scispace - formally typeset
Search or ask a question

Showing papers presented at "International Conference on Service Operations and Logistics, and Informatics in 2014"


Proceedings ArticleDOI
08 Oct 2014
TL;DR: In this article, the authors discussed the current market practice of RTB advertising, presented the key roles and typical business processes in RTB markets, and summarized the current research progresses in the existing literature.
Abstract: Real-time bidding (RTB) is an emerging and promising business model for online computational advertising in the age of big data. Based on analysis of massive amounts of Cookie data generated by Internet users, RTB advertising has the potential of identifying in real-time the characteristic and interest of the target audience in each ad impression, automatically delivering best-matched ads, and optimizing their prices via auction-based programmatic buying scheme. RTB has significantly changed online advertising, evolving from the traditional pattern of "media buying" and "ad-slot buying" to "targetaudience buying", and is expected to be the standard business model for online advertising in the future. In this paper, we discussed the current market practice of RTB advertising, presented the key roles and typical business processes in RTB markets, and summarized the current research progresses in the existing literature. The aim of this paper is to provide useful reference and guidance for future works.

97 citations


Proceedings ArticleDOI
17 Nov 2014
TL;DR: In this paper, the authors study how social manufacturing can redefine the entire value chain of the apparel industry through the help of 3D printing and propose a new phenomenon called social manufacturing.
Abstract: Rapid development in mobile technologies, 3D printing and social networks has paved the way for the new phenomenon called Social manufacturing. Social manufacturing represents a paradigm shift in traditional manufacturing models; in social manufacturing, the role of customers changes from being passive to being fully active agents in the manufacturing of products. This shift allows for the opportunity to produce customized products according to the needs of every single customer in the society. The demand of consumers in the apparel industry is rapidly changing to becoming more personalized. Consequently, social manufacturing can dramatically contribute to customization in the apparel industry through the help of 3D printing. In this paper, we study how social manufacturing can redefine the entire value chain of the apparel industry

36 citations


Proceedings ArticleDOI
20 Nov 2014
TL;DR: A social sensing data analysis framework in cloud for smarter cities, especially to support smart mobility, as a case study, Mobility Analyzer, a subsystem of IRMA (Integrated Real-time Mobility Assistant), that is a pilot project of Pavia, Italy, is implemented.
Abstract: One emerging and challenging issue in Smarter Cities is Mobility. In order to gather mobility data for relevant analyses, two solutions are widely discussed, namely the conventional standardized infrastructure sensors and the novel social sensing solution. However infrastructure sensors solution is too costly, that is unfeasible for every city. On the contrast, social sensing is a renewal approach, by which people perform “sensory data” collection tasks. In order to widely conduct the second solution and meet various needs of cities, it requires the ability to 1) support various social data sources, 2) be scalable, customizable and configurable, and 3) use cost-efficient IT resources. However current research cannot overcome these challenges. Therefore, this paper presents a social sensing data analysis framework in cloud for smarter cities, especially to support smart mobility. As a case study, Mobility Analyzer, a subsystem of IRMA (Integrated Real-time Mobility Assistant, that is a pilot project of Pavia, Italy), is implemented. Keywords—Social sensing, Smarter Cities, Social data analysis framework, Smart Mobility, Cloud computing

22 citations


Proceedings ArticleDOI
Gianmario Motta1, Linlin You1, Daniele Sacco1, Tianyi Ma1, Giovanni Miceli1 
20 Nov 2014
TL;DR: A framework for the design of business services, called Service System (SS), is discussed, a layer built on the top of Internet of Things (IoT) and Internet of Services (IOS).
Abstract: This paper discusses a framework for the design of business services, called Service System (SS). SSs are a layer built on the top of Internet of Things (IoT) and Internet of Services (IOS). SSs integrate two components, Internet of Business (IOB) and Internet of Data (IOD). IOB delivers complex business services that combine services from IOS and IOT. In turn, IOD links semantically the information that is extracted from IOS and IOT and that is processed in IOB; also, it provides a repository for future applications. The association of SS architecture with Open Source drives a twofold roadmap, with a top down design and a bottom implementation. The SS concept is exemplified on a IRMA, namely a project on urban mobility, with pilot cities in Europe and China, where a demo SS is being developed by using Open Source software.

