Innovative road distress detection (IR-DD): an efficient and scalable deep learning approach.

In the rapidly evolving landscape of transportation infrastructure, the quality and condition of road networks play a pivotal role in societal progress and economic growth. In the realm of road distress detection, traditional methods have long grappled with manual intervention and high costs, requiring trained observers for time-consuming and expensive data collection processes. The limitations of these approaches are compounded by challenges in adapting to diverse road surfaces and handling low-resolution data, particularly in early automated distress survey technologies. This article addresses the critical need for efficient road distress detection, a key component of ensuring safe and reliable transportation systems. Effectively addressing these challenges is crucial for enhancing the efficiency, accuracy, and safety of road distress detection systems. Leveraging advancements in object detection, we introduce the Innovative Road Distress Detection (IR-DD), a novel framework that integrates the YOLOv8 algorithm to enhance the accuracy and real-time capabilities of road distress detection, catering to applications such as smart cities and autonomous vehicles. Our approach incorporates bidirectional feature pyramid network (BiFPN) recursive feature fusion and bidirectional connections to optimize the utilization of multi-scale features, addressing challenges related to information loss and gradients encountered in traditional methods. Comprehensive experimental analysis demonstrates the superior performance, efficiency, and robustness of our integrated approach, positioning it as a cost-effective and compelling alternative to conventional road distress detection methods. Our findings demonstrate the superior performance of our approach compared to other state-of-the-art methods across various evaluation metrics, including precision, recall, F1 score, and mean average precision (mAP) at different intersection over union (IoU) thresholds. Specifically, our method achieves notable results with a precision of 0.666, F1 score of 0.630, mAP@0.5 of 0.650, all while operating at a speed of 86 frames per second (FPS). These outcomes underscore the effectiveness of our approach in real-time road distress detection. This article contributes to the ongoing innovation in object detection techniques, emphasizing the practicality and effectiveness of our proposed solution in advancing the field of road distress detection.

Identification of two hub genes and miRNA­mRNA interactions in chronic obstructive pulmonary disease (COPD) plasma.

BACKGROUND: We aimed to identify hub genes in chronic obstructive pulmonary disease (COPD) plasma through the exploration of a putative miRNA-mRNA regulatory network. METHODS: Three datasets (GSE24709, GSE102915, GSE136390) were utilized to discern differentially expressed miRNAs (DEMs) between COPD and normal plasma. miRNET was employed to predict the potential targets of DEMs. Subsequent GO and KEGG analyses were conducted using DAVID. For the construction of the protein-protein interaction (PPI) network and screening of hub genes, STRING and Cytoscape were employed. The expression validation was assessed through GSE56768. RESULTS: The results revealed 395 genes targeted by up-regulated DEMs and 234 genes targeted by down-regulated DEMs. The target genes exhibited significant enrichment in the PI3K-Akt signaling pathway and the p53 signaling pathway. Through the validation of hub genes' expression, we proposed two potential miRNA-mRNA interactions: miR-126-5p/miR-495-3p/miR-193b-3p - YWHAZ and miR-937-5p/miR-183-5p/miR-34c-5p/miR-98-5p/miR-525-3p/miR-215-5p - ACTB. CONCLUSIONS: In conclusion, our study posits potential miRNA-mRNA interactions in COPD by analyzing datasets from public databases, contributing valuable insights into the understanding of COPD pathogenesis and potential therapeutic avenues.

Simulation study on assist-as-needed control of a rehabilitation robotic walker.

