Dynamic Data Mining Research Articles

Enhancing urban flood forecasting in drainage systems using dynamic ensemble-based data mining

This study presents a novel approach for urban flood forecasting in drainage systems using a dynamic ensemble-based data mining model which has yet to be utilised properly in this context. The proposed method incorporates an event identification technique and rainfall feature extraction to develop weak learner data mining models. These models are then stacked to create a time-series ensemble model using a decision tree algorithm and confusion matrix-based blending method. The proposed model was compared to other commonly used ensemble models in a real-world urban drainage system in the UK. The results show that the proposed model achieves a higher hit rate compared to other benchmark models, with a hit rate of around 85% vs 70 % for the next 3 h of forecasting. Additionally, the proposed smart model can accurately classify various timesteps of flood or non-flood events without significant lag times, resulting in fewer false alarms, reduced unnecessary risk management actions, and lower costs in real-time early warning applications. The findings also demonstrate that two features, “antecedent precipitation history” and “seasonal time occurrence of rainfall,” significantly enhance the accuracy of flood forecasting with a hit rate accuracy ranging from 60 % to 10 % for a lead time of 15 min to 3 h.

Kernel Online System for Fast Principal Component Analysis and its Adaptive Learning

An artificial neural system for data compression that sequentially processes linearly nonseparable classes is proposed. The main elements of this system include adjustable radial-basis functions (Epanechnikov’s kernels), an adaptive linear associator learned by a multistep optimal algorithm, and Hebb-Sanger neural network whose nodes are formed by Oja’s neurons. For tuning the modified Oja’s algorithm, additional filtering (in case of noisy data) and tracking (in case of nonstationary data) properties were introduced. The main feature of the proposed system is the ability to work in conditions of significant nonlinearity of the initial data that are sequentially fed to the system and have a non-stationary nature. The effectiveness of the developed approach was confirmed by the experimental results. The proposed kernel online neural system is designed to solve compression and visualization tasks when initial data form linearly nonseparable classes in general problem of Data Stream Mining and Dynamic Data Mining. The main benefit of the proposed approach is high speed and ability to process data whose characteristics are changed in time.

An Effectiveness Study of SPC Control Charts on the Quality Control for Construction in Asphalt Pavement

Aiming at the problems of insufficient dynamic control and data mining of Expressway pavement construction quality in Yunnan, this paper analyzes the application of Exponentially Weighted Moving Average (EWMA) control chart in dynamic control of Expressway asphalt pavement construction quality. Firstly, the quality characteristic value of pavement construction is defined as the data type of multiple variation sources, and the mathematical model of multiple variation sources is studied to solve the problem of excessive false alarm. Then, on the theoretical basis of statistical process control (SPC), the paper compares and analyzes the three control chart schemes of traditional Hugh Hart control chart, Tabular Cumulative Sum (CUSUM) control chart and EWMA control chart, and concludes that the application effect of EWMA control chart is obviously better than the other methods in the aspects of applicability and inspection output. Finally, combining with the measured data of asphalt mixture temperature and asphalt weight in pavement construction, EWMA control diagram is used to carry out practical research, and the results are better.

Cancer Prevention Through Improvements on Lifestyle and Metabolism Using GH-Method: Math-Physical Medicine (No. 342)

This paper describes the author’s investigation into the prevention from having various cancers and his risk probability based on improvements on lifestyle and metabolism. His risk probabilities percentage of having cancer over the past 11 years with lower risk percentages (<50%) from 2014 - 2020 and higher risk percentages (>50%) from 2010 - 2013. It should be noted that the higher prediction accuracy occurred during 2015-2020 due to his collection of more completed data. (1) Year of 2010: 88% (2) Year of 2011: 74% (3) Year of 2012: 58% (4) Year of 2013: 55% (5) Year of 2014: 50% (6) Year of 2015: 48% (7) Year of 2016: 46% (8) Year of 2017: 45% (9) Year of 2018: 45% (10)Year of 2019: 45% (11)Year of 2020: 43% It seems that 50% is a reasonable “cut-off ” line between higher risk versus lower risk. The trend of the past 11 years risk probability percentages of having cancer from the viewpoint of cancer prevention is being reduced year after year, which is an encouraging fact. The calculated cancer prevention and risk probability results via lifestyle and metabolism have been validated by his many health examination reports from the past 20 years. This big data based on a dynamic simulation model and data mining using GH-Method: math-physical medicine approach can provide an early warning to which factors or areas to monitor in order to continuously improve his health conditions. The author wrote this article to share with other people, who may have similar interest in reducing their risk probability of getting cancer. As stated previously, he is not an expert on oncology but a research scientist in both lifestyle and metabolism. Metabolism and cancer have a strong relationship with one another; therefore, hopefully, his research method and preliminary findings would have some merit to help others to prevent them from getting cancer.

