This paper presents a multifunctional automated sorting system for kitchen waste based on a Delta robot. The sorting system is divided into three main modules: visual detection, information processing, and multifunctional robotic sorting. The visual detection module captures images of waste on a conveyor belt and transmits them in real-time to the information processing unit, where detection algorithms generate data on waste categories and grasp positions. The robotic arm, equipped with a force sensor, gripper, and suction cup, selects appropriate grasping or suction functions based on the waste type and shape to complete sorting. Additionally, this paper introduces a robust and efficient integrated calibration method for robot hand-eye-conveyor belt-encoder systems (HECE-IC), which enables simultaneous hand-eye and encoder calibration with only three simple steps. In simulations, the proposed method maintains a reconstruction error as low as 0.423 mm even under operation errors up to 0.6 mm. In practical experiments on the sorting platform, the average calibration error stabilized around 0.5 mm, achieving high calibration precision. The system achieved a sorting success rate of 90.2% and a sorting speed of 979 objects per hour. Our code is available at: https://github.com/TDA-2030/XRobot.

Modular Self-Reconfigurable Robot (MSRR) systems are a class of robots capable of forming higher-level robotic systems by altering the topological relationships between modules, offering enhanced adaptability and robustness in various environments. This paper presents a novel MSRR called MODUR, featuring dual-level reconfiguration capabilities designed to integrate reconfigurable mechanisms into MSRR. Specifically, MODUR can perform high-level self-reconfiguration among modules to create different configurations, while each module is also able to change its shape to execute basic motions. The design of MODUR primarily includes a compact connector and scissor linkage groups that provide actuation, forming a parallel mechanism capable of achieving both connector motion decoupling and adjacent position migration capabilities. Furthermore, the workspace, considering the interdependent connectors, is comprehensively analyzed, laying a theoretical foundation for the design of the module’s basic motion. Finally, the motion of MODUR is validated through a series of experiments.

Frequent and high-load manual material handling (MMH) tasks often cause back injuries to the workers, and backsupport exoskeletons are developed for individuals with MMH tasks. However, these exoskeletons usually cannot adapt well to the movements of the wearer's spine. This paper introduces a new bio-inspired 5-DOF origami, and via mechanical design, a unique rigid-flexible coupled bio-inspired origami mechanism is proposed. This origami mechanism is compact and lightweight, and it has stable kinematic behaviors. With the designed origami mechanisms, a novel active origami-based robotic spine assistive exoskeleton (OSAE) is developed to assist individuals with MMH tasks during the symmetric and asymmetric lifting. The OSAE is actuated by a cable-driven module through an under-actuated spine module that consists of seven origami mechanisms. With the designed spine module, the OSAE can adapt well to the wearer's spine motions during MMH tasks. Modeling of the 5- DOF origami is described, and an adaptive control strategy is proposed for the exoskeleton to adapt to different lifting methods and objects with different weights. The experimental results demonstrate the effectiveness of the proposed OSAE. During the symmetric lifting of a 10-kg object, a reduction of 41.28% of the average muscle activity of the wearer's lumbar erector spinae muscle (LES) is observed, and reductions of 30.15% and 39.54% of the average muscle activities of the wearer's left and right LES are observed, respectively, during the asymmetric lifting of a 10- kg object.

Soft exosuits feature nonlinear, low stiffness, and hysteretic behavior, presenting different mechanical responses during loading and unloading of assistive force. Delivering the desired force to the wearer is a challenge in such a system. To address this issue, this article proposed a novel control strategy with adaptive stiffness and iterative position to optimize the assistive forces of the actuators in compliance with the humanexosuit interface stiffness and relative motion. Specifically, a stiffness model was proposed to describe the force loading and unloading behaviors, further an adaptive stiffness-based force controller was designed to improve the force tracking for whole profile by adaptively adjusting the stiffness parameters related to loading and unloading, and iteratively compensating the position error associated with the force amplitude in the model on a step-by-step basis. This control strategy was implemented on a soft exosuit for hip flexion and extension assistance, and its performance was evaluated through walking tests on six subjects. The results showed that after 4 or 5 iterations of optimization based on the initial parameter settings, the proposed controller could comply with the human-exosuit interface stiffness and achieved an improved force tracking, with a minimal root-mean-square error of 7.5 N in desired force profiles tracking, and a metabolic gain of 14.8%, demonstrating a promising potential of the proposed controller for improving the force tracking and the economy of human walking.Note to Practitioners—Soft exosuits have shown promising outcomes in augmenting human walking and reducing fatigue. However, delivering the desired assistive force accurately to the wearer remains challenging due to the nonlinear and variable stiffness nature of the human-exosuit interaction during walking. This article proposed a control strategy for improving the force tracking performance by optimizing the force-positional relationship of the actuators. Specifically, a stiffness model was established to define the relationship between the force and position of the actuators. This model acts as a virtual spring between the wearer and the exosuit, and stiffness of the spring was adjusted to adapt the wearer. On the Basis of this model, we developed a force tracking controller with adaptive stiffness. It can transmit accurately a desired force trajectory to the wearer by adaptively optimizing the stiffness parameters and iteratively compensating the position error in stiffness model. This controller was implemented on a soft exosuit for hip flexion and extension assistance. The results of treadmill and outdoor walking tests with six subjects confirm the significant effect on optimizing the force-positional relationship, improving the force tracking performance, as well as avoiding force hystereses or friction losses. This research addresses the challenge of force control in human-exosuit interaction with variable stiffness characteristics. The limitation of this work is that it only focuses on hip joint assistance. In the future, we hope to extend this control strategy to other joints to achieve the generality of the approach.

