Significant spatial co-distribution pattern discovery

Given instances (spatial points) of different spatial features (categories), significant spatial co-distribution pattern discovery aims to find subsets of spatial features whose spatial distributions are statistically significantly similar to each other. Discovering significant spatial co-distribution patterns is important for many application domains such as identifying spatial associations between diseases and risk factors in spatial epidemiology. Previous methods mostly associated spatial features whose instances are frequently located together; however, this does not necessarily indicate a similarity in the spatial distributions between different features. Thus, this paper defines the significant spatial co-distribution pattern discovery problem and subsequently develops a novel method to solve it effectively. First, we propose a new measure, dissimilarity index, to quantify the difference between spatial distributions of different features under the spatial neighbor relation and then employ it in a distribution clustering method to detect candidate spatial co-distribution patterns. To further remove spurious patterns that occur accidentally, the validity of each candidate spatial co-distribution pattern is verified through a significance test under the null hypothesis that spatial distributions of different features are independent of each other. To model the null hypothesis, a distribution shift-correction method is presented by randomizing the relationships between different features and maintaining spatial structure of each feature (e.g., spatial auto-correlation). Comparisons with baseline methods using synthetic datasets demonstrate the effectiveness of the proposed method. A case study identifying co-morbidities in central Colorado is also presented to illustrate the real-world applicability of the proposed method.     

Energy Band-gap Calculation of d-Ta2O5 Using sX-LDA and B3LYP Methods

The energy band-gap and related factors of tantalum pentoxide with hexagonal phase were investigated using hybrid functional B3 LYP and s X-LDA methods. The results showed that both s X-LDA and B3 LYP techniques reveal the indirect semiconductor nature of δ-Ta2O5, whereas the obtained value of energy band-gap is much higher than previous theoretical reports but closer to the experimental data. The optical bandgap of δ-Ta2O5 is expected to originate from the O 2p→Ta 5d transition which may benefit from the d-s-p hybridization.     

Can child-pedestrians’ hazard perception skills be enhanced?

ObjectiveTraffic collisions yield a substantial rate of morbidity and injury among child-pedestrians. We explored the formation of an innovative hazard perception training intervention – Child-pedestrians Anticipate and Act Hazard Perception Training (CA²HPT). Training was based upon enhancing participants’ ability to anticipate potential hazards by exposing them to an array of traffic scenes viewed from different angles.MethodTwenty-four 7–9-year-olds have participated. Trainees underwent a 40-min intervention of observing typical residential traffic scenarios in a simulated dome projection environment while engaging in a hazard detection task. Trainees were encouraged to note differences between the scenarios presented to them from separate angles (a pedestrian's point-of-view and a higher perspective angle). Next, trainees and control group members were required to perform crossing decision tasks.ResultsTrainees were found to be more aware of potential hazards related to restricted field of view relative to control.ConclusionsChild pedestrians are responsive to training and actively detecting materialized hazards may enrich child-pedestrians’ ability to cross roads.     

Robot learning through task identification

The operation of an autonomous mobile robot in a semi-structured environment is a complex, usually non-linear and partly unpredictable process. Lacking a theory of robot–environment interaction that allows the design of robot control code based on theoretical analysis, roboticists still have to resort to trial-and-error methods in mobile robotics.The RobotMODIC project aims to develop a theoretical understanding of a robot’s interaction with its environment, and uses system identification techniques to identify the system robot–task–environment. In this paper, we present two practical examples of the RobotMODIC process: mobile robot self-localisation and mobile robot training to achieve door traversal.In both examples, a transparent mathematical function is obtained that maps inputs–sensory perception in both cases–to output — location and steering velocity respectively. Analysis of the obtained models reveals further information about the way in which a task is achieved, the relevance of individual sensors, possible ways of obtaining more parsimonious models, etc.     