17 citations


Proceedings ArticleDOI
20 Nov 2014
TL;DR: In this paper, the authors explored the impact of supply chain collaboration through devising a conceptualized model and using questionnaire data to test the hypothetical models and found that both supply chain collaborations and collaborative innovation capability are positively associated with eco-innovation while the latter one mediates the effect of the former one.
Abstract: The facilitating impact of supply chain collaboration on enterprise eco-innovation has been acknowledged both in practice and academia. This study aims to explore the impact of supply chain collaboration through devising a conceptualized model and using questionnaire data to test the hypothetical models. The results reveals that both supply chain collaboration and collaborative innovation capability are positively associated with eco-innovation while the latter one mediates the effect of the former one; internal RD the mediation effect of collaborative innovation capability is moderated by internal R&D with lower internal R&D group of enterprises indicating higher dependence on the mediation instrument.

17 citations


Proceedings ArticleDOI
20 Nov 2014
TL;DR: A multi-hop announcement scheme for VANETs which supports message broadcasting and forwarding, and two algorithms to evaluate the reliability of messages and aggregate the reputation scores respectively are proposed.
Abstract: Vehicular ad hoc networks (VANETs) allow vehicles to generate and broadcast messages to inform nearby vehicles about road conditions. We propose a multi-hop announcement scheme for VANETs which supports message broadcasting and forwarding. In this scheme, we propose two algorithms to evaluate the reliability of messages and aggregate the reputation scores respectively. The major principle of the reliability evaluation algorithm is Dempster-Shafter Theory and the reputation aggregation algorithm is a variant of weighted averaging function. To balance the message coverage area and the cost of forwarding messages, we also provide a message forwarding criterion. The proposed multi-hop scheme offers satisfactory robustness and preserves privacy property. Most importantly, the multi-hop scheme not only guarantees better message flexibility, but also can generate more satisfactory message drop rate. In addition, in the message forward criterion of our multi-hop scheme, it is up to vehicles (i.e., user friendly) to regulate the trade-off between the message utility rate and the maximal message broadcasting bandwidth, based on their real needs.

13 citations


Proceedings ArticleDOI
20 Nov 2014
TL;DR: In this paper, an effective method for automatic license plate recognition (ALPR) is proposed, on the basis of extreme learning machine (ELM), where morphological Top-Hat filtering operator is applied to do the image pre-processing.
Abstract: In this paper, an effective method for automatic license plate recognition (ALPR) is proposed, on the basis of extreme learning machine (ELM). Firstly, morphological Top-Hat filtering operator is applied to do the image pre-processing. Then candidate character regions are extracted by means of maximally stable extremal region (MSER) detector. Thirdly, most of the noise character regions are removed according to the geometrical relationship of characters in standard license plates. Finally, the histograms of oriented gradients (HOG) features are extracted from each character of every plate detected and the characters are recognized by the classifier trained though the ELM. Experimental evaluation shows that our approach significantly performs well in the ALPR systems.

11 citations


Proceedings ArticleDOI
01 Oct 2014
TL;DR: A cooperative system which offer drivers the ability to manage their consumption and driving style, suggesting corrections to the behavior usually adopted is presented, based also on crowdsourcing of the specific vehicle consumption performances.
Abstract: The European Commission has recently promoted research programs aimed at finding solutions to the ever more compelling problem of air pollution from road vehicles and has also indicated among the possible impacts of cooperative Intelligent transportation a better sustainability, by cutting down pollutant emissions and reducing consumptions. In fact many practical solutions will develop that allow drivers and managements to optimize resources and to contain costs and the emissions of pollutants by applying communication systems between vehicles (V2V) and between vehicles and infrastructure (V2I). Along this mainstream this paper present a cooperative system which offer drivers the ability to manage their consumption and driving style, suggesting corrections to the behavior usually adopted. The new contribution of this paper is the cooperative approach between drivers to achieve a common goal of a better common energy consumption strategy. Since the fuel consumption has to be evaluated with regards to the specific vehicle type the system is based also on crowdsourcing of the specific vehicle consumption performances. The paper describes a system that gathers data on fuel consumption from the cooperating drivers that by can build together the data set necessary to the system itself and accept this new paradigm: crowd sourced cooperation for a better world.

