Industrial practitioner's perception on the application of exoskeleton system in automotive assembly industries: A Malaysian case study

The automotive industry is a key manufacturing industry for the Malaysian economy, where manual jobs and task are still common. Hence, Work-related Musculoskeletal Disorders (WMSD) is a common type of injury among workers. Exoskeleton system has gained global traction as a possible solution to reduce the risk of MSD among workers. Nonetheless, the application of exoskeleton in the automotive industry in Malaysia remains unknown. As such, this study attempts to provide insight into the industry's perception on the potential of exoskeleton application within the context of Malaysian automotive assembly sector. Therefore, a total of 52 management level respondents from various manufacturers participated in this study. It is found that, although the technology seems to be relatively new and disruptive, the respondents have a positive perception towards it with an acceptance rate of 86.5%. Cost of implementation exoskeleton technologies seems to be primary concern from the respondents, other concern such as maintenance cost and ease of application into existing application is also highlighted.

Design and Characterization of a Low-Cost and Efficient Torsional Spring for ES-RSEA

The design of torsional springs for series elastic actuators (SEAs) is challenging, especially when balancing good stiffness characteristics and efficient torque robustness. This study focuses on the design of a lightweight, low-cost, and compact torsional spring for use in the energy storage-rotary series elastic actuator (ES-RSEA) of a lumbar support exoskeleton. The exoskeleton is used as an assistive device to prevent lower back injuries. The torsion spring was designed following design for manufacturability (DFM) principles, focusing on minimal space and weight. The design process involved determining the potential topology and optimizing the selected topology parameters through the finite element method (FEM) to reduce equivalent stress. The prototype was made using a waterjet cutting process with a low-cost material (AISI-4140-alloy) and tested using a custom-made test rig. The results showed that the torsion spring had a linear torque-displacement relationship with 99% linearity, and the deviation between FEM simulation and experimental measurements was less than 2%. The torsion spring has a maximum torque capacity of 45.7 Nm and a 440 Nm/rad stiffness. The proposed torsion spring is a promising option for lumbar support exoskeletons and similar applications requiring low stiffness, low weight-to-torque ratio, and cost-effectiveness.

Design and Shape Optimization of Strain Gauge Load Cell for Axial Force Measurement for Test Benches

The load cell is an indispensable component of many engineering machinery and industrial automation for measuring and sensing force and torque. This paper describes the design and analysis of the strain gauge load cell, from the conceptional design stage to shape optimization (based on the finite element method (FEM) technique) and calibration, providing ample load capacity with low-cost material (aluminum 6061) and highly accurate force measurement. The amplifier circuit of the half Wheatstone bridge configuration with two strain gauges was implemented experimentally with an actual load cell prototype. The calibration test was conducted to evaluate the load cell characteristics and derive the governing equation for sensing the unknown load depending on the measured output voltage. The measured sensitivity of the load cell is approximately 15 mV/N and 446.8 µV/V at a maximum applied load of 30 kg. The findings are supported by FEM results and experiments with an acceptable percentage of errors, which revealed an overall error of 6% in the worst situation. Therefore, the proposed load cell meets the design considerations for axial force measurement for the laboratory test bench, which has a light weight of 20 g and a maximum axial force capacity of 300 N with good sensor characteristics.

Deep Learning for Plant Species Classification Using Leaf Vein Morphometric

An automated plant species identification system could help botanists and layman in identifying plant species rapidly. Deep learning is robust for feature extraction as it is superior in providing deeper information of images. In this research, a new CNN-based method named D-Leaf was proposed. The leaf images were pre-processed and the features were extracted by using three different Convolutional Neural Network (CNN) models namely pre-trained AlexNet, fine-tuned AlexNet, and D-Leaf. These features were then classified by using five machine learning techniques, namely, Support Vector Machine (SVM), Artificial Neural Network (ANN), k-Nearest-Neighbor (k-NN), Naïve-Bayes (NB), and CNN. A conventional morphometric method computed the morphological measurements based on the Sobel segmented veins was employed for benchmarking purposes. The D-Leaf model achieved a comparable testing accuracy of 94.88 percent as compared to AlexNet (93.26 percent) and fine-tuned AlexNet (95.54 percent) models. In addition, CNN models performed better than the traditional morphometric measurements (66.55 percent). The features extracted from the CNN are found to be fitted well with the ANN classifier. D-Leaf can be an effective automated system for plant species identification as shown by the experimental results.

