Search

This study presents an effective data-driven anomaly detection scheme for drunk driving detection. Specifically, the proposed anomaly detection approach amalgamates the desirable features of the t-distributed stochastic neighbor embedding (t-SNE) as a feature extractor with the Isolation Forest (iF) scheme to detect drivers’ drunkenness status. We used the t-SNE model to exploit its capacity in reducing the dimensionality of nonlinear data by preserving the local and global structures of the input data in the feature space to obtain good detection. At the same time, the iF scheme is an effective and unsupervised tree-based approach to achieving good detection of anomalies in multivariate data. This approach only employs normal events data to train the detection model, making them more attractive for detecting drunk drivers in practice. To verify the detection capacity of the proposed t-SNE-iF approach in reliably detecting drivers with excess alcohol, we used publically available data collected using a gas sensor, temperature sensor, and a digital camera. The overall detection system proved a high detection performance with AUC around 95%, demonstrating the proposed approach’s robustness and reliability. Furthermore, compared to the Principal Component Analysis (PCA), Incremental PCA (IPCA), Independent component analysis (ICA), Kernel PCA (kPCA), and Multi-dimensional scaling (MDS)-based iForest, EE, and LOF detection schemes, the proposed t-SNE-based iF scheme offers superior detection performance of drunk driver status.

Accurate modulation identification of the received signals is undoubtedly a central component in multiple-input multiple-output (MIMO) communication systems, facilitating the demodulation task. This study presents a flexible and semi-supervised deep learning-driven strategy for automatic modulation identification. To this end, the multiclass classification problem is treated as multiple binary discrimination problems to address modulation identification challenges. Here, we merge the features extraction ability of the Generative Adversarial Network (GAN) model and the semi-supervised anomaly detection scheme, the one-class Support Vector Machine (1SVM). Essentially, a single GAN-based 1SVM detector is trained using training data of each class, with the samples of that class as inlier and all other samples as anomalies (i.e., one-vs.-rest). The 1SVM is trained using the features learned by the GAN model. A dataset consisting of three digital modulations (i.e., BFSK, CPFSK, and PAM4) and three analog modulations (i.e., AM-DSB, AM-SSB, and WB-FM), widely used in wireless communications systems, is employed to demonstrate the performance of the considered deep learning-based methods. Compared to Restricted Boltzmann Machine (RBM) and Deep Belief Network (DBN)-based 1SVM, the conventional GAN, DBN, and RBM with softmax layer as discriminator layer, the proposed GAN-based 1SVM detector offers superior discrimination performance of modulation types by achieving an averaged accuracy of 0.951 and F1-Score of 0.954. Results also showed that the GAN-1SVM detector dominates the state-of-the-art modulation classification techniques.

Wind power is one of the most potential energies and the major available renewable energy sources. Precisely predicting wind power production is essential for the management and the integration of wind power in a smart grid. The goal of this study is to predict wind power production with sufficient accuracy based on various factors using ensemble learning-based methods that consider the time-dependent nature of the wind power measurements. Essentially, the ensemble learning methods combine multiple learners to obtain an enhanced prediction performance in comparison to conventional standalone learners. In addition, they reduce the overall prediction error and have the capacity to merge various models. At first, this paper investigates the prediction capability of the well-known ensemble approaches Boosted Trees, Random Forest, and Generalized Random Forest for wind power prediction. We compared the prediction performance of these ensemble models to two frequently used prediction methods: Gaussian process regression, and Support Vector Regression. Experimental measurements recorded every ten minutes from actual wind turbines located in France and Turkey are used to test the prediction efficiency of the studied models. Experimental results have shown that the ensemble methods can predict wind power production with high accuracy compared to the standalone models. Furthermore, the findings clearly reveal that the lagged variables contribute significantly to the ensemble models, and permits constructing more parsimonious models.

Accurately detecting Parkinson's disease (PD) at an early stage is certainly indispensable for slowing down its progress and providing patients the possibility of accessing to disease-modifying therapy. Towards this end, the premotor stage in PD should be carefully monitored. An innovative deep-learning technique is introduced to early uncover whether an individual is affected with PD or not based on premotor features. Specifically, to uncover PD at an early stage, several indicators have been considered in this study, including Rapid Eye Movement and olfactory loss, Cerebrospinal fluid data, and dopaminergic imaging markers. A comparison between the proposed deep learning model and twelve machine learning and ensemble learning methods based on relatively small data including 183 healthy individuals and 401 early PD patients shows the superior detection performance of the designed model, which achieves the highest accuracy, 96.45% on average. Besides detecting the PD, we also provide the feature importance on the PD detection process based on the Boosting method.

