Signals, Volume 3, Issue 4 (December 2022) – 15 articles

Multilabel learning goes beyond standard supervised learning models by associating a sample with more than one class label. Among the many techniques developed in the last decade to handle multilabel learning best approaches are those harnessing the power of ensembles and deep learners. This work proposes merging both methods by combining a set of gated recurrent units, temporal convolutional neural networks, and long short-term memory networks trained with variants of the Adam optimization approach. We examine many Adam variants, each fundamentally based on the difference between present and past gradients, with step size adjusted for each parameter. We also combine Incorporating Multiple Clustering Centers and a bootstrap-aggregated decision trees ensemble, which is shown to further boost classification performance. In addition, we provide an ablation study for assessing the performance improvement that each module of our ensemble produces. Multiple experiments on a large set of datasets representing a wide variety of multilabel tasks demonstrate the robustness of our best ensemble, which is shown to outperform the state-of-the-art. Full article

The construction of intelligent logistics by intelligent wireless sensing is a modern trend. Hence, this study uses the multistate flow network (MFN) to explore the actual environment of logistics delivery and to consider the different types of transportation routes available for logistics trucks in today’s practical environment, which have been neglected in previous studies. Two road types, namely highways and slow roads, with different speed limits are explored. The speed of the truck is fast on the highway, so the completion time of the single delivery is, of course, fast. However, it is also because of its high speed that it is subject to many other conditions. For example, if the turning angle of the truck is too large, there will be a risk of the truck overturning, which is a quite serious and important problem that must be included as a constraint. Moreover, highways limit the weight of trucks, so this limit is also included as a constraint. On the other hand, if the truck is driving on a slow road, where its speed is much slower than that of a highway, it is not limited by the turning angle. Nevertheless, regarding the weight capacity of trucks, although the same type of trucks running on slow roads can carry a weight capacity that is higher than the load weight limit of driving on the highway, slow roads also have a load weight limit. In addition to a truck’s aforementioned turning angle and load weight capacity, in today’s logistics delivery, time efficiency is extremely important, so the delivery completion time is also included as a constraint. Therefore, this study uses the improved d-MP method to study the reliability of logistics delivery in trucks driving on two types of roads under constraints to help enhance the construction of intelligent logistics with intelligent wireless sensing. An illustrative example in an actual environment is introduced. Full article

This paper uses millimeter-wave radar to recognize gestures in four different scene domains. The four scene domains are the experimental environment, the experimental location, the experimental direction, and the experimental personnel. The experiments are carried out in four scene domains, using part of the data of a scene domain as the training set for training. The remaining data is used as a validation set to validate the training results. Furthermore, the gesture recognition results of known scenes can be extended to unknown stages after obtaining the original gesture data in different scene domains. Then, three kinds of hand gesture features independent of the scene domain are extracted: range-time spectrum, range-doppler spectrum, and range-angle spectrum. Then, they are fused to represent a complete and comprehensive gesture action. Then, the gesture is trained and recognized using the three-dimensional convolutional neural network (CNN) model. Experimental results show that the three-dimensional CNN can fuse different gesture feature sets. The average recognition rate of the fused gesture features in the same scene domain is 87%, and the average recognition rate in the unknown scene domain is 83.1%, which verifies the feasibility of gesture recognition across scene domains. Full article

In this paper, a new sampling technique is proposed that can be used in the Multistart global optimization technique as well as techniques based on it. The new method takes a limited number of samples from the objective function and then uses them to train an Radial Basis Function (RBF) neural network. Subsequently, several samples were taken from the artificial neural network this time, and those with the smallest network value in them are used in the global optimization method. The proposed technique was applied to a wide range of objective functions from the relevant literature and the results were extremely promising. Full article

In this study, a new method for the optimal design of multimode shunt-damping circuits is presented. A modification of the “current-flowing” shunt circuit is employed to control multiple vibration modes of a piezoelectric laminate beam. In addition to the resistor damping components, the method considers the capacitances and the shunting branch inductors as new design variables. The $H_{\infty }$ norm of the damped system is minimized using the particle swarm optimization (PSO) method in the suggested optimization strategy. Two additional numerical models are addressed in order to compare the proposed method with other methods from the literature and to thoroughly examine the effect of the design variables on damping performance. To simulate the dynamic behavior of the piezoelectric composite beam, a finite-element model is created which provides more accurate modeling of thick beam structures. Results show that the suggested method may improve damping efficiency when compared to other models, since it generates a highest peak amplitude reduction of 39.61 dB for the second mode and 55.92 dB for the third mode. Finally, another benefit provided by the suggested optimal design is the reduction of the required shunt inductance values. Full article

