Search

Well-honed CNN architectures trained with massive labeled images datasets are the state-of-the-art solution in many fields. In this paper, the weights of five commonly used pre-trained models are carefully analyzed for extracting their numerical characteristics and spatial distribution law. The general characteristics are: (1) the weights of a single convolutional layer conform to the distribution of symmetric power law. (2) the power exponent at the center of its convolutional kernel is relatively large, and the power exponent decreases radially from the center. (3) the value range of power exponents between layers is continuous from - 0.5 to - 3.5 . Based on these founding, a weight initialization method is proposed in order to speed up the convergence and improve the performance of CNN models. The proposed weight initialization method is compared with several commonly used methods. Extensive experiments show that it can improve the convergence speed of the CNN models, and the model accuracy is improved by 1–3%. [ABSTRACT FROM AUTHOR]

Polarization is an independent dimension of light wave information that has broad application prospects in machine vision and remote sensing tasks. Polarization imaging using a division-of-focal-plane (DoFP) polarimetric sensor can meet lightweight and real-time application requirements. Similar to Bayer filter-based color imaging, demosaicing is a basic and important processing step in DoFP polarization imaging. Due to the differences in the physical properties of polarization and the color of light waves, the widely studied color demosaicing method cannot be directly applied to polarization demosaicing. We propose a polarized intensity ratio constraint demosaicing model to efficiently account for the characteristics of polarization detection in this work. First, we discuss the special constraint relationship between the polarization channels. It can be simply described as: for a beam of light, the sum of the intensities detected by any two vertical ideal analyzers should be equal to the total light intensity. Then, based on this constraint relationship and drawing on the concept of guided filtering, a new polarization demosaicing method is developed. A method to directly use raw images captured by the DoFP detector as the ground truth for comparison experiments is then constructed to aid in the convenient collection of experimental data and extensive image scenarios. Results of both qualitative and quantitative experiments illustrate that our method is an effective and practical method to faithfully recover the full polarization information of each pixel from a single mosaic input image. [ABSTRACT FROM AUTHOR]

Background and Objective. Xuefu Zhuyu decoction has good efficacy in both stable and unstable angina pectoris; however, the reasons for this remain elusive. We propose a systematic process to investigate the effectiveness of the formula and the underlying material basis and mechanism of action. Methods. Firstly, we used a network proximity approach to calculate and compare the effectiveness of the formula with that of Western drugs for each type of angina, including all targets and intersecting targets, from a topological perspective. Secondly, we compared the mechanisms of action of the two angina pectoris at three levels and five aspects, including conventional and modular analysis approaches. Thirdly, based on the unique functions of each angina in the complex heterogeneous network, we designed a reverse process for finding the material basis using dynamic, static, and enriched items as well as a total item. Finally, the designed inverse process, material basis, and mechanism of action were validated. Results. The target network of Xuefu Zhuyu decoction is closer to the target network of each type of angina than that of Western drugs, and the intersection targets have a closer proximity. Comparison of the mechanisms of action showed that stable angina and unstable angina had 158 common targets, while the unique targets were 34 and 1, respectively. Modularity analysis showed that the GO similarity of target modules was highly correlated with KEGG similarity. We ended up with 67 compounds upregulated for stable angina and 47 compounds upregulated for unstable angina. Our results were validated by literature mining, high-volume molecular docking, and miRNA enrichment analysis. Conclusions. For both types of angina pectoris, Xuefu Zhuyu decoction is superior to Western drugs. A comparison of various aspects led to the unique mechanisms of action, from which the material basis of each type of angina was deduced. [ABSTRACT FROM AUTHOR]

β-cyclodextrin has a unique annular hollow ultrastructure that allows encapsulation of various poorly water-soluble drugs in the resulting cavity, thereby increasing drug stability. As a bioactive molecule, the metabolism of β-cyclodextrin is mainly completed by the flora in the colon, which can interact with API. In this study, understanding the in vivo fate of β-cyclodextrin, a LC-MS/MS method was developed to facilitate simultaneous quantitative analysis of pharmaceutical excipient β-cyclodextrin and API dextromethorphan hydrobromide. The established method had been effectively used to study the pharmacokinetics, tissue distribution, excretion, and metabolism of β-cyclodextrin after oral administration in rats. Results showed that β-cyclodextrin was almost wholly removed from rat plasma within 36 h, and high concentrations of β-cyclodextrin distributed hastily to organs with increased blood flow velocities such as the spleen, liver, and kidney after administration. The excretion of intact β-cyclodextrin to urine and feces was lower than the administration dose. It can be speculated that β-cyclodextrin metabolized to maltodextrin, which was further metabolized, absorbed, and eventually discharged in the form of CO2 and H2O. Results proved that β-cyclodextrin, with relative low accumulation in the body, had good safety. The results will assist further study of the design and safety evaluation of adjuvant β-cyclodextrin and promote its clinical development. [ABSTRACT FROM AUTHOR]

