Intelligent Data Processing Research Articles

A Mechanism for a Solution Search within the Formalism of Functional Neural Networks

This paper describes the development of the formalism of functional neuron networks (FN-networks), which is designed to create a range of information systems that perform intelligent computer processing of heterogeneous data from various information sources in automated decision support systems. The problems that affect the rate of finding solutions are considered. To increase this rate, it is recommended to use an archive of previously found solutions. We propose a method for generalizing the solutions, which makes it possible to reduce the archive size and expand the applicability of the found generalizations to a wider class of possible problems.

Visualization techniques to support CCTV operators of smart city services

In this paper visualization techniques for modern closed circuit television (CCTV) smart city services are discussed with application to prevention of threats. Unconventional approaches to the intelligent visual data processing are proposed in order to support video surveillance operators, thus to make their work less exhaustive and more effective. Although registration of a huge amount of video data requires development of intelligent and automatic signal processing information extraction techniques, improvement of visualization methods for operators is also a very important task, because of the crucial role the human factor plays and should always play in the decision making, e.g. in the operator reactions to various crisis situations, which can never be fully eliminated by artificial intelligence. Four software based mechanisms connected with a standard or with a slightly extended hardware are proposed as options for the CCTV operators. They utilize rather known ideas but are implemented with new extensions to original algorithms, as well as with additional, innovative modifications and solutions (not presented in the literature). With them they become reliable and efficient tools for the CCTV systems. First, generation of cylindrical panoramas is suggested in order to make long-time video content analysis of a defined area easier and faster. Using panoramas it is possible to reduce the time that is required to watch the video by a factor of hundreds or even thousands and perform an efficient compression of the video stream for the long-time storage. Second, the controlled stereovision option is discussed for quicker and more precise extraction of relevant information from the observed scene. Third, the thermo-vision is analyzed for faultless detection of pedestrians at night. Finally, a novel high dynamic range (HDR) technique is proposed, dedicated to the CCTV systems, in contrast to other typical entertainment oriented HDR approaches, for clear visualization of important and meaningful image details, otherwise invisible. We validated usefulness of the proposed techniques with many experiments presented in this paper.

Research and Application of Key Technologies for Medical Image Intelligence Knowledge Discovery and Data Processing

Hospitals have accumulated a large amount of medical image data which need to be analyzed and integrated so as to be able to find the needed medical image in time, which is the basis of key technologies such as intelligent diagnosis of diseases. Meanwhile, through the analysis and integrated processing of medical images, the potential value of existing medical image data can be fully explored. In this paper, the key technologies in the intelligent image knowledge discovery system and the characteristics of medical image data are studied and improved. In this paper, the characteristics of knowledge discovery and medical image data are comprehensively considered, and RDM texture features are selected as the feature representation of medical images. An improved RDM operator is proposed and proved by experimental results. Experimental results show that the improved RDM coding method can improve the stability of medical image data expression.

INFORMATION TECHNOLOGY OF AUTOMATIC DETECTION AND IDENTIFICATION OF STATIONARY OBJECTS WITH UNMANNED AERIAL VEHICLES

The subject matter of the article is the process of developing information technology for the automated detection and identification of stationary objects by unmanned aerial vehicles arises. The goal of the study is to development of the main points for information technology of automated detection and identification of stationary objects by unmanned aerial vehicles. The tasks to be solved are: the structural diagram of the preparatory stage of information technology for automated detection and identification of stationary objects is constructed; the structural diagram of the basic, additional and final stages of information technology automated detection and identification of fixed objects is constructed. General scientific and special methods of scientific knowledge are used. One of the most effective approaches to the recognition and identification of objects is an approach based on the use of deep learning methods. A new model of UAV motion is proposed based on image recognition methods. The methods of pattern recognition with application of neural networks are considered in detail in this work too. The following results are obtained. The developed information technology is implemented in four stages: preparatory, basic, additional and final. Each stage consists of separate procedures aimed at collecting, processing, storing and transmitting information during the flight UAV. Conclusions . Information technology for the automated detection and identification of stationary objects by unmanned aerial vehicles is based on the knowledge-oriented representation of the stages of image processing of objects on digital aerial photographs on board the UAV. This allows to provide intelligent real-time data processing, changing UAV flight routes depending on the objects detected to improve the effectiveness of the search tasks. Further development of this information technology lies in the development of automated methods of planning UAV routes, automatic change of route parameters in flight processes (performance of a flight task), based on knowledge-oriented technologies. Information technology for the automated detection and identification of stationary objects by unmanned aerial vehicles can become an element of intelligent decision support systems for the use of UAVs (teams of UAVs) to search for both stationary and dynamic objects.