Assessing regional left ventricular thickening dysfunction and dyssynchrony via personalized modeling and 3D wall thickness measurements for acute myocardial infarction

BACKGROUND

Existing clinical diagnostic and assessment methods could be improved to facilitate early detection and treatment of cardiac dysfunction associated with acute myocardial infarction (AMI) to reduce morbidity and mortality.

PURPOSE

To develop 3D personalized left ventricular (LV) models and thickening assessment framework for assessing regional wall thickening dysfunction and dyssynchrony in AMI patients.

STUDY TYPE

Retrospective study, diagnostic accuracy.

SUBJECTS

Forty-four subjects consisting of 15 healthy subjects and 29 AMI patients.

FIELD STRENGTH/SEQUENCE

1.5T/steady-state free precession cine MRI scans; LGE MRI scans.

ASSESSMENT

Quantitative thickening measurements across all cardiac phases were correlated and validated against clinical evaluation of infarct transmurality by an experienced cardiac radiologist based on the American Heart Association (AHA) 17-segment model.

STATISTICAL TEST

Nonparametric 2-k related sample-based Kruskal-Wallis test; Mann-Whitney U-test; Pearson's correlation coefficient.

RESULTS

Healthy LV wall segments undergo significant wall thickening (P < 0.05) during ejection and have on average a thicker wall (8.73 ± 1.01 mm) compared with infarcted wall segments (2.86 ± 1.11 mm). Myocardium with thick infarct (ie, >50% transmurality) underwent remarkable wall thinning during contraction (thickening index [TI] = 1.46 ± 0.26 mm) as opposed to healthy myocardium (TI = 4.01 ± 1.04 mm). For AMI patients, LV that showed signs of thinning were found to be associated with a significantly higher percentage of dyssynchrony as compared with healthy subjects (dyssynchrony index [DI] = 15.0 ± 5.0% vs. 7.5 ± 2.0%, P < 0.01). Also, a strong correlation was found between our TI and left ventricular ejection fraction (LVEF) (r = 0.892, P < 0.01), and moderate correlation between DI and LVEF (r = 0.494, P < 0.01).

DATA CONCLUSION

The extracted regional wall thickening and DIs are shown to be strongly correlated with infarct severity, therefore suggestive of possible practical clinical utility.

LEVEL OF EVIDENCE

2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;49:1006-1019.

Integrative machine learning analysis of multiple gene expression profiles in cervical cancer

Although most of the cervical cancer cases are reported to be closely related to the Human Papillomavirus (HPV) infection, there is a need to study genes that stand up differentially in the final actualization of cervical cancers following HPV infection. In this study, we proposed an integrative machine learning approach to analyse multiple gene expression profiles in cervical cancer in order to identify a set of genetic markers that are associated with and may eventually aid in the diagnosis or prognosis of cervical cancers. The proposed integrative analysis is composed of three steps: namely, (i) gene expression analysis of individual dataset; (ii) meta-analysis of multiple datasets; and (iii) feature selection and machine learning analysis. As a result, 21 gene expressions were identified through the integrative machine learning analysis which including seven supervised and one unsupervised methods. A functional analysis with GSEA (Gene Set Enrichment Analysis) was performed on the selected 21-gene expression set and showed significant enrichment in a nine-potential gene expression signature, namely PEG3, SPON1, BTD and RPLP2 (upregulated genes) and PRDX3, COPB2, LSM3, SLC5A3 and AS1B (downregulated genes).

Exoskeleton robot control for synchronous walking assistance in repetitive manual handling works based on dual unscented Kalman filter

Prolong walking is a notable risk factor for work-related lower-limb disorders (WRLLD) in industries such as agriculture, construction, service profession, healthcare and retail works. It is one of the common causes of lower limb fatigue or muscular exhaustion leading to poor balance and fall. Exoskeleton technology is seen as a modern strategy to assist worker’s in these professions to minimize or eliminate the risk of WRLLDs. Exoskeleton has potentials to benefit workers in prolong walking (amongst others) by augmenting their strength, increasing their endurance, and minimizing high muscular activation, resulting in overall work efficiency and productivity. Controlling exoskeleton to achieve this purpose for able-bodied personnel without impeding their natural movement is, however, challenging. In this study, we propose a control strategy that integrates a Dual Unscented Kalman Filter (DUKF) for trajectory generation/prediction of the spatio-temporal features of human walking (i.e. joint position, and velocity, and acceleration) and an impedance cum supervisory controller to enable the exoskeleton to follow this trajectory to synchronize with the human walking. Experiment is conducted with four subjects carrying a load and walking at their normal speed- a typical scenario in industries. EMG signals taken at two muscles: Right Vastus Intermedius (on the thigh) and Right Gastrocnemius (on the calf) indicated reduction in muscular activation during the experiment. The results also show the ability of the control system to predict spatio-temporal features of the pilots’ walking and to enable the exoskeleton to move in concert with the pilot.