The drying process of waterborne wood coating (WWC) is mainly driven by the moisture gradient, part of the water evaporates to the air, other part enters into the wood structure. The water absorption and conduction rate vary within various wood substrates, which have a great influence on the drying rate of WWC. Herein, the focus of this paper is on studying the influence of water movement behavior on the drying efficiency and film-forming performance of WWC under conventional hot-air drying process. A waterborne acrylic-polyurethane was used as representative coating in the study. It was found that balsa wood had more pores and higher specific surface area than oak wood, allowing a faster water transfer at the wood surface. The shortest surface and hard drying time of 573 s and 1393 s were achieved at 60 °C and 40% relative humidity for WWC on balsa wood. The dynamic drying rate study showed that the water transfer on the surface of oak was slower than that of balsa. Based on the film-forming performance of WWC under different drying conditions, a better film property could be obtained by adjusting the drying conditions to achieve a dynamic balance between water evaporation to air and water transfer into the wood substrate. The drying characteristics of WWC on different wood surfaces and drying conditions were comprehensively evaluated by radar map analysis. The results in this work contributed to the efficient and green processing in furniture and coating industries. [ABSTRACT FROM AUTHOR]

Significant public opinion events often trigger pronounced fluctuations in online discourse. While existing models have been extensively employed to analyze the propagation of public opinion, they frequently overlook the intricacies of information dissemination among heterogeneous users. To comprehensively address the implications of public opinion outbreaks, it is crucial to accurately predict the evolutionary trajectories of such events, considering the dynamic interplay of multiple information streams. In this study, we propose a SEInR model based on cellular automata to simulate the propagation dynamics of multi-information. By delineating information dissemination rules that govern the diverse modes of information propagation within the network, we achieve precise forecasts of public opinion trends. Through the concurrent simulation and prediction of multi-information game and evolution processes, employing Weibo users as nodes to construct a public opinion cellular automaton, our experimental analysis reveals a significant similarity exceeding 98% between the proposed model and the actual user participation curve observed on the Weibo platform. [ABSTRACT FROM AUTHOR]

Language has been widely acknowledged as the benchmark of intelligence. However, evidence from cognitive science shows that intelligent behaviors in robust social interactions preexist the mastery of language. This review approaches human‐unique intelligence, specifically cooperation and communication, from an agency‐based theory of mind (ToM) account, emphasizing the ability to understand others' behaviors in terms of their underlying mental states. This review demonstrates this viewpoint by first reviewing a series of empirical works on the socio‐cognitive development of young children and non‐human primates in terms of their capacities in communication and cooperation, strongly suggesting that these capacities constitute the origin of human‐unique intelligence. Following, it reviews how ToM can be formalized as a Bayesian inference of the mental states given observed actions. Then, it reviews how Bayesian ToM can be extended to model the interaction of minds in cooperation and communication. The advantage of this approach is that non‐linguistic knowledge such as the visual environment can serve as the contextual constraint for multiple agents to coordinate with sparse and limited signals, thus demonstrating certain cognitive architectures underlying human communication. This article is categorized under:Applications of Computational Statistics > PsychometricsStatistical Models > Bayesian ModelsStatistical Models > Agent‐Based Models [ABSTRACT FROM AUTHOR]

