Showing papers in "Electronics Letters in 2020"
TL;DR: In this paper, a new no-equilibrium chaotic system with hidden attractors and coexisting attractors is reported, which generates chaos through period-doubling bifurcation with the variation of system parameters.
Abstract: This Letter reports a new no-equilibrium chaotic system with hidden attractors and coexisting attractors. Bifurcation diagram shows that the proposed system generates chaos through period-doubling bifurcation with the variation of system parameters, and the hidden chaotic and periodic attractors are visually given by phase portraits. The coexisting chaotic and periodic attractors from different initial conditions are observed in the system. The analogue circuit realisation and microcontroller-based experimental implementation of the system are given to verify its physical existence.
65 citations
TL;DR: In this article, a second-order discrete map model based on a simple sampling switch-based memristor-capacitor circuit is presented, which exhibits chaotic and hyperchaotic behaviours via a period-doubling bifurcation scenario.
Abstract: This Letter presents a new second-order discrete map model, which is derived from a simple sampling switch-based memristor-capacitor circuit. The memristor-based map model has infinite unstable and critical stable fixed points, and exhibits chaotic and hyperchaotic behaviours via a period-doubling bifurcation scenario. These complex dynamical behaviours are confirmed by the phase portraits, iterative sequences and basins of attraction.
56 citations
TL;DR: In this paper, a novel framework is proposed for the automated accurate classification of motor-imagery (MI) tasks in brain-computer interface (BCI), which achieved 95.3% of total classification accuracy with 100% outcome for subject with very small training samples.
Abstract: Brain complexity and non-stationary nature of electroencephalography (EEG) signal make considerable challenges for the accurate identification of different motor-imagery (MI) tasks in brain–computer interface (BCI). In the proposed Letter, a novel framework is proposed for the automated accurate classification of MI tasks. First, raw EEG signals are denoised with multiscale principal component analysis. Secondly, denoised signals are decomposed by empirical wavelet transform into different modes. Thirdly, the two-dimensional (2D) modelling of modes is introduced to identify the variations of different signals. Fourthly, a single geometrical feature name as, a summation of distance from each point relative to a coordinate centre is extracted from 2D modelling of modes. Finally, the extracted feature vectors are provided to the feedforward neural network and cascade forward neural networks for classification check. The proposed study achieved 95.3% of total classification accuracy with 100% outcome for subject with very small training samples, which is outperforming existing methods on the same database.
53 citations
TL;DR: A music genre classification system and music recommendation engine, which focuses on extracting representative features that have been obtained by a novel deep neural network model, have been proposed.
Abstract: Today, music is a very important and perhaps inseparable part of people's daily life. There are many genres of music and these genres are different from each other, resulting in people to have different preferences of music. As a result, it is an important and up-to-date issue to classify music and to recommend people new music in music listening applications and platforms. Classifying music by their genre is one of the most useful techniques used to solve this problem. There are a number of approaches for music classification and recommendation. One approach is based on the acoustic characteristics of music. In this study, a music genre classification system and music recommendation engine, which focuses on extracting representative features that have been obtained by a novel deep neural network model, have been proposed. Acoustic features extracted from these networks have been utilised for music genre classification and music recommendation on a data set.
40 citations
TL;DR: The physical layer security for a novel reconfigurable intelligent surface (RIS)-assisted non-orthogonal multiple access (NOMA) system in a multi-user scenario is investigated, where the authors observe that the use of RISs can improve the secrecy performance compared to traditional NOMA systems.
Abstract: In this Letter, the physical layer security for a novel reconfigurable intelligent surface (RIS)-assisted non-orthogonal multiple access (NOMA) system in a multi-user scenario is investigated, where the authors consider the worst case that the eavesdropper also utilises the advantage of the RISs. More specifically, they derive analytical results for the secrecy outage probability (SOP). From the numerical results, they observe that the use of RISs can improve the secrecy performance compared to traditional NOMA systems. However, for the worst case that the received signals at the eavesdropper come from the RISs and source, increasing the number of intelligent elements on the RIS has a negative impact on the secrecy performance. At high signal-to-noise ratios, the system's SOP tends to a constant. Finally, the secrecy performance can be improved through group selection.
32 citations
TL;DR: Comparative experimental results, provided with state-of-the-art DC offset rejection-based enhanced phase locked-loop, clearly demonstrate the suitability of the proposed technique.