Automated classification of tropical shrub species: a hybrid of leaf shape and machine learning approach

Plants play a crucial role in foodstuff, medicine, industry, and environmental protection. The skill of recognising plants is very important in some applications, including conservation of endangered species and rehabilitation of lands after mining activities. However, it is a difficult task to identify plant species because it requires specialized knowledge. Developing an automated classification system for plant species is necessary and valuable since it can help specialists as well as the public in identifying plant species easily. Shape descriptors were applied on the myDAUN dataset that contains 45 tropical shrub species collected from the University of Malaya (UM), Malaysia. Based on literature review, this is the first study in the development of tropical shrub species image dataset and classification using a hybrid of leaf shape and machine learning approach. Four types of shape descriptors were used in this study namely morphological shape descriptors (MSD), Histogram of Oriented Gradients (HOG), Hu invariant moments (Hu) and Zernike moments (ZM). Single descriptor, as well as the combination of hybrid descriptors were tested and compared. The tropical shrub species are classified using six different classifiers, which are artificial neural network (ANN), random forest (RF), support vector machine (SVM), k-nearest neighbour (k-NN), linear discriminant analysis (LDA) and directed acyclic graph multiclass least squares twin support vector machine (DAG MLSTSVM). In addition, three types of feature selection methods were tested in the myDAUN dataset, Relief, Correlation-based feature selection (CFS) and Pearson’s coefficient correlation (PCC). The well-known Flavia dataset and Swedish Leaf dataset were used as the validation dataset on the proposed methods. The results showed that the hybrid of all descriptors of ANN outperformed the other classifiers with an average classification accuracy of 98.23% for the myDAUN dataset, 95.25% for the Flavia dataset and 99.89% for the Swedish Leaf dataset. In addition, the Relief feature selection method achieved the highest classification accuracy of 98.13% after 80 (or 60%) of the original features were reduced, from 133 to 53 descriptors in the myDAUN dataset with the reduction in computational time. Subsequently, the hybridisation of four descriptors gave the best results compared to others. It is proven that the combination MSD and HOG were good enough for tropical shrubs species classification. Hu and ZM descriptors also improved the accuracy in tropical shrubs species classification in terms of invariant to translation, rotation and scale. ANN outperformed the others for tropical shrub species classification in this study. Feature selection methods can be used in the classification of tropical shrub species, as the comparable results could be obtained with the reduced descriptors and reduced in computational time and cost.

Multi-objective AGV scheduling in an FMS using a hybrid of genetic algorithm and particle swarm optimization

Flexible manufacturing system (FMS) enhances the firm’s flexibility and responsiveness to the ever-changing customer demand by providing a fast product diversification capability. Performance of an FMS is highly dependent upon the accuracy of scheduling policy for the components of the system, such as automated guided vehicles (AGVs). An AGV as a mobile robot provides remarkable industrial capabilities for material and goods transportation within a manufacturing facility or a warehouse. Allocating AGVs to tasks, while considering the cost and time of operations, defines the AGV scheduling process. Multi-objective scheduling of AGVs, unlike single objective practices, is a complex and combinatorial process. In the main draw of the research, a mathematical model was developed and integrated with evolutionary algorithms (genetic algorithm (GA), particle swarm optimization (PSO), and hybrid GA-PSO) to optimize the task scheduling of AGVs with the objectives of minimizing makespan and number of AGVs while considering the AGVs’ battery charge. Assessment of the numerical examples’ scheduling before and after the optimization proved the applicability of all the three algorithms in decreasing the makespan and AGV numbers. The hybrid GA-PSO produced the optimum result and outperformed the other two algorithms, in which the mean of AGVs operation efficiency was found to be 69.4, 74, and 79.8 percent in PSO, GA, and hybrid GA-PSO, respectively. Evaluation and validation of the model was performed by simulation via Flexsim software.