11 citations


Proceedings ArticleDOI
Li Bowen1, Yao Danya1
01 Oct 2014
TL;DR: A method to calculate the vehicle real-time position overcoming the GPS positioning latency with low-cost MEMS (Micro-Electro-Mechanical System) INS (Inertial Navigation System) to reduce the error caused by the GPS latency is presented.
Abstract: GPS (Global Positioning System) always has the problem of positioning latency which make it can't output the real-time position. Different GPS may have different latencies. The positioning latency of consumer-grade GPS often used in vehicles is especially relatively larger. In this paper, we present a method to calculate the vehicle real-time position overcoming the GPS positioning latency with low-cost MEMS (Micro-Electro-Mechanical System) INS (Inertial Navigation System). We compute the latency through comparing the degree of correlation between the velocity difference time series obtained from the GPS output and the acceleration time series outputted by the accelerometer. Then fuse the GPS/INS data according to the latency in order to improve accuracy for the position that has been outputted by the GPS, and estimate the vehicle real-time with the acceleration time series outputted in the latency. At last, a neural network is established to correct the estimated position to reduce the error. Meanwhile, a GPS/INS data synchronization method is presented for the GPS which can't output 1 pps (Pulse Per Second) signal. The experimental results show the methods can calculate the accurate vehicle real-time eliminating the positioning error caused by the GPS latency. The methods achieve a good effect.

11 citations


Proceedings ArticleDOI
20 Nov 2014
TL;DR: In this article, the authors proposed a profit-maximizing auction mechanism for the use of the UCC's last-mile delivery service, which addresses the challenge that many shippers/carriers plan their deliveries many weeks ahead, and simultaneously allows last-minute bidders to compete for the resources.
Abstract: A number of cities around the world have adopted urban consolidation centres (UCCs) to address some challenges of their last-mile deliveries. At the UCC, goods are consolidated based on their destinations prior to their deliveries into the city centre. In many examples, the UCC owns a fleet of eco-friendly vehicles to carry out the deliveries. A carrier/shipper who buys the UCC’s service hence no longer needs to enter the city centre in which time-window and vehicle-type restrictions may apply. As a result, it becomes possible to retain the use of large trucks for the economies of scale outside the city centre. Furthermore, time which would otherwise be spent in the city centre can then be used to deliver more orders. With possibly tighter regulation and thinning profit margin in near future, requests for the use of the UCC’s service shall become more and more common. In [1], the authors proposed a profit-maximizing auction mechanism for the use of the UCC’s last-mile delivery service. In this paper, we extend that work with the idea of a rolling horizon to give bidders greater flexibility in competing for the UCC’s resources in advance. In particular, it addresses the challenge that many shippers/carriers plan their deliveries many weeks ahead, and simultaneously allows last-minute bidders to compete for the UCC’s resources.

10 citations


Proceedings ArticleDOI
20 Nov 2014
TL;DR: In this article, a methodology for the identification of road anomalies through the coupled measurements of vertical acceleration and sound pressure levels is presented, which is based on a commercially available instrumentation possessed by most drivers.
Abstract: This article show a methodology for the identification of road anomalies through the coupled measurements of vertical acceleration and sound pressure levels. The innovative solution of this methodology lays in the possibility to evaluate road anomalies by using the time derivative of acceleration and sound pressure. Furthermore, this methodology has been developed and validated using a commercially available instrumentation possessed by most drivers, such as, smartphones and tablets. The current smartphone devices, in fact, are equipped with GPS, gyroscope and microphone that allow to simultaneously record data relating to geolocation, acceleration and sound pressure. The widespread distribution of this equipment could allow local administration to acquire a large number of surveys carried out by normal drivers and build a large Data Base on road anomalies representative of a whole network of infrastructures with a very small cost. Finally, the application of the methodology overturns current monitoring policies of road infrastructure that can be carried out only by the management staff by crowdsourcing the DB system with continuous real time updates brought by normal road users.

Proceedings ArticleDOI
01 Oct 2014
TL;DR: Using a real-world example of a process in a company's warehouse, the potential facilitated by Future-Internet-based logistics control towers is presented by evaluating the usefulness of the solution with regard to the potential of a more resource-efficient configuration of business processes.
Abstract: Lacking available information and missing integration of existing IT solutions between the planning level and the execution level are major reasons for many enterprises from the transportation and logistics failing to realize an optimal setup of process executions. Future-Internet-based logistics control towers promise a viable solution to such problems. With the help of such control towers, the problem is to be addressed. Using a real-world example of a process in a company's warehouse, the present paper presents the potential facilitated by Future-Internet-based logistics control towers by evaluating the usefulness of the solution with regard to the potential of a more resource-efficient configuration of business processes.

