Search results

Vehicles estimation can be used in evaluating traffic conditions and facilitating traffic control, which is an important task in intelligent transportation system. The paper aims to propose a vehicle-counting method based on the analysis of surveillance videos.

The paper proposes a novel two-step method using low-rank representation (LRR) detection and locality-constrained linear coding (LLC) classification to count the number of vehicles in traffic video sequences automatically. The proposed method is based on an offline training to understand an LLC-based classifier with extracted features for vehicle and pedestrian classification, followed by an online counting algorithm to count the number of vehicles detected from the image sequence.

The proposed method allows delivery estimation (counting the number of vehicles at each frame only) and total number estimation of vehicles shown in the scene. The paper compares the proposed method with other similar methods on three public data sets. The experimental results show that the proposed method is competitive and effective in terms of computational speed and evaluation accuracy.

The proposed method does not consider illumination. Hence, the results might be unsatisfactory under low-lighting condition. Therefore, researchers are encouraged to add a term that controls the illumination changes into the energy function of vehicle detection in future work.

The paper bridges the gap between LRR detection and vehicle counting by taking advantage of existing LLC classification algorithm to distinguish different moving objects.

Construction enterprises are achieving the goal of production safety by increasingly focusing on the critical factor of “human” and the impact of individual characteristics on safety performance. Emotional intelligence is categorized into three models: skill-based, trait-based and emotional learning systems. However, the mechanism of action and the internal relationship between emotional intelligence and safety performance must be further studied. This study intends to examine the internal mechanism of emotional intelligence on safety performance in construction projects, which would contribute to the safety management of construction enterprises.

A structural equation model exploring the relationship between emotional intelligence and safety performance is developed, with political skill introduced as an independent dimension, situational awareness presented as a mediator, and management safety commitment introduced as a moderator. Data were collected by a random questionnaire and analyzed by SPSS 24.0 and AMOS 26.0. The structural equation model tested the mediation hypothesis, and the PROCESS macro program tested the moderated mediation hypothesis.

The results showed that construction workers' emotional intelligence directly correlates with safety performance, and situational awareness plays a mediating role in the relationship between emotional intelligence and the safety performance of construction workers. Management safety commitment weakens the positive predictive relationships between emotional intelligence and situational awareness and between emotional intelligence and safety performance.

This research reveals a possible impact of emotional intelligence on safety performance. Adding political skills to the skill-based model of emotional intelligence received a test pass. Political skill measures the sincere and cooperative skills of construction workers. Using people as a critical element plays a role in the benign mechanism of “Emotional Intelligence – Situational Awareness – Safety Performance.” Improving emotional intelligence skills through training, enhancing situational awareness, understanding, anticipation and coordination and activating management environment factors can improve safety performance. Construction enterprises should evaluate and train workers' emotional intelligence to improve workers' situational awareness and safety performance.

As an important connecting component, the reliability of aluminium alloy welded joints influences the whole structural effectiveness and stability of equipment. The purpose of this paper is to propose a novel reliability estimation approach to the welded joints based on time-transformed Wiener process with automatic image measurement of crack growth. The crack length information of the welded joints is incorporated into reliability analysis to reflect the product time-varying characteristics.

The proposed approach is superior to other crack growth estimations in that it innovatively introduce a non-contact and flexible photogrammetry technique.First, on-line crack growth images of aluminium alloy welded joints are acquired by the designed monitor system. Second, crack length is calculated with image measurement, then the crack growth data during the manufacturing process is prepared. Finally, a time-transformed Wiener process is used to modeling the degradation, and reliability estimation is carried out with Wiener model. The approach has been validated on five 7075-T7351 welded joint samples.

The method has a twofold task: first, the extraction of crack length growth data by a sequence of image processing. The main step is to model the crack skeleton with crack skeleton tree, and remove it edges to calculate the length of crack; second, the prediction of crack growth and reliability estimation.

The limitation of proposed method should not be ignored. The pixel/mm scale should be calibrated in advance that means once we have built the monitor system, the relative position of the CCD camera and the surveyed crack cannot change anymore. It has reduced the flexibility. To improve this, we can obtain binocular vision in crack image measurement. The 3-D measurements could solve calibration problem and provide more information, such as the depth and the orientation of crack to research. Therefore, future work can be centered on the improvement of monitor system and measurement precision.

In the paper a novel method to estimate reliability of crack growth from welded joint based on image measurement has been presented. This method could be widely applied in different filed of manufacturing systems, reliability engineering and structural analysis.

