Measurement of vessel traffic service operator performance

To meet the growing demands for yet more efficient and safer traffic, traffic control is deployed in all modes of transportation. In maritime transportation, traffic control is performed by Vessel Traffic Services (VTS). This paper describes research which is focused upon measurement of VTS operator performance. The concept of situation awareness is introduced as a means to describe and quantify VTS operator performance. Situation awareness is tested in a full scale interactive simulator. A scoring system for VTS operator performance accounts for the specific characteristics of VTS operator work, such as accuracy and relevance of information.     

An intelligent real-time multi-vessel collision risk assessment system from VTS view point based on fuzzy inference system

Due to brisk industrial growth, the marine traffic has become an imperative subject in the open sea nowadays. The crew inside the vehicle traffic service (VTS) centre is facing challenging issues on account of continuous growth in vessel number. Currently, most of VTS centers’ are using the ARPA RADAR based conventional vehicle traffic management system and VTS staff has to carry out most of the things manually to guide the ship’s captain properly. Therefore, there is a strong impetus in the field of ocean engineering to develop a smart system which can take the data from RADAR and autonomously manipulate it, to calculate the degree of collision risk among all vessels from the VTS centre. Later on, the traffic management officer utilizes this information for intelligent decision making. In the past, several researchers have addressed this issue to facilities the VTS crew and captain of the ship but mostly, their research work was for academic purposes and could not get popularity because of extra manual workload. Our proposed vessel collision risk assessment system is an intelligent solution which is based on fuzzy inference system and has the ability to solve the said issues. We calculated the DCPA, TCPA, bearing and VCD among all vessels ships from the VTS centre by using conventional marine equipments and exploited the extracted information to calculate and display the degree of collision risk among all vessels. Furthermore, we developed the RADAR filtration algorithm which helps the VTS officer to gauge out the degree of collision risk around a particular ship. To authenticate the validity and to monitor the performance efficiency, we developed RADAR operated intelligent software which directly gets the required data from RADAR and displays the vessels list based on their degree of collision severity. The laboratory experiments confirm the validity of the proposed system.     

Maritime traffic management: a need for central coordination?

Traffic management is not formally organised in the maritime domain. Ships are autonomous and find their own way. Traffic is organised through rules, regulations, and “good seamanship”; it is a distributed system. In areas of high traffic-density support is proved by vessel traffic service (VTS) to promote traffic safety and fluency. VTS does not take control. This organisational structure has proven itself in situations with sufficient resources. When resources become insufficient (e.g. not enough sailing space), the traffic needs an organising mechanism. In this article, the authors argue that the most promising way to do this is by organising centralised planning coordination, whilst leaving maritime traffic a distributed system with no additional central control.     

Non-technical communication factors at the Vessel Traffic Services

This study done at the Vessel Traffic Services (VTS) explored how the VTS operators (VTSOs) communicated with ships and other actors in the maritime sociotechnical system and how decisions were made with regard to assisting traffic in maintaining safe passage in port areas, where most vessel movements are seen and accidents occur. The fieldwork was done during four independent visits to a VTS centre under the Swedish Maritime Authority, with a total sample of six VTSOs and one VTS instructor. The qualitative data were sorted and coded using a grounded theory approach. The data pointed at non-technical information processing and communication factors that play a role in decision-making and ultimately in safety. During protocol operations at the VTS, these factors influenced how VTSOs judged the skills of the vessels’ bridge teams, and how they approached them. This is a time where much effort is being put into upgrading technological systems, and these will have the power to change the ways in which the maritime network obtains and processes information, as well as how they can communicate with each other. The further development of technological systems, work protocols and training programmes can benefit from taking the soft aspects of communication and the needs of the operators and their tasks into account for the enhancement of safety.     

