AI Methods for Intelligent Sensing: History
View Latest Version
Please note this is an old version of this entry, which may differ significantly from the current revision.
Contributor:
Abhishek Sharma
,
Dushantha Nalin K. JAYAKODY
,
,
Hwang-Cheng Wang
,
Chathuranga basnayaka
,
Ammar Muthanna

An overview of learning models based on AI and used for intelligent sensing applications is presented. Key parameters that affect the performance of intelligent sensing are also discussed.

  • artificial intelligence
  • machine learning
  • intelligent sensing
  • neural networks
  • IoT
  • learning algorithms

1. Introduction

Smart sensors complement and enhance the capabilities of human beings and have been widely embraced in numerous application areas. Artificial intelligence (AI) has made astounding growth in domains of natural language processing, machine learning (ML), and computer vision. The methods based on AI enable a computer to learn and monitor activities by sensing the source of information in a real-time environment. The combination of these two technologies provides a promising solution in intelligent sensing. 
A smart sensor is a sensor that can detect an object’s information, and can learn, judge, and process the data in the form of signals. It can calibrate automatically, collect data, and compensate it. In the 1980s, the effort was focused on integrating computer memory, signal processing circuit, interface circuit, and a microprocessor to one chip so that the sensor can achieve certain AI capability [1]. Smart sensors have emerged due to technological demands and feasibility [2]. The primary source is the sensing element, which can trigger the sensing component to deliver a self-test facility. For this, a reference voltage is applied to monitor the response of the sensor. Amplification is necessary, as most of the sensors produce signals that are lower than signal levels of a digital processor. For example, a piezoelectric sensor requires charge amplification, while resistive sensors need instrumentation amplification. Analog filtering is used to block the aliasing effect in the data conversion stage.
The data conversion is associated with the digitization process, wherein analog signals are converted into discrete signals [3]. In this stage, input from sensors is fed into the data conversion unit to implement different forms of compensation. Signals in the frequency domain like those from resonant sensors do not need conversion and can be fed directly into a digital system. Digital processors are required to implement sensor compensation like cross-sensitivity, linearization, offset, etc., for pattern recognition methods. Finally, data communication unit sends signals to the sensor bus and deals with the passing and receiving of data.
In the following sections, an overview of ML and DL algorithms from an intelligent sensing perspective is presented. The aim is to highlight learning algorithms that are widely used in many real-time applications. Furthermore, parameters affecting the performance of intelligent sensing are also discussed. 

2. AI-Based Algorithms/Models in Intelligent Sensing

A machine that is able to make decisions on its own is said to possess AI. There is a broad spectrum of applications for AI, ranging from machine learning to robotics. By combining the current advancements in machine and deep learning, huge amounts of data from various sources are analyzed by utilizing AI to identify patterns and make intelligent predictions [4]. However, recent advances in artificial intelligence systems and robotics still need more research to solve complex problems. The tremendous growth in AI has ushered in a wave of applications using sensors. As a result, the demand for intelligent sensing increases in the market. Using sensor signals, the analysis of sensor data based on AI provides robust predictions and classifications. Hence, intelligent sensing will be the bright future of AI, where human behavior and emotions can be recognized by AI machines. 

