The rise of digitalization and Industry 4.0 has led to significant changes in industrial warehouse management. However, managing warehouses remains challenging due to reliance on manual labor and limited automation. This article focuses on addressing issues in warehouse management, specifically in drug identification and counting. Although traditional methods such as barcode systems and RFID are common, artificial intelligence (AI) offers a promising solution. In this paper, an advanced visual recognition based on Faster R‐CNN is introduced to accurately identify and count pharmaceutical items in pharmacies. The obtained results suggest that intelligent warehouse management in pharmacies can lead to cost savings and improved efficiency. The study also compares the proposed model with popular classification methods such as CNN, SVM, KNN, YOLOv5, and SSD, showing the effectiveness of the new approach.

Understanding drivers’ emotions is crucial for safety and comfort in autonomous vehicles. While Facial Expression Recognition (FER) systems perform well in controlled environments, struggle in real driving situations. To address this challenge, an Interlaced Local Attention Block within a Convolutional Neural Network (ILAB-CNN) model has been proposed to analyze drivers’ emotions. In real-world scenarios, not all facial regions contribute equally to expressing emotions; specific areas or combinations are key. Inspired by the attention mechanism , an ILAB and a Modified Squeeze-and-Excitation (MSE) block has been proposed to learn more discriminative features . The MSE block applies a self-attention mechanism on the channels, effectively identifying key features by incorporating global information and discarding irrelevant features. ILAB employs the MSE and encoder-decoder structures for region-channel specific attention in one branch and combines it with the obtained feature map of the MSE from the other branch. The proposed approach successfully captures essential information from facial expressions while utilizing a reduced number of parameters, leading to significantly improved recognition accuracy and recognition time for real-time applications. Evaluated on diverse datasets, our method shows 75.3 % recognition rate on FER-2013, 85.06 % on RAF-DB, and 98.8 % on KMU-FED, demonstrating its potential to advance FER technology.

In recent years, because of the growing demand for location based services in indoor environment and development of Wi-Fi, fingerprint-based indoor localization has attracted many researchers’ interest. In Wireless Sensor Networks (WSNs), fingerprint based localization methods estimate the target location by using a pattern matching model for the measurements of the Received Signal Strength (RSS) from the available transmitter sensors, which are collected by a smartphone with internal sensors. Due to the dynamic nature of the environment, the fingerprint database needs to be updated, periodically. Hence, it is better to add new fingerprint data to the primary database in order to update them. However, collecting the labeled data is time consuming and labor intensive. In this paper, we propose a novel algorithm, which uses high level extracted features by an autoencoder to improve the localization performance in the classification process. Furthermore, to update the fingerprint data base, we also add crowd-sourced labeled and unlabeled data in order to improve the localization performance, gradually. Simulation results indicate that the proposed method provides a significant improvement in localization performance, using high level extracted features by the autoencoder, and by increasing the number of unlabeled training data.

This work presents a study of ultra wideband (UWB) technology to compute the energy transmission level as an electromagnetic impulse traveling from the transmitter antenna into the human body, and reaching the receiver antenna. The consideration is based on two center frequencies at 3.5 GHz which occupies 1 GHz bandwidth and at 6.1 GHz occupying 6 GHz bandwidth. A small discone antenna with gain of 1.8 dBi is employed as the transmitter antenna and a designed implantable patch antenna with gain of 4 dBi is also used as the receiver antenna. The distance between two antennas is 23.6 mm and the tissue attenuation has been considered for two layers including skin and fat with thickness of 2 mm and 9.6 mm respectively. The computation is accomplished for one way-link UWB communication system with respect to FCC regulation, UWB antenna characteristic and Biological tissue model focusing on attenuation affects. The attenuation is based on the response of the transmitted incident power to reflection, absorption and thickness of the human tissue including frequency-dependent parameters such as permittivity and conductivity. Computer simulation results demonstrate the power comparison for two center frequencies in terms of bandwidth and attenuation. Since the lower band of UWB is suitable for radiation into the human body due to the greater penetration of signals, the results indicate that despite the increasing frequency from 3.5 GHz to 6.1 GHz, there is only minor power variations at the receiver.