A wireless sensor networks MAC protocol for real-time applications

Wireless sensor networks (WSN) are designed for data gathering and processing, with particular requirements: low hardware complexity, low energy consumption, special traffic pattern support, scalability, and in some cases, real-time operation. In this paper we present the virtual TDMA for sensors (VTS) MAC protocol, which intends to support the previous features, focusing particularly on real-time operation. VTS adaptively creates a TDMA arrangement with a number of timeslots equal to the actual number of nodes in range. Thus, VTS achieves an optimal throughput performance compared to TDMA protocols with fixed size of frame. The frame is set up and maintained by a distributed procedure, which allows sensors to asynchronously join and leave the frame. In addition, duty cycle is increased or decreased in order to keep latency constant below a given deadline. Therefore, a major advantage of VTS is that it guarantees a bounded latency, which allows soft real-time applications.

Boosting learning-by-teaching in virtual tutoring

Research has shown that students tend to engage in quality learning when they are asked to teach (i.e., learning-by-teaching). In this study, a web-based tutoring environment has been developed to enhance the learning of college students by their teaching others: the Virtual Tutee System (VTS). In the VTS, students take the role of tutor and teach a virtual character about what they learn from readings. The design of the VTS has been refined through several iterations of formative evaluation. The current study explored whether the recent improvements made in the VTS augmented the learning-by-teaching effects. The VTS was evaluated with regard to its' effects on students' reading engagement and reading performance. Results indicated that students were behaviorally and cognitively engaged in reading with use of the VTS. Also, the study found a significant improvement in students' emotional engagement in reading after using the VTS. Limited support was found for enhancement of reading performance with repeated use of the VTS. Implications of the study findings are discussed, and suggestions for future research are provided.     

面向QoS保障的虚拟可信服务*

针对服务计算模型中对应用的可信特性支持不足问题,提出面向QoS保障的虚拟可信服务VTS,并依据VTS设计了一种基于反馈控制的自适应QoS保障机制。首先将VTS的QoS保障转换为反馈控制问题,给出一种自适应QoS保障框架,再在此框架下对VTS的QoS维护过程和策略进行建模,设计和实现了相应的动态组建、调节算法和实时评估策略。最后通过仿真实验的结果分析表明,该保障机制能够有效地增强VTS对服务实体运行时的QoS保障能力。     

Discriminative classifiers with adaptive kernels for noise robust speech recognition

Discriminative classifiers are a popular approach to solving classification problems. However, one of the problems with these approaches, in particular kernel based classifiers such as support vector machines (SVMs), is that they are hard to adapt to mismatches between the training and test data. This paper describes a scheme for overcoming this problem for speech recognition in noise by adapting the kernel rather than the SVM decision boundary. Generative kernels, defined using generative models, are one type of kernel that allows SVMs to handle sequence data. By compensating the parameters of the generative models for each noise condition noise-specific generative kernels can be obtained. These can be used to train a noise-independent SVM on a range of noise conditions, which can then be used with a test-set noise kernel for classification. The noise-specific kernels used in this paper are based on Vector Taylor Series (VTS) model-based compensation. VTS allows all the model parameters to be compensated and the background noise to be estimated in a maximum likelihood fashion. A brief discussion of VTS, and the optimisation of the mismatch function representing the impact of noise on the clean speech, is also included. Experiments using these VTS-based test-set noise kernels were run on the AURORA 2 continuous digit task. The proposed SVM rescoring scheme yields large gains in performance over the VTS compensated models.     

The case for virtual teaming systems

Virtual teaming systems (VTS) can provide your organization with new capabilities that will enhance its competitiveness. Our company, Ventana Corp., markets GroupSystems, the first virtual teaming system. The ideas behind GroupSystems came from years of rigorous academic research into the ways people collaborate. A VTS applies computing technology to team work, using automation to accelerate collaborative thinking, consensus building, decision making, and planning. It also provides the seed for a knowledge base of organizational expertise     

Prediction of manually controlled vessels’ position and course navigating in narrow waterways using Artificial Neural Networks

Despite modern navigation devices, there are still some problems for navigating of vessels in narrow waterways because of geographical structures and various disturbances. In this study, a guidance and an early warning method by means of predicting three-minute-ahead position of a vessel, especially in the turning points, has been developed for navigating in narrow waterways. The Istanbul Strait has been specifically studied as a model. Since operators in Vessel Traffic Services (VTS) can watch only straight bearing of vessels on VTS panels but especially for turning regions, they have to foresee a risk on time which may result in a disaster. The objective of this study is to predict the future coordinates of a manually controlled vessel using Artificial Neural Networks (ANN).Artificial Neural Networks have been trained by using position and speed data collected from vessels which navigated manually in the Strait. Three-minute-ahead position of vessels has been predicted by using the trained ANN. Some on-line experiments have been done in Istanbul VTS centre and it has been observed that the method satisfied the goal in especially turning points of the Strait. Hence the proposed method could be utilized for warning system by VTS operators and guidance system by vessel crew.     