Urban expressway parallel pattern recognition based on intelligent IOT data processing for smart city

With the sustained and rapid development of the social economy and the rapid growth of urban vehicles, urban expressway has developed rapidly. As the roadmap of urban traffic, the urban expressway has a relatively high and stable driving speed, and also bears a large amount of urban traffic. However, in recent years, with the expansion of the city scale, the congestion of urban expressways has become increasingly severe. In various areas of the merged area, due to various factors such as mismatched traffic capacity and reduced driving speed, it is easy to cause deterioration of road conditions in a short period of time and cause more secondary accidents. In order to reduce the incidence of expressway traffic accidents and to avoid as much as possible the casualties and property losses caused by accidents, Intelligent Transportation Systems (ITS) supported by information technology, data communication transmission technology, control technology and traffic engineering were introduced. With the rise of artificial intelligence and the continuous development of ITS, the video acquisition methods of real-time traffic flow data and the image recognition ability of video sequences continue to improve, providing theoretical basis and technical support for the research of urban expressway parallel pattern recognition. Aiming at the shortcomings of traditional pattern recognition methods, such as weak anti-interference to complex traffic environment and low correct recognition rate, this paper studies the pattern recognition method based on image processing, and selects the fuzzy C-means clustering in the currently used clustering methods (FCM) algorithm Because the FCM algorithm cannot obtain the global optimal solution and need to determine the number of cluster categories in advance, this paper uses ReliefF algorithm and Particle Swarm Optimization (PSO) to compare the feature weight and number of clusters of traditional FCM algorithm. Make improvements. Through the experimental analysis of the acquired video images, the results show that the improved FCM algorithm based on the proposed method has better real-time and accuracy in the application of urban expressway parallel pattern recognition.

CONCEPT OF INFORMATION PROCESSES ORGANIZATION IN HUMAN VISUAL SYSTEM

Recent studies have shown that both traditional and modern (electronic) visual media significantly affect the processes occurring in the visual system of children and adolescents, iin the development of which the concept of controlled and uncontrolled elements is used. When studying the adaptation of the visual system to a visual load, ensuring the uptake, transmission and processing of visual information, its structural and functional organization is taken into account. The proposed summarized scheme of information processes in the visual system takes into account and significantly supplements the main provisions of the object−oriented model of selective visual attention, based on current methods of intelligent data processing. The results of the study indicate the complexity of the visual information transformation path from a visual stimulus to the creation and awareness of the image, occurring in the higher parts of the brain. The whole apparatus of encoding, transmitting, processing and perceiving visual information is useless if the guidance and focusing unit does not provide a clear and undistorted image of the objects of the outside world on the retina. In case of any malfunctions of the first unit or in the presence of defects in the visual system, the processes of finding compensation for this condition and modes of operation are started, which allows to obtain the most complete and high−quality perception of visual objects. These processes can lead to the formation of a visual system with sufficiently high visual functions or monocular one, if the compensation of existing problems will have a high "price". With the help of the proposed concept of organization of information processes in the visual system it is possible to assess the role of each of its considered blocks not only in the perception of visual information, but also the formation of this system in children and adolescents. Key words: visual system, information processes, visual information.

