Search

As the 5G environment is established due to the development of network and information and network technologies, wireless sensor network is drawing attention as a technology that will lead the information technology industry in the future. The sensor-based service must collect and process data recognized from various sensors and deliver information to users to understand. However, there is no research to visually express information about sensor resources to make it easier for users to understand. Therefore, this research proposes an efficient visualization model that is both realistic and economical. Then, we designed a scenario applied to real life and built a webpage.

With the continuous enrichment of scientific and technological means, the production of most chicken farms has been able to achieve automation, but for the dead and sick chickens in the farm, there is no automatic monitoring step, only through continuous manual inspection and discovery. In the face of this problem, there are many solutions to identify dead and sick chickens through sound and image, but they can not achieve the ideal effect. In this paper, a sensor detection method based on artificial intelligence is proposed. This method 1) The maximum displacement of chicken activity is measured by fastening a foot ring on each chicken, and the three-dimensional total variance is designed and calculated to represent the chicken activity intensity. 2) The detection terminal collects the sensing data of foot ring through ZigBee network. 3) The state of chicken (dead chicken and sick chicken) can be identified by machine learning algorithm. This method of artificial intelligence combined with sensor network not only has high recognition rate, but also can reduce the operation cost. The practical results show that the accuracy of the system to identify dead and sick chickens is 95.6%, and the cost of the system running for 4 years can be reduced by 25% compared with manual operation.

Applicability of the whispering gallery mode sensor in the form of the multiresonator imaging device for the atmospheric-relevant parameters monitoring has been demonstrated. The sensor design and the appropriate techniques for sensing data collection have been discussed. The sensor performance has been numerically and experimentally studied on examples of the temperature variation detection and the monitoring of small spherical microparticles ( $ ) that have been used to mimic the particulate contamination of the environment. The thermal sensitivity of the sensor on the level of 8.6 pm/°C has been experimentally demonstrated. The experimental results on the distinguishing of the microparticle concentrations (0.5% and 1%) via the wavelength sweeping technique and the results on the single particle detection under illumination at the fixed wavelength have been shown.

With the rapid development of smart cities, smart buildings are generating a massive amount of building sensing data by the equipped sensors. Indeed, building sensing data provides a promising way to enrich a series of data-demanding and cost-expensive urban mobile applications. In this paper, we study how to reuse building sensing data to predict traffic volume on nearby roads. Nevertheless, it is non-trivial to achieve accurate prediction on such cross-domain data with two major challenges. First, relationships between building sensing data and traffic data are not unknown as prior, and the spatio-temporal complexities impose more difficulties to uncover the underlying reasons behind the above relationships. Second, it is even more daunting to accurately predict traffic volume with dynamic building-traffic correlations, which are cross-domain, non-linear, and time-varying. To address the above challenges, we design and implement BuildSenSys, a first-of-its-kind system for nearby traffic volume prediction by reusing building sensing data. First, we conduct a comprehensive building-traffic analysis based on multi-source datasets, disclosing how and why building sensing data is correlated with nearby traffic volume. Second, we propose a novel recurrent neural network for traffic volume prediction based on cross-domain learning with two attention mechanisms. Specifically, a cross-domain attention mechanism captures the building-traffic correlations and adaptively extracts the most relevant building sensing data at each predicting step. Then, a temporal attention mechanism is employed to model the temporal dependencies of data across historical time intervals. The extensive experimental studies demonstrate that BuildSenSys outperforms all baseline methods with up to 65.3% accuracy improvement (e.g., 2.2% MAPE) in predicting nearby traffic volume., Comment: 17 pages; 17 figures. in IEEE Transactions on Mobile Computing

Calibration curves are essential constructs in analytical chemistry to determine parameters of sensing performance. In the classification of sensing data of complex samples without a clear dependen...

