Electrical Engineering And Systems Science

Listening to lung sounds through auscultation is vital in examining the respiratory system for abnormalities. Automated analysis of lung auscultation sounds can be beneficial to the health systems in low-resource settings where there is a lack of skilled physicians. In this work, we propose a lightweight convolutional neural network (CNN) architecture to classify respiratory diseases using hybrid scalogram-based features of lung sounds. The hybrid scalogram features utilize the empirical mode decomposition (EMD) and continuous wavelet transform (CWT). The proposed scheme's performance is studied using a patient independent train-validation set from the publicly available ICBHI 2017 lung sound dataset. Employing the proposed framework, weighted accuracy scores of 99.20% for ternary chronic classification and 99.05% for six-class pathological classification are achieved, which outperform well-known and much larger VGG16 in terms of accuracy by 0.52% and 1.77% respectively. The proposed CNN model also outperforms other contemporary lightweight models while being computationally comparable.

The advancing deployment of ubiquitous Internet of Things (IoT)-powered vehicle detection and classification systems will successively turn the existing road infrastructure into a highly dynamical and interconnected Cyber-physical System (CPS). Though many different sensor systems have been proposed in recent years, these solutions can only meet a subset of requirements, including cost-efficiency, robustness, accuracy, and privacy preservation. This paper provides a modular system approach that exploits radio tomography in terms of attenuation patterns and highly accurate channel information for reliable and robust detection and classification of different road users. Hereto, we use Wireless Local Area Network (WLAN) and Ultra-Wideband (UWB) transceiver modules providing either Channel State Information (CSI) or Channel Impulse Response (CIR) data. Since the proposed system utilizes off-the-shelf and power-efficient embedded systems, it allows for a cost-efficient ad-hoc deployment in existing road infrastructures. We have evaluated the proposed system's performance for cyclists and other motorized vehicles with an experimental live deployment. In this concern, the primary focus has been on the accurate detection of cyclists on a bicycle path. However, we also have conducted preliminary evaluation tests measuring different motorized vehicles using a similar system configuration as for the cyclists. In summary, the system achieves up to 100% accuracy for detecting cyclists and more than 98% classifying cyclists and cars.

In this paper, we study the problem of direction of arrival estimation and model order selection for systems employing subarray sampling. Thereby, we focus on scenarios, where the number of active sources is not smaller than the number of simultaneously sampled antenna elements. For this purpose, we propose new schemes based on neural networks and estimators that combine neural networks with gradient steps on the likelihood function. These methods are able to outperform existing estimators in terms of mean squared error and model selection accuracy, especially in the low snapshot domain, at a drastically lower computational complexity.

Forward channel state information (CSI) often plays a vital role in scheduling and capacity-approaching transmission optimization for massive multiple-input multiple-output (MIMO) communication systems. In frequency division duplex (FDD) massive MIMO systems, forwardlink CSI reconstruction at the transmitter relies critically on CSI feedback from receiving nodes and must carefully weigh the tradeoff between reconstruction accuracy and feedback bandwidth. Recent studies on the use of recurrent neural networks (RNNs) have demonstrated strong promises, though the cost of computation and memory remains high, for massive MIMO deployment. In this work, we exploit channel coherence in time to substantially improve the feedback efficiency. Using a Markovian model, we develop a deep convolutional neural network (CNN)-based framework MarkovNet to differentially encode forward CSI in time to effectively improve reconstruction accuracy. Furthermore, we explore important physical insights, including spherical normalization of input data and convolutional layers for feedback compression. We demonstrate substantial performance improvement and complexity reduction over the RNN-based work by our proposed MarkovNet to recover forward CSI estimates accurately. We explore additional practical consideration in feedback quantization, and show that MarkovNet outperforms RNN-based CSI estimation networks at a fraction of the computational cost.

This paper presents a formulation of Snapshot Positioning as a mixed-integer least-squares problem. In snapshot positioning one estimates a position from code-phase and possibly Doppler observations of a Global Navigation Satellite Systems (GNSS) without knowing the time of departure (timestamp) of the codes. Solving the problem allows a receiver to determine a fix from short radio-frequency snapshots missing the time-stamp information embedded in the GNSS data stream. This is used to reduced the time to first fix in some receivers, and it is used in certain wildlife trackers. This paper presents two new formulations of the problem and an algorithm that solves the resulting mixed-integer least-squares problems. We also show that the new formulations can produce fixes even with huge initial errors, much larger than permitted in Van Diggelen's widely-cited coarse-time navigation method.