Proceedings ArticleDOI
20 Nov 2014
TL;DR: A methodology for identifying vehicle speed by obtaining a sparse optical flow from image sequences by utilizing Lucas-Kanade method for optical flow calculation and RANSAC algorithm is introduced to optimize the matched corners.
Abstract: It has great significance to acquire vehicle speed for active safety system. This paper presents a methodology for identifying vehicle speed by obtaining a sparse optical flow from image sequences. Distinct corners can be detected by Harris corner detector after image enhancement. Then, Lucas-Kanade method for optical flow calculation is utilized to match the sparse feature set of one frame on the consecutive frame. In order to the accuracy of optical flow, RANSAC algorithm is introduced to optimize the matched corners. Finally, the vehicle speed can be determined by averaging all the speeds estimated by every optimized matched corner. The results of field test indicated that the computation time of the developed method to execute for one time was 59ms, and the mean error of speed estimation relative to the measurement of GPS was 0.121 m/s. The developed method can achieve satisfying performance, such as accuracy and output frequency.

Proceedings ArticleDOI
20 Nov 2014
TL;DR: Based on the closed-loop supply chain system of an automobile manufacturer and a retailer, the differential pricing model and revenue sharing contract model of the participating enterprises in vehicle closed loop supply chain are analyzed in this paper.
Abstract: Based on the closed-loop supply chain system of an automobile manufacturer and a retailer, the differential pricing model and revenue sharing contract model of the participating enterprises in vehicle closed-loop supply chain are analyzed. The double marginalization is found in the decentralized decision mode through the comparative analysis of differential pricing in centralized and decentralized decision modes. Moreover, revenue sharing contract is used to coordinate the differential pricing decisions in closed-loop supply chain. The validity of the model is proven with numerical example.

Proceedings ArticleDOI
Rong Liu1, Qicheng Li1, Feng Li1, Lijun Mei1, Juhnyoung Lee1 
20 Nov 2014
TL;DR: A new analysis architecture using Big Data techniques is proposed that leverages stream computing and MapReduce techniques to analyze data from various data sources, uses NoSQL databases to store incident-related documents and their relationships, and further utilizes other analytical techniques to examine the documents for root causes and failure prediction.
Abstract: IT incident management aims to restore normal service quality and availability of IT systems from interruptions. IT incidents often have complicated causes aggregated from an IT environment composed of thousands of interdependent components. Incident diagnosis then requires collecting and analyzing a large scale of data regarding these components, often, in real time to find suspect causes. It is extremely difficult to fulfill this requirement using traditional techniques. In this paper, we propose a new analysis architecture using Big Data techniques. This architecture leverages stream computing and MapReduce techniques to analyze data from various data sources, uses NoSQL databases to store incident-related documents and their relationships, and further utilizes other analytical techniques to examine the documents for root causes and failure prediction. We demonstrate this approach using a real-world example and present evaluation results from a recent pilot study.

Proceedings ArticleDOI
20 Nov 2014
TL;DR: This paper model the general version of an autonomous vehicle sequencing problem as a single machine scheduling problem in which jobs can be processed in parallel and shows that this problem is strongly NP-hard for arbitrary number of families.
Abstract: In this paper, we study the complexity of an autonomous vehicle sequencing problem under the framework of Autonomous Intersection Management (AIM) Since the objective is to schedule all approaching vehicles to pass this intersection in the shortest duration, we model the general version of this problem as a single machine scheduling problem in which jobs can be processed in parallel Release date and chain constraint are also considered We show that this problem is strongly NP-hard for number of families is the perma­ nent growth of population in a relatively small area The consequence of this fact is the increase in the number of vehicles and pedestrians This gives more and more pressure and difficulty to the traffic control, whose aim is to ensure the safety and improve the efficiency of traffic movement at same time The conventional traffic control method is by using traffic signals, and it generally falls into two basic categories: pre-timed control strategy, which is also called the fixed-time control, and the semi/fully traffic actuated control Both strategies are usually based on the estimation of traffic flow rates Since the flow rate is a continuous variable that needs a period of time to be estimated, there are always big deviations between the last computed flow rate and the actual one

