exploits the common features between domains as additional information, so the adaptation can be performed in an unsupervised manner. However, it still neglects the possibility of the common features between domains having different distribution, which may lead to the negative transfer of the domain-specific features. In this work, we introduce a domain-invariant latent representation of the common features to enhance the specific feature transfer in the hybrid domain adaptation approach. The latent representation learning and the domain-specific feature transfer are performed jointly using an autoencoder-based framework. The experimental result shows that the performance improves when the common features are furthermore aligned in the latent space. It is also shown that, in overall, our model outperforms existing approaches, yielding up to 9.48% accuracy improvement. [ABSTRACT FROM AUTHOR]

During the Covid19 pandemic, many local businesses were struggling to survive. With the rising of click and collect solutions, business strives to survive by offering pick-up points and maintaining the social distance policy. The demand for goods and services of customers are met instantly from the local offline shops via digital platform. Meanwhile, local businesses in a specific geographical area are still striving from the hard times due to least popularity and competitivenes in the services such as delivery. Hyperlocal delivery comes into the logistics industry to meet the issues from local businesses. While the hyperlocal delivery terminology is still new, there have been some real world practices. This study attempts to define the hyperlocal delivery and explore multiple case studies to analyze the on-foot delivery as a rising of quick commerce in the gig economy. The multiple case studies will take place on the hyperlocal delivery business models in South Korea. The overview of the hyperlocal "on-foot" delivery will be described in four dimension of analysis; strategy, customer, cost-revenue, and process model. At the end, some research challenges and opportunities are presented to show how the research communities can contribute to the field. [ABSTRACT FROM AUTHOR]

Inspired by the recent success of deep learning (DL) approaches in computer vision domain, this Letter proposes a framework to encode the sensor data into an image representation for the activity recognition task. The signal from sensors is encoded based on the Gramian Angular Field. The encoding technique increases the dimension of the data, captures a local temporal relationship in terms of temporal correlation between time intervals on the geometric interpretation, and can be easily applied to the pre‐trained DL architecture. The proposed framework is examined with respect to six popular sensor‐based activity recognition datasets. Using the authors' framework, the results show that their approach outperforms most of the state‐of‐the‐art approaches. [ABSTRACT FROM AUTHOR]

Inspired by the recent success of deep learning (DL) approaches in computer vision domain, this Letter proposes a framework to encode the sensor data into an image representation for the activity recognition task. The signal from sensors is encoded based on the Gramian Angular Field. The encoding technique increases the dimension of the data, captures a local temporal relationship in terms of temporal correlation between time intervals on the geometric interpretation, and can be easily applied to the pre-trained DL architecture. The proposed framework is examined with respect to six popular sensor-based activity recognition datasets. Using the authors' framework, the results show that their approach outperforms most of the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Human behavior computing has received a lot of attention in many business domains to derive daily routines, such as company's regular operations and cultural activities, especially towards to the development of smart industries in the fourth industrial revolution. Using the recent technology such as adaptive sensor devices, human movement and activity can be detected and traced. Discovering daily routines from lifelog can assist the growth of individual and organizations but yet needs a reliable approach to produce a representative behavior model. Some conformance checking approaches have been developed to verify the conformity of a real log with a generated model. However, the existing conformance checking approach relies on the business process property which is less reliable to the human behavior. Accordingly, limited approaches attempt to assess the conformity between the discovered model and self-elicited behavior (lifelog). This study presents norm approaches to assess the deviation between model space and lifelog. Two approaches, approximate and aggregate norm, are proposed to evaluate the discovered (routine) model according to the respective lifelog and a particular person. In this study, the model has been derived using the concept of time-lapse embedded in the sequential rules. The result of the experiment using the two-norm approaches shows that the routine models have 99% characteristics compared with the lifelog. [ABSTRACT FROM AUTHOR]