In a world of aging infrastructure, structural health monitoring (SHM) emerges as a major step towards resilient and sustainable societies. The current advancements in machine learning and sensor technology have made SHM a more promising damage detection method than the traditional non-destructive testing methods. SHM using unsupervised learning methods offers an attractive alternative to the more commonly used supervised learning since it only requires data of the structure in normal conditions for the training process. The density-based novelty detection method provides a statistical element to the damage detection process but it relies heavily on the accuracy of the estimated probability density function (PDF). In this study, a novel unsupervised learning approach for SHM is proposed. It is based on the Kernel Density Maximum Entropy method by leveraging Bayesian optimization for hyperparameter tuning and also by extending the method into the multivariate space by the use of independent components analysis. The proposed approach is evaluated on a numerically simulated three-story reinforced concrete moment frame, where 94% of accuracy is achieved in structural damage detection.

Earthquake signals are non-stationary in nature and thus in real-time, it is difficult to identify and classify events based on classical approaches like peak ground displacement, peak ground velocity. Even the popular algorithm of STA/LTA requires extensive research to determine basic thresholding parameters so as to trigger an alarm. Also, many times due to human error or other unavoidable natural factors such as thunder strikes or landslides, the algorithm may end up raising a false alarm. This work focuses on detecting earthquakes by converting seismograph recorded data into corresponding audio signals for better perception and then uses popular Speech Recognition techniques of Filter bank coefficients and Mel Frequency Cepstral Coefficients (MFCC) to extract the features. These features were then used to train a Convolutional Neural Network(CNN) and a Long Short Term Memory(LSTM) network. The proposed method can overcome the above-mentioned problems and help in detecting earthquakes automatically from the waveforms without much human intervention. For the 1000Hz audio data set the CNN model showed a testing accuracy of 91.1% for 0.2-second sample window length while the LSTM model showed 93.99% for the same. A total of 610 sounds consisting of 310 earthquake sounds and 300 non-earthquake sounds were used to train the models. While testing, the total time required for generating the alarm was approximately 2 seconds which included individual times for data collection, processing, and prediction taking into consideration the processing and prediction delays. This shows the effectiveness of the proposed method for Earthquake Early Warning (EEW) applications. Since the input of the method is only the waveform, it is suitable for real-time processing, thus the models can also be used as an onsite EEW system requiring a minimum amount of preparation time and workload.

Time-frequency analysis is often used to study non stationary multicomponent signals, which can be viewed as the surperimposition of modes, associated with ridges in the TF plane. To understand such signals, it is essential to identify their constituent modes. This is often done by performing ridge detection in the time-frequency plane which is then followed by mode retrieval. Unfortunately, existing ridge detectors are often not enough robust to noise therefore hampering mode retrieval. In this paper, we therefore develop a novel approach to ridge detection and mode retrieval based on the analysis of the short-time Fourier transform of multicomponent signals in the presence of noise, which will prove to be much more robust than state-of-the-art methods based on the same time-frequency representation.

Sparse signal recovery algorithms like sparse Bayesian learning work well but the complexity quickly grows when tackling higher dimensional parametric dictionaries. In this work we propose a novel Bayesian strategy to address the two dimensional harmonic retrieval problem, through remodeling and reparameterization of the standard data model. This new model allows us to introduce a block sparsity structure in a manner that enables a natural pairing of the parameters in the two dimensions. The numerical simulations demonstrate that the inference algorithm developed (H-MSBL) does not suffer from source identifiability issues and is capable of estimating the harmonic components in challenging scenarios, while maintaining a low computational complexity.

Deep neural network is an effective choice to automatically recognize human actions utilizing data from various wearable sensors. These networks automate the process of feature extraction relying completely on data. However, various noises in time series data with complex inter-modal relationships among sensors make this process more complicated. In this paper, we have proposed a novel multi-stage training approach that increases diversity in this feature extraction process to make accurate recognition of actions by combining varieties of features extracted from diverse perspectives. Initially, instead of using single type of transformation, numerous transformations are employed on time series data to obtain variegated representations of the features encoded in raw data. An efficient deep CNN architecture is proposed that can be individually trained to extract features from different transformed spaces. Later, these CNN feature extractors are merged into an optimal architecture finely tuned for optimizing diversified extracted features through a combined training stage or multiple sequential training stages. This approach offers the opportunity to explore the encoded features in raw sensor data utilizing multifarious observation windows with immense scope for efficient selection of features for final convergence. Extensive experimentations have been carried out in three publicly available datasets that provide outstanding performance consistently with average five-fold cross-validation accuracy of 99.29% on UCI HAR database, 99.02% on USC HAR database, and 97.21% on SKODA database outperforming other state-of-the-art approaches.