Abstract: This Letter proposes demodulation type PLL for phase and frequency estimation of single-phase system that can reject DC offset. Using results from the adaptive estimation literature, this Letter proposes a linear parametric model-based initial phase angle estimation approach. Then by using differentiation and integration operation on the estimated initial phase angle, the frequency is estimated. This avoids the use of any low-pass filter unlike conventional demodulation-based technique. Moreover, unlike existing demodulation-based technique, the proposed technique can completely reject DC offset. Comparative experimental results, provided with state-of-the-art DC offset rejection-based enhanced phase locked-loop, clearly demonstrate the suitability of the proposed technique.
28 citations
TL;DR: In this article, the authors proposed a secure resource allocation model by developing a threat detector based on the analysis of co-located inter-VM relations and a workload predictor in the background.
Abstract: Cloud clients face high security risks while sharing physical resources with multiple users. A malicious cloud user exploits co-residency and hypervisor vulnerabilities to steal and hamper sensitive information of victim virtual machine (VM). To address this alarming issue, this Letter proposes a secure resource allocation model by developing a threat detector based on the analysis of co-located inter-VM relations and a workload predictor in the background. The anomalous network traffic, response speed, bandwidth usage and illegal inter-VM links are considered as security breaches indicator that assists in future threat detection beforehand and consequently guides the secure and resource efficient VM allocation. The comparison of proposed model with state-of-the-art: FCFS, Random-fit and NSGA-II based resource allocation approaches indicate that it significantly reduce security threats by 77.38% and number of active servers up to 5.39% with improved resource utilisation up to 26.84% over Random-fit.
27 citations
TL;DR: In this article, the authors developed an efficient framework based on deep learning concept for automatic identification of human emotion from EEG signals, where the signals are pre-processing for removing noises by low-pass filtering and then delta rhythm is extracted.
Abstract: Identification of human emotion involving electroencephalogram (EEG) signals has become an emerging field in health monitoring application as EEG signals can give us a more diverse insight on emotional states. The aim of this study is to develop an efficient framework based on deep learning concept for automatic identification of human emotion from EEG signals. In the proposed framework, the signals are pre-processing for removing noises by low-pass filtering and then delta rhythm is extracted. After that, the extracted rhythm signals are converted into the EEG rhythm images by employing the continuous wavelet transform and then deep features are discovered by using a pre-trained convolutional neural networks model. Afterwards, MobileNetv2 is used for deep feature selection to obtain the most efficient features and finally, long short term memory method is employed for classification of selected features. The proposed methodology is tested on ‘DEAP EEG data set’ (publicly available). This study considers two emotions namely ‘Valence’ and ‘Arousal’ for classification. The experimental results demonstrate that the proposed approach produced accuracies of 96.1% for low/high valence and 99.6% for low/high arousal classification. A further comparison of the proposed method is also carried out and it is seen that the proposed method outperforms other compared methods.
26 citations
TL;DR: In this article, the authors developed an efficient autism diagnostic system that can automatically identify autism based on time-frequency spectrogram images from EEG signals, which achieved an average of 95.25% accuracy in tenfold cross-validation evaluation.
Abstract: Autism is a type of neurodevelopment disorder in which individuals often have difficulties in social relationship, communication, expressing and controlling emotions and poor eye contact, among other symptoms. Currently, electroencephalography (EEG) is the most popular tool to investigate the presence of autism biomarkers. Generally, EEG recordings generate huge volume data with dynamic behaviour. In current practice, the massive EEG data are visually analysed by specialist clinicians to identify autism, which is time consuming, costly, subject to human error, and reduces decision-making reliability. Hence this Letter aims to develop an efficient autism diagnostic system that can automatically identify autism based on time–frequency spectrogram images from EEG signals. Firstly, the raw EEG data is pre-processed using several techniques, such as re-referencing, filtering and normalisation. After that, the pre-processed EEG signals are converted to two-dimensional images using a short-time Fourier transform. Then, textural features are extracted, and significant features are selected using principal component analysis, and feed to support vector machine classifier for classification. The proposed system achieved an average of 95.25% accuracy in ten-fold cross-validation evaluation. The developed system's simplicity and performance indicates usefulness as a decision support tool for healthcare professionals in autism diagnosis.