STAD: Spatio-Temporal Anomaly Detection Mechanism for Mobile Network Management

Unusual Spatio-Temporal fluctuations in cellular network traffic may lead to drastic network management misbehaviors and at least abnormal drops in quality of experience. It is also expected that the management of future cellular networks will mostly rely on machine learning and automation. In this article, we present a dynamic on-line data mining technique to detect these network anomalies allowing, network operators to pro-actively monitor and control a variety of real-world phenomena with less damage to the overall experience. To overcome the network performance degradation that can occur in real time, the network manager must imperatively and instantly identify abnormalities and hence provide a better continuous quality of service for the subscribers. Based on real cellular communication traces, we propose an automated framework, called STAD, ensuring spatio-temporal detection outliers using a combination of machine learning techniques including One-class SVM (OCSVM), Support Vector Regression (SVR) and recurrent neural networks, Long Short-Term Memory (LSTM). STAD is double checked with two real datasets of CDRs where results show high accuracy compared to the Isolation Forest and Auto-Regressive Integrated Moving Average (ARIMA) models.

Research on Intelligent Analysis of Port Logistics Information Based on Dynamic Data Mining

Zhang, C. and Shao, X., 2020. Research on intelligent analysis of port logistics information based on dynamic data mining. In: Bai, X. and Zhou, H. (eds.), Advances in Water Resources, Environmental Protection, and Sustainable Development. Journal of Coastal Research, Special Issue No. 115, pp. 93-95. Coconut Creek (Florida), ISSN 0749-0208.Intelligent port logistics information analysis strategies and methods are of great value for improving port logistics information management and service quality, promoting the development of logistics information management theory, and promoting the application of information technology in logistics enterprises. With the gradual arrival of the data age, useful data behind a large amount of data needs to be mined. Data mining plays an important role in data analysis and is widely used in many fields. As the starting point and end point of maritime transportation, the junction point of various production factors and the junction point of important information, modern ports integrate commodity flow, information flow, capital flow and talent flow. In the long-term operation of port logistics, a large number of dynamic data have been accumulated. It has become a common cognition to strengthen the mining of these data values. According to the dynamic characteristics of port logistics information, this paper proposes an intelligent analysis strategy of port logistics information based on dynamic data mining technology.

Neck injury mechanisms in train collisions: Dynamic analysis and data mining of the driver impact injury

Human necks are vulnerable in train collision accidents. To design a safer cab workspace, the driver neck injury mechanism should be investigated first. In this study, this issue is addressed by investigating how neck injuries are influenced by the cab workspace dimensions. The driver-console-seat dynamic models are developed to quantify the neck injuries. The three-pivot head-neck-upper torso model is used to evaluate the relative rotation angle between head and upper torso (β+γ). The injury mechanism with the larger (β+γ) value results in more severe neck injuries. The decision tree model is established to explore the most important cab workspace dimensional parameter. The driver submarining posture (the driver exhibits the tendency of sliding down from the seat after contacting the console) generates more (β+γ) value than the flipping over behavior (the driver contacts the console and the upper body continues to move over the top of the console). Four neck injury mechanisms are classified, in which the chest-first impact mechanisms are more dangerous than the knee-first impact mechanisms. The distance between the console edge and knee bolster has the greatest effect on the neck injury. This parameter determines the injury mechanism type as it influences the first contact region of the driver. The distance between the console and seat and the pedal height are the secondary dominant attributes. These three parameters should be considered preferentially for establishing driver protection measures.