Reservoir-infiltration uranium deposits («sandstone» type) today are the main active source of uranium mineral raw materials in the world and the only one in Kazakhstan. Their main advantage in the form of better environmental friendliness, productivity and minimum production costs creates prospects for their further detection in various parts of the world. It is important to simplify and improve multi-stage, expensive and difficult geological exploration works for the purpose of forecasting and searching them with affordable innovative solutions. The available multispectral satellite imagery has opened up new opportunities for the study of uranium ore provinces. Mapping of uranium ore provinces based on multispectral satellite imagery allows them to be compared with certain key ore-controlling data from geological and geophysical studies. The near-surface visible nature of geotectonic structures, climatic conditions and zonal anomalies are more easily and efficiently visualized using modern space technologies and computer solutions. The explanation of the derived correlations with the geotectonic and climatic conditions allows the use of multispectral images in order to simplify and improve the quality of forecasting, prospecting and exploration of reservoir-infiltration uranium deposits. More advanced aerial and space remote sensing methods make it possible to detect surface anomalies associated with this type of ore. The scientific explanation of the nature of these anomalies and their role in the geological and genetic model of ore formation creates a solid theoretical basis for improving the exploration methodology. The convergence of the results obtained, their theoretical explanation, simplicity and convincingness of the results make it possible to make new predictions of promising areas of reservoir-infiltration uranium regions for several of the key ore-controlling factors and use this methodology in conjunction with other data from regional and local studies at all stages of exploration.

Remote sensing using drones has the advantage of being able to quickly monitor large areas such as rivers, oceans, mountains, and urban areas. In the case of applications dealing with large sensing data, it is not possible to send data from a drone to the server online, so it must be copied to the server offline after the end of the flight. However, online transmission is essential for applications that require real-time data analysis. The existing computation offloading scheme enables online transmission by processing large amounts of data in a drone and transferring it to the server, but without consideration for real-time constraints. We propose a novel computation offloading scheme which considers real-time constraints while minimizing the energy consumption of drones. Experimental results showed that the proposed scheme satisfied real-time constraints compared to the existing computation offloading scheme. Furthermore, the proposed technique showed that real-time constraints were satisfied even in situations where delays occurred on the server due to the processing of requests from multiple drones.

Even though Internet of things (IoT) sensing services are introduced in a wide range of areas, it is not applicable to mission-critical services due to the lack of the trustworthiness of the IoT sensing data. To address this problem, we propose TruSense, a novel trusted sensing framework for the IoT environment that covers end-to-end implementation from an IoT device to a cloud service. The TruSense framework includes a small sensing board, a communication protocol, and a cloud service for the trusted sensing in the IoT environment. To show our framework's feasibility, we design an ARM TrustZone-based IoT sensing board and implement an application and a trusted sensing service running in the Secure world. We also implement a cloud service for the trusted sensing in Google app engine, which is one of the widely used cloud services.

Part distortion during additive manufacturing (AM) may lead to catastrophic failure and significant waste of resources. Existing work often focuses on identification and detection of individual root causes such as melt pool geometries or extruder clogging to prevent part failures. Since the end-effect of major print failures can be the result of multiple error sources (including unknowns), relying on detection of individual root causes may misclassify some failed prints as successful. Instead, detecting end-effects or part distortion could provide early warning of major failures regardless of potential error sources. Distortion detection, however, currently involves computationally expensive simulation and analysis of sensing data. One promising solution is to adopt digital twin strategy to quickly compare model prediction to features extracted from in situ sensing data. This study extends the digital twin strategy to major distortion detection by developing (1) a multi-view optical sensing system for movable print beds and (2) failure detection methods by analyzing multi-view of part images layer by layer. Since the digital twin of actual prints at specific layers are generated offline, delay can be reduced to determine if a significant enough quality departure has occurred to justify termination of the print. In the experimental evaluation of this approach for a FDM machine with a moving print bed, failure was rapidly detected in two of the three test prints, while in the remaining print, failure was successfully detected after a short delay.

