ATM-R: An Adaptive Tradeoff Model With Reference Points for Constrained Multiobjective Evolutionary Optimization.

The goal of constrained multiobjective evolutionary optimization is to obtain a set of well-converged and well-distributed feasible solutions. To achieve this goal, a delicate tradeoff must be struck among feasibility, diversity, and convergence. However, balancing these three elements simultaneously through a single tradeoff model is nontrivial, mainly because the significance of each element varies in different evolutionary phases. As an alternative approach, we adapt distinct tradeoff models in various phases and introduce a novel algorithm named adaptive tradeoff model with reference points (ATM-R). In the infeasible phase, ATM-R takes the tradeoff between diversity and feasibility into account, aiming to move the population toward feasible regions from diverse search directions. In the semi-feasible phase, ATM-R promotes the transition from "the tradeoff between feasibility and diversity" to "the tradeoff between diversity and convergence." This transition is instrumental in discovering an adequate number of feasible regions and accelerating the search for feasible Pareto optima in succession. In the feasible phase, ATM-R places an emphasis on balancing diversity and convergence to obtain a set of feasible solutions that are both well-converged and well-distributed. It is worth noting that the merits of reference points are leveraged in ATM-R to accomplish these tradeoff models. Also, in ATM-R, a multiphase mating selection strategy is developed to generate promising solutions beneficial to different evolutionary phases. Systemic experiments on a diverse set of benchmark test functions and real-world problems demonstrate that ATM-R is effective. When compared to eight state-of-the-art constrained multiobjective optimization evolutionary algorithms, ATM-R consistently demonstrates its competitive performance.

Modular hierarchical reinforcement learning for multi-destination navigation in hybrid crowds.

Real-world robot applications usually require navigating agents to face multiple destinations. Besides, the real-world crowded environments usually contain dynamic and static crowds that implicitly interact with each other during navigation. To address this challenging task, a novel modular hierarchical reinforcement learning (MHRL) method is developed in this paper. MHRL is composed of three modules, i.e., destination evaluation, policy switch, and motion network, which are designed exactly according to the three phases of solving the original navigation problem. First, the destination evaluation module rates all destinations and selects the one with the lowest cost. Subsequently, the policy switch module decides which motion network to be used according to the selected destination and the obstacle state. Finally, the selected motion network outputs the robot action. Owing to the complementary strengths of a variety of motion networks and the cooperation of modules in each layer, MHRL is able to deal with hybrid crowds effectively. Extensive simulation experiments demonstrate that MHRL achieves better performance than state-of-the-art methods.

Human-in-the-Loop Reinforcement Learning in Continuous-Action Space.

Human-in-the-loop for reinforcement learning (RL) is usually employed to overcome the challenge of sample inefficiency, in which the human expert provides advice for the agent when necessary. The current human-in-the-loop RL (HRL) results mainly focus on discrete action space. In this article, we propose a Q value-dependent policy (QDP)-based HRL (QDP-HRL) algorithm for continuous action space. Considering the cognitive costs of human monitoring, the human expert only selectively gives advice in the early stage of agent learning, where the agent implements human-advised action instead. The QDP framework is adapted to the twin delayed deep deterministic policy gradient algorithm (TD3) in this article for the convenience of comparison with the state-of-the-art TD3. Specifically, the human expert in the QDP-HRL considers giving advice in the case that the difference between the twin Q -networks' output exceeds the maximum difference in the current queue. Moreover, to guide the update of the critic network, the advantage loss function is developed using expert experience and agent policy, which provides the learning direction for the QDP-HRL algorithm to some extent. To verify the effectiveness of QDP-HRL, the experiments are conducted on several continuous action space tasks in the OpenAI gym environment, and the results demonstrate that QDP-HRL greatly improves learning speed and performance.

3-D Brain Reconstruction by Hierarchical Shape-Perception Network From a Single Incomplete Image.

3-D shape reconstruction is essential in the navigation of minimally invasive and auto robot-guided surgeries whose operating environments are indirect and narrow, and there have been some works that focused on reconstructing the 3-D shape of the surgical organ through limited 2-D information available. However, the lack and incompleteness of such information caused by intraoperative emergencies (such as bleeding) and risk control conditions have not been considered. In this article, a novel hierarchical shape-perception network (HSPN) is proposed to reconstruct the 3-D point clouds (PCs) of specific brains from one single incomplete image with low latency. A branching predictor and several hierarchical attention pipelines are constructed to generate PCs that accurately describe the incomplete images and then complete these PCs with high quality. Meanwhile, attention gate blocks (AGBs) are designed to efficiently aggregate geometric local features of incomplete PCs transmitted by hierarchical attention pipelines and internal features of reconstructing PCs. With the proposed HSPN, 3-D shape perception and completion can be achieved spontaneously. Comprehensive results measured by Chamfer distance (CD) and PC-to-PC error demonstrate that the performance of the proposed HSPN outperforms other competitive methods in terms of qualitative displays, quantitative experiment, and classification evaluation.