The risk of a catastrophic or existential disaster for our civilization is increasing this century. A significant motivation for a near-term space settlement is the opportunity to safeguard civilization in the event of a planetary-scale disaster. A catastrophic event could destroy the significant cultural, scientific, and technological progress on Earth. However, early space settlements can preserve records of human activity by maintaining a backup data storage system. The backup can also store information about the events leading up to the disaster. The system would improve the ability of early space settlers to recover our civilization after collapse. We show that advances in laser communications and data storage enable the development of a data storage system on the lunar surface with a sufficient uplink data rate and storage capacity to preserve valuable information about the achievements of our civilization and the chronology of the disaster. Full article

This paper presents a machine-learning approach for detecting swarming events. Three different classification algorithms are tested: The k-Nearest Neighbors algorithm (k-NN) and Support Vector Machine (SVM), and a newly proposed by the authors, U-Net Convolutional Neural Network (CNN), developed for biomedical image segmentation. Next, the authors present their experimental scenario of collecting audio data of swarming and non-swarming events and evaluating the results from the k-NN and SVM classifiers and their proposed CNN algorithm. Finally, the authors compare these three methods and present the cross-comparison results of the optimal method for early and late/close-to-the-event detection of swarming. Full article

Compressive sensing is a simultaneous data acquisition and compression technique, which can significantly reduce data bandwidth, data storage volume, and power. We apply this technique for transient photometric events. In this work, we analyze the effect of noise on the detection of these events using compressive sensing (CS). We show numerical results on the impact of source and measurement noise on the reconstruction of transient photometric curves, generated due to gravitational microlensing events. In our work, we define source noise as background noise, or any inherent noise present in the sampling region of interest. For our models, measurement noise is defined as the noise present during data acquisition. These results can be generalized for any transient photometric CS measurements with source noise and CS data acquisition measurement noise. Our results show that the CS measurement matrix properties have an effect on CS reconstruction in the presence of source noise and measurement noise. We provide potential solutions for improving the performance by tuning some of the properties of the measurement matrices. For source noise applications, we show that choosing a measurement matrix with low mutual coherence can lower the amount of error caused due to CS reconstruction. Similarly, for measurement noise addition, we show that by choosing a lower expected value of the binomial measurement matrix, we can lower the amount of error due to CS reconstruction. Full article

Visible light communication (VLC ) is an emerging research area in wireless communication. The system works the same way as optical fiber-based communication systems. However, the VLC system uses free space as its transmission medium. The invention of the light-emitting diode (LED) significantly updated the technologies used in modern communication systems. In VLC, the LED acts as a transmitter and sends data in the form of light when the receiver is in the line of sight (LOS) condition. The VLC system sends data by blinking the light at high speed, which is challenging to identify by human eyes. The detector receives the flashlight at high speed and decodes the transmitted data. One significant advantage of the VLC system over other communication systems is that it is easy to implement using an LED and a photodiode or phototransistor. The system is economical, compact, inexpensive, small, low power, prevents radio interference, and eliminates the need for broadcast rights and buried cables. In this paper, we investigate the performance of an indoor VLC system using Optisystem simulation software. We simulated an indoor VLC system using LOS and non-line-of-sight (NLOS) propagation models. Our simulation analyzes the LOS propagation model by considering the direct path with a single LED as a transmitter. The NLOS propagation model-based VLC system analyses two scenarios by considering single and dual LEDs as its transmitter. The effect of incident and irradiance angles in an LOS propagation model and an eye diagram of LOS/NLOS models are investigated to identify the signal distortion. We also analyzed the impact of the field of view (FOV) of an NLOS propagation model using a single LED as a transmitter and estimated the bitrate $\left(R_b\right)$. Our theoretical results show that the system simulated in this paper achieved bitrates in the range of $2.1208\times {10}^7$ to $4.2147\times {10}^7$ bits/s when the FOV changes from ${30}^{\circ }$ to ${90}^{\circ }$. A VLC hardware design is further considered for real-time implementations. Our VLC hardware system achieved an average of 70% data recovery rate in the LOS propagation model and a 40% data recovery rate in the NLOS propagation model. This paper’s analysis shows that our simulated VLC results are technically beneficial in real-world VLC systems. Full article

In recent years, a wide range of hyperspectral imaging systems using coded apertures have been proposed. Many implement compressive sensing to achieve faster acquisition of a hyperspectral data cube, but it is also potentially beneficial to use coded aperture imaging in sensors that capture full-rank (non-compressive) measurements. In this paper we analyse the signal-to-noise ratio for such a sensor, which uses a Hadamard code pattern of slits instead of the single slit of a typical pushbroom imaging spectrometer. We show that the coded slit sensor may have performance advantages in situations where the dominant noise sources do not depend on the signal level; but that where Shot noise dominates a conventional single-slit sensor would be more effective. These results may also have implications for the utility of compressive sensing systems. Full article