Proceedings ArticleDOI
20 Nov 2014
TL;DR: A vehicle classification system based on dynamic Bayesian network (DBN) that classify a vehicle into one of four classes: sedan, bus, microbus, and unknown is introduced.
Abstract: Vehicle classification system is an important part of intelligent transportation system (ITS), which can provide us the necessary information for autonomous navigation, toll systems, surveillance and security systems, and transport planning. In this paper, we introduce a vehicle classification system based on dynamic Bayesian network (DBN). Three main types of features are employed in our system: the geometrical characteristic of the vehicle, the location and shape of license plate, and the vehicle pose. Firstly, vehicle detection and tracking method are used to locate the vehicle. Then, we extract the features from video sequences. Gaussian Mixture Model (GMM) is used to construct the probability distribution of the feature. Finally, we classify a vehicle into one of four classes: sedan, bus, microbus, and unknown. The experiment shows the proposed method can achieve classification exactly and credibly.

Proceedings ArticleDOI
20 Nov 2014
TL;DR: The paper is devoted to the problem that estimates the vehicle position in real world using only a single 2D image, and proposes a solution that calculates the position with sufficient accuracy through incorporating the geometric constants in the traffic scene.
Abstract: Determination of the correct positional relation is vital for human driver For unmanned vehicles, the obstacle position in front of the view is also necessary for collision detection The paper is devoted to the problem that estimates the vehicle position in real world using only a single 2D image The estimation is an ill-posed problem due to the projective transform; however, through incorporating the geometric constants in the traffic scene, we proposed a solution that calculates the position with sufficient accuracy The contribution of the proposed method is the use of two geometric constants: the standard size of license plate and the lane-width Observation shows that the size of license plates has limited patterns and lane-width between two adjacent lanes is usually constant Introduction of the two constants compensates the uncertainty caused by lack of depth in the mapping between the detected license plates and its position in real world The conducted experiments show that compared to the conventional methods, the proposed one is accurate for estimating the position

Proceedings ArticleDOI
Xin Zhou1, Feng Li1, Yabin Dang1, Hao Chen1, Shao Chun Li1, Guangtai Liang1 
20 Nov 2014
TL;DR: This paper proposes and implements a collaborative change impact analysis approach which effectively coordinates involvements and incorporates insights of relevant SMEs and shows the effectiveness of the proposed approach on real enterprise applications.
Abstract: Change impact analysis is increasingly challenging for enterprise applications due to that applications in an enterprise portfolio usually heavily depend on each other and also grow rapidly in both of scale and complexity. Automatic impact analysis based on intra- and inter-application dependencies implies potential impact propagation directions. However, due to the variety and complexity of dependencies, determining real impacts is intelligence intensive and usually needs interventions of Subject Matter Experts (SMEs) on each involved application. In this paper, to enable a more agile enterprise application evolution, we propose and implement a collaborative change impact analysis approach which effectively coordinates involvements and incorporates insights of relevant SMEs. In the approach, we first construct an initial collaborative change impact analysis roadmap based on application dependencies. Then, we iteratively invite and coordinate relevant SMEs based on the roadmap, and then leverage their insights to dynamically refine the roadmap. The evaluations on real enterprise applications show the effectiveness of our proposed approach.

Proceedings ArticleDOI
20 Nov 2014
TL;DR: The exponential function of I - V characteristic equation based on Chebyshev Polynomials is expressed and an explicit analytical description for two-diode model of photovoltaic modules is obtained according to the given accuracy.
Abstract: In this paper, we propose a new modeling method for two-diode model of photovoltaic modules. The I–V characteristic equation for two-diode model is implicit and nonlinear, so this paper expresses the exponential function of I – V characteristic equation based on Chebyshev Polynomials and we can obtain an explicit analytical description for two-diode model according to the given accuracy. And then two new five-parameter models based on Chebyshev Polynomials are presented. We can use the two proposed five-parameter model to the obtain the values of the cell parameters only by using manufacturers' data and the given accuracy. To validate the proposed I–V modeling method, we test the I – V characteristic of Siemens SP-75 PV module. The results show it is an easy, fast, accurate method to obtain the I – V characteristic for two-diode model of solar cells.

