This work has presented a simulation platform to examine trading strategies and assess their profitability and risk exposure. The methodologies consist of evaluating risk measures such as annual return and maximum drawdown and analyzing the features of trading signals through an extensive amount of market data covering various market scenarios. The Heston model is proposed to simulate different markets that represent all possible cases of trends and fluctuations that will possibly occur in the future but may not be discovered in the historical data. The proposed simulation platform serves as an evaluation tool to select trading strategies under different markets.

The Smart Wealth Management Platform (SWMP) is an intelligent cloud-based system that aims to provide a unified wealth management service with smart risk-assessment and diversified products for institutional and retail investors in China and Hong Kong. An efficient computational architecture supports high performance data processing for financial analysis, huge amount of calculation for portfolio optimization and simulation, and know your customer (KYC) module based on behavioral finance. Leading market core technologies from big data, AI, financial engineering, and financial real time data analysis are cohesively integrated to form a dynamic platform with excellent user experience to support rationalized investment and deliver specialized consultancy.

In order to help track and disclose environmental performance across the textile and apparel supply chain, DLT is proposed as an ideal tool for information storage and communication in a highly transparent network. Every participant in the network can get access to the information for supply chain process, and eventually build a high level of trust on suppliers' environmental governance. This paper aims to bring out the potential of DLT technology on the textile and apparel supply chain. We discuss how to utilize the unique characteristics of DLT for achieving low carbon emissions during textile and apparel manufacturing through better supply chain transparency. In details, an overview of DLT technology is provided in this paper by showing the design, business implications and opportunities in the textile and apparel supply chain. In addition, a case study is illustrated on DLT technology in the textile and apparel supply chain transparency for World Wide Fund for Nature (WWF)'s Low Carbon Manufacturing Programme (LCMP).

A disruptive revolution is forming for the blockchain based communication network framework with end-to-end P2P based architecture of distributed computation, storage, and networking paradigm - the Next Generation Blockchain Network (NGBN). The core theme of NGBN is to push up communication PHY layer and push down application layer (e.g. storage and computation) to converge on a single networking layer - called Blockchain Network Layer (BNL) - such that blockchain token economy can be efficiently implemented to support an end-to-end P2P mesh network with unlimitedly scalable, available to everyone, and expandable by peer nodes' joining openly, robust and secure network environment for all the IoT, big data, AI applications to be coming in the next 10 years. To achieve this goal, a joint effort is needed to pull together various resources, including network resources, communication resources, application and chip level support, software and system, and initial proof of concept trials for the end-to-end deployment.

The constrained local model (CLM) proposes a paradigm that the locations of a set of local landmark detectors are constrained to lie in a subspace, spanned by a shape point distribution model (PDM). Fitting the model to an object involves two steps. A response map, which represents the likelihood of locations for a landmark, is first computed for each landmark using local-texture detectors. Then, an optimal PDM is determined by jointly maximizing all the response maps simultaneously, with a global-shape constraint. This global optimization can be considered a Bayesian inference problem, where the posterior distribution of the shape parameters, as well as the pose parameters, can be inferred using maximum a posteriori (MAP). In this paper, based on the CLM model, we present a novel CLM variant, which employs random-forest regressors to estimate the location of each landmark, as a likelihood term, efficiently. This novel CLM framework is called efficient likelihood Bayesian constrained local model (elBCLM). Furthermore, in each stage of the regressors, the PDM local non-rigid parameters, i.e. the shape parameters, of the previous stage can work as shape clues for training the regressors for the current stage. To further improve the efficiency, we also propose a feature-switching scheme used in the cascaded framework. Experimental results on benchmark datasets show our approach achieves about 3 to 5 times speed-up, when compared with the existing CLM models, and improves by around 10% on fitting accuracy, when compared with the other regression-based models.

Streaming layered video over peer-to-peer (P2P) networks has been recognized as an efficient way to address the receiver heterogeneity problem. The distinctive characteristics of layer encoded video also introduce complexities to data scheduling. In this paper, we propose a new data scheduling algorithm for layered P2P video-on-demand (VoD) streaming networks. Our algorithm consists of two parts: 1) layer adaptation, where peers adaptively adjust the number of subscribed layers to ensure a continuous playback of the highest possible video quality; and 2) piece selection, in which a peer selects a missing data piece to request based on its utility. The piece utility is calculated based on the playback constraint and the layer dependency of a piece. Through extensive packet-level simulations we show that our proposed data scheduling algorithm can effectively enhance the video playback quality.