3. Machine Learning Algorithms/Models in Intelligent Sensing

The tremendous growth of ML-based approaches has expanded the research area of intelligent sensing. Generally, ML can be considered to be a subset of AI which handles complexities to solve a specific task. In this subsection, a brief overview of existing ML algorithms that improve the functioning of sensing systems is presented together with their advantages and disadvantages. Various scenarios portraying how machine learning methods are applied in intelligent sensing is depicted in Figure 1. ML algorithms are divided into supervised, semi-supervised, unsupervised, and reinforcement learning.
Figure 1. Various Scenarios Portraying ML and DL-based Intelligent Sensing.
  • Supervised learning-based intelligent sensing—Supervised learning deals with the known and labeled data and is divided into two types: classification and regression. This approach has been successfully implemented for many years in the fields of image classification, fraud detection, medical diagnosis, weather forecasting, market forecasting, and life expectancy estimation. In [5], ECG data are collected via wearable sensors, which detect heartbeats automatically, and a supervised learning approach is used for arrhythmia classification. An artificial haptic neuron system is fabricated in [6]. The system comprises a Nafion-based memristor and a piezoelectric sensor. The sensory receptor converts external stimulus into an electric signal, and the memristor is used for further processing of the data collected from the sensor. A supervised learning method is implemented for the recognition of English letters by placing the sensor on the joint of a finger. A novel methodology proposed in [7] using supervised learning for resolving the collision of cash tags yields high classification accuracy of listed companies in London Stock Exchange. A hybrid model that combines ML and game theory is proposed in [8] to solve issues related to network selection in ultra-dense heterogeneous networks.
    • K-Nearest Neighbors (K-NN) is an effective classification algorithm used for large datasets. Here, K represents the number of training samples that are near the test sample in the feature space [9]. In [10], a machine learning-based K-NN approach is used for load classification by collecting data from various smart plug sensors and other devices.
    • Support Vector Machine (SVM) is mainly used to categorize data attributes between classes by creating two-dimensional planes to minimize the classification error [11]. For example, Ref. [12] introduces a danger-pose detection system based on Wi-Fi devices that is used to monitor a bathroom while ensuring privacy. A machine learning-based detection approach usually requires large amount of data collected in target scenarios, which is challenging to detect danger situations. However, this work employed a machine learning-based anomaly-detection technique which requires a small amount of data in anomalous conditions. In this work, researchers first extracted the amplitude and phase shift from Wi-Fi Channel State Information (CSI) in order to detect low-frequency components associated with human activities. The static and dynamic features were then derived from the CSI changes over time. Finally, the static and dynamic characteristics are input into a one-class SVM which is employed as an anomaly-detection method to determine if a person is not in the bathtub, is bathing safely or in unsafe situations.
    • Decision Tree (DT) model consists of branches and nodes, wherein every node represents a test on every feature, and each branch has a value that the associated node can use to classify a sample [13]. A decision tree-based approach was presented in [14] for an intelligent transportation system (ITS). LIDAR sensors obtain point cloud data, which are then projected onto the XOY plane. After that, the images are classified into road and background grids for monitoring road traffic.
    • Ensemble Learning (EL) is a method based on combining the outputs of basic classification algorithms to boost the performance of classification. It is robust to data overfitting problem and is better than a single classifier [15]. This method is proposed in [16], where soft sensors are used to collect data to predict the composition, flow rate, and other features of the product, e.g., fatty acid methyl esters (FAME), in the procedure of production of biodiesel from vegetable oil.
    • Random Forest (RF) is made of a combination of several DTs and constructed randomly to form a model for improving the overall results [17]. A random forest-based classifier is proposed in [18] for estimating the content of bulky metals in agricultural soil using hyperspectral sensor data and is shown to reduce computational cost and time.
  • Unsupervised learning-based intelligent sensing—Due to the large amount of unlabeled data in our everyday life, researchers have emphasized the unsupervised learning-based algorithms for intelligent sensing applications. This method consists of dimensionality reduction, generative networks, and clustering. Unsupervised learning-based intelligent sensing is proposed in [19], which is applied for real-time environment sensing to detect rare event instances intelligently. An unsupervised clustering-based method is introduced in [20] to describe an individual’s behavioral pattern by analyzing 100 days of unlabeled sensor data of 17 older adults from their homes and extract information of their day-to-day activities at different times. To detect the change in Landsat images, unsupervised learning is used in [21] with mean-shift clustering and hybrid wavelet transform under the Multi-Objective Particle Swarm optimization (MO-PSO) framework.
  • Semi-Supervised intelligent sensing—This method deals with the combination of labeled and unlabeled data. To reduce the complexity of labeling all data for large datasets, semi-supervised methods are used. A robust model based on a semi-supervised approach is proposed in [22] to warn about the aircraft fault during the flight of a UAV by sensing real-time data such as angular velocity and pitch angle from flight sensors, and dramatically reduces the manual work. To detect faults in Additive Manufacturing (AM) products, a semi-supervised method with a few labeled data and a large number of unlabeled data is explored in [23].