Large airport operational readiness (LAOR) is a critical factor that directly impacts the opening of airports to the public. However, limited research exists on the risks affecting LAOR schedules. This article explores the risk breakdown structure and risk interactions model of LAOR schedule risk. An empirical investigation was conducted on four large hub airports from 2009 to 2021 using grounded theory procedures. The study identified 21 risk factors categorized into management (highest frequency), technical, process, participant, and environmental risks (lowest frequency), which implied that risks primarily existed within a project rather than in the external environment. A systematic model incorporating risks and their interactions revealed that the primary risk transfer path was from the subject subsystem (participant risk) to the object subsystem (technical and process risk). The findings expand the knowledge domain of infrastructure risk and provide pragmatic risk evaluation and response guidelines. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to put forward a kind of new method of intelligent trust engineering metrics for application of mobile ad hoc network (MANET). Design/methodology/approach: The new method calculates the communication trust by using the number of data packets among the nodes of MANET, predicts intelligently the trust and calculates the comprehensive trust based on the historical trust; then calculates the energy trust based on the residual energy of the nodes of MANET, calculates the direct trust based on the communication trust and energy trust. The new method calculates the recommendation trust based on the recommendation reliability; adopts the adaptive weighting to calculate the integrated direct trust by considering the direct trust with recommendation trust. Findings: Based on the integrated direct trust and the factor of trust propagation distance, the indirect trust among the nodes of MANET is calculated. The above process can be optimized based on the dynamic machine learning presented in this study. The advantage of the new method is its intelligent ability to discover malicious nodes. Originality/value: The advantage of the new method is its intelligent ability to discover malicious nodes which can partition the network by falsely reporting other nodes as misbehaving and proceeds to protect the network. The authors have done the experiments based on the tool kits such as NS3, QualNet, OMNET++ and MATLAB. The experimental results show that this study's approach can effectively avoid the attacks of malicious nodes, and more conformable to the actual engineering application of MANET. [ABSTRACT FROM AUTHOR]

Oil spills lead to catastrophic problems. In most oil spill cases, the spatial and temporal intractability of the detriment cannot be neglected, and problems related to economic, social and environmental factors constantly appear for a long time. Remote sensing has been widely used as a powerful means to conduct oil spill detection. Optical polarization remote sensing, thriving in recent years, shows a novel potential for oil spill detection. This paper provides a demonstration of the use of open-source POLDER/PARASOL polarization time-series data to detect oil spill. The Deepwater Horizon oil spill, one of the largest oil spill disasters, is utilized to explore the potential of optical polarization remote sensing for oil spill detection. A total of 24 feature combinations are organized to quantitatively study the positive effect of adding polarization information and the appropriate way to describe polarization characteristics. Random forest classifier models are trained with different combinations, and the results are assessed by 10-fold cross-validation. The improvement from adding polarization characteristics is remarkable ((average) accuracy: +0.51%; recall: +2.83%; precision: +3.49%; F1 score: +3.01%, (maximum) accuracy: +0.80%; recall: +5.09%; precision: +6.92%; F1 score: +4.72%), and coupling between the degree of polarization and the phase angle of polarization provides the best description of polarization information. This study confirms the potential of optical polarization remote sensing for oil spill detection, and some detailed problems related to model establishment and polarization feature characterization are discussed for the further application of polarization information. [ABSTRACT FROM AUTHOR]

Compared with the traditional network tasks, the emerging Internet of Vehicles (IoV) technology has higher requirements for network bandwidth and delay. However, due to the limitation of computing resources and battery capacity of existing mobile devices, it is hard to meet the above requirements. How to complete task offloading and calculation with lower task delay and lower energy consumption is the most important issue. Aiming at the task offloading system of the IoV, this paper considers the situation of multiple MEC servers when modeling, and proposes a dynamic task offloading scheme based on deep reinforcement learning. It improves the traditional Q-Learning algorithm and combines deep learning with reinforcement learning to avoid dimensional disaster in the Q-Learning algorithm. Simulation results show that the proposed algorithm has better performance on delay, energy consumption, and total system overhead under the different number of tasks and wireless channel bandwidth. [ABSTRACT FROM AUTHOR]

This paper presents an improved version of the Vantage Point Bees Algorithm (VPBA‐II), which is implemented to solve the Travelling Salesman Problem. The Vantage Point Tree has been used to produce initial tour solutions and also as a global search operator of the proposed algorithm to find the minimal Hamiltonian tour of the Travelling Salesman Problem. VPBA‐II is tested on 15 different benchmark datasets from TSPLIB, particularly for the high dimensional combinatorial solution spaces, and it outperformed the basic Bees Algorithm. The composition of the local search operators combined with Vantage Point Tours perform better except one dataset and achieved optimum results according to best‐known solutions of Travelling Salesman Problem as a best‐case scenario. The experiments prove that Vantage Point Tour construction could be used as initialization and global search operator to improve the basic Bees Algorithm performance on the combinatorial domains. [ABSTRACT FROM AUTHOR]

Vehicle routing problem (VRP) is a combinatorial optimization problem that has been studied intensively for years. Although VRP can be solved using an exact method for small instances, a more complex one will be impractical due to the nature of the problem as an NP‐hard problem. A metaheuristic is more suitable to solve this kind of problem because the near‐optimal solution can be found in a relatively shorter time compared to the exact algorithm. Bees Algorithm (BA) as nature‐inspired metaheuristic is used to find a near‐optimal solution of VRP‐TSPLIB's datasets. This study aims to provide the results of BA on the standard dataset of VRP. The BA has a very good performance, with 3.9% of the average Best‐Error and 1.2 million of the average evaluations to reach the solution. [ABSTRACT FROM AUTHOR]