Unlike peer-to-peer (P2P) file sharing, P2P live streaming systems have to meet real-time playback constraints, which makes it very challenging yet crucial to maximize the peer uplink bandwidth utilization so as to deliver content pieces in time. In general, this is achieved by adopting tailor-made piece selection and request-peer selection algorithms. The design philosophy is to regulate the network traffic and to balance the load among peers. In this paper, we propose a new request-peer selection algorithm. In particular, a peer in the network estimates the service response time (SRT) between itself and each neighboring peer. An SRT is measured from when a data piece request is sent until the requested piece arrives. When a peer makes a piece request, the neighbor with smaller SRT and fewer data pieces would be favored among potential providers. This is because smaller SRT implies excess serving capacity and fewer data pieces suggests less piece requests received. We evaluate the performance of our request-peer selection algorithm through extensive packet level simulations. Our simulation results show that the traffic load in the network is better balanced in the sense that the difference of the normalized number of data packets uploaded by each peer is getting smaller and the number of repeated piece requests generated by each peer (due to request failure) is significantly reduced. We also found that the load of streaming server is reduced, and the overall quality of service, measured by playback continuity, startup delay etc, is improved as well.

Peer-to-peer (P2P) based video-on-demand (VoD) streaming service has been gaining popularity recently. Unlike live streaming, a VoD peer always starts its playback from the beginning of a stored video. The playback-points of different peers, as well as the amount of video contents/pieces they cached, depend on when they join the video session, or their viewing ages. As a result, the upload bandwidth of younger peers tends to be underutilized because older peers are not interested in their cached video pieces. The collaborative piece exchange among peers is undermined due to the unbalanced supply and demand. To address this issue, a playback-point based request peer selection algorithm is proposed in this paper. Specifically, when a peer requests a particular video piece, among the set of potential providers, a request is sent to the peer that has the smallest playback-point difference with itself. We call this request peer selection algorithm closest playback-point first (CPF). With CPF, peers with similar available content can be loosely grouped together for a more balanced collaborative piece exchange. Extensive packet-level simulations show that with CPF, the video playback quality is enhanced and the VoD server load is significantly reduced.

In this paper, we study the impact of the image quality (hence, the video streaming bit-rate) and the chunk-level impairment (hence the playback discontinuity) on the perceptual assessment of the viewing experience of P2P layered video streaming services. Through subjective QoE experiments, we have obtained several interesting findings and useful insights. The results clearly reveal the tradeoffs between streaming bit-rate (B) and discontinuity (D) on the MOS under certain network condition. It is also showed that B-D tradeoff pattern is video content dependant. Based on these observations, a heuristic model is proposed to derive a group of MOS contours. This type of contours have practical usage and can help selecting suitable video streaming bit-rate (layer) for playback so as to maximize the perceptual QoE of the end users.

Quality of Experience (QoE) refers to subjective criteria for evaluating multimedia content. Methods have been devised to study the design of Voice over IP systems and video codecs. In recent years, due to more abundant network bandwidth, it has become quite popular to watch video streamed over the Internet, whether by clientserver method or through a peer-to-peer (P2P) network. In this paper, we describe our experience in conducting QoE studies of P2P streaming using a chunk-level model. Instead of considering fine-grained network service impairments such as bit errors, packet losses or delays, we focus on chunk level delays. We carry out some preliminary QoE experiments on low-bit rate, low-frame rate and low-resolution video (3L-video) sequences. We apply the chunk-level model to help improve the design of the P2P streaming algorithms, and the design of video players that playback network streamed video.

In this paper, we developed a color model to cancel the dependency between color channels, which enables us to separate spectral processing from, spatial processing. We introduced Independent Component Analysis (ICA) transformation in the wavelet domain to decorrelate the subband color joint statistics. The decorrelated joint color conditional histograms display scaling of variance. Gaussian Scale Mixture (GSM) was used to model the subband color statistics and a normalization scheme was adapted to cancel the pair-wise color subband statistical dependency. This color model was combined with the Portilla/Simoncelli texture model to construct the color texture model. Based on this model, features were extracted and the corresponding color texture synthesis scheme was developed.

We introduce a completely new approach to fitting implicit polynomial geometric shape models to data and to studying these polynomials. The power of these models is in their ability to represent nonstar complex shapes in two(2D) and three-dimensional (3D) data to permit fast, repeatable fitting to unorganized data which may not be uniformly sampled and which may contain gaps, to permit position-invariant shape recognition based on new complete sets of Euclidean and affine invariants and to permit fast, stable single-computation pose estimation. The algorithm represents a significant advancement of implicit polynomial technology for four important reasons. First, it is orders of magnitude taster than existing fitting methods for implicit polynomial 2D curves and 3D surfaces, and the algorithms for 2D and 3D are essentially the same. Second, it has significantly better repeatability, numerical stability, and robustness than current methods in dealing with noisy, deformed, or missing data. Third, it can easily fit polynomials of high, such as 14th or 16th, degree. Fourth, additional linear constraints can be easily incorporated into the fitting process, and general linear vector space concepts apply.