Reliability Analysis of Large Span Cable-stayed Bridges Based on Support Vector Machine

a method of combining the support vector machine and the intelligent algorithm to perform reliability analysis on large span cable-stayed bridges was proposed in this paper. The algorithm is verified by an example, which shows that the algorithm has higher precision and can be extended to the actual project. Therefore, this paper takes Jiangmen North Street Waterway Bridge as the engineering background, uses the finite element software ANSYS to establish the cable-stayed bridge model and MATLAB software to compile the intelligent algorithm and data processing. It mainly analyzes the reliability of the main beam mid-span deflection, the cable stress and main tower stress of the North Street Waterway Bridge. Finally, the general limit range method is used to estimate the reliability index of the North Street waterway bridge structure system. The results show that the cable stay failure has the greatest impact on the reliability of the entire structural system, so it is necessary to pay attention to the maintenance and monitoring of stay cables.

Proximity‐based cloud resource provisioning for deep learning applications in smart healthcare

AbstractDeep learning is a powerful technology that enables intelligent data processing in the smart healthcare domain. Inspired by the tremendous processing power of cloud computing, the training process and the model repository of deep learning are moved to the cloud. Cloud‐assisted deep learning applications enable smart mobile users to experience quick predictive results. Health professionals use smart mobile devices to convey recordings of the patient and to receive the best inference results. The mobility of these devices causes severe performance degradation as it increases the distance between its current location and the edge cloud where the virtual machines are provisioned. Therefore, mobility‐based resource provisioning to identify a suitable server based on deadline constraints, available resources, and cost metrics is crucial. This paper proposes a proximity‐based resource provisioning technique that guarantees minimal delay in obtaining inference results with a local mobile cloud system. The proposed technique comprises two algorithms (a) deadline‐based initial resource provisioning and (b) resource migration and provisioning at suitable cloudlet during location change. The proposed technique is implemented in a mobile cloud platform running the inference method of a smart mobile healthcare application. The performance results show that the proposed technique outperforms the state‐of‐the‐art techniques in terms of the response time, deadline meeting percentage, and system utilization.

IoT and Machine Learning - A Technological Combination for Smart Application

With the rapid developments in hardware, software and communication technologies, a new era of internet connected sensory devices has begun which provides a link between physical and cyber worlds. It is estimated that by 2020 internet connected devices being used will be between 25 and 50 billion. Internet connected devices referred as Internet of Things. IoT provides a huge range of services and applications covering all the domains ranging from infra-structure, retail, transportation and personal health care. Fughua etal. (2015) poised that IoT has empowered the development in internet protocols and communication technologies. In IoT applications, intelligent processing and analysis of big data act as key for their development. Data science technologies help to find new pattern and new insights from data to make IoT applications more intelligent. Data science with IoT is mainly used in various sectors dealing with volume, velocity and pattern recognition. Because of predictive analysis of machine learning, software becomes able to predict incoming desired and undesired events. Therefore, machine learning system is not only recognizing the abnormal behaviour but also help to understand and establish long term trends.A continue correction and supervision is required for effectiveness and efficiency in data analysis. This paper is having two sections- pertaining the different applications of IoT where machine learning helps to make the intelligent system and futuristic scope of IoT and machine learning and how these two technologies help in development of communication devices. This paper will provide the answers to questions such as what is the taxonomy of machine learning that can be adopted in IoT, how can machine learning be applied to IoT applications.

The Design of Intelligent Transportation Video Processing System in Big Data Environment

The intelligent transportation system in big data environment is the development trend of future transportation system, which effectively integrates advanced information technology, data communication transmission technology, electronic sensor technology, control technology and computer technology and is applied to overall ground transportation management. Hence, it establishes a real-time, accurate, efficient and comprehensive transportation management system that functions in a wide range and all-round aspects. In order to meet the demands of the intelligent transportation big data processing, this paper puts forward a high performance computing architecture of large-scale transportation video data management based on cloud computing, designs a parallel computing model containing the distributed file system and distributed computing system to solve the problems such as flexible server increase or decrease, load balancing and flexible dynamic storage increase or decrease, computing power and great improvement of storage efficiency. On the basis of this technical architecture, the system adopts BP neural network-related algorithms to extract the static transportation signs in road videos, and uses interframe difference algorithm and Gaussian mixture model (GMM) fusion algorithm to extract the moving targets in road transportation videos. In this way, they are taken as important integral parts and data sources of key frames of intelligent video image recognition to improve the recognition ability of key frames and eventually utilize semantic recognition model based on CNN (Convolutional Neural Network) to complete the intelligent recognition of whole transportation videos. Through network pressure test, computing ability test, recognition ability test and other tests, it has been proved that the intelligent transportation video processing system based on big data environment is successful and the design scheme of this system has strong practical application value.