Upper limb rehabilitation is an effective methodology to restore and improve the functionality of patients after multiple medical events, such as strokes, arthroscopic surgery, and breast cancer surgery. High-quality rehabilitation training can promote the independent living of patients, thus enhancing the quality of life and reducing the financial burden. Traditional training sessions have some limitations, including high expenses, low compliance, and inaccurate evaluations. This paper presents a novel approach to assist healthcare professionals in assessing the functionality of upper limbs based on multimodal sensing data and deep learning algorithms. There are five different types of sensing data employed in the proposed approach: accelerometer, angular velocity, device orientation, RGB image, and depth image data. In order to assess the accuracy of training actions, the presented approach applies two machine learning algorithms, which are the dynamic time warping-K-nearest neighbor (DTW-KNN) algorithm and the long short-term memory (LSTM) neural network. The experimental results show that multimodal sensing data can improve the modeling accuracy compared with unimodal sensing data. The LSTM model can achieve better accuracy (96.3%) than DTW-KNN (74.07%) with multimodal sensing data. Moreover, LSTM performs extremely efficiently in modeling high-dimensional sensing data.

Urban functional zones (UFZs) are the urban spaces divided by various functional activities and are the basic units of daily human activities. UFZ mapping, which identifies the UFZ categories in different spatial areas of a city, is of considerable significance to urban management, design, and sustainable development. Various deep learning-based (DL-based) methods, which achieved remarkable results in an end-to-end supervised process, were proposed for UFZ mapping. However, the excellent performance of DL-based models relies heavily on a large number of well-annotated samples, which is impossible to obtain in practical UFZ mapping scenarios. Obtaining these well-annotated samples requires a lot of manual costs, which greatly limits the outcome of these methods in practical UFZ mapping tasks. In this article, we proposed a UFZ mapping method using OpenStreetMap-based (OSM-based) sample generation and the bi-branch neural network (BibNet). By adopting the idea of OSM-based sample generation, the proposed method utilized large-scale crowdsourcing labeled data (source domain) in OSM to generate a UFZ dataset (target domain) from OSM using remote sensing and social sensing data. Considering the inconsistent response of UFZ to various data observations, it is difficult to fully reflect the characteristics of UFZs using only remote sensing or social sensing data. We further proposed the BibNet, which utilizes two different deep neural network branches to comprehensively harness remote sensing images and social sensing data to map the UFZ. Experiments were conducted in Shenzhen City and Hong Kong City (Yau Tsim Mong District, Sham Shui Po District and Kowloon City District). The proposed method achieved an overall accuracy (OA) of 94.46% in the testing set of Shenzhen City and OA of 91.90% in the testing set of Hong Kong City.

Soil acidification is caused by natural paedogenetic processes and anthropogenic impacts but can be counteracted by regular lime application. Although sensors and applicators for variable-rate liming (VRL) exist, there are no established strategies for using these tools or helping to implement VRL in practice. Therefore, this study aimed to provide guidelines for site-specific liming based on proximal soil sensing. First, high-resolution soil maps of the liming-relevant indicators (pH, soil texture and soil organic matter content) were generated using on-the-go sensors. The soil acidity was predicted by two ion-selective antimony electrodes (RMSEpH: 0.37); the soil texture was predicted by a combination of apparent electrical resistivity measurements and natural soil-borne gamma emissions (RMSEclay: 0.046 kg kg−1); and the soil organic matter (SOM) status was predicted by a combination of red (660 nm) and near-infrared (NIR, 970 nm) optical reflection measurements (RMSESOM: 6.4 g kg−1). Second, to address the high within-field soil variability (pH varied by 2.9 units, clay content by 0.44 kg kg−1 and SOM by 5.5 g kg−1), a well-established empirical lime recommendation algorithm that represents the best management practices for liming in Germany was adapted, and the lime requirements (LRs) were determined. The generated workflow was applied to a 25.6 ha test field in north-eastern Germany, and the variable LR was compared to the conventional uniform LR. The comparison showed that under the uniform liming approach, 63% of the field would be over-fertilized by approximately 12 t of lime, 6% would receive approximately 6 t too little lime and 31% would still be adequately limed.