The accurate forecast of wastewater treatment plant (WWTP) key features can comprehend and predict the plant behavior to support process design and controls, improve system reliability, reduce operational costs, and endorse optimization of overall performances. Deep learning technologies as proven data-driven soft-sensors should be developed for WWTP applications to tackle the process of non-linearity and the dynamic nature of environmental data. This study adopts deep learning-based models as soft-sensors to forecast WWTP key features, such as influent flow, influent temperature, influent biochemical oxygen demand (BOD), effluent chloride, effluent BOD, and power consumption. We constructed six deep learning models derived from long short-term memory (LSTM) and gated recurrent unit (GRU), namely traditional LSTM and GRU, the exponentially smoothed LSTM, and the adaptive version of LSTM and smoothed LSTM. The employment of a smoothed LSTM technique is expected to reduce the outlier effect and to improve forecasting accuracy. Meanwhile, the usage of adaptive deep models will enhance the capabilities of the LSTM to quickly and accurately follow the trend of future data. We compared the performance of these models with Bi-directional LSTM (BiLSTM) and the seasonal decomposition using local regression. The historical records from a coastal municipal WWTP in Saudi Arabia are used to verify the investigated models' effectiveness. The proposed models provide promising forecasting results but require no assumptions on the data distributions. In terms of efficiency, GRU based models converge faster than LSTM based models. In terms of accuracy, the LSTM soft-sensor shows overall the optimal result for all key features followed by the exponentially-smoothed GRU and LSTM. By contrast, the adaptive models achieved the lowest forecasting performance compared to the other models. These findings will benefit practitioners to achieve data-driven WWTP management.

Falls are an important healthcare problem for vulnerable persons like seniors. Response to potential emergencies can be fastened timely detection and classification of falls. This paper addresses the detection of human falls using relevant pixel-based features reflecting variations in body shape. Specifically, the human body is divided into five partitions that correspond to five partial occupancy areas. For each frame, area ratios are calculated and used as input data for fall detection and classification. First, the detection of falls is addressed from a statistical point of view as an anomaly detection problem. Towards this end, an integrated approach merging a detection step with a classification step is proposed for enabling efficient human fall detection in a home environment. In this regard, an effective fall detection approach using generalized likelihood ratio (GLR) scheme is designed. However, a GLR scheme cannot discriminate between true falls and like-fall events, such as lying down. To mitigate this limitation, the support vector machine algorithm has been successfully applied on features of the detected fall to recognize the type of fall. Tests on two publicly available datasets show the effectiveness of the proposed approach to appropriately detecting and identifying falls. Compared with the neural network, k -nearest neighbor, decision tree and naïve Bayes procedures, the two steps approach achieved better detection performance.

To operate wastewater treatment plants (WWTPs) with optimized efficiency, influent conditions (ICs) as initial states of inflow fed to WWTPs were monitored to identify potential anomalies that would trigger adverse events or system crash. To employ voluminous measurements for data-driven decisions, the non-linear, non-Gaussian, non-stationary, auto-correlated, cross-correlated, hetero-skedastic, case-specific nature of multivariate environmental datasets must be considered. This research proposed kernel machine learning models, the kernel principal components analysis based one-class support vector machine (KPCA-OCSVM) with various kernels, to learn anomaly-free training set then classify the testing set. A seven-years multivariate ICs time series was introduced with exploratory analysis performed to reveal temporal behaviors and statistical properties. KPCA with polynomial kernels sufficiently output representative features, based on which OCSVM with Gaussian kernels sensitively and specifically identified anomalies in ICs that were previously omitted by WWTP operators. The proposed kernel algorithms surpassed previous linear PCA-based K-nearest-neighbors models, and improved outcomes with limited increase in computation cost. Without requiring linear, Gaussian, stationary, independent, and homo-skedastic qualities from data, the proposed flexible environmental data science approach could be transferred, rebuilt, and tuned conveniently for ICs from different WWTPs.

Aggregation is a vital behavior when performing complex tasks in most of the swarm systems, such as swarm robotics systems. In this paper, three new aggregation methods, namely the distance-angular, the distance-cosine, and the distance-Minkowski k-nearest neighbor (k-NN) have been introduced. These aggregation methods are mainly built on well-known metrics: the cosine, angular, and Minkowski distance functions, which are used here to compute distances among robots' neighbors. Relying on these methods, each robot identifies its k-nearest neighborhood set that will interact with. Then, in order to achieve the aggregation, the interactions sensing capabilities among the set members are modeled using a virtual viscoelastic mesh. Analysis of the results obtained from the ARGoS simulator shows a significant improvement in the swarm aggregation performance compared to the conventional distance-weighted k-NN aggregation method. Also, the aggregation performance of the methods is reported to be robust to partially faulty robots and accurate under noisy sensors.