A resilient robot is a robot that can recover its function after the robot is partially damaged. In this paper, a study of an under-actuated resilient robot with closed loops and passive joints is presented. First, a prototype system was built, which serves as a study vehicle and is called R-Robot II for short. Second, the kinematics of the prototype robot R-Robot II, necessarily for the change of the robot structure in, was developed. Finally, the experimentation of the R-Robot II was carried out. The result shows that the desired resilient behavior of R-Robot II can be exhibited. The architecture of R-Robot II, along with the design of the mechanical modules and simulation, was reported elsewhere. This paper focuses on the physical realization of R-Robot II and on the experimentation.

Fall detection is of increasing significance in terms of the health monitoring of the elderly and disabled people, as falls may lead to physical injuries or even mental trauma. The existing fall detection methods have achieved impressive performance, but limitations present in operability, interface with public healthcare systems, and other technical issues such as high-power consumption, cost, and reliability. In this article, we present a wearable fall detection system, which is based on a novel multilevel threshold algorithm. The algorithm combines micro-electro-mechanical-systems (MEMS) with narrow band Internet of Things (NB-IoT). The system also includes a user interface for healthcare professionals, developed based on the cloud technology and server-client architecture. For the verification of the algorithm, we recruited 20 volunteers to perform the activities of daily living and falls. The experimental result showed that the proposed algorithm can achieve an accuracy of 94.88%, a sensitivity of 95.25%, and a specificity of 94.5%, suggesting the effectiveness of our system.

Colon cancer is the third most common cancer in the world, and it is increasingly threatening people’s health. Early diagnosis is crucial to reducing the threat; however, the chance of missed polyps in today’s colonoscopy examination is still high (about 10%) due to limitations in diagnosis techniques and data analysis methods. The colonoscope is a kind of robot and on its tip there is a camera to acquire images. This paper presents a study aimed to improve the rate of successful diagnosis with a new image data analysis approach based on the faster regional convolutional neural network (faster R-CNN). This new approach has two steps for data analysis: (i) pre-processing of images to characterize polyps, and (ii) incorporating of the result of the pre-processing into the faster R-CNN. Specifically, the pre-processing of colonoscopy was expected to reduce the influence of specular reflections, resulting in an improved image, upon which the faster R-CNN algorithm was aplied. There are several improvements of the faster r-CNN tailoring to the task of colon polyps detection. To confirm the superiority of this new approach, the mean average precision (mAP) was used to compare the results obtained with the new approach and the faster R-CNN algorithm. The experimental result shows that the mAP of the new approach is 91.43%, as opposed to 90.57% with the faster R-CNN, which shows a significant improvement.

Recent years have seen deep learning algorithms such as Convolutional Neural Networks (CNNs) and their variants achieving competitive performance in the application of medical image processing. Yet their shortcomings are: (i) the need of a large collection of annotated data, and (ii) the involvement of careful design of CNN layers. In this paper, we presented a novel polyp detection architecture based on two ideas: (i) to use Conditional Generative Adversarial Network (CGAN) to expand the training datasets, specifically the Generator takes advantage of the Efficient Spatial Pyramid (ESP) and the Discriminator is based on the PatchGAN; (ii) to modify the architecture of YOLOv4 using dilated convolution and skip connections. Experiments were performed using three publicly available datasets, i.e., CVC-ClinicDB, CVC-ColonDB, and ETIS-Larib Polyp DB. Experimental results showed that our generative network outperformed U-Net and can synthesize more realistic polyp images. The modified YOLOv4 significantly improved the performance of polyp detection using the expanded dataset, with an accuracy of 92.37% and a detection rate of 17.2 frames per second.

In the past few decades, the rapid development of haptic technology has made it widely used in the fields of virtual reality, video games, rehabilitation, education and manufacturing. This paper presents a study on rapid construction of a cost-effective virtual haptic device. In this connection, the study proposed a new design concept called haptic environment. A whole haptic system is divided into an environment, which consists of all common modules, and a haptic robot. As such, a customized haptic robot can be plugged into the environment to form a haptic system. The environment also contains adapters that facilitate the accommodation of the customized haptic robot into the environment. To show the effectiveness of this concept, a three-degree-of-freedom robot along with the environment was implemented in this study. Experiments were conducted to understand the performance of the prototype of the haptic system, as developed, and the results show that the developed haptic system has the graphical refresh frequency of about 60 HZ and the haptic rendering frequency of about 500 HZ, nearly three times faster than the Phantom Omni device commercially available. The contribution of the study reported in this paper includes: (1) the demonstration of the feasibility of rapid construction of a virtual haptic device and (2) the provision of a cost-effective haptic device for applications in robotic rehabilitation and human assistive systems