Aerodynamic Optimization of the Low-Pressure Turbine Module: Exploiting Surrogate Models in a High-Dimensional Design Space

Abstract Further improvement of state-of-the-art low-pressure (LP) turbines (LPTs) has become progressively more challenging. LP design is more than ever confronted to the need to further integrate complex models and to shift from single-component design to the design of the complete LPT module at once. This leads to high-dimensional design spaces and automatically challenges their applicability within an industrial context, where computing resources are limited and the cycle time is crucial. The aerodynamic design of a multistage LP turbine is discussed for a design space defined by 350 parameters. Using an online surrogate-based optimization (SBO) approach, a significant efficiency gain of almost 0.5pt has been achieved. By discussing the sampling of the design space, the quality of the surrogate models, and the application of adequate data mining capabilities to steer the optimization, it is shown that despite the high-dimensional nature of the design space, the followed approach allows to obtain performance gains beyond target. The ability to control both global as well as local characteristics of the flow throughout the full LP turbine, in combination with an agile reaction of the search process after dynamically strengthening and/or enforcing new constraints in order to adapt to the review feedback, not only illustrates the feasibility but also the potential of a global design space for the LP module. It is demonstrated that intertwining the capabilities of dynamic SBO and efficient data mining allows to incorporate high-fidelity simulations in design cycle practices of certified engines or novel engine concepts to jointly optimize the multiple stages of the LPT.

A Simulation Data-Driven Design Approach for Rapid Product Optimization

Abstract Traditional design optimization is an iterative process of design, simulation, and redesign, which requires extensive calculations and analysis. The designer needs to adjust and evaluate the design parameters manually and continually based on the simulation results until a satisfactory design is obtained. However, the expensive computational costs and large resource consumption of complex products hinder the wide application of simulation in industry. It is not an easy task to search the optimal design solution intelligently and efficiently. Therefore, a simulation data-driven design approach which combines dynamic simulation data mining and design optimization is proposed to achieve this purpose in this study. The dynamic simulation data mining algorithm—on-line sequential extreme learning machine with adaptive weights (WadaptiveOS-ELM)—is adopted to train the dynamic prediction model to effectively evaluate the merits of new design solutions in the optimization process. Meanwhile, the prediction model is updated incrementally by combining new “good” data set to reduce the modeling cost and improve the prediction accuracy. Furthermore, the improved heuristic optimization algorithm—adaptive and weighted center particle swarm optimization (AWCPSO)—is introduced to guide the design change direction intelligently to improve the search efficiency. In this way, the optimal design solution can be searched automatically with less actual simulation iterations and higher optimization efficiency, and thus supporting the rapid product optimization effectively. The experimental results demonstrate the feasibility and effectiveness of the proposed approach.

Dynamic Data Mining of Sensor Data

The research of data mining has aroused widespread concern in academia and industry. However, an important mark of the Internet of Things era is that sensor data replaces artificially compiled data. How to extract valuable knowledge and patterns from a large amount of data generated by sensors is a meaningful research topic. This paper proposes a dynamic data mining framework for processing sensor data. A sensor data mining model which can be used in the process of dynamic change is constructed. In this model, different sensor network environments are considered as different physical systems. The physical system and its parameters are trained by collecting and mining historical changes in sensor data; the associations between different sensor network environments are discovered by mining the associations between the parameters of different physical systems. In our limited experimental environment, the physical quantities considered included transmission distance, transmission delay, sensor data, data changes, and so on. Experiments were carried out on the designated experimental platform, and the results showed that the model could mine the dynamic data and find stable patterns. Through the analysis of the experimental results, it was found that the model had reference value for the dynamic mining of sensor data, and was expected to construct new methods for industrial big data analysis.

A Novel Framework for Recommending Data Mining Algorithm in Dynamic IoT Environment

Internet of Things (IoT) has been the driving force for many smart city applications. The huge volume of IoT data generated from these applications require efficient processing to get the insight, which poses significant difficulty. Data mining and machine learning (DM) algorithms are used to minimize such difficulty. However, it is still very challenging to select a particular DM algorithm that can process a dynamic IoT dataset based on some application-specific goals to achieve better accuracy. This paper proposes a knowledge-driven framework that considers the knowledge of datasets, available DM algorithms, and application goals to select the suitable DM algorithm for performing a target data processing task. This work considers data from cultural domain, health domain, and transportation domain in the experiment. The results show that the proposed approach dynamically selects the best-suited DM algorithms for the available datasets and target goals that exhibits satisfactory performance in obtaining accurate results compared to the existing work. The proposed approach not only provides flexibility in conducting dynamic IoT data mining tasks, but also reduces the complexity that would otherwise be necessary while adopting the traditional data mining approaches.