In composite event detection systems such as fire alarms, the two foremost goals are speed and accuracy. One way to achieve these goals is by performing data aggregation at central nodes. This helps reduce energy consumption and redundancy. In this paper we present a new hybrid approach that involves the use of k-means algorithm with neural networks, an efficient supervised learning algorithm that extracts patterns and detects trends that are hidden in complex data. Previous research on event detection concentrates majorly on the use of feed forward neural network and other classifiers such as naive Bayes and decision tree alone for modern fire detection applications. In our approach presented here, we combine k-means with neural networks and other classifiers in order to improve the detection rate of event detection applications. To demonstrate our approach, we perform data aggregation on normalized multi-dimensional fire datasets in order to remove redundant data. The aggregated data forms two clusters which represent the two class labels (actual outputs) with the aid of k-means clustering. The resulting data outputs are trained by the Feed Forward Neural Network, Naive Bayes, and Decision Trees. This approach was found to significantly improve fire detection performance.

Recently there has been renewed interest in the application of photoplethysmography signals for cardiovascular disease assessment. Photoplethysmography signals are acquired non-invasively using visible and infrared light passed through the finger pulp. Unfortunately, this method commonly suffers from many forms of interference and distortion such as; baseline wander, mains-line interference and random spikes or other such artifacts. This paper presents a new approach for effective filtering of the photoplethysmography signal. Specifically, a cascaded filtering method for removing the artifacts from photoplethysmography signals based on the median and polynomial filters (MdPF) is proposed. Recordings from the PhysioNet database are used to validate the proposed method. Our experimental results show that the performance of MdPF cascaded filtering method is more effective than other current methods alone in removing artifacts from photoplethysmography signals. Root mean square error measurements are used for comparison purposes. This paper follows from previous work on median based method for baseline wander removal in photoplethysmogram signals.

Removal of baseline wander is a crucial step in the signal conditioning stage of photoplethysmography signals. Hence, a method for removing the baseline wander from photoplethysmography based on two-stages of median filtering is proposed in this paper. Recordings from Physionet database are used to validate the proposed method. In this paper, the twostage moving average filtering is also applied to remove baseline wander in photoplethysmography signals for comparison with our novel two-stage median filtering method. Our experiment results show that the performance of two-stage median filtering method is more effective in removing baseline wander from photoplethysmography signals. This median filtering method effectively improves the cross correlation with minimal distortion of the signal of interest. Although the method is proposed for baseline wander in photoplethysmography signals, it can be applied to other biomedical signals as well.

In this study, the authors present a novel geometrically driven multilateration technique that is based on ultra‐wideband (UWB) technology. The authors refer to their proposed solution as time reflection of arrival (TROA). They demonstrate in this study how the position estimation error is improved upon by carefully considering the inherent properties of the UWB technology and the reflection properties of transmitted UWB signals. By a direct comparison between TROA and two widely used multilateration techniques, the authors show that indoor position estimation can be done much more effectively using their proposed solution. They also derive a new Cramér–Rao lower bound for TROA multilateration and use it to show its level of efficiency.

Cognitive radio is expected to improve the efficiency of frequency usage, capacity, and dependability of a wireless system. In order to change the radio parameters flexibly, the CR terminal should measure the radio environments on adjacent channels as well as the channel for communication. This paper proposes an overlapped FFT energy detection of adjacent channels with frame summation. The proposed scheme constructs new frame through summation and reduces the energy of the noise at the outputs of FFT. Numerical results obtained through computer simulation have shown that the overlapped FFT with no frame summation and with frame summation improve the probability of detection by about 2% and 3%, respectively, as compared to that without overlapping on the adjacent channel.