Hemiplegia is a condition caused by brain injury and affects a significant percentage of the population. The effect of patients suffering from this condition is a varying degree of weakness, spasticity, and motor impairment to the left or right side of the body. This paper proposes an automatic feature selection and construction method based on grammatical evolution (GE) for radial basis function (RBF) networks that can classify the hemiplegia type between patients and healthy individuals. The proposed algorithm is tested in a dataset containing entries from the accelerometer sensors of the RehaGait mobile gait analysis system, which are placed in various patients’ body parts. The collected data were split into 2-second windows and underwent a manual pre-processing and feature extraction stage. Then, the extracted data are presented as input to the proposed GE-based method to create new, more efficient features, which are then introduced as input to an RBF network. The paper’s experimental part involved testing the proposed method with four classification methods: RBF network, multi-layer perceptron (MLP) trained with the Broyden–Fletcher–Goldfarb–Shanno (BFGS) training algorithm, support vector machine (SVM), and a GE-based parallel tool for data classification (GenClass). The test results revealed that the proposed solution had the highest classification accuracy (90.07%) compared to the other four methods. Full article

Time reversal has been demonstrated to be effective for source and novelty detection and localization. We extend here previous work in the case of a coupled structural-acoustic system, to which we refer to as vibro-acoustic. In this case, novelty means a change that the structural system has undergone and which we seek to detect and localize. A single source in the acoustic medium is used to generate the propagating field, and several receivers, both in the acoustic and the structural part, may be used to record the response of the medium to this excitation. This is the forward step. Exploiting time reversibility, the recorded signals are focused back to the original source location during the backward step. For the case of novelty detection, the difference between the field recorded before and after the structural modification is backpropagated. We demonstrate that the performance of the method is improved when the structural components are taken into account during the backward step. The potential of the method for solving inverse problems as they appear in non destructive testing and structural health monitoring applications is illustrated with several numerical examples obtained using a finite element method. Full article

Grammatical inference of context-free grammars using positive and negative language examples is among the most challenging task in modern artificial and natural language technology. Recently, several implementations combining various techniques, usually including the Backus–Naur form, have been proposed. In this paper, we explore a new implementation of grammatical inference using evolution methods focused on the Greibach normal form and exploiting its properties, and also propose new solutions both in the evolutionary processes and in the corresponding fitness estimation. Full article

Validating RF applications is traditionally time consuming, even for relatively simple systems. We developed the WISCA Software-Defined Radio Network (WISCANet) to accelerate the implementation and validation of radio applications over-the-air (OTA). WISCANet is a hardwareagnostic control software that automatically configures and controls a software-defined radio (SDR) network. By abstracting the hardware controls away from the user, WISCANet allows a non-expert user to deploy an OTA application by simply defining a baseband processing chain in a high level language. This technology reduces transition time between system design and OTA deployment, accelerates debugging and validation processes, and makes OTA experimentation more accessible to users that are not radio hardware experts. WISCANet emulates real-time RF operations, enabling users to perform real-time experiments without the typical restrictions on processing speed and hardware capabilities. WISCANet also supports multiple RF front-ends (RFFEs) per compute node, allowing sub-6 and mmWave systems to coexist on the same node. This coexistence enables simultaneous baseband processing that simplifies and enhances advanced algorithms and beyond-5G applications. In this study, we highlight the capabilities of WISCANet in several sub-6 and mmWave over-the-air demonstrations. The open source release of this software may be found on the WISCA GitHub page. Full article

This paper presents a novel method of tensor rank regularization with bias compensation for channel estimation in a hybrid millimeter wave MIMO-OFDM system. Channel estimation is challenging due to the unknown number of multipath components that determines the channel rank. In general, finding the intrinsic rank of a tensor is a non-deterministic polynomial-time (NP) hard problem. However, by leveraging the sparse characteristics of millimeter wave channels, we propose a modified CANDECOMP/PARAFAC (CP) decomposition-based method that jointly estimates the tensor rank and channel component matrices. Our approach differs from most existing works that assume the number of channel paths is known and the proposed method is able to estimate channel parameters accurately without the prior knowledge of number of multipaths. The objective of this work is to estimate the tensor rank by a novel sparsity-promoting prior that is incorporated into a standard alternating least squares (ALS) function. We introduce a weighting parameter to control the impact of the previous estimate and the tensor rank estimation bias compensation in the regularized ALS. The channel information is then extracted from the estimated component matrices. Simulation results show that the proposed scheme outperforms the baseline l1 strategy in terms of accuracy and robustness. It also shows that this method significantly improves rank estimation success at the expense of slightly more iterations. Full article