Search results

The purpose of this paper is to propose a whole set of methods for underwater target detection, because most underwater objects have small samples, low quality underwater images problems such as detail loss, low contrast and color distortion, and verify the feasibility of the proposed methods through experiments.

The improved RGHS algorithm to enhance the original underwater target image is proposed, and then the YOLOv4 deep learning network for underwater small sample targets detection is improved based on the combination of traditional data expansion method and Mosaic algorithm, expanding the feature extraction capability with SPP (Spatial Pyramid Pooling) module after each feature extraction layer to extract richer feature information.

The experimental results, using the official dataset, reveal a 3.5% increase in average detection accuracy for three types of underwater biological targets compared to the traditional YOLOv4 algorithm. In underwater robot application testing, the proposed method achieves an impressive 94.73% average detection accuracy for the three types of underwater biological targets.

Underwater target detection is an important task for underwater robot application. However, most underwater targets have the characteristics of small samples, and the detection of small sample targets is a comprehensive problem because it is affected by the quality of underwater images. This paper provides a whole set of methods to solve the problems, which is of great significance to the application of underwater robot.

Limited by the types of sensors, the state information available for musculoskeletal robots with highly redundant, nonlinear muscles is often incomplete, which makes the control face a bottleneck problem. The aim of this paper is to design a method to improve the motion performance of musculoskeletal robots in partially observable scenarios, and to leverage the ontology knowledge to enhance the algorithm’s adaptability to musculoskeletal robots that have undergone changes.

A memory and attention-based reinforcement learning method is proposed for musculoskeletal robots with prior knowledge of muscle synergies. First, to deal with partially observed states available to musculoskeletal robots, a memory and attention-based network architecture is proposed for inferring more sufficient and intrinsic states. Second, inspired by muscle synergy hypothesis in neuroscience, prior knowledge of a musculoskeletal robot’s muscle synergies is embedded in network structure and reward shaping.

Based on systematic validation, it is found that the proposed method demonstrates superiority over the traditional twin delayed deep deterministic policy gradients (TD3) algorithm. A musculoskeletal robot with highly redundant, nonlinear muscles is adopted to implement goal-directed tasks. In the case of 21-dimensional states, the learning efficiency and accuracy are significantly improved compared with the traditional TD3 algorithm; in the case of 13-dimensional states without velocities and information from the end effector, the traditional TD3 is unable to complete the reaching tasks, while the proposed method breaks through this bottleneck problem.

In this paper, a novel memory and attention-based reinforcement learning method with prior knowledge of muscle synergies is proposed for musculoskeletal robots to deal with partially observable scenarios. Compared with the existing methods, the proposed method effectively improves the performance. Furthermore, this paper promotes the fusion of neuroscience and robotics.

A workplace bullying dynamic involving multiple individuals targeting victims can lead to the victim losing emotional bonds or affect-based trust with their colleagues, resulting in employee silence. The literature has largely ignored this negative aspect of social dynamics. This study aims to examine the relationship between workplace bullying and employee silence behaviors and determine whether affect-based trust mediates this relationship and whether climate for conflict management moderates the mediated relationship.

Hypotheses are tested using surveys and scenario-based experiments among faculty members in Indian Universities. There were 597 participants in the survey and 166 in the scenario-based experiment.

Results revealed that workplace bullying correlated positively with silence behaviors, and affect-based trust mediated the bullying-silence relationship. The hypothesized moderated mediation condition was partially supported as moderated the mediating pathway, i.e. indirect effects of workplace bullying on defensive silence and ineffectual silence via affect-based trust were weaker for employees with high climate for conflict management. However, the study failed to support the moderation of climate for conflict management in the relationship between workplace bullying and affect-based trust and workplace bullying and relational silence. The results of this moderated effect of climate for conflict management were similar in both studies.

This study is one of the few attempts to examine employee silence in response to workplace bullying in academia. Additionally, the study revealed a critical area of trust depletion associated with bullying and the importance of employee perceptions of fairness toward their institutions’ dispute resolution processes.