  • Reinforcement learning-based intelligent sensing—In the context of AI, reinforcement learning learns to make a sequence of decisions by interacting with its environment. One of the successful applications of this approach is to control autonomous cars by training the model. A deep reinforcement learning-based multi-sensor tracking fusion is proposed in [24] for vehicle tracking by learning on fused data from different sensors (camera and LIDAR). An intelligent sensing-based approach is introduced in [25] to autonomously monitor bridge conditions by collecting data from sensor nodes and make decisions using the reinforcement learning method. A novel approach based on YOLO V3 is proposed in [26] for multi-object tracking based on multi-agent deep reinforcement learning. This approach performs better in terms of precision, accuracy, and robustness. A routing protocol built on reinforcement learning is developed in [27] to find an optimal routing path for data transmission in a wireless network.
Table 1 shows the comparison of several ML and DL algorithms used in different areas of intelligent sensing. ML is a branch of AI that advocates the idea of acquiring the right data so that a machine can learn how to solve a particular problem by itself. The rise of ML is due to the availability of large datasets, and the adoption of ML algorithms in the field of intelligent sensing is to create smart devices that can take actions based on what they sense from the environment. With the implementation of ML in sensors, the efficiency and robustness of the system will reach the next level in smart sensing applications. Using sensor data, ML algorithms enable more robust predictions and classifications as compared to other physics-based models that envisage AI being added eventually to devices to adapt to the new circumstances. Therefore, the use of machine learning, including deep learning algorithms, is appropriate for performing challenging tasks in intelligent sensing, as shown in Figure 1.
Table 1. Comparison of Machine Learning Algorithms/Models in Intelligent Sensing.
Reference Number Machine Learning Algorithm/Model Dataset Used Description Parameters Influencing the Performance Advantages Limitations
[28] epsilon-SVR
(eSVR), Linear regression (LR), Convolutional Neural Network (CNN), STSVR, T-SVR.		 DEAP Dataset [29]. A Framework is proposed for stress recognition in real-time using peripheral physiological signals. BVP and GSR. 1. Less Prediction error;
2. Convenient for real-world applications.		 The model is limited to the slight movement of physiological signals.
[30] Linear regression (LR) and neural network (NN). Chronic Kidney Disease (CKD) from patients. A hybrid intelligent model is proposed to guess chronic kidney disease from a patient’s data on the cloud environment to improve services in healthcare in smart cities. Feature weights (FW). The proposed model significantly improves accuracy compared to other models. The hybrid model is limited to a small amount of data of a patient’s record.
[31] R.A.L.E lung sound Database [32]. DEAP Dataset [29]. Performance of K-NN and SVM classifiers are compared using the pulmonary acoustic signal from RALE database for diagnosing respiratory pathologies. Mel-frequency cepstral coeffcients (MFCC). Analysis of feature vectors is via ANOVA and separately fed into SVM and K-NN classifiers. 1. The amount of data used to train and test the classifier is very small.
2. Collection of data was carried out in a controlled environment.
[33] Ranking SVM. NUS-WIDE dataset [34]. The interaction between social images and online users is analyzed. Color, texture, and GIST features. Powerful learning method and heterogeneous social sensory data improve performance. External factors such as images based on cultural and geographical locations are not considered for prediction.
[35] K-NN, AdaBoost, SVM, RF and Logistic regression (LR). Non-contact sensor data. The non-contact sensor the device is designed to predict the signs of HR, RR, HRV parameters from a patient’s records during a period of 23 weeks of HD sessions. Age and BMI (body mass index) of patients. Using machine learning-based predictive models, high accuracy is obtained. The main limitation is the prediction of clinical events in advance and the other parameters like BP and the patient’s medical history using a multi-class prediction model.
[36] Support Vector Machine (SVM). CRCNS-ORIG and DIEM. A model is proposed to detect mental weakness of older and younger people by collecting their eye-tracking data while watching a video. Pupil diameters, eye blinking, gaze allocation, and saccade mean velocity. Improves detection accuracy using an automated feature selection method. 1. Limited no. of participants.
2. Eye-tracking data are collected in a controlled environment.
The availability of datasets and the invention of new algorithms have increased the usage of ML and DL in the last few years. The supervised learning method has been used in numerous applications, such as object recognition, speech recognition, and spam detection. It predicts the value of one or more output variables (in the form of continuous or discrete) by observing input variables. The unsupervised learning method is generally used for gene clustering, social media analysis, and market research. The main focus of this method is to analyze unlabeled data. Semi-supervised learning is the hybrid model of supervised and unsupervised learning methods, which is used to solve problems with a few data points labeled and most of the data unlabeled. Reinforcement learning (RL) is used in applications such as finance, inventory management, and robotics, where the purpose is to learn a policy, i.e., to map situations between states of the environment to perform actions appropriately.