Proceedings ArticleDOI
20 Nov 2014
TL;DR: The method is proposed based on the survey that it is an essential way to take full advantages of accidents information to enhance process safety management and the key functions of PSMS are detailed and the needs for accident database are demanded.
Abstract: To fulfil the objective of changing “accident handling, postmortem prevention” to “intrinsic safety, advance prevention” in chemical industry, this paper covers research to develop a process safety management system (PSMS). First of all, the method is proposed based on the survey, which pointed that it is an essential way to take full advantages of accidents information to enhance process safety management. Secondly, the key functions of PSMS are detailed and the needs for accident database are demanded. The defects of chemical database existing were concluded through literature review. Thirdly, the outline design of PSMS chemical accident database is presented. The work can provide some theoretical and practical reference for the study and development of the process safety management system.

Proceedings ArticleDOI
20 Nov 2014
TL;DR: The introduction of the particle filters improves the proposed method greatly to handle the dynamic and uncertainty of the system and validate this method can be applied on the route travel time prediction of a dynamic traffic flow.
Abstract: Focusing on the dynamic travel time prediction for the intelligent transportation system (ITS), this paper proposes a new prediction method by introducing the particle filters algorithm. Based on the interval velocity measurement system, various traffic parameters of the highway are obtained, and a state model with these associated parameters is built for the travel time estimation. Then, the probability distribution of the system state is simulated by a set of particles according to Bayesian theory. The distribution of these particles is updated real-time based on the state transition model and re-sampling method at last. The estimated travel time is given based on the predicted system state distribution. The proposed method learns the system state transition model based on the history data derived from the interval velocity measurement system. And the introduction of the particle filters improves the proposed method greatly to handle the dynamic and uncertainty of the system. Simulation experiments are taken on the traffic data from the detection sensors on several road sections. The results show that the proposed method has much better prediction performance than some traditional methods, and validate this method can be applied on the route travel time prediction of a dynamic traffic flow.

Proceedings ArticleDOI
01 Oct 2014
TL;DR: Wang et al. as mentioned in this paper presented a hybrid method using period refinement scheme and adaptive strategy for building peak hour period and off-peak hour period models in day-of-week for one-day-ahead for load forecasting.
Abstract: Electrical load forecasting is vitally important to modern power system planning, operation, and control. In this paper, by focusing on historical load data and calendar factors, we present a hybrid method using period refinement scheme and adaptive strategy for building peak hour period and off-peak hour period models in day-of-week for one-day-ahead for load forecasting. They are evaluated using three full years of Shenzhen city electricity load data. Experimental results shows the adaptive model for each period, confirm good accuracy of the proposed approach to load forecasting and indicate that it has better forecasting accuracy than traditional ANN method.

Proceedings ArticleDOI
20 Nov 2014
TL;DR: The results demonstrate the efficiency and feasibility of the MPC signal control method, which can take all the operational constraints into consideration easily and can also be applied for other infrastructure systems whose characteristics are common intelligent, from a generic point of view.
Abstract: In this paper, we consider the problem of designing traffic network signal control systems for congested urban road networks, aiming to relieve traffic congestion and improve the utilization of the existing traffic infrastructures. A Model Predictive Control (MPC) method is introduced which is based on a microscopic store-and-forward modeling (SFM) paradigm. Moreover, a preliminary simulation of urban traffic flow management is implemented with the help of MATLAB/SIMULINK and PARAMICS. The results demonstrate the efficiency and feasibility of the MPC signal control method, which can take all the operational constraints into consideration easily. And the MPC control framework can also be applied for other infrastructure systems whose characteristics are common intelligent, from a generic point of view.

Proceedings ArticleDOI
Lijun Mei1, Qicheng Li1, Rangachari Anand1, Juhnyoung Lee1, Feng Li1, Shao Chun Li1 
01 Oct 2014
TL;DR: A service-orientation is provided for Dialog Manager, aiming to enable customized service-based knowledge applications to empower the usage of dialog and enable subject matter expert to specify the external services to make good use of user dialog data to facilitate ticket issuing and resolution.
Abstract: The Dialog Manager is a conversational web-based tool that helps organizations manage procedural knowledge. A dialog is a visual knowledge representation of certain procedural knowledge enriched with interactive guides. To empower the usage of dialog, we further provide a service-orientation for Dialog Manager, aiming to enable customized service-based knowledge applications. Such service-orientation will enable a user to select services to answer questions from dialog automatically during runtime. It will also enable the subject matter expert (SME) to specify the external services to make good use of user dialog data to facilitate ticket issuing and resolution. Through a case study, we will demonstrate the great business impact of our proposal.