Improving Human-Robot Interaction Utilizing Learning and Intelligence: A Human Factors-Based Approach

Several decades of development in the fields of robotics and automation have resulted in human–robot interaction is commonplace, and the subject of intense study. These interactions are particularly prevalent in manufacturing, where human operators (HOs) have been employed in numerous robotics and automation tasks. The presence of HOs continues to be a source of uncertainty in such systems, despite the study of human factors, in an attempt to better understand these variations in performance. Concurrent developments in intelligent manufacturing present opportunities for adaptability within robotic control. This article examines relevant human factors and develops a framework for integrating the necessary elements of intelligent control and data processing to provide appropriate adaptability to robotic elements, consequently improving collaborative interaction with human colleagues. A neural network-based learning approach is used to predict the influence on human task performance and use these predictions to make informed changes to programed behavior, and a methodology developed to explore the application of learning techniques to this area further. This article is supported by an example case study, in which a simulation model is used to explore the application of the developed system, and its performance in a real-world production scenario. The simulation results reveal that adaptability can be realized with some relatively simple techniques and models if applied in the right manner and that such adaptability is helpful to tackle the issue of performance disparity in manufacturing operations. Note to Practitioners —This article presents research into the application of intelligent methodologies to this problem and builds a framework to describe how this information can be captured, generated, and used within manufacturing production processes. This framework helps identify which areas require further research and serves as a basis for the development of a methodology, by which a control system may enable adaptable behavior to reduce the impact of human performance variation and improve human–machine interaction (HMI). This article also presents a simulation-based case study to support the development and evaluate the presented control system on a representative real-world problem. The methodology makes use of a machine-learning approach to identify the complex influence of several identified human factors on human performance. This knowledge can be used to adjust the robotic behavior to match the predicted performance of multiple different operators over different scenarios. This adaptability reduces performance disparity by reducing idle times and enabling leaner production through workpiece-in-progress reduction. Future work will focus on expanding the intelligent capabilities of the proposed system to deal with uncertainty and improve decision-making ability.

DeepOcean: A General Deep Learning Framework for Spatio-Temporal Ocean Sensing Data Prediction

The emerging Internet of Underwater Things (IoUT) and deep learning technologies are combined to provide a novel, intelligent, and efficient data processing and analyzing schema, which facilitates the sensing and computing abilities for the smart ocean. The underwater acoustic (UWA) communication network is an essential part of IoUT. The thermocline, in which temperature and density change drastically, affects the connectivity and communication performance between IoUT nodes, as well as the network topologies. In this paper, we propose DeepOcean, a deep learning framework for spatio-temporal ocean sensing data prediction, which consists of a generative module and a prediction module. We implement the generative module with a multi-layer perceptron (MLP) to capture the spatial dependencies and construct high-resolution data based on sparse observations. The prediction module is implemented with our proposed Multivariate Convolutional LSTM (MVC-LSTM) neural network, which captures both the spatio-temporal dependencies and the interactions of different oceanographic features for prediction. We evaluate the effectiveness of DeepOcean with Argo data, where the proposed framework outperforms fifteen state-of-art baselines in terms of accuracy.