4. Deep Learning Algorithms/Models in Intelligent Sensing

Deep Learning is now dominating the industry and research spheres for the growth of a range of smart-world systems for good reasons. DL has shown considerable potential in approximating and reducing huge datasets into accurate predictive and transformational output, greatly facilitating human-centered smart systems. This section discusses deep learning models based on intelligent sensing.
  • Convolutional Neural Network—CNN is a robust supervised DL algorithm with better performance than other DL algorithms. IoT security is one of CNN’s applications where the features of the security data can be automatically learned by the sensors [37]. Deep CNN-based learning is proposed in [38] to recognize human emotions using electrodermal activity (EDA) sensors. These devices capture emotional patterns from a group of persons. The paper [39] proposed a system that detects the physical activity of older people from wearable sensors. For rotation-invariant features, each feature triplet is extracted from the X, Y, and Z axes and reduced to one feature represented by a 3D vector. Other works similar to this also achieve high accuracy in the study of younger people.
  • Recurrent Neural Network—RNN is an important algorithm of DL in which present and past inputs depend on the output of the neural network. It is used to handle sequential inputs, which can be speech, text, or sensor data [40]. An RNN-based approach is discussed in [41], which is meant to interpolate sparse geomagnetic data from lost traces to reduce the time taken by linear interpolation approaches. The study in [42] discussed a mobile positioning method using RNN to analyze the strength of received signals. The authors experiment with the training of two RNNs separately for estimating latitude and longitude, which results in overfitting. An RNN-based learning model is proposed in [43] to monitor underwater sensor networks in real time, which improves the delay and reduces the cost of packet transmission.
  • Generative Adversarial Network—GAN comprises two models; one is the generator, and the other is the discriminator. The two are trained in tandem via an adversarial process. These networks have been implemented for the security of IoT systems [44]. A conditional GAN-based DL method is presented for the reconstruction of CS-MRI that is compressed sensing magnetic resource imaging using compressed MR data [45]. In [46], the authors proposed a GAN-based method to generate X-ray prohibited images with different item poses. According to the paper, the quality of the images is good as compared to DC-GAN and WGAN-GP. After the images are generated, they are added to the real images and FID (Fréchet inception distance) is used to evaluate the performance of GANs.
  • Long Short-Term Memory—LSTM is a type of recurrent neural network that is intended to model temporal sequences and their long-range dependencies more accurately than conventional RNNs [47]. The LSTM comprises units called memory blocks in the recurrent hidden layers. The memory blocks contain memory cells with self-connections that store the temporal state of the network in addition to special multiplicative units called gates to control the flow of information. A DL-based approach is used in [48] for emotion classification, dealing with a large number of sensor signals from different modalities. From the results presented in the paper, it came to be known that ad-hoc feature extraction may not be compulsory as DL models extract the high-level features automatically.