In this work we study the problem of collecting protected data in ad-hoc sensor network using a mobile entity called MULE. The objective is to increase information survivability in the network. Sensors from all over the network, route their sensing data through a data gathering tree, towards a particular node, called the $sink$. In case of a failed sensor, all the aggregated data from the sensor and from its children is lost. In order to retrieve the lost data, the MULE is required to travel among all the children of the failed sensor and to re-collect the data. There is a cost to travel between two points in the plane. We aim to minimize the MULE traveling cost, given that any sensor can fail. In order to reduce the traveling cost, it is necessary to find the optimal data gathering tree and the MULE location. We are considering the problem for the unit disk graphs (UDG) and Euclidean distance cost function. We propose a primal-dual algorithm that produces a $\left(20+\varepsilon\right)$-approximate solution for the problem, where $\varepsilon\rightarrow0$ as the sensor network spreads over a larger area. The algorithm requires $O\left(n^{3}\cdot\varDelta\left(G\right)\right)$ time to construct a gathering tree and to place the MULE, where $\varDelta\left(G\right)$ is the maximum degree in the graph and $n$ is the number of nodes., Comment: 27 pages, 5 figures

Internet of Things (IoT) is considered the future network to support wireless communications. To realize an IoT network, sufficient spectrum should be allocated for the rapidly increasing IoT devices. Through cognitive radio, unlicensed IoT devices exploit cooperative spectrum sensing (CSS) to opportunistically access a licensed spectrum without causing harmful interference to licensed primary users (PUs), thereby effectively improving the spectrum utilization. However, an open access cognitive IoT allows abnormal IoT devices to undermine the CSS process. Herein, we first establish a hard‐combining attack model according to the malicious behavior of falsifying sensing data. Subsequently, we propose a weighted sequential hypothesis test (WSHT) to increase the PU detection accuracy and decrease the sampling number, which comprises the data transmission status‐trust evaluation mechanism, sensing data availability, and sequential hypothesis test. Finally, simulation results show that when various attacks are encountered, the requirements of the WSHT are less than those of the conventional WSHT for a better detection performance.

Characterizing risky driving behavior is crucial in a connected vehicle environment, particularly to improve driving experience through enhanced safety features. Artificial intelligence-backed solutions are vital components of the modern transportation. However, such systems require significant volume of driving event data for an acceptable level of performance. To address the issue, this study proposes a novel framework for precise risky driving behavior detection that takes advantage of an attention-based neural network model. The proposed framework aims to recognize five driving events including harsh brake, aggressive acceleration, harsh left turn and harsh right turn alongside the normal driving behavior. Through numerical results, it is shown that the proposed model outperforms the state-of-the-art solutions by reaching an average accuracy of 0.96 and F1-score of 0.92 for all classes of driving events. Thus, it reduces the false positive instances compared to the previous models. Furthermore, through extensive experiments, structural details of the attention-based neural network is investigated to provide the most viable configuration for the analysis of the vehicular sensory data.

Accurate multiphase flowrate measurement is challenging but vital in the energy industry to monitor the production process. Machine learning has recently emerged as a promising method for estimating multiphase flowrates based on different conventional flow meters. In this paper, we propose a Convolutional Neural Network (CNN)-Long-Short Term Memory (LSTM) model and a Temporal Convolutional Network (TCN) model to estimate the volumetric liquid flowrate of oil/gas/water three-phase flow based on the Venturi tube. The volumetric flowrates of the liquid and gas phase vary from 0.1 - 10 m3/h and 7.6137 - 86.7506 m3/h, respectively. We collected time series sensing data from a Venturi tube installed in a pilot-scale multiphase flow facility and utilized single-phase flowmeters to acquire reference data before mixing. Experimental results suggest that the proposed CNN-LSTM and TCN models can effectively deal with the time series sensing data from the Venturi tube and achieve a good accuracy of multiphase flowrate estimation under different flow conditions. TCN achieves a better accuracy for both liquid and phase flowrate estimation than CNN-LSTM. The results indicate the possibility of leveraging conventional flow meters for multiphase flowrate estimation under various flow conditions.