BACKGROUND: Along with China entering an aging society, the percentage of people that over 60 will reach 34.9% in 2050, resulted in a significant increase in stroke patients. OBJECTIVE: This paper proposes a rehabilitation robotic walker for walking assistance during the daily life, and a control method for the motor relearning during the gait training. The walker consists of an omni-directional mobile platform (OMP) which ensures the walker can move on the ground, a body weight support system (BWS) which is capable of providing the desired unloading force, and a pelvic assist mechanism (PAM) to provide the user with four degrees of freedom and avoid the rigid impact. The study goal is to gain a better understanding of the assist-as-needed control strategy during the gait training. METHODS: For the man-machine interaction control, the assist-as-needed control strategy is adopted to guide the users' motions and improve the interaction experience. To build the force field in the three-dimensional space, the dynamics of the system is derived to increase the accuracy of force control. RESULTS: The simulation results show that the force field around the motion trajectory was generated in the three-dimensional space. In order to understand the force field, we designed the simulation on sagittal plane and the controller can generate the appropriate force field. The preliminary experiment results were consistent with the simulation results. CONCLUSION: Based on the mathematical simulation and the preliminary test, the results demonstrate that the proposed system can provide the guide force around the target trajectory, the accuracy of force control still remains to be improved.

Multimodal fusion and human-robot interaction control of an intelligent robot.

Introduction: Small-scaled robotic walkers play an increasingly important role in Activity of Daily Living (ADL) assistance in the face of ever-increasing rehab requirements and existing equipment drawbacks. This paper proposes a Rehabilitation Robotic Walker (RRW) for walking assistance and body weight support (BWS) during gait rehabilitation. Methods: The walker provides the patients with weight offloading and guiding force to mimic a series of the physiotherapist's (PT's) movements, and creates a natural, comfortable, and safe environment. This system consists of an omnidirectional mobile platform, a BWS mechanism, and a pelvic brace to smooth the motions of the pelvis. To recognize the human intentions, four force sensors, two joysticks, and one depth-sensing camera were used to monitor the human-machine information, and a multimodal fusion algorithm for intention recognition was proposed to improve the accuracy. Then the system obtained the heading angle E, the pelvic pose F, and the motion vector H via the camera, the force sensors, and the joysticks respectively, classified the intentions with feature extraction and information fusion, and finally outputted the motor speed control through the robot's kinematics. Results: To validate the validity of the algorithm above, a preliminary test with three volunteers was conducted to study the motion control. The results showed that the average error of the integral square error (ISE) was 2.90 and the minimum error was 1.96. Discussion: The results demonstrated the efficiency of the proposed method, and that the system is capable of providing walking assistance.

New lanostane-type triterpenoids with proangiogenic activity from the fruiting body of Ganoderma applanatum.

Two new lanostane-type triterpenoids, ganoderenicfys A (1) and B (2), together with six related known terpenoids (3-8), were isolated and identified from the fruiting body of Ganoderma applanatum. The structures of these compounds were established on the basis of detailed interpretation of their NMR and HRESIMS data. The absolute configurations of 1 and 2 were determined by quantum chemical electronic circular dichroism (ECD) calculations. All of the isolated compounds were evaluated for their proangiogenic activities in a transgenic fluorescent zebrafish model. Compounds 1-6 displayed dose-dependently proangiogenic activity in a PTK787-induced vascular injury zebrafish model, while compounds 1, 2 and 4 significantly promoted the angiogenesis. This is the first report for proangiogenic activities of lanostane-type triterpenoids.

Design and Simulation Analysis of a Robot-Assisted Gait Trainer with the PBWS System.

In response to the ever-increasing demand of lower limb rehabilitation, this paper presents a novel robot-assisted gait trainer (RGT) to assist the elderly and the pediatric patients with neurological impairments in the lower limb rehabilitation training (LLRT). The RGT provides three active degrees of freedom (DoF) to both legs that are used to implement the gait cycle in such a way that the natural gait is not significantly affected. The robot consists of (i) the partial body weight support (PBWS) system to assist patients in sit-to-stand transfer via the precision linear rail system and (ii) the bipedal end-effector (BE) to control the motions of lower limbs via two mechanical arms. The robot stands out for multiple modes of training and optimized functional design to improve the quality of life for those patients. To analyze the performance of the RGT, the kinematic and static models are established in this paper. After that, the reachable workspace and motion trajectory are analyzed to cover the motion requirements and implement natural gait cycle. The preliminary results demonstrate the usability of the robot.

Analysis and modeling of human seat interaction with a focus on the upper body and backrest using biomechanics and contact mechanics.