5. Parameters Affecting the Performance of Intelligent Sensing

This section presents a review of some of the parameters that affect the performance of intelligent sensing. Intelligent sensing methods have been promising with state-of-the-art results in several areas, such as healthcare, image segmentation, agriculture, soft sensors, etc. The use of sensor systems in industrial, scientific, and consumer equipment is extensive and is continuously increasing in domains like automation. Essentially, industrial information revolutions need more sensors of every kind. The focus of the sensor system is to provide reliable signals and evaluate information. The smart sensing units include a sensing element and proper signal processing function within the same package.
Table 2 gives a list of parameters that affect the performance of intelligent sensing based on the results reported in literature. Key information includes the title and year of publication of each paper, and parameters that influence the performance of the various intelligent sensing approaches, such as temperature, accuracy, cost, time, occupancy, dependency, etc. One of the parameters is feature extraction in image recognition. Several techniques of pre-processing are used for enhancing certain features and removing unnecessary data. These techniques include digital spatial filtering, contrast enhancement, gray level distribution linearization, and image subtraction [49]. Measurement of redundancy in test samples is attempted to achieve test loss minimization, which can lead to a reduction of test maintenance costs and also ensure the integrity of test samples [50]. Evaluating ML algorithms is an important part of any project. Accuracy is one of the essential parameters to judge the performance of the trained model. Classification accuracy is defined as the fraction of correct predictions relative to the total number of input samples.
Table 2. Parameters Influencing the Performance of Intelligent Sensing.
Ref. Number Year Title of Paper Parameter 1 Parameter 2 Parameter 3 Parameter 4 Parameter 5 Parameter 6 Description
[51] 2019 A review on EMG based motor intention prediction of continuous human upper limb motion for human-robot collaboration. EMG signal acquisition Pre-processing Feature extraction Accuracy of continuous motion Dependency on autonomy Redundancy Researchers have explored several approaches and models for motor intention prediction based on EMG signals for estimation of continuous motion of the human upper limb and also discussed motion parameters for measuring the performance of the system.
[52] 2019 Toward biotherapeutic product real time quality monitoring. Dynamic nature Adaptive model structure High levels of noise Complexity Heteroge- neity Real-time monitoring Close monitoring of Critical Quality Attributes (CQAs) of the product in real time is critical to increasing product quality and improving process control. A CQA value is a physical, chemical, biological, or microbiological property or characteristic that should be within an appropriate limit, range, or distribution to ensure the desired product quality. Various monitoring techniques are surveyed to detect CQA value uncertainty and subsequent reduction in end-product variability.
[53] 2019 A novel segmentation based depth map up-sampling. Depth maps Geodesic distances Super pixels Initial no. of pixels Scale constant Splitting threshold Proposed color image segmentation according to the guidance of the depth. Hence, the segmented regions observe the depth of the boundary well.
[54] 2018 Design and applications of soft sensors in polymer processing: A review. Temperature Pressure Process speed Flow index Viscosity Product dimensions Researchers have done a comprehensive survey on soft sensing techniques applied for polymer processing and its importance for the growth of process monitoring, process control and fault diagnostics. These techniques have replaced the use of physical sensors for practical process measurements in industries.
[55] 2019 Prediction of occupancy level and energy consumption in an office building using blind system identification and neural networks. Occupancy Prediction accuracy Time factor Historical internal load Energy consumption Structure parameters A prediction model based on the feed forward network, ensemble models as well as extreme learning machine (ELM) is established for measuring electricity consumption of the AC system, and based on the approach of blind system identification (BSI) model, the occupancy profile is estimated in an office building.
[56] 2019 Semi-supervised deep learning for hyperspectral image classification. Training samples Classification accuracy Bias parameters Kappa coefficient Weight decay Momentum A novel method based on a semi-supervised deep feature fusion network for classifying hyperspectral images by integrating the original training set with pseudo labeled samples to reduce the problem of overfitting during training of DNN.
The most crucial aspect of this matter is the collection of data from multiple sources. The data usually goes through several stages of pre-processing to make it in presentable form. Intelligent sensing approaches are in general associated with technological applications where they are applied. For example, in cognitive radio, the sensing approach will be different from applications in a smart grid. The work in [57] presented an artificial intelligence-based approach for high-speed data delivery with latency regulation. Compared to CogMAC (Cognitive Medium Access Control) and AHP (Analytic Hierarchy Process) protocols, the decentralized approach helps in creating opportunistic methods for spectrum access and better design of channel selection mechanisms. The work presented in [58] proposed a method for integrating intelligence close to the sensor, which will enable decision-making in local nodes before transferring the information to the cloud or server. The local intelligence will be helpful in producing smart data that can be used for analysis to produce effective outcomes. Techniques such as normalization, linearization, and data cleaning can be done at local nodes in a piconet. Such inclusion will be helpful in the elimination of unnecessary steps, which needs to be done very frequently before data is used in artificial intelligence algorithms.
It is very important to identify data anomalies as data sometimes are collected from multiple platforms. In such cases, the source of data needs to be tracked for threat and irregularity. The work presented in [59] proposed scheduling and anomaly handling mechanisms in cross-platform IoT systems using cognitive tokens. The proposed methods use intelligent sensing with fair play and exponential growth procedures. In contrast to current technology trends in full-stack system development, a layered architecture-based approach was proposed in [60]. The proposed method will help to collect data, extract useful information, and transfer it for further processing. In the case of more sensitive data sensing, such as clinical or eHealth, Ref. [61] presented the implementation of gateway and scoring mechanisms to reduce the latency and to analyze the performance of systems. Such implementations have shown good performance in fog computing environments, where restricted resources are available at local nodes. The work presented in [62] shows the importance and challenges of IoT-based healthcare information sensing. The work presents challenges related to information acquisition, sensing, storage, processing, analytics, and presentation.