In this paper we propose a novel system of semantic feature extraction and retrieval for interior design and decoration application. The system, V/sup 2/ID (virtual visual interior design), uses colored texture and spatial edge layout to obtain simple information about global room environment. We address the domain specific segmentation problem in our application and the techniques for obtaining semantic features from a room environment. We also discuss heuristics for making use of these features (color, texture or shape) to retrieve objects from an existing database. The final resynthesized room environment with original scene and novel object from database is created for the purpose of animation and virtual room walkthrough.

We present completely new very powerful solutions to two fundamental problems central to computer vision. Given data sets representing C objects to be stored in a database, and given a new data set for an object, determine the object in the database that is most like the object measured. We solve this problem through use of PIMs ("Polynomial Interpolated Measures"), which is a new representation integrating implicit polynomial curves and surfaces, explicit polynomials, and discrete data sets which may be sparse. The method provides high accuracy at low computational cost. 2. Given noisy 2D data along a curve (or 3D data along a surface), decompose the data into patches such that new data taken along affine transformations or Euclidean transformations of the curve (or surface) can be decomposed into corresponding patches. Then recognition of complex or partially occluded objects can be done in terms of invariantly determined patches. We briefly outline a low computational cost image-database indexing-system based on this representation for objects having complex shape-geometry.

We present a novel application for Content Based Retrieval Techniques in Electronic Commerce using Interactive Multimedia, in which visual queries play a central role. We address some of the technical issues in representing and analysing image primitive features that are the building blocks of the MIRACLE system. These can be generalized into a much broader range of applications as well. We believe that Electronic Commerce is a very promising area with much potential for growth and that it covers a spectrum of rich research topics.

A new implicit polynomial (IP) fitting method is presented. It provides a different way of viewing the IP fitting problem from those of the nonlinear optimization approaches. It requires less computation, and can be done automatically or interactively. Linear programming is used to do the fitting. The approach can incorporate a variety of distance measures and global geometric constraints.

Query By Sketch for indexing into an image database involves presenting the machine with a sketch of the object to be found in the database. The sketch can be of the object shape or distinct contours on the image of the object. This sketch can be made from memory, or can be refined interactively in response to what the database search returns at each iteration. Or the sketch can be made by generating curves of an object boundary or object-surface image-discontinuities from an example image. This paper introduces and describes a family of 2D curves for this purpose, and an algorithm for generating a representation which passes within E of a set of control points specified by the user. Control points can be placed at arbitrary locations and in arbitrary order, and can be erased by the user at will, in order to arrive at the desired shape representation. These curves can be applied in a number of ways: we illustrate their use in one approach to indexing.

Denote a point in the plane by z=(z,y) and a polynomial of nth degree in z by f(z) /spl Sigma//sub i,j//spl ges/o/sub 1/i+j/spl les/n(a/sub ij/x/sup i/y/sup j/). Denote by Z(f) the set of points for which f(z)=0. Z(f) is the 2D curve represented by f(z). In this paper, we present a new approach to fitting 2D curves to data in the plane (or 3D surfaces to range data) which has significant advantages over presently known methods. It requires considerably less computation and the resulting curve can be forced to lie close to the data set at prescribed points provided that there is an nth degree polynomial that can reasonably approximate the data. Linear programming is used to do the fitting. The approach can incorporate a variety of distance measures and global geometric constraints.

Implicit polynomial 2D curves and 3D surfaces are potentially among the most useful object or data representations for use in computer vision and image analysis. This is because of their interpolation property, Euclidean and affine invariants, and Bayesian recognizers. The paper studies and compares various fitting algorithms in a unified framework of stability analysis. It presents a new robust 3L fitting method that is repeatable, numerically stable and computationally fast and can be used for high degree implicit polynomials to capture complex object structure. With this, the authors lay down a foundation that enables a technology based on implicit polynomial curves and surfaces for applications in indexing into pictorial databases, robot vision, CAD for free-form shapes, etc.

An effective approach has appeared in the literature for recognizing a 2D curve or 3D surface objects of modest complexity based on representing an object by a single implicit polynomial of 3/sup rd/ or 4/sup th/ degree, computing a vector of Euclidean or affine invariants which are functions of the polynomial coefficients, followed by Bayesian object recognition of the invariants, thus producing a low computational cost robust recognition. This paper extends the approach, as well as an initial work on mutual invariants recognizers, to the recognition of objects too complicated to be represented by a single polynomial. Hence, an object to be recognized is partitioned into patches, each patch is represented by a single implicit polynomial, mutual invariants are computed for pairs of polynomials for pairs of patches, and the object recognition is via a Bayesian recognition of vectors of self and mutual invariants. We discuss why the complete object geometry can be captured by the geometry of pairs of patches, how to design mutual invariants, and how to match patches in the data with those in the database at a low computational cost. The approach is a low computational cost recognition of partially occluded articulated objects in an arbitrary position and in noise by recognizing the self or joint geometry of one or more patches.