A new Edge Architecture for AI-IoT services deployment

Abstract Artificial intelligence (AI) and Internet of things (IoT) have progressively emerged in all domains of our daily lives. Nowadays, both domains are combined in what is called artificial intelligence of thing (AIoT). With the increase of the amount of data produced by the myriad of connected things and the large wide of data needed to train Artificial Intelligence models, data processing and storage became a real challenge. Indeed, the amount of data to process, to transfer by network and to treat in the cloud have call into question classical data storage and processing architectures. Also, the large amount of data generated at the edge has increased the speed of data transportation that is becoming the bottleneck for the cloud-based computing paradigms. The post-cloud approaches using Edge computing allow to improve latency and jitter. These infrastructures manage mechanisms of containerization and orchestration in order to provide automatic and fast deployment and migration of services such as reasoning mechanisms, ontology, and specifically adapted artificial intelligence algorithms. In this paper we propose a new architecture used to deploy at edge level micro services and adapted artificial intelligence algorithms and models.

FENCE: Fast, ExteNsible, and ConsolidatEd Framework for Intelligent Big Data Processing

The proliferation of smart devices and the advancement of data-intensive services has led to explosion of data, which uncovers massive opportunities as well as challenges related to real-time analysis of big data streams. The edge computing frameworks implemented over manycore systems can be considered as a promising solution to address these challenges. However, in spite of the availability of modern computing systems with a large number of processing cores and high memory capacity, the performance and scalability of manycore systems can be limited by the software and operating system (OS) level bottlenecks. In this work, we focus on these challenges, and discuss how accelerated communication, efficient caching, and high performance computation can be provisioned over manycore systems. The proposed Fast, ExteNsible, and ConsolidatEd (FENCE) framework leverages the availability of a large number of computing cores and overcomes the OS level bottlenecks to provide high performance and scalability for intelligent big data processing. We implemented a prototype of FENCE and the experiment results demonstrate that FENCE provides improved data reception throughput, read/write throughput, and application processing performance as compared to the baseline Linux system.

Predicting students' academic performance: Levy search of cuckoo-based hybrid classification

Educational Data Mining (EDM) exists as a novel trend in the Knowledge Discovery in Databases (KDD) and Data Mining (DM) field that concerns in mining valuable patterns and finding out practical knowledge from the educational systems. However, evaluating the educational performance of students is challenging as their academic performance pivots on varied constraints. Hence, this paper intends to predict the educational performance of students based on socio-demographic information. To attain this, performance prediction architecture is introduced with two modules. One module is for handling the big data via MapReduce (MR) framework, whereas the second module is an intelligent module that predicts the performance of the students using intelligent data processing stages. Here, the hybridisation of classifiers like Support Vector Machine (SVM) and Deep Belief Network (DBN) is adopted to get better results. In DBN, Levy Search of Cuckoo (LC) algorithm is adopted for weight computation. Hence, the proposed prediction model SVM-LCDBN is proposed that makes deep connection with the hybrid classifier to attain more accurate output. Moreover, the adopted scheme is compared with conventional algorithms, and the results are attained.

Predicting students' academic performance: Levy search of cuckoo-based hybrid classification

Educational Data Mining (EDM) exists as a novel trend in the Knowledge Discovery in Databases (KDD) and Data Mining (DM) field that concerns in mining valuable patterns and finding out practical knowledge from the educational systems. However, evaluating the educational performance of students is challenging as their academic performance pivots on varied constraints. Hence, this paper intends to predict the educational performance of students based on socio-demographic information. To attain this, performance prediction architecture is introduced with two modules. One module is for handling the big data via MapReduce (MR) framework, whereas the second module is an intelligent module that predicts the performance of the students using intelligent data processing stages. Here, the hybridisation of classifiers like Support Vector Machine (SVM) and Deep Belief Network (DBN) is adopted to get better results. In DBN, Levy Search of Cuckoo (LC) algorithm is adopted for weight computation. Hence, the proposed prediction model SVM-LCDBN is proposed that makes deep connection with the hybrid classifier to attain more accurate output. Moreover, the adopted scheme is compared with conventional algorithms, and the results are attained.