Challenges of developing the complex socio-technical system: realising the present, acknowledging the past, and envisaging the future of vessel traffic services

This paper raises the question of how to guide the development of an emerging complex socio-technical system. The empirical basis for the discussion is a study of Vessel Traffic Services (VTS). We analysed the current state and the history of the service in Finland in four studies and identified several development needs. The results showed that there are differences between the outcome, practices and conceptions of the core task across different experts in the VTS centres, which can be explained by the current state of the constituents and the history of the activity system. Qualitatively different development phases characterised either by a top-down standardisation or bottom-up construction process were recognised. A combination of these processes was suggested for the future development strategy of the VTS. This could allow both continuous development within VTS and recognition of the need for a new system. A promising way to achieve continuous development is by creating reflective practices supported for instance with annual simulator exercises aimed at procedure development. We conclude that solving the current problems and promoting the development of the complex system call for a dynamic, open vision of the target future of the system, in which the pressures from the social, political and technological environments are taken into account. The results of ergonomics studies can help in self-reflecting, envisaging and developing supportive methods for the system but the persons within the system create the will to develop and find their way towards the development horizon.     

Panel Summaries: Real-Time Volume Diagnostics--Requirements and Challenges

A report on the IEEE VLSI Test Symposium (VTS 06) panel on "Real-time volume diagnostics: requirements and challenges.     

Trajectory based abnormal event detection in video traffic surveillance using general potential data field with spectral clustering

Detection of abnormal trajectories in a traffic scene is an important problem in Video Traffic Surveillance (VTS). Recently, General Potential Data Field (GPDf)-based trajectory clustering scheme has been adopted for detecting abnormal events such as illegal U-turn, wrong side and unusual driving behaviors and it uses spatial and temporal attributes explicitly. The concept of data field is used to discover the relation between the spatial points in data-space and grouping them into clusters based on their mutual interaction. Existing methodologies related to potential data field-based clustering have certain limitations such as pre-defined cluster size, non-effective cluster center identification, and limitation in range estimation using isotropic impact factor (h) which leads to inaccurate results. In order to address the above-mentioned issues, this paper proposes an efficient anomaly detection scheme based on General Potential Data field with Spectral Clustering (GPDfSC). The proposed GPDfSC scheme utilizes potential data field technique along with spectral clustering for effective identification of abnormalities. The Limitation in impact factor(h) is overcome by using anisotropic impact parameter Bmat. Further, Bayesian Decision theory is used to classify the events as normal or abnormal. The proposed scheme is implemented in real time using GPU and from the results it is found that it gives 12% better accuracy in detecting abnormalities than the state of art technique.

     

Establishing the Usability of a Virtual Training System for Assembly Operations within the Automotive Industry

Virtual training systems deliver training within a virtual environment (VE) using virtual reality (VR) or augmented reality (AR) technologies. However, to be fully accepted as a valid tool for training within the automotive industry, evidence is required on the ability of these systems to deliver effective and efficient training to the relevant users. This paper aims to investigate the effectiveness and efficiency of the first prototype of the virtual training system (VTS) developed within the VISTRA (Virtual Simulation and Training of Assembly and Service Processes in Digital Factories) project (FP7‐ICT‐285176), using real end users from the OPEL automotive plant in Rüsselsheim, Germany. Two separate and independent studies were employed that used objective and subjective methods of investigation to establish performance and usability measures. The objective results show that virtual training was effective in reducing error during task performance when compared to traditional training. The subjective results concluded that the opinions of the participants were mainly positive concerning the overall use of the VTS for assembly operation training; however, a number of issues were highlighted and reported to the developers for further advancement of the system.     

