Data Representation Scheme Research Articles

Modeling of limit order book data with ordered fuzzy numbers

This paper presents a novel approach to representing the Limit Order Book data at a given timestamp using the Ordered Fuzzy Numbers concept. The limit order book contains all buy and sell orders placed by investors, updated in real-time, for the most liquid securities, even several hundred times a minute. Due to its irregular nature (different and dynamic changes in the number of buy and sell orders), direct calculations on the order book data are not feasible without transforming it into feature vectors. Currently, most studies use a price level-based data representation scheme when applying deep learning models on limit order book data. However, this scheme has limitations, particularly its sensitivity to subtle perturbations that can negatively impact model performance. On the other hand, the ordered fuzzy number is a mathematical object (a pair of two functions) used to process imprecise and uncertain data. Ordered Fuzzy Numbers possess well-defined arithmetic properties. Converting the limit order book data to ordered fuzzy numbers allows the creation of a time series of ordered fuzzy numbers (order books) and use them for further calculations, e.g., to represent input data for deep learning models or employing the concept of fuzzy time series in various domains, such as defining liquidity measures based on limit order book data. In this paper, the proposed approach is tested using one-year market data from the Polish Stock Exchange for the five biggest companies. The DeepLOB model is employed to predict mid-price movement using different input data representations. The proposed representation of Limit Order Book data demonstrated remarkably stable out-of-sample prediction accuracy, even when subjected to data perturbation.

NLP-based music processing for composer classification

Categorizing music pieces by composer is a challenging task in digital music processing due to their highly flexible structures, introducing subjective interpretation by individuals. This research utilized musical data from the MIDI and audio edited for synchronous tracks and organization dataset of virtuosic piano pieces. In this work, pitch and duration were the musical features of interest. The goal was to innovate an approach to representing a musical piece using SentencePiece and Word2vec, which are natural language processing-based techniques. We attempted to find correlated melodies that are likely to be formed by single interpretable units of music via co-occurring notes, and represented them as a musical word/subword vector. Composer classification was performed in order to ensure the efficiency of this musical data representation scheme. Among classification machine learning algorithms, k-nearest neighbors, random forest classifier, logistic regression, support vector machines, and multilayer perceptron were employed to compare performances. In the experiment, the feature extraction methods, classification algorithms, and music window sizes were varied. The results were that classification performance was sensitive to feature extraction methods. Musical word/subword vector standard deviation was the most effective feature, resulting in classification with a high F1-score, attaining 1.00. No significant difference was observed among model classification performances.

Flow time history representation and reconstruction based on machine learning

Based on deep learning technology, a new spatiotemporal flow data representation and reconstruction scheme is proposed by using flow time history (FTH) data instead of flow snapshots. First, the high-dimensional nonlinear flow system is reduced to a low-dimensional representation latent code using the FTH autoencoder model. Second, the mapping from physical space to latent code space is built using mathematical and machine-learning schemes. Finally, FTH at unavailable positions in physical space is generated by the FTH generator. The proposed scheme is validated by three case studies: (i) representing and recovering the FTH data of periodic laminar flow around a circular cylinder at Re = 200 and generating high-resolution laminar flow data; (ii) reconstructing complex FTH of flow past cylinder at Re = 3900 which including laminar and turbulent flow region and generating three-dimensional high-resolution turbulent flow data, respectively; (iii) representing and generating multi-variable turbulent flow data simultaneously using the multi-channel model. The results show that the proposed scheme is an effective low-dimensional representation for complex flow time variant features, which is suitable for both laminar and turbulent FTH data to generate spatiotemporal high-resolution FTH data in three-dimensional space.

Graph-based data management system for efficient information storage, retrieval and processing

Data management systems rely on a correct design of data representation and software components. The data representation scheme plays a vital role in how the data are stored, which influences the efficiency of its processing and retrieval. The system components design realizes software engineering concepts to enable performance metrics such as scalability, efficiency, flexibility, maintainability, and extendibility. This paper presents a data management system that uses a graph-based data representation scheme to achieve an efficient data retrieval when using graph-based databases. Input data are transformed into vertices, edges, and labels while inserting them into the database. The proposed system consists of three layers which are: system beans layer, data access layer, and the database engine. Healthcare data are used to evaluate the system in comparison with resource description framework (RDF) semantics. Extensive experiments are conducted to compare different scenarios of data storage and retrieval using Neo4J, OrientDB, and RDF4J. Experimental results show that the performance of the proposed graph-based approach outperforms RDF4J framework in terms of insertion and retrieval time.