The electrochemical biosensors are a class of biosensors which convert biological information such as analyte concentration that is a biological recognition element (biochemical receptor) into current or voltage. Electrochemical biosensors depict propitious diagnostic technology which can detect biomarkers in body fluids such as sweat, blood, feces, or urine. Combinations of suitable immobilization techniques with effective transducers give rise to an efficient biosensor. They have been employed in the food industry, medical sciences, defense, studying plant biology, etc. While sensing complex structures and entities, a large data is obtained, and it becomes difficult to manually interpret all the data. Machine learning helps in interpreting large sensing data. In the case of biosensors, the presence of impurity affects the performance of the sensor and machine learning helps in removing signals obtained from the contaminants to obtain a high sensitivity. In this review, we discuss different types of biosensors along with their applications and the benefits of machine learning. This is followed by a discussion on the challenges, missing gaps in the knowledge, and solutions in the field of electrochemical biosensors. This review aims to serve as a valuable resource for scientists and engineers entering the interdisciplinary field of electrochemical biosensors. Furthermore, this review provides insight into the type of electrochemical biosensors, their applications, the importance of machine learning (ML) in biosensing, and challenges and future outlook.

This is the era of Intelligent cognitive radio network technology that provides the available spectrum with efficient utilization. Cognitive Radio technology must promise to allow interference-free spectrum access by users. The paper discusses the several attacks and motives of attacks. The authentication mechanism role to prevent the attacks for hassle-free spectrum utilization is demonstrated. In this paper, resolving the cognitive network security issues by the authentication mechanism and the methods and need of authentication is discussed. This paper addresses the research challenges in the way of securing the cognitive radio network and countermeasures in CRN security strategies. Cognitive radio is an empowering innovation that guarantees to achieve spectrum utilization. In cognitive radio networks, several security threats affect the process of cognitive radio. Spectrum sensing data falsification (SSDF) attack is most disruptive in which the malicious users degrade the decision-making process by sending the false sensing reports to data fusion centres thus preventing honest users from utilizing the spectrum. Hence, security is a very important issue in cognitive radio networks that needs to be addressed for proper utilization of available spectrum by the users. Cognitive radio technology must promise secure spectrum dynamic access to users. In this paper, to counter the SSDF attack, the trust-based security mechanism is demonstrated to authenticate the honest users and it is observed that the proposed framework in the MATLAB environment is efficient and able to detect malicious users. Cognitive radio technology is the strategy applied to the spectrum to make it efficient for wireless communication. The strategy is an intelligent way to access the spectrum as it can learn its environment and make decisions by easy adaptation of operating parameters. The multiple nodes scenario is a good perspective. Software-defined radio is an essential component of cognitive radio Here, secondary users can access the spectrum to primary users whenever their vacant spectrum is available. The initial step is to sense the spectrum available further steps are spectrum decision making, spectrum management, and spectrum mobility. The network is vulnerable to various attacks on spectrum sensing and policy protocols which lead to disturbing functionality of cognitive radio technology. The defence mechanism based on public-key cryptography is proposed in which PU is authenticated by appending signature provided to PU signal. Authentication with a tag to the primary users is another perspective proposed. CRN technology should provide integrity, confidentiality and authenticity to the users.

