Search

(1) Background: With the economic development and population change, the unique village ecological structure in plain and lake areas is facing various threats. This study aims to explore ways to increase the stability of the rural ecological space and promote the construction and development of green and livable villages from the perspective of spatial resilience. (2) Method: The framework for the assessment of spatial resilience for villages was constructed, the spatial resilience characteristics in Qing Yanggang were analyzed through a field investigation and qualitative analysis, and a spatial resilience planning path for the village in river and lake areas was established. (3) Results: By integrating the natural and artificial elements in rural space, the rural spatial resilience planning can reduce the sensitivity, vulnerability and potential risks of rural areas, which is an important strategy to improve rural sustainable development. (4) Conclusions: For rural areas in plain and lake areas, it is important to optimize rural land use structures, divide rural ecological resilience zones, establish ecological zoning control systems, implement water system connectivity, improve water system patterns to achieve ecological restoration, and implement the adaptive cycle of rural water ecosystem to form a rural spatial resilience planning model. In this way, the Goals n.6 of “Provide Water and Sanitation” of the 2030 Agenda for Sustainable Development can be achieved at the rural scale.

Cancer immunotherapy is an effective antitumor approach through activating immune systems to eradicate tumors by immunotherapeutics. However, direct administration of “naked” immunotherapeutic agents (such as nucleic acids, cytokines, adjuvants or antigens without delivery vehicles) often results in: (1) an unsatisfactory efficacy due to suboptimal pharmacokinetics; (2) strong toxic and side effects due to low targeting (or off-target) efficiency. To overcome these shortcomings, a series of polysaccharide-based nanoparticles have been developed to carry immunotherapeutics to enhance antitumor immune responses with reduced toxicity and side effects. Polysaccharides are a family of natural polymers that hold unique physicochemical and biological properties, as they could interact with immune system to stimulate an enhanced immune response. Their structures offer versatility in synthesizing multifunctional nanocomposites, which could be chemically modified to achieve high stability and bioavailability for delivering therapeutics into tumor tissues. This review aims to highlight recent advances in polysaccharide-based nanomedicines for cancer immunotherapy and propose new perspectives on the use of polysaccharide-based immunotherapeutics., Graphical abstract Image 1, Highlights • Cancer immunotherapy is an emerging antitumor approach but with drawbacks. • Polysaccharides can interact with the immune system to enhance immune response. • Polysaccharides can be applied as nano-carriers for cancer immunotherapeutics with enhanced anti-tumor efficacy. • Polysaccharide-based nanomedicines can relieve the toxic and side effect of cancer immunotherapy.

"MOOCs have brought many possibilities for both learners and teachers. For learners, they can study from distances and search for courses that fit their professions. For teachers, a MOOC can fully demonstrate his/her research basis, personal charisma and versatile abilities. MOOCs also bring teachers new challenges that may be overlooked in traditional education processes, especially when they are creating highly attractive, high-quality courses. In this paper, we first introduce the information about our courses that each has been attracting more than 10,000 learners at a rapid speed. Then, we recall our personal experiences of creating them. Personal experiences include surveying and implementing: we survey the related attraction/quality research in the MOOC education literature to stand us high in the beginning. The implementing experience is in chronological order, consisting of the planning-and-preparation, presentation, uploading and post-course interaction stages. And then, we summarize our suggestions for successful MOOCs, concretely: the comprehensive preparation, including content selection and learner estimation, is important; the teamwork is crucial to make decisions more reasonable and to progress faster; the third is the presentation of the courses and then the first-eye attraction tricks; the post-course interactions and course updates are also important, which are factors of a persistent course attraction; the last but not least is the MOOC and education research--- A good pedagogy understanding enables a teacher to outstand wherever in MOOC or traditional classroom."