Spatial Decomposition-Based Fault Detection Framework for Parabolic-Distributed Parameter Processes.

Fault detection for distributed parameter processes (heat processes, fluid processes, etc.) is vital for safe and efficient operation. On one hand, the existing data-driven methods neglect the evolution dynamics of the processes and cannot guarantee that they work for highly dynamic or transient processes; on the other hand, model-based methods reported so far are mostly based on the backstepping technique, which does not possess enough redundancy for fault detection since only the boundary measurement is considered. Motivated by these considerations, we intend to investigate the robust fault detection problem for distributed parameter processes in a model-based perspective covering both boundary and in-domain measurement cases. A real-time fault detection filter (FDF) is presented, which gets rid of a large amount of data collection and offline training procedures. Rigorous theoretic analysis is presented for guiding the parameters selection and threshold computation. A time-varying threshold is designed such that the false alarm in the transient stage can be avoided. Successful application results on a hot strip mill cooling system demonstrate the potential for real industrial applications.

Handling Constrained Multiobjective Optimization Problems via Bidirectional Coevolution.

Constrained multiobjective optimization problems (CMOPs) involve both conflicting objective functions and various constraints. Due to the presence of constraints, CMOPs' Pareto-optimal solutions are very likely lying on constraint boundaries. The experience from the constrained single-objective optimization has shown that to quickly obtain such an optimal solution, the search should surround the boundary of the feasible region from both the feasible and infeasible sides. In this article, we extend this idea to cope with CMOPs and, accordingly, we propose a novel constrained multiobjective evolutionary algorithm with bidirectional coevolution, called BiCo. BiCo maintains two populations, that is: 1) the main population and 2) the archive population. To update the main population, the constraint-domination principle is equipped with an NSGA-II variant to move the population into the feasible region and then to guide the population toward the Pareto front (PF) from the feasible side of the search space. While for updating the archive population, a nondominated sorting procedure and an angle-based selection scheme are conducted in sequence to drive the population toward the PF within the infeasible region while maintaining good diversity. As a result, BiCo can get close to the PF from two complementary directions. In addition, to coordinate the interaction between the main and archive populations, in BiCo, a restricted mating selection mechanism is developed to choose appropriate mating parents. Comprehensive experiments have been conducted on three sets of CMOP benchmark functions and six real-world CMOPs. The experimental results suggest that BiCo can obtain quite competitive performance in comparison to eight state-of-the-art-constrained multiobjective evolutionary optimizers.

Effect of cold atmospheric plasma treatment on the metabolites of human leukemia cells.

BACKGROUND: Acute myeloid leukemia (AML) is a typically fatal malignancy and new drug and treatment need to be developed for a better survival outcome. Cold atmospheric plasma (CAP) is a novel technology, which has been widely applied in biomedicine, especially in various of cancer treatment. However, the changes in cell metabolism after CAP treatment of leukemia cells have been rarely studied. METHODS: In this study, we investigated the metabolite profiling of plasma treatment on leukemia cells based on Gas Chromatography Tandem Time-of-Flight Mass Spectrometry (GC-TOFMS). Simultaneously, we conducted a series of bioinformatics analysis of metabolites and metabolic pathways with significant differences after basic data analysis. RESULTS: 800 signals were detected by GC-TOF mass-spectrometry and then evaluated using PCA and OPLS-DA. All the differential metabolites were listed and the related metabolic pathways were analyzed by KEGG pathway. The results showed that alanine, aspartate and glutamate metabolism had a significant change after plasma treatment. Meanwhile, d-glutamine and d-glutamate metabolism were significantly changed by CAP. Glutaminase activity was decreased after plasma treatment, which might lead to glutamine accumulation and leukemia cells death. CONCLUSIONS: We found the above two metabolic pathways vulnerable to plasma treatment, which might result in leukemia cells death and might be the cornerstone of further exploration of plasma treatment targets.

Discharge Plasma-Activated Saline Protects Against Abdominal Sepsis by Promoting Bacterial Clearance.

AIM: The aim of the present study was to investigate the effect of cold atmospheric discharge plasma-activated saline (DPAS) on abdominal sepsis. METHODS: For in vitro research, Methicillin-resistant Staphylococcus aureus (MRSA) was treated with DPAS, and the survival was detected. For in vivo research, male C57BL/6 mice were induced to sepsis by cecal ligation and puncture (CLP) and were randomly allocated into saline and DPAS control groups, CLP group, and low or high doses of DPAS (CLP + DPAS 5 and CLP + DPAS 10) groups. In experiment 1, mice were monitored for 120 h to conduct a Kaplan-Meier survival curve analysis. In experiment 2, blood, peritoneal fluid, and lung and intestinal tissues in experimental groups were collected at 4, 8, and 24 h after the CLP/sham operation to determine the severity of sepsis. RESULTS: In vitro results showed that DPAS significantly inhibited MRSA proliferation. In vivo results showed that both low and high doses of DPAS could significantly improve septic survival in the mice. DPAS treatment also significantly attenuated the lung and intestine histopathological injuries; lung wet/dry ratio; inflammatory reaction; bacterial load in the peritoneal cavity, blood, and lungs; HMGB1 and NF-κB p65 expression levels; cell apoptosis in the lung and intestine. However, there was no difference between CLP + DPAS 5 and CLP + DPAS 10 groups. CONCLUSION: In conclusion, DPAS had markedly protective effects on abdominal sepsis in mice, and the potential mechanism was associated with the ability of reactive species in DPAS to promote bacterial clearance, inhibit the inflammatory response and cell apoptosis.