25 citations
TL;DR: A waveguide step-twist integrated with a bandpass filter is presented in this article, where the twist is composed of four equally rotated cavities to achieve polarisation rotation and filtering functionalities simultaneously.
Abstract: A novel waveguide step-twist integrated with a bandpass filter is presented in this Letter. The twist is composed of four equally rotated cavities to achieve polarisation rotation and filtering functionalities simultaneously. Such step-twist can achieve a significant reduction in size and weight. The design is demonstrated at Ka-band using waveguide technology and is fabricated using a stereolithography apparatus 3D printing together with metal plating. The device is designed to have a centre frequency of 32 GHz and a bandwidth of 1 GHz. The measured result shows good agreement with simulations, with a measured average insertion loss of 0.84 dB and a return loss better than 15 dB across the passband.
25 citations
TL;DR: FPGA implementation results show that the overhead and the helper data length of the authors proposed key generator are significantly lower than that of the state-of-the-art schemes when generating a 128-bit key with a bit error rate of 10−9.
Abstract: This Letter proposes a reliable and lightweight key generator based on a novel bit-self-test arbiter physically unclonable function (BST-APUF). The BST-APUF adds a delay detection circuit into a classical APUF to automatically test the delay deviation that produces each bit of the PUF response and generates a reliability-flag for each response to indicate its reliability. The key generator collects robust responses and produces a secure key using a cryptographic entropy accumulator. FPGA implementation results show that the overhead and the helper data length of the authors proposed key generator are significantly lower than that of the state-of-the-art schemes when generating a 128-bit key with a bit error rate of 10−9.
TL;DR: In this article, a recorded single channel of 6915-Gbit/s white-light visible light communication (VLC) system is reported and experimentally demonstrated by optimising the bitloading algorithm onto the direct-current optical OFDM signal and without using an optical blue filter.
Abstract: In this Letter, a recorded single channel of 6915-Gbit/s white-light visible light communication (VLC) system is reported and experimentally demonstrated By optimising the bit-loading algorithm onto the direct-current optical OFDM signal and without using an optical blue filter, the high data rate can be achieved After a free-space propagation distance of 15 m, the white-light beam diameter of 14 cm and illuminance of 795 lux are measured The proposed white-light VLC system can provide both lighting and communication simultaneously with functional propagation distance
TL;DR: The Dop-NET is a database of radar micro- doppler signatures that are shareable and distributed with the purpose of improving micro-Doppler classification techniques.
Abstract: Radar sensors have a new growing application area of dynamic hand gesture recognition. Traditionally radar systems are considered to be very large, complex and focused on detecting targets at long ranges. With modern electronics and signal processing it is now possible to create small compact RF sensors that can sense subtle movements over short ranges. For such applications, access to comprehensive databases of signatures is critical to enable the effective training of classification algorithms and to provide a common baseline for benchmarking purposes. This Letter introduces the Dop-NET radar micro-Doppler database and data challenge to the radar and machine learning communities. Dop-NET is a database of radar micro-Doppler signatures that are shareable and distributed with the purpose of improving micro-Doppler classification techniques. A continuous wave 24 GHz radar module is used to capture the first contributions to the Dop-NET database and classification results based on discriminating these hand gestures as shown.
TL;DR: The promising performance of the proposed structure, which is beyond the state of art hybrid and frequency-domain tags, shows the potential ofThe proposed designs for identification and authentication applications.
Abstract: Moving towards commercialisation of chipless RFID systems, there are still some pressing issues. In the tag design level, the issues are high data capacity in the order of tens of bits, compact design and the immunity to the interference which can be achieved by a cross-polar response. It is demanded to yield the highest numbers of bits in a tag ID while the occupied physical space and allocated bandwidth are minimised. Increasing the number of resonators in a conventional multi-resonator chipless tag causes a significant tag size growth. The destructive coupling effect between resonators in multi-resonator tags is another critical issue. In this Letter, to combat those issues, a multi-band resonator is proposed. The comb-shaped tags contain both co-polar and cross-polar Radar cross section (RCS) responses, hence they can be used in high reflective environments. Two samples of 14-bit and 40-bit comb-shaped tags are designed, which have physical sizes of 17 mm × 13 and 30 mm × 45 mm, respectively. The promising performance of the proposed structure, which is beyond the state of art hybrid and frequency-domain tags, shows the potential of the proposed designs for identification and authentication applications.