Fractional sampling (FS) has been investigated to achieve path diversity with a single antenna in an OFDM system. However, in the FS-OFDM system, it is necessary to oversample a received signal and it leads to large power consumption in a small terminal. To shift the signal processing burdens for FS from a receiver to a transmitter, a precoded transmit path diversity scheme in OFDM has been proposed. It achieves path diversity without oversampling the received signal at the receiver side on time invariant channels. However, it has not taken time variant channels into consideration. On time variant channels, inter-carrier interference (ICI) deteriorates the bit-error-rate (BER) performance. In this study, the precoding for both ICI suppression and path diversity combining at the transmitter side has been proposed. Computer simulation shows that both the conventional scheme and the proposed scheme can achieve transmit path diversity. On a two path Rayleigh fading channel, the BER performance of the proposed scheme is better than that of the conventional scheme by about 1 dB. On ultra wideband (UWB) channels, the performance of the proposed scheme is 7–10 dB better at BER=10−2 than that of the conventional scheme. It can achieve ICI suppression and path diversity without any specific signal processing at the receiver. The effect of the ICI suppression is more significant as the number of the multipath is larger.

To achieve diversity with a single antenna, a fractional sampling (FS) scheme in OFDM has been proposed. FS achieves path diversity with a higher sampling rate and multiple demodulation branches. In the previous literatures for FS, the sampling interval is fixed even though the initial phase selection of the sampling has been investigated. The fixed sampling interval limits the diversity gain through FS. Thus, in this study, a non-uniform sampling point selection scheme according to the frequency response of a channel is proposed. Numerical results through computer simulation show that the proposed scheme improves the BER performance by about 2 dB when the number of the demodulation branches is 2. While the proposed scheme further improves bit error rate (BER) performance it requires a larger rate and more computational complexity for the selection of the sampling points. Therefore the complexity reduction for the sampling point selection is also investigated. The complexity reduction scheme eliminates the specific sets of the sampling points and reduces the computational complexity of the sampling point selection for the proposed scheme by a factor of 2. Computer simulation also shows that the low complexity version of the proposed scheme even achieves the equivalent BER compared to the original proposed scheme.

This study proposes the use of wavelet transform in long-term evolution (LTE) cellular systems. Mathematical expressions are derived to represent data rate in LTE downlink transmission based on Wavelet and Fourier Transforms. Furthermore, a comparison between these two systems is provided. Simulation results show the proposed orthogonal wavelet division multiplexing (OWDM) approach outperforms the traditional orthogonal frequency division multiplexing-based systems. The data rate can also be increased by the amount of CyclicPrefix/SymbolTime%, as there is no need for a channel prefix in an OWDM-based system.

To achieve diversity with a single antenna, a fractional sampling (FS) scheme in OFDM has been investigated. In addition, to obtain more diversity gain through FS, a sampling point selection (SPS) scheme has been proposed. However, it requires a large number of multiplication operations for the SPS. This leads to large power consumption and costs for additional circuits. In this paper, a low-complexity SPS scheme is proposed. There is the trade-off between the diversity gain and the estimation accuracy. The serial process of the channel estimation requires only a DFT block with the size of N/4 as the additional circuit.

Orthogonal frequency and code division multiplexing (OFCDM) has received large attention as a modulation scheme to realise high data rate transmission. The OFCDM system with fractional sampling (FS) is investigated. FS is a diversity scheme with a single antenna, which achieves path diversity through oversampling and parallel signal reception. However, the correlation among noise components may deteriorate the bit error rate performance at the receiver as the number of subcarriers and oversampling ratio increases. To overcome this problem, the alternative spreading code is used for the FS OFCDM system. Numerical results through computer simulation show that the proposed scheme can improve the performance of the receiver with the large oversampling ratio and the number of subcarriers.

One of the most promising uses for ultra-wideband (UWB) is wireless sensor networks (WSNs). Since WSNs offer a wide variety of services for different application areas, the UWB propagation channel characteristics of each application environment show fundamental differences from each other in many aspects. A reliable and energy-efficient multiple access scheme is thus required to coordinate the transmissions of sensor nodes in these various application channel environments. We develop an analytical framework for evaluating the performance of UWB time-hopping (TH), direct sequence (DS) and orthogonal frequency division multiplexing (OFDM) multiple access schemes with multi-node interference in the following UWB propagation channel environments that have a high importance for WSN applications: residential, office, suburban outdoor, industrial and agricultural. The objective is to determine the most appropriate multiple access scheme to be applied for a particular WSN application channel environment. Performance is evaluated in terms of the average information throughput efficiency, a relevant progress-related measure for multihop WSNs. The mathematical expression of this metric is derived in detail, and is used in numerical evaluations for assessing the performance of the three schemes operating under UWB propagation channel models of the various environments that are characterised by distinct channel parameters and specific valid distance ranges. TH-UWB is shown to be the most suitable multiple access scheme to be adopted for UWB WSNs. It outperforms both the DS-UWB and OFDM-UWB schemes for all application environments and is the most robust and energy efficient. OFDM-UWB is the poorest performing whereas DS-UWB provides similar performance to TH-UWB below a specific threshold number of interfering nodes.