Physical activity recognition using wearable sensors has gained significant interest from researchers working in the field of ambient intelligence and human behavior analysis. The problem of multi-class classification is an important issue in the applications which naturally has more than two classes. A well-known strategy to convert a multi-class classification problem into binary sub-problems is the error-correcting output coding (ECOC) method. Since existing methods use a single classifier with ECOC without considering the dependency among multiple classifiers, it often fails to generalize the performance and parameters in a real-life application, where different numbers of devices, sensors and sampling rates are used. To address this problem, we propose a unique hierarchical classification model based on the combination of two base binary classifiers using selective learning of slacked hierarchy and integrating the training of binary classifiers into a unified objective function. Our method maps the multi-class classification problem to multi-level classification. A multi-tier voting scheme has been introduced to provide a final classification label at each level of the solicited model. The proposed method is evaluated on two publicly available datasets and compared with independent base classifiers. Furthermore, it has also been tested on real-life sensor readings for 3 different subjects to recognize four activities i.e. Walking, Standing, Jogging and Sitting. The presented method uses same hierarchical levels and parameters to achieve better performance on all three datasets having different number of devices, sensors and sampling rates. The average accuracies on publicly available dataset and real-life sensor readings were recorded to be 95% and 85%, respectively. The experimental results validate the effectiveness and generality of the proposed method in terms of performance and parameters. [ABSTRACT FROM AUTHOR]

• A graph convolution model for skeleton-based action recognition is proposed. • Normalized Laplacian Matrix is utilized to encode the graph information. • An attention-based feature aggregation is proposed to extract the salient features. • The proposed method achieves better results than the baseline models. Skeleton-based human action recognition has attracted a lot of attention due to its capability and potential to provide more information than just using the sequence of RGB images. The use of Graph Convolutional Neural Network (GCN) becomes more popular since it can model the human skeleton very well. However, the existing GCN architectures ignore the different levels of importance on each hop during the feature aggregation and use the final hop information for further calculation, resulting in considerable information loss. Besides, they use the standard Laplacian or adjacency matrix to encode the property of a graph into a set of vectors which has a limitation in terms of graph invariants. In this work, we propose a Sequential Inter-hop Graph Convolution Neural Network (SIhGCN) which can capture salient graph information from every single hop rather than the final hop only and our work utilizes the normalized Laplacian matrix which provides better representation since it relates well to graph invariants. The proposed method is validated on two large datasets, NTU-RBG + D and Kinetics, to demonstrate the superiority of our proposed method. [ABSTRACT FROM AUTHOR]

Recently, discriminative learning methods have gained substantial interest in solving inverse imaging problems due to their decent performance and fast inferencing capability. Those methods need separate models for specific noise levels, which in turn require multiple models to be trained to denoise an image. However, images exhibit spatial variant noise which limits the applicability of such methods. In addition, the discriminative learning methods introduce artifacts such as blurring, deblocking, and so forth while denoising an image. To address these issues, we propose a cascaded and recursive convolutional neural network (CRCNN) framework which can cope with spatial variant noise and blur artifacts in a single denoising framework. The CRCNN takes into account down-sampled sub-images for fast inferencing along with the noise level map. We adopt the hybrid orthogonal projection and estimation method on the convolutional layers to improve the generalization capability of the network in terms of non-uniform and spatial variant noise levels. In contrast to the existing methods, the CRCNN framework allows both denoising and deblurring of images using a single framework which preserves the fine details in a denoised image. Extensive experiments have been conducted to validate the effectiveness and flexibility of the CRCNN framework on real as well as synthetic noisy images in comparison to the state-of-the-art denoising methods. The results show that the CRCNN performs effectively on both synthetic as well as spatial variant noise-induced images, thus, proving the practicability of the framework. • The proposed CRCNN framework deals with various noise levels and spatially variant noises. • A total noise loss function is proposed to generalize the denoising task and preserve fine details in restored images. • The noise level mismatch is effectively handled using the Hybrid Orthogonal Projection and Estimation (HOPE) framework. • We prove that the recursive denoising can leverage a deblurring process in order to improve the image quality. • The CRCNN achieves better results on both synthetic and real-world noisy images compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Similarity measures for analyzing human behavior patterns are inseparable part of the intelligent environment, with the assistive functionality as its core value. The measure must represent the contexts properly which characterizes the users' environment. Recent studies attempted to formulate similarity measures for the intelligent environment by incorporating relevant contexts. Yet, they are lacking the integration of multiple inter-related important contexts, which leads to model underestimation and possibly the wrong interpretation. This work proposes a context-based similarity measure for analyzing human behavior patterns. The proposed similarity measure extends and combines the commonly used contexts (i.e., activity, location, and time) into a holistic measure. To avoid the biased representation of activity context similarity, we add one more aspect, namely process context, which describes a wide range of interval relations among the activities of a user. The proposed approach is compared with state-of-the art similarity measures by evaluating both real and simulated data. The result shows that our approach yields the better result in terms of robustness toward noises. In addition, our approach also shows a better reliability compared to previous works in the case of anomaly detection. [ABSTRACT FROM AUTHOR]