TL;DR: In this article, a 60 nm gate length graded-channel AlGaN/GaN high electron mobility transistors (HEMTs) with a record power added efficiency (PAE) of 75% at 2.1 W/mm power density at Vdd = 10 V and the PAE of 65% at 3.0 W /mm power densities at 30 GHz.
Abstract: The authors report on highly scaled 60 nm gate length graded-channel AlGaN/GaN high electron mobility transistors (HEMTs) with a record power added efficiency (PAE) of 75% at 2.1 W/mm power density at Vdd = 10 V and the PAE of 65% at 3.0 W/mm power density at 30 GHz at Vdd = 14 V. Under two-tone power measurement, the graded-channel AlGaN/GaN HEMTs demonstrated similar power performance with peak PAE >70% at 30 GHz. This novel channel design shows great promise for high-efficiency millimetre-wave (mmW) power amplifiers up to 3 W/mm RF power density operation.
TL;DR: In this paper, a circular pulse-shaped framework for OTFS was proposed to reduce the out-of-band (OoB) radiation, which is undesirable for multi-user scenarios.
Abstract: Orthogonal time-frequency space (OTFS) modulation is a recently proposed waveform for efficient data transfer in high-speed vehicular scenario. Use of rectangular pulse shape in OTFS results in high out of band (OoB) radiation, which is undesirable for multi-user scenarios. In this work, the authors present a circular pulse shaped framework for OTFS for reducing the OoB. The authors also design a low complexity transmitter for such a system. They argue in favour of orthogonal transmission for low complexity transceiver structure. The authors establish that frequency-localised circulant Dirichlet pulse is one of the possible pulses having this desirable unitary property, which can reduce OoB radiation significantly (by around 50 dB) without any loss in BER. They also show that the proposed pulse-shaped OTFS has a lower peak to average power ratio than conventional OTFS system.
TL;DR: In this article, the authors presented a computer-aided design-based automated classification strategy that uses optimised transfer learning (TL) utilising two novel paradigms known as MobileNet and Visual Geometric Group-19 (VGG-19).
Abstract: Wilson's disease (WD) is caused by the excessive accumulation of copper in the brain and liver, leading to death if not diagnosed early. WD shows its prevalence as white matter hyperintensity (WMH) in MRI scans. It is challenging and tedious to classify WD against controls when comparing visually, primarily due to subtle differences in WMH. This Letter presents a computer-aided design-based automated classification strategy that uses optimised transfer learning (TL) utilising two novel paradigms known as (i) MobileNet and (ii) the Visual Geometric Group-19 (VGG-19). Further, the authors benchmark TL systems against a machine learning (ML) paradigm. Using four-fold augmentation, VGG-19 is superior to MobileNet demonstrating accuracy and area under the curve (AUC) pairs as 95.46 ± 7.70%, 0.932 (p < 0.0001) and 86.87 ± 2.23%, 0.871 (p < 0.0001), respectively. Further, MobileNet and VGG-19 showed an improvement of 3.4 and 13.5%, respectively, when benchmarked against the ML-based soft classifier – Random Forest.
TL;DR: The proposed method shows significant performance enhancement and outclasses the standard state-of-the-art methods with 98.68% rate of accuracy and is also able to detect zero-day (unseen) attacks.
Abstract: Intrusion detection is a prevailing area of research for several years, and numerous intrusion detection systems have been proposed for industrial control systems (ICS). In recent ages, the attacks like seismic net, duqu and flame against ICS infrastructures have instigated great harm to nuclear infrastructures and precarious facilities in several nations. The authors outline an approach to detect intrusions/anomalies in ICS. A method is presented to detect intrusions in real-time and automatically. The existing techniques are normally designed for open systems and protocols, that lacks adequate generalisation and resistance to acclimate to other networks, and they have either short detection rate or tall rate of false positive. This Letter presents a network packet contents behaviour and bidirectional Gated Recurrent Units-based method to detect intrusions in a timely and efficient manner. The method has proven a robust method of classifying intrusions/anomalies in a proficient way. Through extensive evaluation on an actual huge scale dataset spawned from SCADA-based gas pipeline network, the proposed method shows significant performance enhancement and outclasses the standard state-of-the-art methods with 98.68% rate of accuracy. Moreover, it is also able to detect zero-day (unseen) attacks.