Graph representations for the analysis of multi-agent spatiotemporal sports data

Analyzing tactical patterns in invasion games using multi-agent spatiotemporal data is a challenging task at the intersection of computer and sports science. A fundamental yet understudied problem in this area is finding an optimal data representation for processing athlete trajectories using machine learning algorithms. In the present work, we address this gap by discussing common representations in use and propose Tactical Graphs, an alternative graph-based format capable of producing integrative, contextualized models for machine learning applications. We provide an in-depth, domain-specific motivation of the proposed data representation scheme and show how this approach exploits inherent data traits. We propose Tactical Graph Networks (TGNets), a light-weight, hybrid machine learning architecture sensitive to player interactions. Our method is evaluated with an extensive ablation study and the first comprehensive state of the art comparison between standard feature, state vector, and image-based methods on the same dataset. Experiments were conducted using real-world football data containing short sequences of defensive play labelled according to the outcome of ball winning attempts. The results indicate that TGNets are on par with state-of-the-art deep learning models while exhibiting only a fraction of their complexity. We further demonstrate that selecting the right data representation is crucial as it has a significant influence on model performance. The theoretical findings and the proposed method provide insights and a strong methodological alternative for all classification, prediction or pattern recognition applications in the areas of collective movement analysis, automated match analysis, and performance analysis.

From Platform to Knowledge Graph: Evolution of Laboratory Automation.

High-fidelity computer-aided experimentation is becoming more accessible with the development of computing power and artificial intelligence tools. The advancement of experimental hardware also empowers researchers to reach a level of accuracy that was not possible in the past. Marching toward the next generation of self-driving laboratories, the orchestration of both resources lies at the focal point of autonomous discovery in chemical science. To achieve such a goal, algorithmically accessible data representations and standardized communication protocols are indispensable. In this perspective, we recategorize the recently introduced approach based on Materials Acceleration Platforms into five functional components and discuss recent case studies that focus on the data representation and exchange scheme between different components. Emerging technologies for interoperable data representation and multi-agent systems are also discussed with their recent applications in chemical automation. We hypothesize that knowledge graph technology, orchestrating semantic web technologies and multi-agent systems, will be the driving force to bring data to knowledge, evolving our way of automating the laboratory.

A High-throughput Parallel Viterbi Algorithm via Bitslicing

In this work, we present a novel bitsliced high-performance Viterbi algorithm suitable for high-throughput and data-intensive communication. A new column-major data representation scheme coupled with the bitsliced architecture is employed in our proposed Viterbi decoder that enables the maximum utilization of the parallel processing units in modern parallel accelerators. With the help of the proposed alteration of the data scheme, instead of the conventional bit-by-bit operations, 32-bit chunks of data are processed by each processing unit. This means that a single bitsliced parallel Viterbi decoder is capable of decoding 32 different chunks of data simultaneously. Here, the Viterbi’s Add-Compare-Select procedure is implemented with our proposed bitslicing technique, where it is shown that the bitsliced operations for the Viterbi internal functionalities are efficient in terms of their performance and complexity. We have achieved this level of high parallelism while keeping an acceptable bit error rate performance for our proposed methodology. Our suggested hard and soft-decision Viterbi decoder implementations on GPU platforms outperform the fastest previously proposed works by and , achieving 21.41 and 8.24 Gbps on Tesla V100, respectively.

Flexible data representation with graph convolution for semi-supervised learning

This paper introduces a scheme for semi-supervised data representation. It proposes a flexible nonlinear embedding model that imitates the principle of spectral graph convolutions. Structured data are exploited in order to determine nonlinear and linear models. The introduced scheme takes advantage of data graphs at two different levels. First, it incorporates manifold regularization that is naturally encoded by the graph itself. Second, the regression model is built on the convolved data samples that are obtained by the joint use of the data and their associated graph. The proposed semi-supervised embedding can tackle challenges related to over-fitting in image data spaces. The proposed graph convolution-based semi-supervised embedding paves the way to new theoretical and application perspectives related to the nonlinear embedding. Indeed, building flexible models that adopt convolved data samples can enhance both the data representation and the final performance of the learning system. Several experiments are conducted on six image datasets for comparing the introduced scheme with many state-of-art semi-supervised approaches. These experimental results show the effectiveness of the introduced data representation scheme.