Multi-modal therapeutics are emerging for simultaneous diagnosis and treatment of cancer. Polymeric carriers are often employed for loading multiple drugs due to their versatility and controlled release of these drugs in response to a tumor specific microenvironment. A theranostic nanomedicine was designed and prepared by complexing a small gadolinium chelate, conjugating a chemotherapeutic drug PTX through a cathepsin B-responsive linker and covalently bonding a fluorescent probe pheophorbide a (Ppa) with a branched glycopolymer. The branched prodrug-based nanosystem was degradable in the tumor microenvironment with overexpressed cathepsin B, and PTX was simultaneously released to exert its therapeutic effect. The theranostic nanomedicine, branched glycopolymer-PTX-DOTA-Gd, had an extended circulation time, enhanced accumulation in tumors, and excellent biocompatibility with significantly reduced gadolinium ion (Gd3+) retention after 96 h post-injection. Enhanced imaging contrast up to 24 h post-injection and excellent antitumor efficacy with a tumor inhibition rate more than 90% were achieved from glycopolymer-PTX-DOTA-Gd without obvious systematic toxicity. This branched polymeric prodrug-based nanomedicine is very promising for safe and effective diagnosis and treatment of cancer., Highlights • A cathepsin B-responsive theranostic nanomedicine (glycopolymer-PTX-DOTA-Gd) based on a branched glycopolymer was prepared. • Glycopolymer-PTX-DOTA-Gd can be specifically degradated and release drug at tumor enviornment. • Glycopolymer-PTX-DOTA-Gd enhance the contrast of magnetic resonance imaging (MRI) at tumor sites. • The nanomedicine have good biocompatibility, excellent tumor targeting and anti-tumor efficacy., Graphical abstract Cathepsin B-responsive biodegradable branched glycopolymer-based prodrug was designed and prepared as theranostic nanomedicine for cancer treatments, resulting in significantly enhanced therapeutic indexes and strengthened contrast of magnetic resonance imaging (MRI) at tumor sites.Image 1

Cancer theranostics is a new strategy for combating cancer that integrates cancer imaging and treatment through theranostic agents to provide an efficient and safe way to improve cancer prognosis. Design and synthesis of these cancer theranostic agents are crucial since these agents are required to be biocompatible, tumor-specific, imaging distinguishable and therapeutically efficacious. In this regard, several types of gadolinium (Gd)-based nanomaterials have been introduced to combine different therapeutic agents with Gd to enhance the efficacy of therapeutic agents. At the same time, the entire treatment procedure could be monitored via imaging tools due to incorporation of Gd ions, Gd chelates and Gd/other imaging probes in the theranostic agents. This review aims to overview recent advances in the Gd-based nanomaterials for cancer theranostics and perspectives for Gd nanomaterial-based cancer theranostics are provided.

Multiple sclerosis (MS) is a neurological disorder characterized by loss of the myelin sheath. Since the myelin sheath could insulate nerve fibers from the surrounding environment, its loss would result in dysfunction of the affected neurons in transmitting electrical signals, thus leading to sensation and motor disabilities. The treatment of MS is accompanied by a low treatment efficacy due to the existence of the blood-brain barrier (BBB) and occurrence of side effects due to a poor targeting efficacy. To overcome these obstacles of traditional MS treatment methods, nanomedicines have recently been employed to deliver MS therapeutic agents to the lesions. With deep BBB penetration and specific targeting, these nano-based interventions have received positively encouraging results and become another potential MS treatment method with better therapeutic outcomes. This review will focus on recent advances in nanomedicines for the treatment of MS by critically analyzing their strengths and weaknesses. We will propose perspectives on the development of these MS therapeutic nanomaterials.

Dealing with the robotic continuous control problem with sparse rewards is a longstanding challenge in deep reinforcement learning (RL). While existing DRL algorithms have demonstrated great progress in learning policies from visual observations, learning effective policies still requires an impractical number of real-world data samples. Moreover, some robotic tasks are naturally specified with sparse rewards, which makes the precious data inefficient and slows down the learning process, making DRL infeasible. In addition, manually shaping reward functions is a complex work because it needs specific domain knowledge and human intervention. To alleviate the issue, this paper proposes a model-free, off-policy RL approach named TD3MHER, to learn the manipulating policy for continuous robotic tasks with sparse rewards. To be specific, TD3MHER utilizes Twin Delayed Deep Deterministic policy gradient algorithm (TD3) and Model-driven Hindsight Experience Replay (MHER) to achieve highly sample-efficient training property. Because while the agent is learning the policy, TD3MHER could also help it to learn the potation physical model of the robot which is helpful to solve the task, and it does not necessitate any novel robot-environment interactions. The performance of TD3MHER is assessed on a simulated robotic task using a 7-DOF manipulator to compare the proposed technique to a previous DRL algorithm and to verify the usefulness of our method. Results of the experiments on simulated robotic task show that the proposed approach is capable of successfully utilizing previously store samples with sparse rewards, and obtain a faster learning speed.