This entry is adapted from the peer-reviewed paper 10.3390/electronics11101661

References

  1. Apogeeweb. What is Intelligent Sensor and Its Applications. 2018. Available online: http://www.apogeeweb.net/article/75.html (accessed on 6 January 2022).
  2. White, N. Intelligent sensors: Systems or components? Integr. Vlsi. J. 2005, 3, 471–474.
  3. Powner, E.; Yalcinkaya, F. Intelligent sensors: Structure and system. Sens. Rev. 1995, 15, 31–35.
  4. Lu, H.; Li, Y.; Chen, M.; Kim, H.; Serikawa, S. Brain intelligence: Go beyond artificial intelligence. Mob. Netw. Appl. 2018, 23, 368–375.
  5. Scirè, A.; Tropeano, F.; Anagnostopoulos, A.; Chatzigiannakis, I. Fog-Computing-Based Heartbeat Detection and Arrhythmia Classification Using Machine Learning. Algorithms 2019, 12, 32.
  6. Zhang, C.; Ye, W.B.; Zhou, K.; Chen, H.Y.; Yang, J.Q.; Ding, G.; Chen, X.; Zhou, Y.; Zhou, L.; Li, F.; et al. Bioinspired Artificial Sensory Nerve Based on Nafion Memristor. Adv. Funct. Mater. 2019, 29, 1808783.
  7. Evans, L.; Owda, M.; Crockett, K.; Vilas, A.F. A methodology for the resolution of cashtag collisions on Twitter—A natural language processing & data fusion approach. Expert Syst. Appl. 2019, 127, 353–369.
  8. Wang, X.; Li, J.; Wang, L.; Yang, C.; Han, Z. Intelligent user-centric network selection: A model-driven reinforcement learning framework. IEEE Access 2019, 7, 21645–21661.
  9. Harrington, P. Machine Learning in Action; Manning: Shelter Island, NY, USA, 2012.
  10. Soe, W.T.; Belleudy, C. Load Recognition from Smart Plug Sensor for Energy Management in a Smart Home. In Proceedings of the IEEE Sensors Applications Symposium (SAS), Sophia Antipolis, France, 11–13 March 2019; pp. 1–6.
  11. Cristianini, N.; Shawe-Taylor, J. An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods; Cambridge University Press: Cambridge, UK, 2000.
  12. Zhang, S. An overview of network slicing for 5G. IEEE Wirel. Commun. 2019, 26, 111–117.
  13. Hlynsson, H. Transfer learning using the minimum description length principle with a decision tree application. Master’s Thesis, University of Amsterdam, Amsterdam, The Netherlands, 2007.
  14. Zheng, J.; Yang, S.; Wang, X.; Xia, X.; Xiao, Y.; Li, T. A decision tree based road recognition approach using roadside fixed 3d lidar sensors. IEEE Access 2019, 7, 53878–53890.
  15. Zhou, Z.H. Ensemble Learning. In Encyclopedia of Biometrics; Li, S.Z., Jain, A., Eds.; Springer: Boston, MA, USA, 2009; pp. 270–273.
  16. Ahmad, I.; Ayub, A.; Ibrahim, U.; Khattak, M.K.; Kano, M. Data-Based Sensing and Stochastic Analysis of Biodiesel Production Process. Energies 2019, 12, 63.
  17. Zhang, J.; Zulkernine, M.; Haque, A. Random-Forests-Based Network Intrusion Detection Systems. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 2008, 38, 649–659.
  18. Tan, K.; Ma, W.; Wu, F.; Du, Q. Random forest–based estimation of heavy metal concentration in agricultural soils with hyperspectral sensor data. Environ. Monit. Assess. 2019, 191, 446.
  19. Janjua, Z.H.; Vecchio, M.; Antonini, M.; Antonelli, F. IRESE: An intelligent rare-event detection system using unsupervised learning on the IoT edge. Eng. Appl. Artif. Intell. 2019, 84, 41–50.
  20. Fiorini, L.; Cavallo, F.; Dario, P.; Eavis, A.; Caleb-Solly, P. Unsupervised machine learning for developing personalised behaviour models using activity data. Sensors 2017, 17, 1034.
  21. Kusetogullari, H.; Yavariabdi, A. Unsupervised change detection in landsat images with atmospheric artifacts: A fuzzy multiobjective approach. Math. Probl. Eng. 2018, 2018, 7274141.
  22. Wang, N.; Xu, Z.S.; Sun, S.W.; Liu, Y. Pattern recognition of UAV flight data based on semi-supervised clustering. J. Phys. Conf. Ser. 2019, 1195, 012001.
  23. Okaro, I.A.; Jayasinghe, S.; Sutcliffe, C.; Black, K.; Paoletti, P.; Green, P.L. Automatic fault detection for laser powder-bed fusion using semi-supervised machine learning. Addit. Manuf. 2019, 27, 42–53.
  24. Fang, Y.; Zhao, H.; Zha, H.; Zhao, X.; Yao, W. Camera and LiDAR Fusion for On-road Vehicle Tracking with Reinforcement Learning. In Proceedings of the IEEE Intelligent Vehicles Symposium (IV), Paris, France, 9–12 June 2019; pp. 1723–1730.