Fully Dynamic k-Center Clustering with Improved Memory Efficiency

Static and dynamic clustering algorithms are a fundamental tool in any machine learning library. Most of the efforts in developing dynamic machine learning and data mining algorithms have been focusing on the sliding window model (where at any given point in time only the most recent data items are retained) or more simplistic models. However, in many real-world applications one might need to deal with arbitrary deletions and insertions. We develop a $(2+\epsilon)$ -approximation algorithm for the k-center clustering problem with ``small'' amortized cost under the fully dynamic adversarial model. In such a model, points can be added or removed arbitrarily, provided that the adversary does not have access to the random choices of our algorithm. The amortized cost of our algorithm is poly-logarithmic when the ratio between the maximum and minimum distance between any two points in input is bounded by a polynomial, while k and ϵ are constant. Furthermore, we significantly improve the memory requirement of our fully dynamic algorithm, although at the cost of a worse approximation ratio of $4 +\epsilon$ . Our theoretical results are complemented with an extensive experimental evaluation on dynamic data from Twitter, Flickr, as well as trajectory data, demonstrating the effectiveness of our approach

An Optimized Mining Algorithm for Analyzing Students’ Learning Degree Based on Dynamic Data

With the rapid development of educational informatization, it has enabled education to enter the era of big data. How to extract effective information from educational big data and realize adaptive personalized learning goals have become the current research hotspot. The traditional static data only analyzes the students' learning degree based on the students' final answer, but ignores the dynamic data in the process of answering questions, such as the modification and the time it answered on the question, which makes it difficult to fully and accurately mine the correlation between the massive data, so it turns from static data mining to dynamic data mining. The paper proposes an optimized mining algorithm for analyzing students' learning degree based on dynamic data. The algorithm first uses the optimized text classification technology to match the question texts to the knowledge points automatically, so as to improves the efficiency and quality. Then, it uses the subjective weighting method combined with the expert experience to generate the learning degree matrix of students on knowledge points based on dynamic data of the students' records. Finally, the DBSCAN clustering algorithm is used to cluster the personalized learning characteristics of students according to the learning degree matrix. The experimental result shows that the algorithm can deal with massive data automatically and effectively, and analyze the students' learning degree on knowledge points comprehensively and accurately, so as to classify students and realize personalized teaching.

Architecture and optimization of data mining modeling for visualization of knowledge extraction: Patient safety care

Visualization of the knowledge extraction process is a front line to reveal the detail process and data structure, which is an advanced technique for the presentation of data modeling. However, the mechanisms for healthcare are challenging and dynamic processes to gain a clear insight or understanding of patient care. In this paper, we proposed a new approach of architecture and optimization of data mining modeling for visualization of knowledge extraction by analyzing clinical data sets to define the determinant attributes through modeling techniques. Therefore, architecture for the visualization of the knowledge extraction process is a systematic approach to support users to the best of their knowledge of the issues over the challenge of visualizing techniques. The proposed approach is capable and dynamic to handle and analyze large-scale data in its dimension and context. Such a variable is defined using various techniques to characterize them towards the detection of determinant variables as its influential circumstance. We focused on modeling based visualization as model representation, factor's interaction and integration. The detection process experimented in a different approach and justification as discussed in section five. The finding showed a deep understandability for an advanced and dynamic data mining modeling techniques to integrate applications with domain contexts for the optimal and understandable decision process. The strength of this approach is the depth for visualization towards the knowledge extraction process and its understandability for users as per their background and circumstances. It is also essential to inference for architecture based modeling and visualization for large scale data. Researchers, physicians, experts, and other users are the potentials to refer to these novel ideas and findings.

Dynamic Optimization Model of Container Route Loading for International Logistics Ships

Wang, D., 2019. Dynamic optimization model of container route loading for international logistics ships. In: Guido-Aldana, P.A. and Mulahasan, S. (eds.), Advances in Water Resources and Exploration. Journal of Coastal Research, Special Issue No. 93, pp. 1111–1116. Coconut Creek (Florida), ISSN 0749-0208.Aiming to improve the ability of automatic scheduling for the dynamic loading of shipping container routes in international logistics environment, an automatic scheduling method based on information fusion of association rules for the dynamic loading of shipping container routes in international logistics environment is proposed. The auto-correlation feature scheduling method is used to mine the operation status of shipping container routes under the international logistics environment, and the reliability data of ship container routes operation under the international logistics environment are extracted. According to the results of ship container route stowage feature extraction, the information fusion and quantitative regression analysis, combined with the international logistics ship container route stowage feature scheduling method, are analyzed in this paper. The dynamic data mining of ship container route loading under the international logistics environment is realized. The characteristic distribution model of the ship container route operation state under the international logistics environment is constructed and combined with the information fusion method of association rules. Under the international logistics environment, the automatic scheduling of ship container route loading dynamic is realized. The simulation results show that the proposed method has higher accuracy and better anti-jamming performance under the international logistics environment, and improves the dynamic allocation ability of the ship container route.