Cold atmospheric plasma induces apoptosis of melanoma cells via Sestrin2-mediated nitric oxide synthase signaling.

Cold atmospheric plasma (CAP) represents a promising therapy for selectively cancer killing. However, the mechanism of CAP-induced cancer cell death remains unclear. Here, we identified the tumor necrosis factor-family members, especially Fas, and overloaded intracellular nitric oxide participated in CAP induced apoptosis in A375 and A875 melanoma cell lines, which was known as extrinsic apoptosis pathway. This progress was mediated by antagonistic protein of reactive oxygen species, Sestrin2. The over expression of Sestrin2 induced by plasma treatment resulted in phosphorylation of p38 mitogen-activated protein kinase (MAPK), followed by increased expression of nitric oxide synthase (iNOS), Fas and Fas ligand. Depletion of Sestrin2 reduced iNOS and Fas expression, which was associated with reduction of plasma-induced apoptosis. In contrast, inhibition of iNOS activity and phosphorylation of p38 did not alter Sestrin2 expression in plasma-treated melanoma cells. Taken together, cold atmospheric plasma increases Sestrin2 expression and further activates downstream iNOS, Fas and p38 MAPK signaling to induce apoptosis of melanoma cell lines. These findings suggest a previously unrecognized mechanism in melanoma cells response to cold atmospheric plasma therapy.

Quantitatively Intrinsic Biomimetic Catalytic Activity of Nanocerias as Radical Scavengers and Their Ability against H2O2 and Doxorubicin-Induced Oxidative Stress.

Artificial enzymes as radical scavengers show great potentials in treatments of various diseases induced by oxidative stress. Herein, the quantitative analysis indicates that the intrinsic activity of nanocerias for the degradation of radicals is determined by the concentration of surface defects as well as their morphological features. The surface Ce3+ fraction of the CeO2 nanozymes with a similar morphology can be used as a descriptor to index their catalytic activity as radical scavengers. Defect-abundant porous nanorods of ceria (PN-CeO2) with a large surface area (141 m2/g) and high surface Ce3+ fraction (32.8%) deliver an excellent catalytic capability for the degradation of radicals, which is 15.5 times higher than that of Trolox. Results indicate that PN-CeO2 not only provides more surface catalytic centers but also supplies the active site with higher activity. Oxidative stress induced by doxorubicin (Dox), an essential medicine for a wide range of tumors, was used as the model system to evaluate the radical degradation ability of PN-CeO2. Both in vitro cellar (H9c2 cells) and in vivo animal models revealed that PN-CeO2 did not affect the cell and rat growth and was able to alleviate the Dox-induced oxidative stress. Results suggest that the artificial PN-CeO2 nanozymes have potentials to function as an adjuvant medicine during tumor chemotherapy.

Incorporating Objective Function Information Into the Feasibility Rule for Constrained Evolutionary Optimization.

When solving constrained optimization problems by evolutionary algorithms, an important issue is how to balance constraints and objective function. This paper presents a new method to address the above issue. In our method, after generating an offspring for each parent in the population by making use of differential evolution (DE), the well-known feasibility rule is used to compare the offspring and its parent. Since the feasibility rule prefers constraints to objective function, the objective function information has been exploited as follows: if the offspring cannot survive into the next generation and if the objective function value of the offspring is better than that of the parent, then the offspring is stored into a predefined archive. Subsequently, the individuals in the archive are used to replace some individuals in the population according to a replacement mechanism. Moreover, a mutation strategy is proposed to help the population jump out of a local optimum in the infeasible region. Note that, in the replacement mechanism and the mutation strategy, the comparison of individuals is based on objective function. In addition, the information of objective function has also been utilized to generate offspring in DE. By the above processes, this paper achieves an effective balance between constraints and objective function in constrained evolutionary optimization. The performance of our method has been tested on two sets of benchmark test functions, namely, 24 test functions at IEEE CEC2006 and 18 test functions with 10-D and 30-D at IEEE CEC2010. The experimental results have demonstrated that our method shows better or at least competitive performance against other state-of-the-art methods. Furthermore, the advantage of our method increases with the increase of the number of decision variables.