BACKGROUND: This paper outlines a method to study the interaction between the human body and the aircraft seat concerning the seat comfort. METHOD: Firstly, the human body is modeled based on biomechanics and divided into a number of body segments connected by joints according to human anatomy. The angles between the body segments are obtained by curve fitting of the existing biomechanical research data. The contact forces between the human body and the seat are modeled using pairs of bi-lateral point forces. These forces are calculated and located through the analysis of the center of gravity of each body segment and average muscular structure of the human body. The geometry of the human and the seat is obtained from a 3D scan model or a CAD model. Secondly, the pressure distribution between the human body and the seat is modeled and calculated using the contact stress theory. The results of the two parts are combined to analyze the comfortability in relation to different postures, backrest recline angles and changing in shape and material. RESULTS: Simulations were performed and they are compared with experimental measurement and various FEM studies for validation. It is found that accuracy of this method is comparable with most FEM calculation. CONCLUSION: This method provides a new direction in cushion conform research. It is faster and convenient to use comparing to the FEM, and the result is reliable.

Design and analysis of a novel fall prevention device for lower limbs rehabilitation robot.

BACKGROUND: Most stroke survivors are suffering from physical motor impairments and confronting with the risk of falls, and well trunk stability is essential for balance during daily functional activities. OBJECTIVES: Current fall prevention devices have various limits to the efficient recovery of balance function of the trunk. To provide hemiplegic patients after stroke with the retraining of trunk position sense and a safety environment, a novel fall prevention device is proposed. METHODS: Firstly, the structure of the device is introduced and this work is a first effort towards restoring trunk balance function through retraining of trunk position sense. Secondly, the kinematic and static model of the device are developed. Lastly, kinematic and static analysis are carried out to study the motion characteristics, and a contrast experiment was derived to show the effectiveness of robot. RESULTS: No obvious difference in balance ability between two groups prior treatment (P> 0.05). Fugl-Meyer assessment in all the cases were improved in different extent (P< 0.05). The robot group had significantly higher Fugl-Meyer scores after treatment than the control group (P< 0.05). CONCLUSIONS: The results show that the fall prevention device has good kinematic dexterity within the prescribed workspace and markedly improves balance function.

Force Analysis and Evaluation of a Pelvic Support Walking Robot with Joint Compliance.

The force analysis of a pelvic support walking robot with joint compliance is discussed in this paper. During gait training, pelvic motions of hemiplegic patients may be excessively large or out of control; however, restriction of pelvic motions is not likely to facilitate successful rehabilitation. A robot-assisted pelvic balance trainer (RAPBT) is proposed to help patients control the range of motion via force field, and force analysis is necessary for the control of the compliant joints. Thus, kinematic model and static model are developed to derive the Jacobian and the relation between the interaction forces and the pelvic movements, respectively. Since the joint compliance is realized through a nontorsional spring, a conventional (linear) Jacobian method and a piecewise linear method are derived to relate the interaction forces with the pelvis movements. Three preliminary experiments are carried out to evaluate the effectiveness of the proposed methods and the feasibility of the RAPBT. The experiment results indicate that the piecewise linear method is effective in the calculation of the interaction forces. Gait with pelvic brace strongly resembles free overground walking and partly decreases motion range via force field. The findings of this research demonstrate that the pelvic brace with joint compliance may provide effective interventions.

Iterative Learning Impedance for Lower Limb Rehabilitation Robot.

This paper discusses the problem of squatting training of stroke patients. The main idea is to correct the patient's training trajectory through an iterative learning control (ILC) method. To obtain better rehabilitation effect, a patient will typically be required to practice a reference posture for many times, while most of active training methods can hardly keep the patients training with correct posture. Instead of the conventional ILC strategy, an impedance-based iterative learning method is proposed to regulate the impedance value dynamically and smartly which will help patients correct their posture gradually and perform better. To facilitate impedance-based ILC, we propose two objectives. The first objective is to find the suitable values of impedance based on the ILC scheme. The second objective is to search the moderate learning convergence speed and robustness in the iterative domain. The simulation and experimental results demonstrate that the performance of trajectory tracking will be improved greatly via the proposed algorithm.