Applications of electronically facilitated bidding model to preventing construction disputes

When a lump-sum public construction project is implemented, disputes often arise concerning issues around the accuracy of contracted quantities, the acceptability of unit prices of cost items, and whether an “equal (or equivalent)” for a product (equipment or material) can be used. In Taiwan, contracted quantities and unit prices are primarily based on owner's estimations, and the trademarks of a product specified in a tendering documentation are only for reference. A contractor has to struggle for profit when the amount of work completed differs from the contracted amount, when change orders are priced according to the owner's estimates, and when inexpensive equals may be used. This work comprehensively elaborates the background of the current practice, and presents experience of applying an electronically facilitated bidding model to evaluating the bidder's submitted quantities, unit prices and equals in several practical projects in Taiwan. Results of this study indicate that the aforementioned construction disputes can be prevented or at least mitigated.     

Data monitoring and sports injury prediction model based on embedded system and machine learning algorithm

Managing sports performance is very important in the sports industry. Performance, the executives, centers on boosting competitor execution and decreasing the danger of injury. Several factors contribute to these goals, including player health, emotional status, exercise load and physical intensity requirements. Generally speaking, injury prediction is an essential component of injury prevention, and successful identification of injury prediction is a primary indicator for effective prevention. The proposed Artificial Neural Network (ANN) objective is to develop and use early-doing ability and exercise load data to validate a hierarchical machine learning prediction system with accurate detection of player injuries. The physical and workload that requires detection of this early personalized damage can be avoided with specific help. The framework is used to test 21 soccer players’ sports information from various sources, including gathered and inside burden information, outside burden information, and review information. The entirety of this information is fused into the proposed framework to improve the exactness of harm expectation. This calculation distinguishes competitors in danger of injury, with their early intervention available.     

Investigation of oil palm harvesting tools design and technique on work-related musculoskeletal disorders of the upper body

The oil palm industry is one of the important sectors in Malaysia. The growth and development of this industry shows that Malaysia is the world second-largest oil palm producers. However, in the fresh fruit bunch (FFB) harvesting process, the harvesters are exposed to many types of work-related musculoskeletal disorders (WMSDs). The FFB harvesters tend to develop WMSDs especially the shoulders and trunk. Hence, it is important to identify the exposure levels, awkward postures and the reaction forces of muscle activity based on the posture and movement of the harvesters when using pole, chisel and loading spike during the harvesting process. The objective of this study was to investigate the effect of the design of oil palm FFB harvesting tools on WMSDs of the upper body. Rapid Upper Limb Analysis (RULA) was used to investigate and assess the exposure level on the harvester body during the harvesting process. The assessment showed that the shoulders and trunk have high exposure level and undergo awkward posture. Human Musculoskeletal Model Analysis (HMMA) was used to identify the reaction force exerted on the muscle during the FFB harvesting process. In this study, 4 muscles were analysed including Triceps, Biceps, Erector Spinae and Psoas Major. The highest reaction force of 16.36 N was found on the left triceps when handling a loading spike. In conclusion, it is important to address the risks by reviewing all possible aspects that contribute to the WMSDs and interventions on the tool design, task and working shifts may be required.     

An online multiple object tracker based on structure keeper net

We propose a novel online multiple object tracker taking structure information into account. State-of-the-art multi-object tracking (MOT) approaches commonly focus on discriminative appearance features, while neglect in different levels structure information and the core of data association. Addressing this, we design a new tracker fully exploiting structure information and encoding such information into the cost function of the graph matching model. Firstly, a new measurement is proposed to compare the structure similarity of two graphs whose nodes are equal. With this measurement, we define a complete matching which performs association in high efficiency. Secondly, for incomplete matching scenarios, a structure keeper net (SKnet) is designed to adaptively establish the graph for matching. Finally, we conduct extensive experiments on benchmarks including MOT2015 and MOT17. The results demonstrate the competitiveness and practicability of our tracker.

     

A novel method for camera external parameters online calibration using dotted road line

On board camera is the most important information source for driver assistant application which is based on computer vision. One problem for on board camera is that the external parameters are easy to be changed when moving on the road. Traditional method either calibrates external parameters offline or calibrates external parameters semi-online, which both need human intervention. By observation, it is found that corner connection of dotted road lane can form two groups of parallel lines. Using this geometric characteristics and through theoretical derivation, a novel online camera external parameter calibration method is proposed which focus on the situation when vehicle is moving. The pro of this method is that it maintains relatively high calculation accuracy and more important, it does not require any human intervention in whole calibration process. Experimental and comparison results show that this method is simple and have accurate results which fully meet the requirements of practical application.