In recent years, machine learning (ML) algorithms have been used to minimize maintenance costs and identify problems early in the automotive sector. The determination of an asset's residual useful life of a component at a specific time is known as 'remaining useful life' (RUL). The extensive evolution of data makes it challenging to analyze and interpret high-level and valuable features from the data. The issue arises in all disciplines, and the automotive industry is no exception, given the large number of sensors to consider. Existing RUL research has not given much thought to the influence of high dimensionality data on component maintenance and deterioration. The fundamental purpose of feature selection (FS) is to select a subset of features from the data without compromising model performance. This work proposes a hybrid approach to the FS problem that combines Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO). When tested on public datasets, our results demonstrate a rise in regression accuracy and a reduction in the number of selected features. © 2022 IEEE.

Failures are the eminent aspect of any sophisticated machine such as vehicles. Early detection of faults and prioritized maintenance is a necessity of vehicle manufacturers as it enables them to reduce maintenance costs, safety risks and increase customer satisfaction. In this study, we propose to use a type of Ant Colony Optimization (ACO) algorithm to diagnose vehicles faults. We explore the effectiveness of ACO for solving fault detection in the form of a classification problem, which would be used for predictive maintenance by the manufacturers. We show experimental evaluations on the real data captured from heavy-duty trucks illustrating how optimization algorithms can be used as a classification approach to forecast component failures in the context of predictive maintenance © ESREL 2021

Socially assistive robots are increasingly being designed to interact with humans in various therapeutical scenarios. We believe that one useful scenario is providing exercise coaching for Persons with Dementia (PWD), which involves unique challenges related to memory and communication. We present a design for a robot that can seek to help a PWD to conduct exercises by recognizing their behaviors and providing appropriate feedback, in an online, multimodal, and engaging way. Additionally, following a mid-fidelity prototyping approach, we report on some observations from an exploratory user study using a Baxter robot; although limited by the sample size and our simplified approach, the results suggested the usefulness of the general scenario, and that the degree to which a robot provides feedback–occasional or continuous– could moderate impressions of attentiveness or fun. Some possibilities for future improvement are outlined, touching on richer recognition and behavior generation strategies based on deep learning and haptic feedback, toward informing next designs. © 2020 IEEE.

Background: The degree of difficulty of skills of paretic upper limbs in daily life has not been investigated. Objective: To determine the internal validity and level of difficulty of items of the Functional Skills Measure After Paralysis (FSMAP), which can be used to evaluate the functional skills of daily living for stroke patients. Method: A total of 105 first-stroke patients were assessed using the FSMAP. The evaluation system consists of 65 items in 15 categories. We examined the internal validity and level of difficulty of these items using Rasch analysis. In this study, an item with either infit or outfit of >= 1.5 was defined as underfit. Results: Rasch analysis showed that 8 items were underfit. The highest infit and outfit logits were 2.47 for "Trouser donning/doffing" and 8.44 for "Paper manipulation". "Shirt donning/doffing" was the easiest item and "Coin manipulation" was the most difficult, with difficulty logits of -35.8 and 41.5, respectively. Conclusion: The therapist can confirm items that the patient can or cannot perform. By understanding the level of difficulty of each item, the most appropriate functional skill to focus on acquiring next can be identified.

Rehabilitation and mobility training of post-stroke patients is crucial for their functional recovery. While traditional methods can still help patients, new rehabilitation and mobility training methods are necessary to facilitate better recovery at lower costs. In this work, our objective was to design and develop a rehabilitation training system targeting the functional recovery ofpost-stroke users with high efficiency. To accomplish this goal, we applied a bilateral training method, which proved to be effective in enhancing motor recovery using tactile feedback for the training. One participant with hemiparesis underwent six weeks of training. Two protocols, “contralater alarm matching” and “both arms moving together”, were carried out by the participant. Each ofthe protocols consisted of “shoulder abduction” and “shoulder flexion” at angles close to 30 and 60 degrees. The participant carried out 15 repetitions at each angle for each task. For example, in the“contralateral arm matching” protocol, the unaffected arm of the participant was set to an angle close to 30 degrees. He was then requested to keep the unaffected arm at the specified angle while trying to match the position with the affected arm. Whenever the two arms matched, a vibration was given on both brachialis muscles. For the “both arms moving together” protocol, the two arms were first set approximately to an angle of either 30 or 60 degrees. The participant was asked to return both arms to a relaxed position before moving both arms back to the remembered specified angle.The arm that was slower in moving to the specified angle received a vibration. We performed clinical assessments before, midway through, and after the training period using a Fugl-Meyer assessment (FMA), a Wolf motor function test (WMFT), and a proprioceptive assessment. For the assessments, two ipsilateral and contralateral arm matching tasks, each consisting of three movements (shoulder abduction, shoulder flexion, and elbow flexion), were used. Movements were performed at two angles, 30 and 60 degrees. For both tasks, the same procedure was used. For example, in the case of the ipsilateral arm matching task, an experimenter positioned the affected arm of the participant at 30 degrees of shoulder abduction. The participant was requested to keep the arm in that positionfor ~5 s before returning to a relaxed initial position. Then, after another ~5-s delay, the participant moved the affected arm back to the remembered position. An experimenter measured this shoulder abduction angle manually using a goniometer. The same procedure was repeated for the 60 degree angle and for the other two movements. We applied a low-cost Kinect to extract the participant’s body joint position data. Tactile feedback was given based on the arm position detected by the Kinect sensor. By using a Kinect sensor, we demonstrated the feasibility of the system for the training ofa post-stroke user. The proposed system can further be employed for self-training of patients at home. The results of the FMA, WMFT, and goniometer angle measurements showed improvements in several tasks, suggesting a positive effect of the training system and its feasibility for further application for stroke survivors’ rehabilitation. © 2019 by the authors.

Sensory disorder is a factor preventing recovery from motor paralysis after stroke. Although several robot-assisted exercises for the hemiplegic upper limb of stroke patients have been proposed, few studies have examined improvement in function in stroke patients with sensory disorder using robot-assisted training. In this study, the efficacies of robot training for the hemiplegic upper limb of three stroke patients with complete sensory loss were compared with those of 19 patients without complete sensory loss. Robot training to assist reach motion was performed in 10 sessions over a 2-week period for 5 days per week at 1 h per day. Before and after the training, the total Fugl–Meyer Assessment score excluding coordination and tendon reflex (FMA-total) and the FMA shoulder and elbow score excluding tendon reflex (FMA-S/E) were evaluated. Reach and patherrors (RE and PE) during the reach motion were also evaluated by the arm-training robot. In most cases, both the FMA-total and the FMA-S/E scores improved. Cases with complete sensory loss showed worse RE and PE scores. Our results suggest that motor paralysis is improved by robot training. However, improvement may be varied according to the presence or absence of somatic sensory feedback. © 2019 MDPI (Basel, Switzerland).