TL;DR: In this article, a novel time-order representation based on the S-transform and convolutional neural network (CNN) is proposed for the identification of human emotions, which helps in the development of affective computing, braincomputer interface, medical diagnosis system, etc.
Abstract: Emotions are the most powerful information source to study the cognition, behaviour, and medical conditions of a person. Accurate identification of emotions helps in the development of affective computing, brain–computer interface, medical diagnosis system, etc. Electroencephalogram (EEG) signals are one such source to capture and study human emotions. In this Letter, a novel time-order representation based on the S-transform and convolutional neural network (CNN) is proposed for the identification of human emotions. EEG signals are transformed into time-order representation (TOR) based on the S-transform. This TOR is given as an input to CNN to automatically extract and classify the deep features. Emotional states of happiness, fear, sadness, and relax are classified with an accuracy of 94.58%. The superiority of the method is judged by evaluating four performance parameters and comparing it with existing state-of-the-art on the same dataset.
TL;DR: In this article, a triple-mode SIW filter with high selectivity and controllable bandwidth was proposed, which can produce three finite-transmission zero (FTZ) by changing the size of a floating circular patch.
Abstract: A novel high-selective triple-mode substrate integrated waveguide (SIW) bandpass filter using higher-order resonant modes is proposed in this Letter. The new triple-mode SIW resonator is realised by the second degenerate dual modes TM
210
and one perturbed higher-order mode TM
020
in a circular SIW cavity. The resonance of TM
020
mode can be independently moved to that of dual modes TM
210
by changing the size of a floating circular patch. The proposed triple-mode SIW filter can produce three finite-transmission zeros (FTZs), which can also be controlled well by the angle between two feeding lines. For the demonstration, a triple-mode SIW filter with the centre frequency of 13.5 GHz was designed, fabricated and measured. The proposed triple-mode circular SIW filter has the merits of the high-quality factor, high selectivity and controllable bandwidth as well as FTZs.
TL;DR: In this article, the authors proposed a four-element MIMO antenna with high isolation with a tapered microstrip line fed rectangular monopole antenna arranged in orthogonal symmetric fashion on the interconnected partial ground plane.
Abstract: A compact wideband four-element multiple-input-multiple-output (MIMO) antenna with high isolation is proposed in this Letter. The proposed MIMO antenna consists of a tapered microstrip line fed rectangular monopole antenna arranged in orthogonal symmetric fashion on the interconnected partial ground plane. The overall size of the proposed antenna is 35 × 35 × 0.8 mm
3
with 9.5 mm edge-to-edge separation between a pair of radiating elements. The proposed MIMO antenna has a -10 dB fractional impedance bandwidth of 49.57% covering 4.4-7.3 GHz, encompassing sub-6 GHz 5G (4.5 GHz), WLAN (5/5.2/5.8 GHz), WiMAX (5.5 GHz), HYPERLAN/1, 2, and ISM bands (5.2/5.8 GHz) applications. The proposed MIMO antenna has a minimum isolation value of 21 dB, maximum envelope correlation coefficient (ECC) value of 0.014 between antenna elements throughout the band. The measured results are found in good agreement with the simulated S
-parameters, radiation patterns, ECC, total active reflection coefficient, and channel capacity loss.
TL;DR: In this article, metal-insulator-semiconductor field effect transistors (MISFETs) with gate length of 350 nm were fabricated on hydrogen-terminated polycrystalline diamond by a self-aligned process.
Abstract: In this work, metal–insulator–semiconductor field effect transistors (MISFET) with gate length of 350 nm were fabricated on hydrogen-terminated polycrystalline diamond by a self-aligned process. Aluminium film with thickness of 2 nm was evaporated on the sample and formed self-oxidised alumina to act as the gate dielectric. The devices show good direct current and radio frequency performances with a maximum frequency of oscillation (f max) of 34 GHz and continuous-wave output power density of 650 mW/mm at 10 GHz.
TL;DR: In this article, a generic nano-power voltage and current reference topology is developed to provide reliable bias and reference signals for the analogue integrated blocks used in the Internet-of-Things applications.