In this paper, we propose a pilot-channel-assisted log-likelihood-ratio selective combining (PCA-LLR-SC) scheme for Rake receivers that will be used in long-range low-rate UWB communications targeted by the IEEE 802.15.4a specification. The pilot and data channels are constructed using quadrature sinusoidal bursts that have the same Gaussian envelope. The system parameters are optimized through jointly minimizing the channel estimation mean square error and maximizing the receiver output signal-to-noise ratio. Simulation results show that the proposed PCA-LLR-SC scheme is able to provide robust low-rate UWB communications in fast-fading multipath channels.

Aiming to generate ultra wideband (UWB) pulses based on wavelet packets, four different circuits are proposed. It has been shown that the wavelet packets are quasi-orthogonal and have almost identical time duration, and therefore appear to be valuable candidates for UWB pulse shape modulation systems. However, as with any technology, circuitry is an important challenge to solve before a theoretical application can live up to its full potential. The four proposed circuits are based on different interpretations of the equation defining the wavelet packets and their performance is investigated by computer simulation. The research also illustrates the characteristics and the consequent implementation advantages or issues afferent to each circuit.

The use of wavelet transform in multicarrier ultra wideband (UWB) systems is analysed and the results are compared with Fourier-based multicarrier UWB systems. It is well known that convolution in time domain is equivalent to multiplication in frequency domain; however, there is no closed-form expression in the literature for convolution's counterpart in the wavelet domain. A formula is derived to represent convolution's counterpart in the wavelet domain. Furthermore, the effects of choice and type of wavelet filters and different decomposition levels are investigated. Finally, a performance comparison of both techniques for IEEE 802.15.3a channel models using IEEE802.15.3a multiband‐orthogonal frequency division multiplexing UWB specifications is provided.

Time-hopping ultra wideband (TH-UWB) and direct-sequence ultra wideband (DS-UWB) systems are among the standards proposed for UWB communications scenarios. A general unified mathematical approach has been proposed for calculating the bit error rate (BER) for both TH-UWB and DS-UWB systems in the presence of multiple-user interference and a strong narrow-band interference in a multi-path scenario. Unlike many other mathematical models that provide upper or lower bounds for BER, this model calculates the exact values for BER in given scenarios. A partial rake receiver has been chosen as the receiving terminal. The modified Saleh-Valenzuela channel model has been used in this analysis. The model can asses the effect of any given narrow-band interfering systems. For the purpose of simulation, the narrow-band interfering system used is a Wi-Max transceiver based on IEEE 802.16-2004 standard. The validity of the model has been checked by comparing the mathematical results with numerical values achieved trough simulation. It is important to notice that this method can simultaneously be applied to both TH-UWB and DS-UWB.

For ultra-wideband (UWB) communications with signal energy dispersed by a large number of multipath compnents, the design of a Rake receiver that can provide a desirable output signal-to-noise ratio (SNR) using only a moderate number of fingers becomes an important issue. In this paper, we propose a pilot-channel-assisted log-likelihood-ratio selective combining (PCA-LLR-SC) scheme for UWB Rake receivers to be used in long-range low-rate UWB communications envisioned by the IEEE 802.15.4a PHY specification. The pilot and data channels are constructed using quadrature sinusoidal bursts that have the same Gaussian envelope. The system parameters are optimized through jointly minimizing the channel estimation mean square error and maximizing the receiver output SNR. Extensive simulations confirm that the proposed PCA-LLR-SC scheme is capable of providing robust low-rate UWB communications in fast-fading multipath channels and in the presence of multi-user interference.