Hepatic fibrosis is induced by chronic hepatic injuries before it turns into hepatic cirrhosis/carcinoma. It is characterized by the formation of collagen and other extracellular matrices around damaged hepatic tissues; consequently, the normal architecture of liver would be disrupted and its function impaired. Diagnosis of hepatic fibrosis, especially at the early stage, is crucial because most fibrotic changes are reversible during the hepatic fibrosis stage. However, early and more accurate diagnosis of hepatic fibrosis still remains a great challenge. With their promising structural adjustability and targeting ability, nanomedicines have recently been introduced to improve diagnosis of hepatic fibrosis. By targeting fibrogenic cells, receptors, and extracellular matrix components, these nanomedicines can achieve detection of hepatic tissues with high sensitivity and specificity at the early stage. The use of nanomedicines can also enable theranostics of this chronic hepatic disease. This review aims to present an overview of recent advances of nanomedicines in diagnosis and theranostics of hepatic fibrosis.

In the design of intelligent driving systems, reliable and accurate trajectory prediction of pedestrians is necessary. With the prediction of pedestrians’ trajectory, the possible collisions can be avoided or warned as early as possible by changing the behaviour of intelligent vehicles. The trajectory prediction problem can be considered as a sequence learning problem, in which one of the recurrent neural network (RNN) models called long short term memory (LSTM) has been regarded as a promising method. The authors present a new method for predicting the pedestrian's trajectory, which is called Social-Grid LSTM based on RNN architecture. The proposed method combines the human–human interaction model called social pooling and the Grid LSTM network model. The performance of the proposed method is demonstrated on two available public datasets, and compared with two baseline methods (LSTM and Social LSTM). The experimental results indicate that the authors’ proposed method outperforms previous prediction approaches.

This paper presents a novel cooperative trajectory planning approach for semi-autonomous driving. The machine interacts with the driver at the decision level and the trajectory generation level. To minimize conflicts between the machine and the human, the trajectory planning problem is decomposed into a high-level behavior decision-making problem and a low-level trajectory planning problem. The approach infers the driver’s behavioral semantics according to the driving context and the driver’s input. The trajectories are generated based on the behavioral semantics and driver’s input. The feasibility of the proposed approach is validated by real vehicle experiments. The results prove that the proposed human–machine cooperative trajectory planning approach can successfully help the driver to avoid collisions while respecting the driver’s behavior.

This paper proposes a maneuver evaluation approach to enhance driving safety by providing decision aids. Based on the deliberative understanding of environmental semantic information, the proposed algorithm evaluates the risk of candidate driving maneuvers, including aggressive lane-change maneuver, passive lane-change maneuver, lane-change abort maneuver, and lane-keeping maneuver. The effectiveness of the proposed method is validated through various simulation experiments. The experimental results demonstrate that the proposed approach is capable of efficiently evaluating the feasibility and the cost of each candidate driving maneuver. The approach also provides suggestions on how to adjust the speed, and when to initiate a lane-change maneuver.

Reinforcement learning from demonstration (RLfD) is considered to be a promising approach to improve reinforcement learning (RL) by leveraging expert demonstrations as the additional decision-making guidance. However, most existing RLfD methods only regard demonstrations as low-level knowledge instances under a certain task. Demonstrations are generally used to either provide additional rewards or pretrain the neural network-based RL policy in a supervised manner, usually resulting in poor generalization capability and weak robustness performance. Considering that human knowledge is not only interpretable but also suitable for generalization, we propose to exploit the potential of demonstrations by extracting knowledge from them via Bayesian networks and develop a novel RLfD method called Reinforcement Learning from demonstration via Bayesian Network-based Knowledge (RLBNK). The proposed RLBNK method takes advantage of node influence with the Wasserstein distance metric (NIW) algorithm to obtain abstract concepts from demonstrations and then a Bayesian network conducts knowledge learning and inference based on the abstract data set, which will yield the coarse policy with corresponding confidence. Once the coarse policy’s confidence is low, another RL-based refine module will further optimize and fine-tune the policy to form a (near) optimal hybrid policy. Experimental results show that the proposed RLBNK method improves the learning efficiency of corresponding baseline RL algorithms under both normal and sparse reward settings. Furthermore, we demonstrate that our RLBNK method delivers better generalization capability and robustness than baseline methods.