Dynamics reconstruction and classification via Koopman features.

Knowledge discovery and information extraction of large and complex datasets has attracted great attention in wide-ranging areas from statistics and biology to medicine. Tools from machine learning, data mining, and neurocomputing have been extensively explored and utilized to accomplish such compelling data analytics tasks. However, for time-series data presenting active dynamic characteristics, many of the state-of-the-art techniques may not perform well in capturing the inherited temporal structures in these data. In this paper, integrating the Koopman operator and linear dynamical systems theory with support vector machines, we develop an ovel dynamic data mining framework to construct low-dimensional linear models that approximate the nonlinear flow of high-dimensional time-series data generated by unknown nonlinear dynamical systems. This framework then immediately enables pattern recognition, e.g., classification, of complex time-series data to distinguish their dynamic behaviors by using the trajectories generated by the reduced linear systems. Moreover, we demonstrate the applicability and efficiency of this framework through the problems of time-series classification in bioinformatics and healthcare, including cognitive classification and seizure detection with fMRI and EEG data, respectively. The developed Koopman dynamic learning framework then lays a solid foundation for effective dynamic data mining and promises a mathematically justified method for extracting the dynamics and significant temporal structures of nonlinear dynamical systems.

Real-time co-creation and nowness service: lessons from tourism and hospitality

ABSTRACTBrands take advantage of technology, social media and constant connectivity to foster organic consumer engagement and interactions towards co-creating personalised customer service. Real-time service offers dynamic engagement with connected consumers. Brands in tourism and hospitality use technology to dynamically enhance consumer experience through co-creation. The integration of real-time consumer intelligence, dynamic big data mining, artificial intelligence, and contextualisation can transform service co-creation by mobilising recourses in the ecosystem. Nowness service emerges by dynamically engaging consumers in experience cocreation in real time. It has five interconnected characteristics that revolutionise the tourism and hospitality, namely: real-time, co-creation, data-driven, consumer-centric and experience co-creation.

Research on distributed dynamic traffic data mining based on vehicular ad hoc network

There are some problems in current traffic data mining methods, such as poor accuracy, high energy consumption, high packet loss rate and lengthy times. A distributed dynamic traffic data mining method based on vehicular ad hoc network is proposed. Before mining, congestion, routing changes, data channel errors and connection interruptions in vehicular ad hoc networks are detected respectively. Particle Swarm Optimisation (PSO) is introduced to realise traffic data classification mining based on vehicular ad hoc networks under network coding and clustering fusion. The simulations results show that the method has high accuracy and efficiency, low-energy consumption and packet loss rate, and high feasibility.

Research on distributed dynamic traffic data mining based on vehicular ad hoc network

There are some problems in current traffic data mining methods, such as poor accuracy, high energy consumption, high packet loss rate and lengthy times. A distributed dynamic traffic data mining method based on vehicular ad hoc network is proposed. Before mining, congestion, routing changes, data channel errors and connection interruptions in vehicular ad hoc networks are detected respectively. Particle Swarm Optimisation (PSO) is introduced to realise traffic data classification mining based on vehicular ad hoc networks under network coding and clustering fusion. The simulations results show that the method has high accuracy and efficiency, low-energy consumption and packet loss rate, and high feasibility.

Stability-based model for evacuation system using agent-based social simulation and Monte Carlo method

The agent-based modelling is used for modelling many complex dynamic systems, especially those including autonomous individuals such as human beings' societies, animals' societies, robots, insects' societies, etc. Evacuation systems such as those needed for supermarket buildings are considered as complex dynamic systems. In these systems, we have to deal with the problem of rescuing a high number of people of different ages, sex, physical characteristics, etc. Furthermore, this process mostly runs in buildings with different constraints like locations of the rows of shelves, exit gates, etc. On one hand, in order to deal with disasters such as fire propagation, studying this kind of system using a dynamic model has a great importance in order to avoid the maximum of casualties. On the other hand, the model that represents this kind of system must take into account several factors such as time, the building's characteristics and people's characteristics. In this study, an agent-based model has been designed to visualise the dynamic system behaviour via these internal entities that often interact. Additionally, we use some dynamic data mining methods such as Monte Carlo method to calculate the stable characteristics of this model via probabilistic approach.