The log-normal probability distribution is commonly used in wireless communications to model the shadowing and more recently the small scale fading for indoor ultra wideband communications. In this paper, an accurate closed-form approximation of the average probability of error over a log-normal fading channel is derived for various constellation types and sizes. This expression can be used to evaluate and compare easily the symbol-error performance of communication systems over a log-normal fading channel.

In this paper we analyse the application of wavelet transform as an alternative to the conventional Fourier-based multicarrier UWB systems. In Fourier based multicarrier UWB systems a cyclic prefix (CP) with the same length of the channel impulse response must be added to each symbol in order to convert linear convolution into circular convolution. The CP must consist of identical copies of the transmitted data in each symbol and therefore is a waste of bandwidth and resources. In this paper we present a framework for wavelet based multicarrier UWB systems and it is shown that they do not require the cyclic prefix for transmission and, hence throughput increases. Moreover, a closed form formula is derived to represent convolution's counterpart in the wavelet domain. Finally, a performance comparison of both techniques is provided.

This paper proposes a positioning routing algorithm for UWB ad hoc networks. The algorithm is deployed in two main scenarios: Multi-Coordinate System (MCS) and Unique Coordinate System (UCS). A Packet Forwarding Zone (PFZ) is proposed to investigate the performance where a limited forwarding region is used. New ideas have been included in the routing algorithm, such as the use of the Davidon-Fletcher-Powell (DFP) algorithm to estimate the position of the locally available beacon nodes, and the Reference Group (RG) concept as formed by suitable nodes with the Reference Group Master (RGM) chosen as elected by the nodes in the RG. The RG group characteristics particularly apply in the UCS case. In addition, the performance of Direct Method (DM) and DFP position estimation algorithms are also analyzed.

Providing diversity is one of the two possible objectives (the other one is providing multiplexing) of a multi-input multi-output (MIMO) system. For ultra wideband (UWB) impulse radio systems using rake receivers, there are already richly inherent multipath diversities. However, there may be UWB applications making use of more than one UWB transmit antenna and/or receive antenna, which leads to UWB MIMO systems. The difference between the diversity analyse of a UWB MIMO system from that of a narrow band system lies in the different choice of propagation channel model for the branches linking each transmit antenna and receive antenna. Similar to the narrow band system, the existence of the correlation between the branches can severely degrade the diversity performance, and complicate the performance analyse. In this paper, the wideband propagation channel for the UWB MIMO system, with pre-defined correlation model for the branches, is broken down into several uncorrelated elementary narrow-band propagation channels with equivalent diversity performance. Based on this, a novel method for evaluating the diversity performance of a MIMO UWB impulse radio system is presented.

In this paper, we propose a pulse-coded orthogonal M-ary pulse position modulation (PPM) scheme that employs coded equivalent pulses, for non-coherent receivers operating in low-data-rate ultra-wideband (UWB) communications. Major system parameters, such as the size of pulse coding and the temporal spacing between adjacent pre-coding pulses, are provided to fully exploit the FCC average- and peak-power constraints. Simulation results show that the performance of the proposed scheme in conjunction with a square-law detector applying fixed large integration duration compares favourably with that of a selective Rake receiver, under realistic UWB channel models

In this paper the effect of aggregate interference produced by a group of ultra wideband (UWB) transmitters using direct sequence technology on a Wi-Max/IEEE-802.16 based system is investigated. Various simulations with different parameters like victim receiver bandwidth, carrier frequency, activity factor and the number of users are performed to measure the produced interference. Finally these measured values are compared to the maximum tolerable interference levels specified for Wi-Max systems to assess if UWB system will create problems for the operation of Wi-Max/IEEE 802.16 based system. It is demonstrated that in a realistic hot spot scenario, the interference produced by the UWB system will fall below the threshold values and this system will not harm the operation of the Wi-Max receiver.