One of most emerging technology in the recent years in the field of wireless communication is the Cognitive Radio (CR) technology, which reduces spectrum scarcity significantly. The main function of CR technology is detecting spectrum holes or unused spectrum of primary users (PUs), also called as licensed users, and assigning this unused spectrum to the secondary users (SUs), also called unlicensed users. As the CR technology is open to every user, there are many security issues such as Primary User Emulsion Attack (PUEA), Jamming Attack, Spectrum Sensing Data Falsification (SSDF) Attack, Lion Attack, and Sink Hole Attack and so on. SSDF attack is the one of major security attack in cognitive radio in which a malicious user sends false data intentionally to the other secondary users. The main aim of the SSDF attack is to disturb the communication between the secondary users or to gain more channel resources. One of the solutions to mitigating SSDF attack is the cooperative spectrum sensing. In this paper, we propose a new algorithm of cooperative sensing based on trust values of secondary users, and compares with the conventional cooperative spectrum sensing with the proposed algorithm. The simulation of cooperative sensing also performed in both time variant channel and time invariant (Rayleigh) channel. The authors also compare the three basic hard fusion techniques such as AND, OR, MAJORITY rule

Vehicle technology development drives economic development but also causes severe mobile pollution sources. Eco-driving is an effective driving strategy for solving air pollution and achieving driving safety. The on-board diagnostics II (OBD-II) module is a common monitoring tool used to acquire sensing data from in-vehicle electronic control units. However, different vehicle models use different controller area network (CAN) standards, resulting in communication difficulties, however, relevant literature has not discussed compatibility problems. The present study researched and developed the universal OBD-II module, adopted deep learning methods to evaluate fuel consumption, and proposed an intuitive driving graphic user interface design. In addition to using the universal module to obtain data on different CAN standards, this study used deep learning methods to analyze the fuel consumption of three vehicles of different brands on various road conditions. The accuracy was over 96%, thus validating the practicability of the developed system. This system will greatly benefit future applications that employ OBD-II to collect various types of driving data from different car models. For example, it can be implemented for achieving eco-driving in bus driver training. The developed system outperforms those proposed by previous research regarding its completeness and universality.

Including members of the public in the development of effective environmental monitoring systems is gaining traction. This research assesses the potential for a hybrid monitoring system for the case of coral at the Great Barrier Reef. Based on a review of citizen-derived data sources, the paper first develops a framework and then populates it with five datasets. These are then compared based on data volumes, type of data, spatial coverage, and bleaching patterns. The results reveal the inherent difficulties – both in terms of quantity and quality – for collective sensing data (Twitter in this case) and more structured human sensors approaches (Eye on the Reef Sightings). However, more targeted approaches, such as CoralWatch and tourism-operator based data collection, emerged as important contributors to information generation on the state of coral. Citizen-based data that either deliver a high data density per location, a wide geographic coverage, or regular observations over time are particularly valuable. Recommendations are made for developing a hybrid monitoring system that integrates citizen-derived with professionally collected data.

In this study, under the assumption that a robot (1) has a remotely controllable yawing camera and (2) moves in a uniform linear motion, we propose and investigate how to improve the target recognition rate with the camera, by using wireless feedback loop control. We derive the allowable data rate theoretically, and, from the viewpoint of error and delay control, we propose and evaluate QoS-Hybrid ARQ schemes under data rate constraints. Specifically, the theoretical analyses derive the maximum data rate for sensing and control based on the channel capacity is derived with the Shannon-Hartley theorem and the path-loss channel model inside the human body, i.e. CM2 in IEEE 802.15.6 standard. Then, the adaptive error and delay control schemes, i.e. QoS-HARQ, are proposed considering the two constraints: the maximum data rate and the velocity of the camera's movement. For the performance evaluations, with the 3D robot simulator GAZEBO, we evaluated our proposed schemes in the two scenarios: the static environment and the dynamic environment. The results yield insights into how to improve the recognition rate considerably in each situation.