It is widely agreed that amputees have to rely on visual input to monitor and control the position of the prosthesis while reaching and grasping because of the lack of proprioceptive feedback. Therefore, visual information has been a prerequisite for prosthetic hand biofeedback studies. This is why, the underlying characteristics of other artificial feedback methods used to this day, such as auditive, electro‐tactile, or vibro‐tactile feedback, has not been clearly explored. The purpose of this paper is to explore whether it is possible to use audio feedback alone to convey more than one independent variable (multichannel) simultaneously, without relying on the vision, to improve the learning of a new perceptions, in this case, to learn and understand the artificial proprioception of a prosthetic hand while reaching.

Experiments are conducted to determine whether the audio signals could be used as a multi‐variable dynamical sensory substitution in reaching movements without relying on the visual input. Two different groups are tested, the first one uses only audio information and the second one uses only visual information to convey computer‐simulated trajectories of two fingers.

The results show that it is possible to use auditive feedback to convey artificial proprioceptive information instead of vision as a guide, thus assist users by internalizing new perceptions.

This way, the strong and weak points of auditive feedback can be observed and can be used to improve future feedback systems or schemes, which can integrate different feedback methods to provide more information to the user.

The aim of this paper is to develop autonomous mobile home healthcare robots, which are capable of observing patients’ motions, recognizing the patients’ behaviours based on observation data, and providing automatically calling for medical personnel in emergency situations. The robots to be developed will bring about cost‐effective, safe and easier at‐home rehabilitation to most motor‐function impaired patients (MIPs).

The paper has developed following programs/control algorithms: control algorithms for a mobile robot to track and follow human motions, to measure human joint trajectories, and to calculate angles of lower limb joints; and algorithms for recognizing human gait behaviours based on the calculated joints angle data.

A Hidden Markov Model (HMM) based human gait behaviour recognition taking lower limb joint angles and body angle as input was proposed. The proposed HMM based gait behaviour recognition is compared with the Nearest Neighbour (NN) classification methods. Experimental results showed that a human gait behaviour recognition using HMM can be achieved from the lower limb joint trajectory with higher accuracy than compared classification methods.

The research addresses human motion tracking and recognition by a mobile robot. Human gait behaviour recognition is HMM based lower limb joints and body angle data from extracted from kinect sensor at the mobile robot.

This study investigates the impact of board independence on firm risk of Vietnamese listed firms and the moderating effect of capital expenditure on this relationship.

This paper applies fixed effects and dynamic generalized method of moments (GMM) models to examine hypothesized associations between the proportion of nonexecutive directors and stock return volatility, as well as the moderating effect of capital expenditure. The robustness tests are implemented by applying alternative measures of overinvestment and firm risk.

The results show that the presence of nonexecutive directors on board increases firm risk. However, the combination of nonexecutive ratio and capital expenditure ratio has a significant negative impact on firm risk. The result is also confirmed by the difference between the monitoring role of nonexecutive directors in overinvesting and underinvesting firms.

The results imply that Vietnamese listed firms take stock return volatility into consideration before nominating and appointing nonexecutive directors into their board, especially in overinvesting firms. From another perspective, the shift toward having a majority of nonexecutive directors on boards can play a significant role in pursuing a stable or risky business strategy.

This paper investigates the influences of nonexecutive directors on firm risk in the context of Vietnam.

This chapter looks at the crucial role that local action plays in achieving the SDGs. It begins by revisiting the transition from the Millennium Development Goals to the Sustainable Development Goals and ponders the reasons why we should have faith in the prospect for successful goal attainment. Next, it demonstrates the importance of local responses to global problems and challenges targeted by the SDGs and discusses the motivation of local actors to contribute to the changes that need to be made in order to generate inclusive prosperity while protecting the planet. Finally, the chapter identifies some of the key barriers to local action and reflects on how we broaden the scope and improve the conditions for local people and organizations to initiate and drive change.

The purpose of this paper is to focus on the design and development of computer-aided fabric defect detection and classification employing advanced learning algorithm.

To make a fast and effective classification of fabric defect, the authors have considered a characteristic of texture, namely its colour. A deep convolutional neural network is formed to learn from the training phase of various defect data sets. In the testing phase, the authors have utilised a learning feature for defect classification.

The improvement in the defect classification accuracy has been achieved by employing deep learning algorithm. The authors have tested the defect classification accuracy on six different fabric materials and have obtained an average accuracy of 96.55 per cent with 96.4 per cent sensitivity and 0.94 success rate.

The authors had evaluated the method by using 20 different data sets collected from different raw fabrics. Also, the authors have tested the algorithm in standard data set provided by Ministry of Textile. In the testing task, the authors have obtained an average accuracy of 94.85 per cent, with six defects being successfully recognised by the proposed algorithm.

The quantitative value of performance index shows the effectiveness of developed classification algorithm. Moreover, the computational time for different fabric processing was presented to verify the computational range of proposed algorithm with the conventional fabric processing techniques. Hence, this proposed computer vision-based fabric defects detection system is used for an accurate defect detection and computer-aided analysis system.