  25. Putra, S.A.; Trilaksono, B.R.; Riyansyah, M.; Laila, D.S.; Harsoyo, A.; Kistijantoro, A.I. Intelligent Sensing in Multiagent-Based Wireless Sensor Network for Bridge Condition Monitoring System. IEEE Internet Things J. 2019, 6, 5397–5410.
  26. Jiang, M.; Hai, T.; Pan, Z.; Wang, H.; Jia, Y.; Deng, C. Multi-agent deep reinforcement learning for multi-object tracker. IEEE Access 2019, 7, 32400–32407.
  27. Guo, W.; Yan, C.; Lu, T. Optimizing the lifetime of wireless sensor networks via reinforcement-learning-based routing. Int. J. Distrib. Sens. Netw. 2019, 15, 1–20.
  28. Li, M.; Xie, L.; Wang, Z. A transductive model-based stress recognition method using peripheral physiological signals. Sensors 2019, 19, 429.
  29. Koelstra, S.; Muhl, C.; Soleymani, M.; Lee, J.S.; Yazdani, A.; Ebrahimi, T.; Pun, T.; Nijholt, A.; Patras, I. Deap: A database for emotion analysis; using physiological signals. IEEE Trans. Affect. Comput. 2011, 3, 18–31.
  30. Abdelaziz, A.; Salama, A.S.; Riad, A.M.; Mahmoud, A.N. A Machine Learning Model for Predicting of Chronic Kidney Disease Based Internet of Things and Cloud Computing in Smart Cities. In Security in Smart Cities: Models, Applications, and Challenges; Hassanien, A.E., Elhoseny, M., Ahmed, S.H., Singh, A.K., Eds.; Springer International Publishing: Cham, Switzerland, 2019; pp. 93–114.
  31. Palaniappan, R.; Sundaraj, K.; Sundaraj, S. A comparative study of the svm and k-nn machine learning algorithms for the diagnosis of respiratory pathologies using pulmonary acoustic signals. BMC Bioinform. 2014, 15, 223.
  32. Pasterkamp, H. RALE Lung Sound Repository. Available online: http://www.rale.ca (accessed on 6 January 2022).
  33. Aloufi, S.; Zhu, S.; El Saddik, A. On the Prediction of Flickr Image Popularity by Analyzing Heterogeneous Social Sensory Data. Sensors 2017, 17, 631.
  34. Chua, T.S.; Tang, J.; Hong, R.; Li, H.; Luo, Z.; Zheng, Y. NUS-WIDE: A real-world web image database from National University of Singapore. In Proceedings of the ACM International Conference on Image and Video Retrieval, Santorini, Fira, Greece, 8–10 July 2009.
  35. Thakur, S.S.; Abdul, S.S.; Chiu, H.Y.S.; Roy, R.B.; Huang, P.Y.; Malwade, S.; Nursetyo, A.A.; Li, Y.C.J. Artificial-Intelligence-Based Prediction of Clinical Events among Hemodialysis Patients Using Non-Contact Sensor Data. Sensors 2018, 18, 2833.
  36. Yamada, Y.; Kobayashi, M. Detecting mental fatigue from eye-tracking data gathered while watching video: Evaluation in younger and older adults. Artif. Intell. Med. 2018, 91, 39–48.
  37. Kotlar, M.; Bojic, D.; Punt, M.; Milutinovic, V. A survey of deep neural networks deployment location and underlying hardware. In Proceedings of the 14th Symposium on Neural Networks and Applications (NEUREL), Belgrade, Serbia, 20–21 November 2018.
  38. Al Machot, F.; Elmachot, A.; Ali, M.; Al Machot, E.; Kyamakya, K. A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors. Sensors 2019, 19, 1659.
  39. Papagiannaki, A.; Zacharaki, E.I.; Kalouris, G.; Kalogiannis, S.; Deltouzos, K.; Ellul, J.; Megalooikonomou, V. Recognizing Physical Activity of Older People from Wearable Sensors and Inconsistent Data. Sensors 2019, 19, 880.
  40. Shiva Prakash, B.; Sanjeev, K.V.; Prakash, R.; Chandrasekaran, K. A Survey on Recurrent Neural Network Architectures for Sequential Learning. In Soft Computing for Problem Solving; Bansal, J.C., Das, K.N., Nagar, A., Deep, K., Ojha, A.K., Eds.; Springer: Singapore, 2019; pp. 57–66.
  41. Liu, H.; Liu, Z.; Dong, H.; Ge, J.; Yuan, Z.; Zhu, J.; Zhang, H.; Zeng, X. Recurrent Neural Network-Based Approach for Sparse Geomagnetic Data Interpolation and Reconstruction. IEEE Access 2019, 7, 33173–33179.
  42. Wu, L.; Chen, C.H.; Zhang, Q. A Mobile Positioning Method Based on Deep Learning Techniques. Electronics 2019, 8, 59.
  43. Wei, X.; Liu, Y.; Gao, S.; Wang, X.; Yue, H. An RNN-based delay-guaranteed monitoring framework in underwater wireless sensor networks. IEEE Access 2019, 7, 25959–25971.