Principles of organizing earthquake forecasting based on multiparameter sensor-WEB monitoring data

The paper describes an approach that allows, basing on the data of multiparameter monitoring of atmospheric and ionospheric parameters and using ground-based and satellite measurements, to select from the data stream a time interval indicating the beginning of the final stage of earthquake preparation, and finally using intelligent data processing to carry out a short-term forecast for a time interval of 2 weeks to 1 day before the main shock. Based on the physical model of the lithosphere-atmospheric-ionospheric coupling, the precursors are selected, the ensemble of which is observed only during the precursory periods, and their identification is based on morphological features determined by the physical mechanism of their generation, and not on amplitude selection based on statistical data processing. Basing on the developed maquette of the automatic processing service, the possibility of real-time monitoring of the situation in a seismically active region will be demonstrated using the territory of the Kamchatka region and the Kuril Islands.

Review—Machine Learning Techniques in Wireless Sensor Network Based Precision Agriculture

The use of sensors and the Internet of Things (IoT) is key to moving the world’s agriculture to a more productive and sustainable path. Recent advancements in IoT, Wireless Sensor Networks (WSN), and Information and Communication Technology (ICT) have the potential to address some of the environmental, economic, and technical challenges as well as opportunities in this sector. As the number of interconnected devices continues to grow, this generates more big data with multiple modalities and spatial and temporal variations. Intelligent processing and analysis of this big data are necessary to developing a higher level of knowledge base and insights that results in better decision making, forecasting, and reliable management of sensors. This paper is a comprehensive review of the application of different machine learning algorithms in sensor data analytics within the agricultural ecosystem. It further discusses a case study on an IoT based data-driven smart farm prototype as an integrated food, energy, and water (FEW) system.

Global Mapping of GDP at 1 km2 Using VIIRS Nighttime Satellite Imagery

Frequent and rapid spatially explicit assessment of socioeconomic development is critical for achieving the Sustainable Development Goals (SDGs) at both national and global levels. Over the past decades, scientists have proposed many methods for estimating human activity on the Earth’s surface at various spatiotemporal scales using Defense Meteorological Satellite Program Operational Line System (DMSP-OLS) nighttime light (NTL) data. However, the DMSP-OLS NTL data and the associated processing methods have limited their reliability and applicability for systematic measuring and mapping of socioeconomic development. This study utilized Visible Infrared Imaging Radiometer Suite (VIIRS) NTL and the Isolation Forest machine learning algorithm for more intelligent data processing to capture human activities. We used machine learning and NTL data to map gross domestic product (GDP) at 1 km2. We then used these data products to derive inequality indexes (e.g., Gini coefficients) at nationally aggregate levels. This flexible approach processes the data in an unsupervised manner at various spatial scales. Our assessments show that this method produces accurate subnational GDP data products for mapping and monitoring human development uniformly across the globe.

Review on big data application of medical system based on fog computing and IoT technology

From the current general situation of big data in medical systems, most of the medical system architectures of comprehensive related literature are based on cloud computing. With the deepening of big data application in the medical system, the drawbacks of medical network systems are apparent, for example, long network time delay, cloud computing overload, information leakage. A new intelligent medical system based on fog computing and IoT technology is proposed to effectively solve the problem of big data application through the comprehensive analysis of many works of literature. Compared with the traditional cloud computing model, the system which adopts a distributed fog computing model based on edge computing has the advantages of reducing network delay and plays its benefits of distributed, edge and decentralization. That the system takes advantage of IoT’s features of multi-node, low-energy consumption and big data technology is a new type of medical system that integrates intelligence and big data application. The system is effective through the application and practice of many medical institutions. In short, this system has several characteristics. For example, it can effectively improve medical intelligence and big data processing ability, significantly reduce network delay, effectively improve data security and effectiveness, largely improve the management level and service quality of medical institutions, play the important role of artificial intelligence and big data in the medical field, and greatly improve disease screening rate and reduce misdiagnosis rate. Ultimately it leads to reducing the contradiction between doctors and patients, providing patients with more convenience, faster and more efficient service quality, and alleviating the current situation of difficult and time-consuming medical treatment.