Summary: In the face of the current huge amount of intelligent traffic data, collecting and statistical processing is a necessary and important process. But the inevitable data missing problem is the current research focus. In this paper, a novel approach of tensor‐based data missing estimation for Internet of Vehicles is proposed for the problem of missing the Internet of Vehicles data: Integrated Bayesian tensor decomposition (IBTD). In the data model construction stage, the random sampling principle is used to randomly extract the missing data to generate a subset of data. And the optimized Bayesian tensor decomposition algorithm is used for interpolation. Introduce the integration idea, analyze, and sort the error results after multiple interpolations, consider the space‐time complexity, and choose the optimal average to get the best result. The performance of the proposed model was evaluated by mean absolute percentage error (MAPE) and root mean square error (RMSE). The experimental results show that the proposed method can effectively interpolate the traffic data sets with different missing quantities and get good interpolation results. [ABSTRACT FROM AUTHOR]

Disassembly is a core procedure in remanufacturing. Disassembly is currently carried out mainly by human operators. It is important to reduce the labor content of disassembly through automation, to make remanufacturing more economically attractive. Threaded fastener removal is one of the most difficult disassembly tasks to be fully automated. This article presents a new method developed for automating the unfastening of screws. An electric nutrunner spindle with a geared offset adapter was fitted to the end of a collaborative robot. The position of a hexagonal headed screw in a fitted stage was known only approximately, and its orientation in the hole was unknown. The robot was programed to perform a spiral search motion to engage the tool onto the screw. A control strategy combining torque and position monitoring with active compliance was implemented. An existing robot cell was modified and utilized to demonstrate the concept and to assess the feasibility of the solution using a turbocharger as a disassembly case study. Note to Practitioners—Remanufacturing is known to generate substantial economic, social, and environmental benefits. Disassembly is the first operation in a remanufacturing process chain. Unfastening threaded parts (“unscrewing”) is a common disassembly task accounting for approximately 40% of all disassembly activity. Like other disassembly tasks, often, unscrewing has to be carried out manually in remanufacturing due to difficulties caused by the variable and unpredictable condition of the end-of-life (EoL) products to be remanufactured. Automating unscrewing operations should reduce the labor content of disassembly, thus lowering remanufacturing costs and promoting the adoption of remanufacturing. This article proposes the use of a collaborative robot to perform autonomous unfastening of hexagonal headed screws. Collaborative robots have built-in force sensors and can be programed to carry out operations involving not only position but also active force and compliance control. They can work safely alongside human operators, enabling the latter to focus on jobs requiring high cognitive or manipulation abilities. The article presents a novel spiral search technique developed to improve the rate of successful engagement between the robot end effector and the screw heads despite uncertainties in the location of the screws. The technique was successfully demonstrated on the dismantling of a turbocharger but can readily be applied to other EoL products with hexagonal headed screws. It can also be used with other kinds of screws (e.g., Phillips screws and slotted-head screws) simply by changing the tool and tuning the robot control parameters. A limitation of the proposed technique is that it can only deal reliably with undamaged screws. In our future research, we will consider screws that are in imperfect conditions through usage and develop appropriate solutions for their removal by robots. [ABSTRACT FROM AUTHOR]

Bi 2 WO 6 has attracted much attention as a visible-light-driven photocatalyst, but its photocatalytic activity should be further improved for future practical application. Herein, we prepared Yb 3+ /Er 3+ co-doped Bi 2 WO 6 (Yb 3+ /Er 3+ -Bi 2 WO 6 ) by a facile hydrothermal route followed by a calcination process. Yb 3+ /Er 3+ -Bi 2 WO 6 sample consisted of two dimensional nanosheets with the thickness of about 50 nm and length of 1–2 μm. Under visible light irradiation ( λ >400 nm), Yb 3+ /Er 3+ -Bi 2 WO 6 exhibited higher photocatalytic degradation efficiency (99.5%) for Rhodamine B than Er 3+ doped Bi 2 WO 6 (86.0%) and pure Bi 2 WO 6 (14.7%) in 20 min. Furthermore, after four photodegradation cycles, there was no significant loss for the photocatalytic activity of the nanosheets. Therefore, Yb 3+ /Er 3+ -Bi 2 WO 6 nanosheets can be used as an efficient and stable VLD photocatalyst. [ABSTRACT FROM AUTHOR]