Panoptic segmentation is a challenging scene understanding task that unifies semantic segmentation and instance segmentation. Namely, each pixel of an image is assigned a semantic label and an instance id. Existing works have elaborated end-to-end panoptic segmentation networks and made great progress in non-proposal-based methods. In this work, we adopt a box-free strategy and incorporate a graph-based clustering method to merge repetitive kernel weights for object instances. An alternative graph-based clustering algorithm like Markov clustering performs effective random walks for unsupervised clustering without pre-defined cluster numbers. Our proposed deep Markov clustering scheme provides an efficient alternative to guarantee instance-aware label prediction in both training and inference stages. On the COCO dataset, our method achieves promising accuracy (PQ=42.1), which is comparable with state-of-the-art methods.

The protein Yin Yang 1 (YY1) could form dimers that facilitate the interaction between active enhancers and promoter-proximal elements. YY1-mediated enhancer-promoter interaction is the general feature of mammalian gene control. Recently, some computational methods have been developed to characterize the interactions between DNA elements by elucidating important features of chromatin folding; however, no computational methods have been developed for identifying the YY1-mediated chromatin loops. In this study, we developed a deep learning algorithm named DeepYY1 based on word2vec to determine whether a pair of YY1 motifs would form a loop. The proposed models showed a high prediction performance (AUCs$\ge$0.93) on both training datasets and testing datasets in different cell types, demonstrating that DeepYY1 has an excellent performance in the identification of the YY1-mediated chromatin loops. Our study also suggested that sequences play an important role in the formation of YY1-mediated chromatin loops. Furthermore, we briefly discussed the distribution of the replication origin site in the loops. Finally, a user-friendly web server was established, and it can be freely accessed at http://lin-group.cn/server/DeepYY1.

MOTIVATION: Protein carbonylation is one of the most important oxidative stress-induced post-translational modifications, which is generally characterized as stability, irreversibility and relative early formation. It plays a significant role in orchestrating various biological processes and has been already demonstrated to be related to many diseases. However, the experimental technologies for carbonylation sites identification are not only costly and time consuming, but also unable of processing a large number of proteins at a time. Thus, rapidly and effectively identifying carbonylation sites by computational methods will provide key clues for the analysis of occurrence and development of diseases. RESULTS: In this study, we developed a predictor called iCarPS to identify carbonylation sites based on sequence information. A novel feature encoding scheme called residues conical coordinates combined with their physicochemical properties was proposed to formulate carbonylated protein and non-carbonylated protein samples. To remove potential redundant features and improve the prediction performance, a feature selection technique was used. The accuracy and robustness of iCarPS were proved by experiments on training and independent datasets. Comparison with other published methods demonstrated that the proposed method is powerful and could provide powerful performance for carbonylation sites identification. AVAILABILITY AND IMPLEMENTATION: Based on the proposed model, a user-friendly webserver and a software package were constructed, which can be freely accessed at http://lin-group.cn/server/iCarPS. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The Engineering training course takes the responsibility of cultivating students' innovation, team cooperation and practical operation ability. Now there are two ways to improve the innovation training performance in the engineering practical course. The most popular way is to carry on a project-based curriculum which has the practical training as one section of the course. Another way is to create new practice teaching methods. Our research is a combination of the project curriculum and the innovative training methods. It is focused on the Virtual reality (VR) for the engineering practice teaching. First of all, the project-based course named "Comprehensive innovation training" was offered for the junior or senior students. VR methods applied for the practice course was one of the projects in the course. Instructors built the initial model from the real practice situation into the virtual environment by the software Unreal Engine (UE) 4, and guided students the basic operation of the software. Then the students in the class would design the motion of the equipment based on the reality rules, finish the operating system with the VR device, and debug the program for the final application. Thirdly, this project was applied as an assistant practice method for the sophomores in their practice training class, and the students would give feedbacks to the system. Finally, when those sophomore students become juniors and seniors, they could involve in the project-based course, and contribute to the VR training project. Now the project is carried on, and the model of drilling machine and lathe machine are established in the virtual environment. The engineering practice assistant training system based on VR has already applied for the junior students, and some of feedbacks have been received. There is 81 percent of the students shown interest in the new method. As the platform depends on the open source software, and the whole project is sustainable and the system will be abundant in the next few years.