Ultra-wideband (UWB) radio communication systems operate using extremely short duration base-band pulses. This paper compares the performance of three competing multiple access modulation schemes that have been proposed for application to UWB based wireless sensor networks. These multiple access schemes are ultra-wideband Time-Hopping (TH-UWB), Direct Sequence Spread Spectrum (DSSS-UWB) and Orthogonal Frequency Division Multiplexing (OFDM-UWB). Each system was investigated under four operating conditions of different bandwidths and bit rates for three different transmission ranges. The attributes measured to compare the performance of the multiple access schemes under consideration were packet link error rate, throughput and energy efficiency. TH-UWB outperforms DSSS-UWB and OFDM-UWB for high bandwidth conditions. Whereas, DSSS-UWB performs better in low bandwidth conditions compared to the other two systems. Decreasing the transmission range significantly degrades the overall performance of the systems.

Ultra wideband (UWB) systems have attracted a lot of research interest lately, owing to their appealing features in short-range mobile communications. These features include low power peer-to-peer transmissions, multiple access communications, high data rates, and precise positioning capabilities. Space-time coding (STC) techniques, such as the block coding scheme, or the trellis coding scheme, are known to be simple and practical ways to increase the spectral efficiency in wireless communications. We aim to combine a pulse position modulation (PPM) impulse radio multiple access (IRMA) system with two different space-time coding techniques. Thus, we developed a space-time block code scheme and adapted a space-time trellis code scheme to UWB signalling, relying on the channel state information (CSI) at the receiver side. Then the added diversity produced by these techniques is exploited to enhance the performance of UWB systems. Analysis is conducted in a typical UWB environment, with fractionally-spaced (FS) coherent RAKE detection.

Digital radiology places very high demands on the networking and digital storage infrastructure of hospitals. In addition to having quite stringent requirements on the quality of the images displayed to the radiologist, much of the technical challenge resides in the necessity of displaying desired images as rapidly as possible. We present an infrastructure for progressive transmission and compression of medical images, which can refine an initial image by increasing the detail information not only in scale-space, but also in coefficient precision. The approach is based on the embedded zerotree wavelet (EZW) algorithm. This algorithm offers a tremendous amount of flexibility in meeting the bandwidth and image quality constraints in a radiological imaging environment. We propose an application of the EZW algorithm in progressive medical image transmission in which it can specify and control both the resolution constraint and rate constraint. The presented method can provide a framework for lossy image compression, with performance far superior to those provided by the standard JPEG algorithm. Also due to the flexibility of the method we will show how any region of interest of an image can be sent progressively.

In this paper novel prolate spheroidal wave functions are proposed as pulse shapes for use in impulse radio (ultra-wideband) communications. These classes of functions yields orthogonal pulses and have a constant pulse width regardless of the pulse order. This is an important property since it eliminates inter-symbol interference. An M-ary communications system is considered that employs these pulses, and the generation of these pulses using the eigenfunction form of a self-adjoint operator is proposed. It is also shown that these pulses are suitable for use in pulse position modulation (PPM) ultra wideband (UWB) communication systems.

Tapped-delay-line processors have been widely employed in conventional wideband digital arrays. This type of space-time processing generally suffers from the need of very high sampling rates, phase shifters and delay elements. An adaptive wideband linear rectangular array of omnidirectional antenna elements is proposed. This array requires no phase compensation and employs a single real multiplier for each antenna branch. In addition to having real multipliers, a practical advantage of the proposed array over other conventional algorithms is that the number of antenna elements, required for a relatively high fractional bandwidth, is much lower than comparable wideband beamformers.

An ideal broadband beamformer requires an increased number of taps for each filter, which in turn increases the complexity of the design. It is shown that for angles near the broadside of the antenna the beamforming is more accurate compared to the angles near the endfire, and it is advantageous to use recursive filters combined with a computed number of zeros for angles near the endfire. The proposed method is used for estimating the arrival angle of the incoming signals and displays uniform accuracy for all angles.

This paper presents a technique for designing a broad-band partially adaptive antenna using a new recursive fan filter. Each beamformer is designed using recursive two-pole sections. This method reduces the number of taps of the fan filter considerably. Interferences occurring in the sidelobes as well as the mainlobe of the desired pattern and having the same frequency as the desired signal and overlap in bandwidths are cancelled effectively independent of frequency.