A residual spatio-temporal architecture for travel demand forecasting

This paper proposes a deep architecture called residual spatio-temporal network (RSTN) for short-term travel demand forecasting. It comprises fully convolutional neural networks (FCNs) and a hybrid module consisting of an extended Conv-LSTM (CE-LSTM) that can achieve trade-off of convolutional operation and LSTM cells by tuning the hyperparameters of Conv-LSTM, convolutional neural networks (CNNs) and traditional LSTM. These modules are combined via residual connections to capture the spatial, temporal and extraneous dependencies of travel demand. The end-to-end trainable RSTN redefines the traditional prediction problem as a learning residual function with regard to the travel density in each time interval. Further more, a dynamic request vector (DRV)-based data representation scheme is presented, which catches the intrinsic characteristics and variation of the trend, to improve the performance of forecasting. Simulations with two real-word data sets show that the proposed method outperforms the existing forecasting algorithms, reducing the root mean square error (RMSE) by up to 17.87%.

Data-Rate Driven Transmission Strategies for Deep Learning-Based Communication Systems

Deep learning (DL) based autoencoder is a promising architecture to implement end-to-end communication systems. One fundamental problem of such systems is how to increase the transmission rate. Two new schemes are proposed to address the limited data rate issue: adaptive transmission scheme and generalized data representation (GDR) scheme. In the first scheme, an adaptive transmission is designed to select the transmission vectors for maximizing the data rate under different channel conditions. The block error rate (BLER) of the first scheme is 80% lower than that of the conventional one-hot vector scheme. This implies that higher data rate can be achieved by the adaptive transmission scheme. In the second scheme, the GDR replaces the conventional one-hot representation. The GDR scheme can achieve higher data rate than the conventional one-hot vector scheme with comparable BLER performance. For example, when the vector size is eight, the proposed GDR scheme can double the date rate of the one-hot vector scheme. Besides, the joint scheme of the two proposed schemes can create further benefits. The effect of signal-to-noise ratio (SNR) is analyzed for these DL-based communication systems. Numerical results show that training the autoencoder using data set with various SNR values can attain robust BLER performance under different channel conditions.

Nature-Inspired Optimization Algorithms for the 3D Reconstruction of Porous Media

One of the most challenging problems that are still open in the field of materials science is the 3D reconstruction of porous media using information from a single 2D thin image of the original material. Such a reconstruction is only feasible subject to some important assumptions that need to be made as far as the statistical properties of the material are concerned. In this study, the aforementioned problem is investigated as an explicitly formulated optimization problem, with the phase of each porous material point being decided such that the resulting 3D material model shows the same statistical properties as its corresponding 2D version. Based on this problem formulation, herein for the first time, several traditional (genetic algorithms—GAs, particle swarm optimization—PSO, differential evolution—DE), as well as recently proposed (firefly algorithm—FA, artificial bee colony—ABC, gravitational search algorithm—GSA) nature-inspired optimization algorithms were applied to solve the 3D reconstruction problem. These algorithms utilized a newly proposed data representation scheme that decreased the number of unknowns searched by the optimization process. The advantages of addressing the 3D reconstruction of porous media through the application of a parallel heuristic optimization algorithm were clearly defined, while appropriate experiments demonstrating the greater performance of the GA algorithm in almost all the cases by a factor between 5%–84% (porosity accuracy) and 3%–15% (auto-correlation function accuracy) over the PSO, DE, FA, ABC, and GSA algorithms were undertaken. Moreover, this study revealed that statistical functions of a high order need to be incorporated into the reconstruction procedure to increase the reconstruction accuracy.

Enhanced clustering models with wiki-based k-nearest neighbors-based representation for web search result clustering

Information retrieval is a difficult process due to the overabundance of information on the web. Nowadays, search result responds to user queries with too many results although only a few are relevant. Therefore, the existing clustering methods that fail in clustering snippets (short texts) of web documents due to the low frequencies of document terms should be deeply investigated. One of the approaches that can be used to solve this problem is the expansion of document terms with semantically similar terms. Hence, a list of terms with their closest and accurate semantically similar words (word representation) must be built. This study aims to design and develop a new framework to enhance the performance of web search result clustering (WSRC). The research also presents a new unsupervised distributed word representation scheme where each word is represented by a vector of its semantically related words; such as scheme expands snippets and user queries. The proposed framework consists of several activities, such as (1) various standard datasets (Open Directory Project [ODP]-239 and MORESQUE) that are used for evaluating search result clustering algorithms for most cited dataset works, (2) text pre-processing, (3) document representation based on a new wiki-based k-nearest neighbors (KNN) representation method, (4) effect of the proposed model on the performance of traditional clustering methods (k-means, k-medoids, single-linkage, and complete-linkage) for WSRC, and (5) evaluation stage of the proposed method. Results indicate that enhanced clustering methods, according to the new wiki-KNN based representation method in comparison with the baseline methods, show a significant improvement in WSRC. Furthermore, the new data representation scheme has enhanced the overall performance of clustering methods.