  44. Ferdowsi, A.; Saad, W. Generative adversarial networks for distributed intrusion detection in the internet of things. In Proceedings of the IEEE Global Communications Conference (GLOBECOM), Waikoloa, HI, USA, 9–13 December 2019; pp. 1–6.
  45. Yang, G.; Yu, S.; Dong, H.; Slabaugh, G.; Dragotti, P.L.; Ye, X.; Liu, F.; Arridge, S.; Keegan, J.; Guo, Y.; et al. DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction. IEEE Trans. Med. Imaging 2018, 37, 1310–1321.
  46. Yang, J.; Zhao, Z.; Zhang, H.; Shi, Y. Data Augmentation for X-Ray Prohibited Item Images Using Generative Adversarial Networks. IEEE Access 2019, 7, 28894–28902.
  47. Sherstinsky, A. Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network. Phys. D Nonlinear Phenom. 2020, 404, 132306.
  48. Kanjo, E.; Younis, E.M.; Ang, C.S. Deep learning analysis of mobile physiological, environmental and location sensor data for emotion detection. Inf. Fusion 2019, 49, 46–56.
  49. Hall, E.; Kruger, R.; Dwyer, S.; Hall, D.; Mclaren, R.; Lodwick, G. A Survey of Preprocessing and Feature Extraction Techniques for Radiographic Images. IEEE Trans. Comput. 1971, C-20, 1032–1044.
  50. Koochakzadeh, N.; Garousi, V.; Maurer, F. Test Redundancy Measurement Based on Coverage Information: Evaluations and Lessons Learned. In Proceedings of the International Conference on Software Testing Verification and Validation, Denver, CO, USA, 1–4 April 2009; pp. 220–229.
  51. Bi, L.; Feleke, A.G.; Guan, C. A review on EMG-based motor intention prediction of continuous human upper limb motion for human-robot collaboration. Biomed. Signal Process. Control 2019, 51, 113–127.
  52. Guerra, A.; von Stosch, M.; Glassey, J. Toward biotherapeutic product real-time quality monitoring. Crit. Rev. Biotechnol. 2019, 39, 289–305.
  53. Qiao, Y.; Jiao, L.; Yang, S.; Hou, B. A novel segmentation based depth map up-sampling. IEEE Trans. Multimed. 2019, 21, 1–14.
  54. Abeykoon, C. Design and applications of soft sensors in polymer processing: A review. IEEE Sens. J. 2019, 19, 2801–2813.
  55. Wei, Y.; Xia, L.; Pan, S.; Wu, J.; Zhang, X.; Han, M.; Zhang, W.; Xie, J.; Li, Q. Prediction of occupancy level and energy consumption in office building using blind system identification and neural networks. Appl. Energy 2019, 240, 276–294.
  56. Fang, B.; Li, Y.; Zhang, H.; Chan, J. Semi-supervised deep learning classification for hyperspectral image based on dual-strategy sample selection. Remote Sens. 2018, 10, 574.
  57. Marques, A.F.F.; Miranda, G.; Silva, L.M.; Ávila, R.S.; Correia, L.H.A. ISCRa—An Intelligent Sensing Protocol for Cognitive Radio. In Proceedings of the IEEE Symposium on Computers and Communication (ISCC), Messina, Italy, 27–30 June 2016; pp. 385–390.
  58. Lee, W.; Sharma, A. Smart sensing for IoT applications. In Proceedings of the 13th IEEE International Conference on Solid-State and Integrated Circuit Technology (ICSICT), Hangzhou, China, 25–28 October 2016; pp. 362–364.
  59. Sharma, V.; You, I.; Kumar, R. ISMA: Intelligent Sensing Model for Anomalies Detection in Cross Platform OSNs with a Case Study on IoT. IEEE Access 2017, 5, 3284–3301.
  60. Ma, M.; Wang, P.; Chu, C.H. Data management for internet of things: Challenges, approaches and opportunities. In Proceedings of the IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing, Beijing, China, 20–23 August 2013; pp. 1144–1151.
  61. Rahmani, A.M.; Gia, T.N.; Negash, B.; Anzanpour, A.; Azimi, I.; Jiang, M.; Liljeberg, P. Exploiting smart e-Health gateways at the edge of healthcare Internet-of-Things: A fog computing approach. Future Gener. Comput. Syst. 2018, 78, 641–658.
  62. Hassanalieragh, M.; Page, A.; Soyata, T.; Sharma, G.; Aktas, M.; Mateos, G.; Kantarci, B.; Andreescu, S. Health Monitoring and Management Using Internet-of-Things (IoT) Sensing with Cloud-Based Processing: Opportunities and Challenges. In Proceedings of the IEEE International Conference on Services Computing, New York, NY, USA, 27 June–2 July 2015; pp. 285–292.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.
This entry is offline, you can click here to edit this entry!
ScholarVision Creations
Feedback