Multi-environment model adaptation based on vector Taylor series for robust speech recognition

In this paper, we propose a multi-environment model adaptation method based on vector Taylor series (VTS) for robust speech recognition. In the training phase, the clean speech is contaminated with noise at different signal-to-noise ratio (SNR) levels to produce several types of noisy training speech and each type is used to obtain a noisy hidden Markov model (HMM) set. In the recognition phase, the HMM set which best matches the testing environment is selected, and further adjusted to reduce the environmental mismatch by the VTS-based model adaptation method. In the proposed method, the VTS approximation based on noisy training speech is given and the testing noise parameters are estimated from the noisy testing speech using the expectation-maximization (EM) algorithm. The experimental results indicate that the proposed multi-environment model adaptation method can significantly improve the performance of speech recognizers and outperforms the traditional model adaptation method and the linear regression-based multi-environment method.     

Towards the development of a virtual environment-based training system for mechanical assembly operations

In this paper, we discuss the development of Virtual Training Studio (VTS), a virtual environment-based training system that allows training supervisors to create training instructions and allows trainees to learn assembly operations in a virtual environment. Our system is mainly focused on the cognitive side of training so that trainees can learn to recognize parts, remember assembly sequences, and correctly orient the parts during assembly operations. Our system enables users to train using the following three training modes: (1) Interactive Simulation, (2) 3D Animation, and (3) Video. Implementing these training modes required us to develop several new system features. This paper presents an overview of the VTS system and describes a few main features of the system. We also report user test results that show how people train using our system. The user test results indicate that the system is able to support a wide variety of training preferences and works well to support training for assembly operations.

---

Weighted Piecewise LDA for Solving the Small Sample Size Problem in Face Verification

A novel algorithm that can be used to boost the performance of face-verification methods that utilize Fisher's criterion is presented and evaluated. The algorithm is applied to similarity, or matching error, data and provides a general solution for overcoming the "small sample size" (SSS) problem, where the lack of sufficient training samples causes improper estimation of a linear separation hyperplane between the classes. Two independent phases constitute the proposed method. Initially, a set of weighted piecewise discriminant hyperplanes are used in order to provide a more accurate discriminant decision than the one produced by the traditional linear discriminant analysis (LDA) methodology. The expected classification ability of this method is investigated throughout a series of simulations. The second phase defines proper combinations for person-specific similarity scores and describes an outlier removal process that further enhances the classification ability. The proposed technique has been tested on the M2VTS and XM2VTS frontal face databases. Experimental results indicate that the proposed framework greatly improves the face-verification performance     

M2DPCA与CCLDA相结合的人脸识别

CCLDA算法将图像矩阵转化为向量进行处理,该算法易造成数据维数很大,计算量复杂并容易出现“小样本”等问题。针对以上这些问题,提出了一种基于模块化2DPCA和CCLDA相结合的协同处理方法并应用于人脸识别领域。并且在ORL和XM2VTS人脸库上的实验结果表明,新方法在识别效果上有比以往的算法更为明显的优势。     

Feature-based affine-Invariant localization of faces

We present a novel method for localizing faces in person identification scenarios. Such scenarios involve high resolution images of frontal faces. The proposed algorithm does not require color, copes well in cluttered backgrounds, and accurately localizes faces including eye centers. An extensive analysis and a performance evaluation on the XM2VTS database and on the realistic BioID and BANCA face databases is presented. We show that the algorithm has precision superior to reference methods.     

局部非参数子空间分析在人脸识别中的应用

提出了一种局部非参数子空间分析算法（Local Nonparametric Subspace Analysis,LNSA）,将其应用在人脸识别中。LNSA算法结合了非参数子空间算法（Nonparametric Subspace Analysis,NSA）与局部保留投影算法（Locality Preserving Projection,LPP）。它利用LPP算法中的相似度矩阵重构NSA的类内散度矩阵,使得在最大化类间散度矩阵的同时保留了类的局部结构。在ORL人脸库和XM2VTS人脸库上作了实验并证明LNSA方法要优于其他方法。