This article takes into account object identification, enhanced visual feature optimization, cost effectiveness and speed selection in response to terrain conditions. Neither supervised machine learning nor manual engineering are used in this work. Instead, the OTV educates itself without instruction from humans or labeling. Beyond its link to stopping distance and lateral mobility, choosing the right speed is crucial. One of the biggest problems with autonomous operations is accurate perception. Obstacle avoidance is typically the focus of perceptive technology. The vehicle's shock is nonetheless controlled by the terrain's roughness at high speeds. The precision needed to recognize difficult terrain is far higher than the accuracy needed to avoid obstacles.

Robots that can drive unattended in an unfamiliar environment should be used for the Orbital Transfer Vehicle (OTV) for the clearance of space debris. In recent years, OTV research has attracted more attention and revealed several insights for robot systems in various applications. Improvements to advanced assistance systems like lane departure warning and intelligent speed adaptation systems are eagerly sought after by the industry, particularly space enterprises. OTV serves as a research basis for advancements in machine learning, computer vision, sensor data fusion, path planning, decision making and intelligent autonomous behavior from a computer science perspective. In the framework of autonomous OTV, this study offers a few perceptual technologies for autonomous driving in this study.

One of the most important steps in the functioning of autonomous OTVs and aid systems is the recognition of barriers, such as other satellites. Using sensors to perceive its surroundings, an autonomous car decides how to operate on its own. Driver-assistance systems like adaptive cruise control and stop-and-go must be able to distinguish between stationary and moving objects surrounding the OTV.

One of the most important steps in the functioning of autonomous OTVs and aid systems is the recognition of barriers, such as other satellites. Using sensors to perceive its surroundings, an autonomous car decides how to operate on its own. Driver-assistance systems like adaptive cruise control and stop-and-go must be able to distinguish between stationary and moving objects surrounding the OTV.

This study investigates the efficiency of value relevance and faithful representation when stock market price derivates from its firm value to the investigated IT companies listed in FTSE Taiwan 50. The empirical investigation reveals one financial indicators: Return on equity (ROE) has explanatory ability among seven financial indicators, earnings per share (EPS), book value (BV), dividend yield (Div.), price–earnings ratio (P/E), ROE, return on assets (ROA), and return on operating asset (ROOA) to both sampled companies, United Microelectronics Corporation, UMC, (2303) and Taiwan Semiconductor Manufacturing Company Limited, TSMC, (2330). Furthermore, the empirical results indicate that the higher order moments, skewness and kurtosis, of price deviation do not provide a reliable prediction or explanatory power for stock price trends.

This study aims to apply the affective events theory and psychological contract theory to investigate how job satisfaction and psychological safety mediate the effect of the behavioral integrity of supervisors on the organizational commitment of employees.

A questionnaire survey was conducted using purposive sampling. In total, 500 questionnaire copies were distributed, and 453 responses were collected, of which 441 were valid (valid response rate = 88.2%).

The behavioral integrity of supervisors has a direct negative effect on organizational commitment but significant positive effects on job satisfaction and psychological safety, and job satisfaction and psychological safety have significant positive effects on organizational commitment. Job satisfaction and psychological safety have significant mediating effects on the association between the behavioral integrity of supervisors and the organizational commitment of employees.

Leaders and top management should “practice what they preach,” integrate honesty into organizational culture through training and establish a code of conduct to ensure that employees uphold their commitments. Companies should establish appropriate disciplinary systems and norms related to work and other aspects of organizational culture; they should also establish fair, just and open assessment systems to minimize the gap between their employees’ actual and expected earnings.

This study is the first to simultaneously consider the mediating effects of job satisfaction and psychological safety on the association between behavioral integrity and organizational commitment.

In recent years, terrorist attacks have gradually become one of the important factors endangering social security. In this context, this research aims to propose methods and principles which can be utilized to make effective evacuation plans to reduce casualties in terrorist attacks.

By analyzing the statistical data of terrorist attack videos, this paper proposes an extended cellular automaton (CA) model and simulates the panic evacuation of the pedestrians in the terrorist attack.