Curriculum mining is a recent research area that applies a data-driven approach to assess students' learning behavior by discovering the curriculum model and compare it with the curriculum guideline. Some previous works exist to cope with the problem to discover the curriculum model from student database, by utilizing the concept of process mining. However, the challenges of discovering the curriculum model remain due to the different nature of student database from event log in twofold; the level of time granularity and variability of instance attributes. Previous works on curriculum mining that deal with conformance checking of the model between student's learning behavior and curriculum guideline are related to sequence matching alignment which is insufficient to understand the patterns of a group of students in a particular level of time granularity, i.e., Semester. This study proposes a curriculum mining methodology for curriculum assessment and students' learning behavior by creating segmentedtrace profiles. The segmented-trace profiles are extracted based on a local alignment of sequences and generated as the input for sequence matching alignment to assess whether the observed students' learning behavior match with the prior curriculum guideline. The profiles would be the features of the clustering approach. Real curriculum data has been used to test the effectivity of the methodology. The results show that the students can be grouped into various clusters per semester that have different characteristics for their learning behavior and performance. The results can be analyzed further to improve the curriculum guideline. [ABSTRACT FROM AUTHOR]

Continuous exposure to stress leads to many health problems and substantial economic loss in companies. A lot of attention has been given to the development of wearable systems for stress monitoring to tackle its long-term effects such as confusion, high blood pressure, insomnia, depression, headache and inability to take decisions. Accurate detection of stress from physiological measurements embedded in wearable devices has been the primary goal in the healthcare industry. Advanced sensor devices with a high sampling rate have been proven to achieve high accuracy in many earlier works. However, there has been a little attempt to employ consumer-based devices with a low sampling rate, which potentially degrades the performance of detection systems. In this paper, we propose a set of new features, local maxima and minima (LMM), from heart rate variability and galvanic skin response sensors along with the voting and similarity-based fusion (VSBF) method, to improve the detection performance. The proposed feature set and fusion method are first tested on the acquired dataset which is collected using the wrist-worn devices with a low sampling rate in workplace environments and validated on a publicly available dataset, driveDB from PhysioNet. The experimental results from both datasets prove that the LMM features can improve the detection accuracy for different classifiers in general. The proposed VSBF method further boosts the recognition accuracy by 5.69% and 2.90% in comparison with the AdaBoost, which achieves the highest accuracy as a single classifier on the acquired, and the DriveDB dataset, respectively. Our analyses show that the stress detection system using the acquired dataset yields an accuracy of 92.05% and an F1 score of 0.9041. Based on the analyses, a soft real-time system is implemented and validated to prove the applicability of the proposed work for stress detection in a real environment. [ABSTRACT FROM AUTHOR]

Market conditions fluctuate abruptly in today's competitive environment and leads to imprecise demand information. In particular, market demand data for freshly launched products is highly uncertain. Further, most of the products are generally manufactured through complex multi-stage production systems that may produce defective items once they enter the out-of-control state. Production management of a multi-stage production system in these circumstances requires robust production model to reduce system costs. In this context, this paper introduces an imperfect multi-stage production model with the consideration of defective proportion in the production process and uncertain product demand. Fuzzy theory is applied to handle the uncertainty in demand information and the center of gravity approach is utilized to defuzzify the objective function. This defuzzified cost objective is solved through the analytical optimization technique and closed form solution of optimal lot size and minimum cost function are obtained. Model analysis verifies that it has successfully achieved global optimal results. Numerical experiment comprising of three examples is conducted and optimal results are analyzed through sensitivity analysis. Results demonstrate that larger lot sizes are profitable as the system moves towards a higher number of stages. Sensitivity analysis indicates that the processing cost is the most influencing factor on the system cost function. [ABSTRACT FROM AUTHOR]