For dynamic complex driving tasks of autonomous vehicle, traditional driving behavior learning methods still need to be improved in terms of learning accuracy and generalization performance. A convolutional neural network gaussian process regression (CNN-GPR) method for driving behavior learning is proposed to tackle these problems that full connection layers of end-to-end convolutional neural networks (CNN) have limited generalization ability and easily converge to local optimization. At the same time, the PilotNet-GPR algorithm based on the CNN-GPR method is designed. The gaussian process regression (GPR) method with global mapping capability and better generalization performance is used to improve fully connected layers of the end-to-end CNN in order to complete the mapping from features extracted to driving actions more efficiently for the proposed CNN-GPR method. In addition, the long short-term memory network (LSTM) is added into CNN-GPR method, and a convolutional long short-term memory network gaussian process regression (CNN-LSTM-GPR) method of driving behavior learning with time-sequential images is proposed in order to further improve the accuracy of driving behavior learning through time-sequential information. This method utilises the gaussian process regression method to improve structures of fully connected layers in the cascaded deep neural network (CNN-LSTM) in order to make a more efficient learning approximation between features extracted by the CNN-LSTM and driving actions. Verification experiments on the Apollo end-to-end dataset for autonomous driving show that the proposed CNN-GPR method can further improve the imitation accuracy for end-to-end driving behavior learning and promote generalization performance of learned models compared with the PilotNet method. compared with related end-to-end driving behavior learning methods based on single image under the same condition, the proposed CNN-LSTM-GPR method can make full use of time-sequential information of images, which leads to smaller imitation errors. Additionally, it can further enhance the learning accuracy and demonstrates a more satisfying generalization performance compared with the CNN-LSTM method.

In recent years, deep reinforcement learning (DRL) has made impressive achievements in many fields. However, existing DRL algorithms usually require a large amount of exploration to obtain a good action policy. In addition, in many complex situations, the reward function cannot be well designed to meet task requirements. These two problems will make it difficult for DRL to learn a good action policy within a relatively short period. The use of expert data can provide effective guidance and avoid unnecessary exploration. This study proposes a deep imitation reinforcement learning (DIRL) algorithm that uses a certain amount of expert demonstration data to speed up the training of DRL. In the proposed method, the learning agent imitates the expert's action policy by learning from demonstration data. After imitation learning, DRL is used to optimise the action policy in a self-learning way. By experimental comparison on a video game called the Mario racing game, it is shown that the proposed DIRL algorithm with expert demonstration data can obtain much better performance than previous DRL algorithms without expert guidance.

Autonomous driving promises to be the main trend in the future intelligent transportation systems due to its potentiality for energy saving, and traffic and safety improvements. However, traditional autonomous vehicles&rsquo, behavioral decisions face consistency issues between behavioral decision and trajectory planning and shows a strong dependence on the human experience. In this paper, we present a planning-feature-based deep behavior decision method (PFBD) for autonomous driving in complex, dynamic traffic. We used a deep reinforcement learning (DRL) learning framework with the twin delayed deep deterministic policy gradient algorithm (TD3) to exploit the optimal policy. We took into account the features of topological routes in the decision making of autonomous vehicles, through which consistency between decision making and path planning layers can be guaranteed. Specifically, the features of a route extracted from path planning space are shared as the input states for the behavioral decision. The actor-network learns a near-optimal policy from the feasible and safe candidate emulated routes. Simulation tests on three typical scenarios have been performed to demonstrate the performance of the learning policy, including the comparison with a traditional rule-based expert algorithm and the comparison with the policy considering partial information of a contour. The results show that the proposed approach can achieve better decisions. Real-time test on an HQ3 (HongQi the third ) autonomous vehicle also validated the effectiveness of PFBD.

In recent years, multi-scale approach has been applied to image restoration tasks, including super-resolution, deblurring, etc., and has been proved beneficial to both optimization-based methods and learning-based methods to improve the restoration performance. Meanwhile, it is observed that high-frequency information plays an important role in blind motion deblurring. Unlike previous learning-based methods, which simply deepen deblurring network without discriminating the low-frequency contents and the high-frequency details, we propose a novel multi-scale convolutional neural network (CNN) framework with residual channel attention block (RCAB) for blind motion deblurring. RCAB has the residual in residual (RIR) structure, which consists of several residual groups with long skip connections and allows low-frequency information pass through the skip connections conveniently, and can adaptively learn more useful channel-wise features and pay more attention to high-frequency information. Experimental results show that our proposed method can obtain better deblurring images than state-of-the-art learning-based image deblurring methods in terms of both quantitative metrics and visual quality.