Design and development of 6-DOF system for Virtual Bicycle

There are many variations to the competition that takes place in Olympic track cycling. Hence, a bicycle simulator will bring a lot of benefits to the coaches and the athletes in a practical training. It is extremely low cost compared to a real Velodrome track which is required long construction time due to the unique geometry and size. In this project, a 6-degree-of-freedom (6-DOF) motion platform is designed and developed to simulate the Velodrome track cycling. The parallel manipulator was chosen to control the moving platform because of higher accuracy and greater weight to strength ratio compare to serial manipulator. The 6-DOF platform is controlled by linear actuators and micro-controller. An optical encoder was installed for closed-loop position feedback control. An inverse kinematics model was developed to obtain the movement of the platform, and it was validated with its CAD model. Besides, a design feasibility program was developed to calculate the optimum design dimension of the motion platform. All the positions (3-axes) and orientations (3-rotational axes) data are tracked for analysis purpose. A lab-scale prototype was successfully built for the analysis and validation purpose. A standard Velodrome track dimensions was chosen to be simulated. On the other hand, a gyro accelerometer was installed at the platform to acquire the actual motion of the platform. The data will be used to validate the control algorithms and accuracy of the motion platform. The experiment was conducted and the results are analyzed for further development.

A genetic programming approach to oral cancer prognosis

Background

The potential of genetic programming (GP) on various fields has been attained in recent years. In bio-medical field, many researches in GP are focused on the recognition of cancerous cells and also on gene expression profiling data. In this research, the aim is to study the performance of GP on the survival prediction of a small sample size of oral cancer prognosis dataset, which is the first study in the field of oral cancer prognosis.

Method

GP is applied on an oral cancer dataset that contains 31 cases collected from the Malaysia Oral Cancer Database and Tissue Bank System (MOCDTBS). The feature subsets that is automatically selected through GP were noted and the influences of this subset on the results of GP were recorded. In addition, a comparison between the GP performance and that of the Support Vector Machine (SVM) and logistic regression (LR) are also done in order to verify the predictive capabilities of the GP.

Result

The result shows that GP performed the best (average accuracy of 83.87% and average AUROC of 0.8341) when the features selected are smoking, drinking, chewing, histological differentiation of SCC, and oncogene p63. In addition, based on the comparison results, we found that the GP outperformed the SVM and LR in oral cancer prognosis.

Discussion

Some of the features in the dataset are found to be statistically co-related. This is because the accuracy of the GP prediction drops when one of the feature in the best feature subset is excluded. Thus, GP provides an automatic feature selection function, which chooses features that are highly correlated to the prognosis of oral cancer. This makes GP an ideal prediction model for cancer clinical and genomic data that can be used to aid physicians in their decision making stage of diagnosis or prognosis.

On Equivalence of FIS and ELM for Interpretable Rule-Based Knowledge Representation

This paper presents a fuzzy extreme learning machine (F-ELM) that embeds fuzzy membership functions and rules into the hidden layer of extreme learning machine (ELM). Similar to the concept of ELM that employed the random initialization technique, three parameters of F-ELM are randomly assigned. They are the standard deviation of the membership functions, matrix-C (rule-combination matrix), and matrix-D [don't care (DC) matrix]. Fuzzy if-then rules are formulated by the rule-combination Matrix of F-ELM, and a DC approach is adopted to minimize the number of input attributes in the rules. Furthermore, F-ELM utilizes the output weights of the ELM to form the target class and confidence factor for each of the rules. This is to indicate that the corresponding consequent parameters are determined analytically. The operations of F-ELM are equivalent to a fuzzy inference system. Several benchmark data sets and a real world fault detection and diagnosis problem have been used to empirically evaluate the efficacy of the proposed F-ELM in handling pattern classification tasks. The results show that the accuracy rates of F-ELM are comparable (if not superior) to ELM with distinctive ability of providing explicit knowledge in the form of interpretable rule base.

Omnidirectional Vision for Mobile Robot Navigation

Machine vision has been widely studied, leading to the discovery of many image-processing and identification techniques. Together with this, rapid advances in computer processing speed have triggered a growing need for vision sensor data and faster robot response. In considering omnidirectional camera use in machine vision, we have studied omnidirectional image features in depth to determine correlation between parameters and ways to flatten 3-dimensional images into 2 dimensions. We also discuss ways to process omnidirectional images based on their individual features.