The main findings are as follows. (1) The panic movement of pedestrians leads to the dispersal of the crowd and the increase in evacuation time. (2) Most deaths occur in the early stage of crowd evacuation while pedestrians gather without perceiving the risk. (3) There is a trade-off between escaping from the room and avoidance of attackers for pedestrians. Appropriate panic contagion enables pedestrians to respond more quickly to risks. (4) Casualties are mainly concentrated in complex terrains, e.g. walls, corners, obstacles, exits, etc. (5) The initial position of the attackers has a significant effect on the crowd evacuation. The evacuation efficiency should be reduced if the attacker starts the attack from the exit or corners.

In this research, the concept of “focus region” is proposed to depict the different reactions of pedestrians to danger and the effects of the attacker’s motion (especially the attack strategies of attackers) are classified. Additionally, the influences on pedestrians by direct and indirect panic sources are studied.

Four reputed leaders for the coming years in the field of special education for individuals with emotional and behavioral disorders (EBD) each with a slightly different perspective on the field were asked to respond independently to a prompt asking what does special education mean for students with EBD and what is being done and how do we maintain tradition? The contributors' responses to the prompt are presented and then summarized across the essays. A remarkable consistency emerges across the independent essays. In addition to the tradition of providing a free and appropriate education in the least restrictive environment, the contributors identify needs to support teachers serving this population. Needs in teacher training and the expertise required to meet the needs of individuals with EBD are outlined as well as potential contributions of technology to carry out specific tasks. We conclude with a call for increased advocacy for use of the knowledge that we currently possess and that which will soon be discovered to support students with EBD as well as their teachers. We also note that the contributors' names are listed alphabetically to acknowledge the equality of each person to the final product.

This paper aims to study the influence of cylindrical texture parameters on the lubrication performance of static and dynamic pressure thrust bearings (hereinafter referred to as thrust bearings) and to optimize their lubrication performance using multiobjective optimization.

The influence of texture parameters on the lubrication performance of thrust bearings was studied based on the modified Reynolds equation. The objective functions are predicted through the BP neural network, and the texture parameters were optimized using the improved multiobjective ant lion algorithm (MOALA).

Compared with smooth surface, the introduction of texture can improve the lubrication properties. Under the optimization of the improved algorithm, when the texture diameter, depth, spacing and number are approximately 0.2 mm, 0.5 mm, 5 mm and 34, respectively, the loading capacity is increased by around 27.7% and the temperature is reduced by around 1.55°C.

This paper studies the effect of texture parameters on the lubrication properties of thrust bearings based on the modified Reynolds equation and performs multiobjective optimization through an improved MOALA.

This paper aims to investigate an autonomous obstacle-surmounting method based on a hybrid gait for the problem of crossing low-height obstacles autonomously by a six wheel-legged robot. The autonomy of obstacle-surmounting is reflected in obstacle recognition based on multi-frame point cloud fusion.

In this paper, first, for the problem that the lidar on the robot cannot scan the point cloud of low-height obstacles, the lidar is driven to rotate by a 2D turntable to obtain the point cloud of low-height obstacles under the robot. Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping algorithm, fast ground segmentation algorithm and Euclidean clustering algorithm are used to recognize the point cloud of low-height obstacles and obtain low-height obstacle in-formation. Then, combined with the structural characteristics of the robot, the obstacle-surmounting action planning is carried out for two types of obstacle scenes. A segmented approach is used for action planning. Gait units are designed to describe each segment of the action. A gait matrix is used to describe the overall action. The paper also analyzes the stability and surmounting capability of the robot’s key pose and determines the robot’s surmounting capability and the value scheme of the surmounting control variables.

The experimental verification is carried out on the robot laboratory platform (BIT-6NAZA). The obstacle recognition method can accurately detect low-height obstacles. The robot can maintain a smooth posture to cross low-height obstacles, which verifies the feasibility of the adaptive obstacle-surmounting method.

The study can provide the theory and engineering foundation for the environmental perception of the unmanned platform. It provides environmental information to support follow-up work, for example, on the planning of obstacles and obstacles.