Proceedings ArticleDOI
20 Nov 2014
TL;DR: This paper investigates the opportunities and comes up with the design of a cross-border parcel handling infrastructure and the implementation of the tracking and tracing system shows the increased visibility during international e-commerce activities.
Abstract: In 2013, as a platform with the 22 largest postal companies in the world, the International Post Corporation has launched the e-Commerce Interconnected Programme (CIP) to setup a new cross-border electronic commerce infrastructure. The CIP aims to help international postal operators to provide more reliable services and operations with respect to more accurately and in-time tracking and tracing postal parcels. This paper investigates the opportunities and comes up with the design of a cross-border parcel handling infrastructure. The low level infrastructure is implemented based on radio frequency identification technology for tracking parcels in international shipments. The high level infrastructure can be achieved via a generic information integration framework. The implementation of the tracking and tracing system shows the increased visibility during international e-commerce activities.

Proceedings ArticleDOI
20 Nov 2014
TL;DR: This paper proposes to use copula functions for specifying and calibrating a tractable dependence structure for link travel times, indicating that travel time data tend to have a quasi-tail dependence structure, which is inconsistent with those embedded in commonly used copulas.
Abstract: Statistical distributions of link and path travel times are important inputs to reliability-sensitive transportation models. This paper proposes to use copula functions for specifying and calibrating a tractable dependence structure for link travel times. Our empirical study indicates that travel time data tend to have a quasi-tail dependence structure, which is inconsistent with those embedded in commonly used copulas. This means that comparing with traditional fields using copula function, such as financial, traffic data demonstrate special features. A new copula function needs to be proposed to model this newly discovered feature.

Proceedings ArticleDOI
20 Nov 2014
TL;DR: The presented system is helpful to visualize production processes, to earlier detect potential problems, to quantitatively analyze various risks, and to verify management strategies by computational experiments, to optimize decisions by parallel execution.
Abstract: With the rapid progress of information and electronic technology, traditional industrial processes are becoming more and more complex. It is very important for manufacturing enterprises to manage and control the product quality under the circumstance of big data. Based on artificial systems, computational experiments, and parallel execution approach, modeling methods by mechanism, data, heuristic rules, etc. are proposed to construct intelligent management and control system for complex manufacturing processes. The presented system is helpful to visualize production processes, to earlier detect potential problems, to quantitatively analyze various risks, to verify management strategies by computational experiments, to optimize decisions by parallel execution.

Proceedings ArticleDOI
20 Nov 2014
TL;DR: A Two-Stage with Enhanced Samples (TSES) prediction framework that can balance the samples using Two- stage classification method and increase the number of sample to make it enough for obtaining an accurate model.
Abstract: Classification is one of the most significant methods in predictive analysis for categorical labeled problem. However, an accurate classification model is difficult to train for some real cases due to imbalanced samples, large fluctuating records, and overlapping class labels. For solving the above problems, in this work, we introduce a Two-Stage with Enhanced Samples (TSES) prediction framework that can balance the samples using Two-Stage classification method and increase the number of sample to make it enough for obtaining an accurate model. The proposed TSES achieves outstanding classification performance on a real case of rainfall prediction. For proving the effectiveness of TSES, we compare it with some traditional classification algorithms. The results show that it can be a promising method for the prediction problems with imbalanced data with overlapping labels.

Proceedings ArticleDOI
Zhen Wei1, Ya Nan Zhang2, Feng Jin2, Wenjun Yin2, Lin Wu 
20 Nov 2014
TL;DR: An innovative model to characterize users' standby power consumption by considering power data as continuous signal is proposed and results show that this method successfully separates standby power from the whole consumption dataset.
Abstract: Standby power consumption often takes place unnoticeably, the negligence of which often leads to intangible energy waste. Although there have been several studies related to this issue, no method has been developed to estimate the amount of power consumed this way by analyzing users' power consumption data. Therefore, this paper, based on findings of previous researches and users' power consumption data, proposes an innovative model to characterize users' standby power consumption. Firstly, by considering power data as continuous signal, standby power consumption is estimated by using frequency analysis and high frequency denoising model. Furthermore, Signal decomposition analysis has also been implemented as well as the conduction of rigorous mathematical derivation to get the average standby power based on thousands of power consumption data from Chinese users. Finally, results show that this method successfully separates standby power from the whole consumption dataset. Users are divided into four types based on the distribution of standby mode and nominal mode.