Precise skin lesion classification is still challenging due to two problems, i.e., (1) inter-class similarity and intra-class variation of skin lesion images, and (2) the weak generalization ability of single Deep Convolutional Neural Network trained with limited data. Therefore, we propose a Global-Part Convolutional Neural Network (GP-CNN) model, which treats the fine-grained local information and global context information with equal importance. The Global-Part model consists of a Global Convolutional Neural Network (G-CNN) and a Part Convolutional Neural Network (P-CNN). Specifically, the G-CNN is trained with downscaled dermoscopy images, and is used to extract the global-scale information of dermoscopy images and produce the Classification Activation Map (CAM). While the P-CNN is trained with the CAM guided cropped image patches and is used to capture local-scale information of skin lesion regions. Additionally, we present a data-transformed ensemble learning strategy, which can further boost the classification performance by integrating the different discriminant information from GP-CNNs that are trained with original images, color constancy transformed images, and feature saliency transformed images, respectively. The proposed method is evaluated on the ISIC 2016 and ISIC 2017 Skin Lesion Challenge (SLC) classification datasets. Experimental results indicate that the proposed method can achieve the state-of-the-art skin lesion classification performance (i.e., an AP value of 0.718 on the ISIC 2016 SLC dataset and an Average Auc value of 0.926 on the ISIC 2017 SLC dataset) without any external data, compared with other current methods which need to use external data.

Recent advances in deep learning have produced encouraging results for biomedical image segmentation; however, outcomes rely heavily on comprehensive annotation. In this paper, we propose a neural network architecture and a new algorithm, known as overlapped region forecast, for the automatic segmentation of gastric cancer images. To the best of our knowledge, this report for the first time describes that deep learning has been applied to the segmentation of gastric cancer images. Moreover, a reiterative learning framework that achieves superior performance without pretraining or further manual annotation is presented to train a simple network on weakly annotated biomedical images. We customize the loss function to make the model converge faster while avoiding becoming trapped in local minima. Patch boundary errors were eliminated by our overlapped region forecast algorithm. By studying the characteristics of the model trained using two different patch extraction methods, we train iteratively and integrate predictions and weak annotations to improve the quality of the training data. Using these methods, a mean Intersection over Union coefficient of 0.883 and a mean accuracy of 91.09% were achieved on the partially labeled dataset, thereby securing a win in the 2017 China Big Data and Artificial Intelligence Innovation and Entrepreneurship Competition.

This research is concerned with the design and analysis of a parallel kinematic manipulator (PKM) with three degrees of freedom (DOF). The proposed PKM combining the spatial rotational and translational degrees of freedom has varied advantages and good potential applications of materials handling. First, the static balancing of the parallel manipulator is investigated. The definition and methodology of static balancing are introduced. Two methods including adjusting kinematic parameters and counterweights are applied to the structure and the counterweights method leads to static balancing of the PKM. The conditions of static balancing are given. Then the dynamic model of the proposed PKM is deduced. It describes the relationship between the driving forces and the motion of the end-effector platform. Two approaches, the Newton-Euler and the Lagrange methods, are compared and the later one is selected to build the dynamic model of the 3-DOF tripod mechanism.

This paper proposes a 6-DOF (Degree of Freedom) heavy-load parallel manipulator with a redundant actuation and fault-tolerant actuator (RFTA). The novel RFTA model of the proposed manipulator is developed and its working principle is described. In order to achieve the given motion, the mathematic models of the proposed manipulator with the RFTA are derived. As a prototype of an earthquake simulator, two experiments are performed. The experimental results demonstrate that the RFTA is able to supply the required double driving force and appropriate used as an actuator of a low frequency earthquake simulator. The results of the fault-tolerant experiment show the earthquake simulator with the RFTA is capable of tolerating some local faults. The proposed parallel manipulator can also be applied under other heavy-load environments.