Generally, the walking assistive device for a visually impaired person is the white cane. The white cane has many problems such as collision and gait imbalance when walking with it. In addition, it is difficult to prepare for falls because the hand holding of the white cane is not free. Therefore, in this study, we developed a shoe-type walking assistive device. The device was equipped with infrared distance sensors, pressure sensors, and vibrating motors in shoes. The infrared sensor detects the distance between obstacles and the shoes. The pressure sensor is attached to detect the heel strike during the gait cycle. The vibration motor changes the intensity of its vibration according to changes in the distance between the shoes and obstacles. To evaluate the effectiveness of the developed shoe-type walking assistive device, we compared the required time, number of collisions, and electromyogram (EMG) of the lower limbs of 11 visually impaired persons while walking with the white cane. The results showed that there was no significant difference in the number of collisions between the white cane and the shoe-type walking assistive device and that the required time of the shoe-type walking assistive device was larger than that of the white cane. In addition, the difference in EMG between the lower limbs when using the shoe-type walking assistive device was smaller than that when using the white cane. Therefore, the developed shoe-type walking assistive device for visually impaired people provides a lower walking velocity than the white cane. However, it can detect obstacles to a similar extent and reduce the imbalance of the user.
Pes planus, one of the most common foot deformities, includes the loss of the medial arch, misalignment of the rearfoot, and abduction of the forefoot, which negatively affects posture and gait. Foot orthosis, which is effective in normalizing the arch and providing stability during walking, is prescribed for the purpose of treatment and correction. Currently, machine learning technology for classifying and diagnosing foot types is being developed, but it has not yet been applied to the prescription of foot orthosis for the treatment and management of pes planus. Thus, the aim of this study is to propose a model that can prescribe a customized foot orthosis to patients with pes planus by learning from and analyzing various clinical data based on a decision tree algorithm called classification and regressing tree (CART). A total of 8 parameters were selected based on the feature importance, and 15 rules for the prescription of foot orthosis were generated. The proposed model based on the CART algorithm achieved an accuracy of 80.16%. This result suggests that the CART model developed in this study can provide adequate help to clinicians in prescribing foot orthosis easily and accurately for patients with pes planus. In the future, we plan to acquire more clinical data and develop a model that can prescribe more accurate and stable foot orthosis using various machine learning technologies.
The contribution of this work is to enable time-sensitive, computation intensive applications on wearable interactive devices. To achieve this goal, this work developed an elastic computation middle-ware to federate computation resources on wearable devices, mobile devices and the connected devices that can be connected via local-and wide-area networks. With the middle-ware, the mobile applications receive mandatory/-critical results before individual deadlines and optional/noncritical results when computation resources are available on either local or connected devices. Compared with multi-tier and resource-aware mobile computation frameworks, the elastic computation middle-ware does not only offload computation workloads to connected devices but also make use of the computation and storage resources on connected devices to enhance the computation results. In addition, the mobility of the devices are taken into account to avoid deny of service attack and fruitless workloads, whose requesters are disconnected at the time of completion. Our evaluation shows that the costperformance ratio of the middle-ware is the best among all the compared algorithms. To be specific, the cost-performance of the developed algorithm can be at least two times better than that of compared algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.