Mahmoud Fakhry

Heart sound signals, phonocardiography (PCG) signals, allow for the automatic diagnosis of potential cardiovascular pathology. Such classification task can be tackled using the bidirectional long short-term memory (biLSTM) network, trained on features extracted from labeled PCG signals. Regarding the non-stationarity of PCG signals, it is recommended to extract the features from multiple short-length segments of the signals using a sliding window of certain shape and length. However, some window contains unfavorable spectral side lobes, which distort the features. Accordingly, it is preferable to adapt the window shape and length in terms of classification performance. We propose an experimental evaluation for three window shapes, each with three window lengths. The biLSTM network is trained and tested on statistical features extracted, and the performance is reported in terms of the window shapes and lengths. Results show that the best performance is obtained when the Gaussian window is used for splitting the signals, and the triangular window competes with the Gaussian window for a length of 75 ms. Although the rectangular window is a commonly offered option, it is the worst choice for splitting the signals. Moreover, the classification performance obtained with a 75 ms Gaussian window outperforms that of a baseline method.

A trained neural network classifier is often used to detect cardiac problems by the classification of heart sound signals, also known as phonocardiogram (PCG) signals. The choice of an appropriate training optimization algorithm for such a classification problem, on the other hand, is still being debated. In this paper, we use the bidirectional long short-term memory (biLSTM) network for the classification of sequences of short-time features extracted from labelled PCG signals. The classification performance of four different trained biLSTM models is described in terms of three different optimization algorithms that are used to train the classifier. The elaborated results on testing PCG signals show that the biLSTM classifier performs better when trained with the stochastic gradient descent with momentum (SGDM) algorithm than when trained with the RMSprop (root mean squared propagation) optimizer or the adaptive moment (ADAM) optimization algorithm. Furthermore, this classification method outperforms a baseline method.

In this paper, an accurate approach for vehicle counting in videos using Mask R-CNN and KLT tracker is proposed. Vehicle detection is performed for each N frames using Mask R-CNN instance segmentation model. This model outperforms other deep learning models that using bounding box detection as it provides a segmentation mask for each detected object, the outperformance comes up clearly in cases of occlusions. Once the objects are detected, their corner points are extracted and tracked. An efficient method is introduced to assign point trajectories to their corresponding detected vehicles. The proposed counting algorithm distinguishes precisely between the new vehicles and the counted ones. The experiments performed on diverse challenging videos show excellent results compared to state-of-the-art counting methods.

Artificial neural networks have proven high efficiency in the classification of features in many application fields. It is widely proved that dynamic recurrent networks perform better than any other types of networks, for the feedback connections and the embedded memory. In this paper, we use a dynamic recurrent network called the nonlinear autoregressive network with exogenous inputs (NARX) for the normal/abnormal classification of phonocardiography (PCG) signals. Up to the authors' knowledge, this is the first time that the NARX network is used for such classification task. The network is trained and tested using a dataset of 6316 feature vectors, each vector of length 27 features. The evaluation of this network is achieved at different sizes of the embedded memory. The experimental results show that the NARX network outperforms other two networks, and its performance increases as a function of the memory size till a certain value. Further increase of the memory size degrades the performance as a results of model overfitting.

Due to the Internet of Things (IoT) requirements for a high-density network with low-cost and low-power physical (PHY) layer design, the low-power budget transceiver systems have drawn momentous attention lately owing to their superior performance enhancement in both energy efficiency and hardware complexity reduction. As the power budget of the classical transceivers is envisioned by using inefficient linear power amplifiers (PAs) at the transmitter (TX) side and by applying high-resolution analog to digital converters (ADCs) at the receiver (RX) side, the transceiver architectures with low-cost PHY layer design (i.e., nonlinear PA at the TX and one-bit ADC at the RX) are mandated to cope with the vast IoT applications. Therefore, in this paper, we propose the orthogonal shaping pulses minimum shift keying (OSP-MSK) as a multiple-input multiple-output (MIMO) modulation/demodulation scheme in order to design the low-cost transceiver architectures associated with the IoT devices. The OSP-MSK fulfills a low-power budget by using constant envelope modulation (CEM) techniques at the TX side, and by applying a low-resolution one-bit ADC at the RX side. Furthermore, the OSP-MSK provides a higher spectral efficiency compared to the recently introduced MIMO-CEM with the one-bit ADC. In this context, the orthogonality between the in-phase and quadrature-phase components of the OSP are exploited to increase the number of transmitted bits per symbol (bps) without the need for extra bandwidth. The performance of the proposed scheme is investigated analytically and via Monte Carlo simulations. For the mathematical analysis, we derive closed-form expressions for assessing the average bit error rate (ABER) performance of the OSP-MSK modulation in conjunction with Rayleigh and Nakagami-m fading channels. Moreover, a closed-form expression for evaluating the power spectral density (PSD) of the proposed scheme is obtained as well. The simulation results corroborate the potency of the conducted analysis by revealing a high consistency with the obtained analytical formulas.