Fast AES Implementation: A High-Throughput Bitsliced Approach

In this work, a high-throughput bitsliced AES implementation is proposed, which builds upon a new data representation scheme that exploits the parallelization capability of modern multi/many-core platforms. This representation scheme is employed as a building block to redesign all of the AES stages to tailor them for multi/many-core AES implementation. With the proposed bitsliced approach, each parallelization unit processes an unprecedented number of thirty-two 128-bit input data. Hence, a high order of prallelization is achieved by the proposed implementation technique. Based on the characteristics of this new implementation model, the ShiftRows stage can be implicitly handled through input rearrangement and is simplified to the point where its computing process can be neglected. In this implementation, costly Byte-wise operations are performed through register shift and swapping. In addition, the need for look-up table based I/O operations, which are used by the Substitute Bytes stage is eliminated through using S-box logic circuit. The S-box logic circuit is optimized to simultaneously process 32 chunks of 128-bit input data. We develop high-throughput CTR and ECB AES encryption/decryption on 6 CUDA-enabled GPUs, which achieve 1.47 and 1.38 Tbps of encryption throughput on Tesla V100 GPU, respectively.

Efficient Learning-Based Recommendation Algorithms for Top- N Tasks and Top- N Workers in Large-Scale Crowdsourcing Systems

The task and worker recommendation problems in crowdsourcing systems have brought up unique characteristics that are not present in traditional recommendation scenarios, i.e., the huge flow of tasks with short lifespans, the importance of workers’ capabilities, and the quality of the completed tasks. These unique features make traditional recommendation approaches no longer satisfactory for task and worker recommendation in crowdsourcing systems. In this article, we propose a two-tier data representation scheme (defining a worker--category suitability score and a worker--task attractiveness score ) to support personalized task and worker recommendations. We also extend two optimization methods, namely least mean square error and Bayesian personalized rank, to better fit the characteristics of task/worker recommendation in crowdsourcing systems. We then integrate the proposed representation scheme and the extended optimization methods along with the two adapted popular learning models, i.e., matrix factorization and kNN, and result in two lines of top- N recommendation algorithms for crowdsourcing systems: (1) Top- N -Tasks recommendation algorithms for discovering the top- N most suitable tasks for a given worker and (2) Top- N -Workers recommendation algorithms for identifying the top- N best workers for a task requester. An extensive experimental study is conducted that validates the effectiveness and efficiency of a broad spectrum of algorithms, accompanied by our analysis and the insights gained.

Personalized Channel Recommendation Deep Learning From a Switch Sequence

Internet protocol TV (IPTV) services could enhance personalized viewing experience in a more interactive way than traditional broadcast TV systems, but it is still difficult for subscribers to quickly find interesting channels to watch from a huge selection. This paper focuses on a framework for personalized live channel recommending via deep learning from a historical switching sequence with a long short-term memory (LSTM) neural network. Using real-world IPTV watching logs, we first obtained insights into user behaviors when watching live channels, and then proposed a learning scheme on how to dynamically generate a recommended channel list for each user with an independent LSTM net trained using the channel watching history during a slide window. For designing a good data architecture and representation scheme for a dynamically learning framework, we then studied the performance of the proposed recommendation method by varying the width of the slide window for training, the length of input sequence for prediction, and the mode to process input and label space. We finally developed a separate learning method to fairly recommend for popular (hot) or unpopular (cold) channels, respectively, based on channel popularity in the training set with an extra price of a possible hit lag after recommendation, in order to alleviate the Matthew effect arising from the conventional recommendation based on historical information. The experimental results show LSTM succeeds in learning from a historical channel switching sequence, outperforms several baseline recommendation methods, especially for hot channels, and the classified recommendation by separate learning brings an overall performance gain.