Scaling end-to-end learning to control robots with vision inputs is a challenging problem in the field of deep reinforcement learning (DRL). While achieving remarkable success in complex sequential tasks, vision-based DRL remains extremely data-inefficient, especially when dealing with high-dimensional pixels inputs. Many recent studies have tried to leverage state representation learning (SRL) to break through such a barrier. Some of them could even help the agent learn from pixels as efficiently as from states. Reproducing existing work, accurately judging the improvements offered by novel methods, and applying these approaches to new tasks are vital for sustaining this progress. However, the demands of these three aspects are seldom straightforward. Without significant criteria and tighter standardization of experimental reporting, it is difficult to determine whether improvements over the previous methods are meaningful. For this reason, we conducted ablation studies on hyperparameters, embedding network architecture, embedded dimension, regularization methods, sample quality and SRL methods to compare and analyze their effects on representation learning and reinforcement learning systematically. Three evaluation metrics are summarized, including five baseline algorithms (including both value-based and policy-based methods) and eight tasks are adopted to avoid the particularity of each experiment setting. We highlight the variability in reported methods and suggest guidelines to make future results in SRL more reproducible and stable based on a wide number of experimental analyses. We aim to spur discussion about how to assure continued progress in the field by minimizing wasted effort stemming from results that are non-reproducible and easily misinterpreted.

One important strategy in semi-supervised learning is to utilize the predicted pseudo labels of unlabeled data to relieve the overdependence on the ground truth of supervised learning algorithms. However, the performance of such kinds of semi-supervised methods heavily relies on the quality of pseudo labels. To address this issue, a robust semi-supervised classification method, named data augmented online extreme learning machines (ELMs) with deep features (DF-DAELM) is proposed. This method firstly extracts features and infers labels for unlabeled data through self-training. Then, with the learned features and inferred labels, two noise-robust shallow classifiers based on data augmentation (i.e., SLI-OELM and CR-OELM) are proposed to eliminate the adverse effects of noises on classifier training. Specifically, inspired by label smoothing, a data augmented method, SLI-OELM is designed based on stochastic linear interpolation to improve the robustness of classifiers based on ELMs. Furthermore, based on the smoothing assumption, the proposed CR-OELM utilizes an l 2 -norm consistency regularization term to implicitly weight noisy samples. Comprehensive experiments demonstrate that DF-DAELM achieves competitive or even better performance on CIFAR-10/100 and SVHN over the related state-of-the-art methods. Meanwhile, for the proposed classifiers, experimental results on the MNIST dataset with different noise levels and sample scales demonstrate their superior performance, especially when the sample scale is small ( ≤ 20 K) and the noise is strong ( 40 % ∼ 80 % ).

It is of utmost importance for advanced driver assistance systems to evaluate the risk of the current situation and make continuous decisions about what kind of evasive maneuver can be initiated. The purpose of this paper is to establish efficient indicators to evaluate the risk of candidate driving maneuvers for a human-in-the-loop vehicle. A novel safe driving envelope generation method is proposed, which takes various constraints into consideration, including the human operation, vehicle motion limits, and collision avoidance with road boundary and obstacles. The efficiency of the proposed method is validated by simulation experiments and real vehicle tests. The results show that the feasibility of candidate driving maneuvers can be efficiently determined by computing the driving envelope, and the proposed driving envelope method can be easily implemented for real-time applications.

In the real-time decision-making and local planning process of autonomous vehicles in dynamic environments, the autonomous driving system may fail to find a reasonable policy or even gets trapped in some situation due to the complexity of global tasks and the incompatibility between upper-level maneuver decisions with the low-level lower level trajectory planning. To solve this problem, this paper presents a synchronous maneuver searching and trajectory planning (SMSTP) algorithm based on the topological concept of homotopy. Firstly, a set of alternative maneuvers with boundary limits are enumerated on a multi-lane road. Instead of sampling numerous paths in the whole spatio-temporal space, we, for the first time, propose using Trajectory Profiles (TPs) to quickly construct the topological maneuvers represented by different routes, and put forward a corridor generation algorithm based on graph-search. The bounded corridor further constrains the maneuver's space in the spatial space. A step-wise heuristic optimization algorithm is then proposed to synchronously generate a feasible trajectory for each maneuver. To achieve real-time performance, we initialize the states to be optimized with the boundary constraints of maneuvers, and we set some heuristic states as terminal targets in the quadratic cost function. The solution of a feasible trajectory is always guaranteed only if a specific maneuver is given. The simulation and realistic driving-test experiments verified that the proposed SMSTP algorithm has a short computation time which is less than 37ms, and the experimental results showed the validity and effectiveness of the SMSTP algorithm., This work has been accepted by IEEE Intelligent Transportation System Magazine