The purpose of this research is how to make an air condition monitoring system by considering the concentration value of carbon monoxide in Riau Province. The technology used to support monitoring system of carbon monoxide concentration, using Wireless Sensor Network Technology (WSN) and Internet of Things (IoT). One of the WSN concepts to be used is a combination of several sensors, the only sensors used to detect the level of carbonmonoxide concentration include: carbon monoxide, temperature and humidity sensors. Air condition data derived from the sensor in the form of concentration value of carbon monoxide, temperature and humidity of air sent to server connected to network using IoT technology. Based on the test results it can be concluded that the air condition monitoring system using WSN and IoT technology can be applied in realtime, this can be proven with the data shown in the monitoring tool. the detection of a fire source using a sensor can be done by using a distance between a smoke source (hotspot) and a device 90cm. From the observation result there is difference between sensing data without smoke and using smoke, such as temperature has 60C difference, humidity 20 rh and carbon monoxide about 17ppm

Depression is a serious public health problem. Current diagnosis techniques rely on physician-administered or patient self-administered interview tools, which are burdensome and suffer from recall bias. Recent studies have proposed new approaches that use sensing data collected on smartphones to serve as "human sensors" for automatic depression screening. These approaches, however, require running an app on the phones for continuous data collection. We explore a novel approach that uses data collected from WiFi infrastructure for large-scale automatic depression screening. Specifically, when smartphones connect to a WiFi network, their locations (and hence the locations of the users) can be determined by the access points that they associate with; the location information over time provides important insights into the behavior of the users, which can be used for depression screening. To investigate the feasibility of this approach, we have analyzed two datasets, each collected over several months, involving tens of participants recruited from a university. Our results demonstrate that WiFi meta-data is effective for passive depression screening: the F1 scores are as high as 0.85 for predicting depression, comparable to those obtained by using sensing data collected directly from smartphones.

Our goal is to develop stable, accurate, and robust semantic scene understanding methods for wide-area scene perception and understanding, especially in challenging outdoor environments. To achieve this, we are exploring and evaluating a range of related technology and solutions, including AI-driven multimodal scene perception, fusion, processing, and understanding. This work reports our efforts on the evaluation of a state-of-the-art approach for semantic segmentation with multiple RGB and depth sensing data. We employ four large datasets composed of diverse urban and terrain scenes and design various experimental methods and metrics. In addition, we also develop new strategies of multi-datasets learning to improve the detection and recognition of unseen objects. Extensive experiments, implementations, and results are reported in the paper., 12 pages, 5 figures

Information on the mixed use of buildings helps understand the status of mixed-use urban vertical land and assists in urban planning decisions. Although a few studies have focused on this topic, the methods they used are quite complex and require manual intervention in extracting different function patterns of buildings, while building recognition rates remain unsatisfying. In this paper, we propose a new method to infer the mixed use of buildings based on a tensor decomposition algorithm, which integrates information from both high-resolution remote sensing images and social sensing data. We selected the Tianhe District of Guangzhou, China to validate our method. The results show that the recognition rate of buildings can reach 98.67%, with an average recognition accuracy of 84%. Our study proves that the tensor decomposition algorithm can extract different function patterns of buildings unsupervised, while remote sensing data can provide key information for inferring building functions. The tensor decomposition-based method can serve as an effective and efficient way to infer the mixed use of buildings, which can achieve better results with simpler steps.

The work is aimed at developing a model of an information system for the analysis and monitoring of remote sensing data by the example of processing hyper- and multispectral satellite images, which are widely used to analyze the state of static and dynamic objects in the Arctic region of the Russian Federation. For automatic analysis and decryption of Arctic data in the development of the model, methods of high-performance computing, radiometric calibration, filtering and clustering of images, as well as intelligent data processing methods using deep learning convolutional neural networks were used. Object-oriented design and united modeling language notation were used to develop the model. A data-level model, a conceptual model of the structure of system modules, including a resource storage center, a resource and results management center, and a presentation-level interface have been developed. To develop a diagram of the use cases of the information system, the structure of actors, use cases and their interrelations were identified. The logical model of the information system was created based on a class diagram consisting of the Resource and Results Manager Center, Intellectual Information System, Functional Neural Modules packages. The practical significance of the study is due to the fact that the results obtained will allow the development of a prototype of an information system that can be used for effective monitoring of “useful data" of the Arctic region of the Russian Federation, as well as to automate the processes of analysis, updating, storage and processing of data from objects in various areas of the Arctic infrastructure.