Energy-Efficient Design of Processing Element for Convolutional Neural Network

Convolutional neural network (CNN) is the most prominent algorithm for its wide usage and good performance. Despite the fact that the processing element (PE) plays an important role in CNN processing, there has been no study focusing on PE design optimized for state-of-the-art CNN algorithms. In this brief, we propose an optimal PE implementation including a data representation scheme, circuit block configurations, and control signals for energy-efficient CNN. To validate the excellence of this brief, we compared our proposed design with several previous methods, and fabricated a silicon chip. The software simulation results demonstrated that we can reduce 54% of data bit lengths with negligible accuracy loss. Our optimization on PE achieves to save computing power up to 47%, and an accelerator exploiting our method shows superior results in terms of power, area, and external DRAM access.

Spreading Modulation for Multilevel Nonvolatile Memories

The aggressive scaling of NAND flash memories has caused significant degradation in their reliability and endurance. One of the dominant factors in this degradation is the inter-cell-interference, by which the programming of a cell can affect nearby neighboring cells corrupting the information that they store. This paper proposes a new data representation scheme, which increases endurance and significantly reduces the probability of error caused by inter-cell-interference. The method is based on using an orthogonal code to spread each bit across multiple cells, resulting in lower variance for the voltages being programmed in the cells. This new data representation method is also shown to present many of the advantages that spreading sequences bring to wireless communications. For example, multiple information sequences can be written on the same cells at different times without interfering with each other. It also allows storing additional information on an already programmed memory in such a way that the new information is hidden by the noise.

Space Structure and Clustering of Categorical Data.

Learning from categorical data plays a fundamental role in such areas as pattern recognition, machine learning, data mining, and knowledge discovery. To effectively discover the group structure inherent in a set of categorical objects, many categorical clustering algorithms have been developed in the literature, among which k -modes-type algorithms are very representative because of their good performance. Nevertheless, there is still much room for improving their clustering performance in comparison with the clustering algorithms for the numeric data. This may arise from the fact that the categorical data lack a clear space structure as that of the numeric data. To address this issue, we propose, in this paper, a novel data-representation scheme for the categorical data, which maps a set of categorical objects into a Euclidean space. Based on the data-representation scheme, a general framework for space structure based categorical clustering algorithms (SBC) is designed. This framework together with the applications of two kinds of dissimilarities leads two versions of the SBC-type algorithms. To verify the performance of the SBC-type algorithms, we employ as references four representative algorithms of the k -modes-type algorithms. Experiments show that the proposed SBC-type algorithms significantly outperform the k -modes-type algorithms.

A Graph-Based Ant Colony Optimization for Association Rule Mining

This study is aimed at proposing a graph-based ant colony optimization (ACO) approach for association rule mining (ARM). The ACO-ARM is a two-phase approach comprising a Boolean transactional data representation scheme and the graph-based ACO. The first phase enhances the normal Apriori algorithm and engages in a data representation scheme. The data representation involves an adapted Boolean matrix representation of the transactional data. A standard Apriori algorithm is applied to the represented data, and n-frequent itemsets are generated. The second phase embellishes the ACO-ARM, which relies on the graph of 2-frequent items to generate the final frequent itemset. We have conducted two experiments. The outcomes of these tests reveal that the graph-based ACO-ARM enhances execution time compared to the standard Apriori algorithm. In addition, ACO-ARM improves the process of data representation in the Apriori algorithm.

Observ-OM and Observ-TAB: Universal syntax solutions for the integration, search, and exchange of phenotype and genotype information

Genetic and epidemiological research increasingly employs large collections of phenotypic and molecular observation data from high quality human and model organism samples. Standardization efforts have produced a few simple formats for exchange of these various data, but a lightweight and convenient data representation scheme for all data modalities does not exist, hindering successful data integration, such as assignment of mouse models to orphan diseases and phenotypic clustering for pathways. We report a unified system to integrate and compare observation data across experimental projects, disease databases, and clinical biobanks. The core object model (Observ-OM) comprises only four basic concepts to represent any kind of observation: Targets, Features, Protocols (and their Applications), and Values. An easy-to-use file format (Observ-TAB) employs Excel to represent individual and aggregate data in straightforward spreadsheets. The systems have been tested successfully on human biobank, genome-wide association studies, quantitative trait loci, model organism, and patient registry data using the MOLGENIS platform to quickly setup custom data portals. Our system will dramatically lower the barrier for future data sharing and facilitate integrated search across panels and species. All models, formats, documentation, and software are available for free and open source (LGPLv3) at http://www.observ-om.org.