Abstract: A generic nano-power voltage and current reference topology, which takes advantage of the unequal threshold voltage ( V TH ) of two MOSFETs in subthreshold region, is developed to provide reliable bias and reference signals for the analogue integrated blocks used in the Internet-of-Things applications. The new architecture is a self-powered four-transistor topology with a single temperature-insensitive resistor, generating both temperature-independent voltage and current without any operational amplifier or bias network. Instead, the resistor defines the absolute value of the current reference ( I REF ) which supplies the core devices. The circuit is designed and simulated for a target current reference of 7.50 nA in 0.18 µm CMOS process, and achieves a worst-case temperature coefficient (TC) of 59.47 ppm/°C over a temperature range from −40 to 125°C and 1.8 V voltage supply. The average voltage reference ( V REF ) is 346 mV, and the worst-case TC of different corners is 21.98 ppm/°C. The nominal current consumption is twice the I REF (15 nA) regardless of the supply and temperature, and can be scaled down by reducing the desired current reference.
TL;DR: A method for personnel recognition using deep convolutional neural networks (DCNNs) based on human micro-Doppler (m-D) signal separation, which shows that an average recognition accuracy of about 90% can be achieved for different human group sizes.
Abstract: In this Letter, the authors propose a method for personnel recognition using deep convolutional neural networks (DCNNs) based on human micro-Doppler (m-D) signal separation. In which, the m-D separation algorithm is firstly performed to separate m-D signal induced by limbs movement and Doppler signal caused by torso motion, which can highlight the difference contained limbs' m-D signatures between the same activity of different people. Afterwards, a five-layer DCNN is used to learn the necessary features directly from the separated m-D spectrogram of walking human and then implement human identification task. The method is validated on real data measured with a 5.8 GHz radar system. Experimental results show that an average recognition accuracy of about 90% can be achieved for different human group sizes.
TL;DR: In this paper, the authors present a study on linear channel estimators and their respective mean square error expressions acknowledging spatially correlated channels and pilot contamination, and investigate the impact of imperfect channel covariance matrix knowledge.
Abstract: In this letter, we present a study on linear channel estimators and their respective mean square error (MSE) expressions acknowledging spatially correlated channels and pilot contamination. We also investigate the impact of imperfect channel covariance matrix knowledge.
TL;DR: A novel deep-learning-based method for semantic segmentation of RGB and thermal images is introduced that employs a novel neural network design for multi-modal fusion based on multi-resolution patch processing.
Abstract: A novel deep-learning-based method for semantic segmentation of RGB and thermal images is introduced The proposed method employs a novel neural network design for multi-modal fusion based on multi-resolution patch processing A novel decoder module is introduced to fuse the RGB and thermal features extracted by separate encoder streams Experimental results on synthetic and real-world data demonstrate the efficiency of the proposed method compared with state-of-the-art methods
TL;DR: In this paper, a hybrid feature selection method based on a multi-attribute decision-making method PROMETHEE (preference ranking organization method for enrichment evaluations) and Jaya optimisation algorithm is proposed.
Abstract: Biomedical data are being collected for fields like cancer diagnosis and prognosis, brain signals, speech signals, genetic engineering to name a few. These data are very high dimensional these days, which makes it difficult to extract knowledge out of it through machine learning algorithms. In this work, the authors proposed a hybrid feature selection method based on a multi-attribute decision-making method PROMETHEE (preference ranking organisation method for enrichment evaluations) and Jaya optimisation algorithm. Their proposed method works in two phases. In the first phase, five filter methods are applied to get the ranking for each feature of the data set. In the second phase, all the five individual ranks are used as input choices for PROMETHEE which gives us a final rank for all the features. Then the top 3% features are selected for training the machine learning model. This technique is applicable for feature reduction in any high-dimensional biomedical data. Here, they have studied Parkinson's disease data set. The result shows that the proposed method improves the classification accuracy by 13.73% and that too in a minimum amount of time with a minimum number of features. Hence, this method can be used as an essential pre-processing step for high-dimensional biomedical data.
TL;DR: In this article, the authors presented a mental task classification model based on the notion of transfer learning that addressed the issue of data scarcity, model selection and misclassification ratio, in which the proposed model uses pre-trained network for the extraction of diverse feature and classify using support vector machine.
Abstract: Electroencephalogram (EEG) measures brainwaves that have been the widely used modality for brain–computer interface (BCI) applications. EEG signal with machine learning has gained substantial success in the BCI. However, the availability of limited training data, appropriate model selection and high false-positive rates are the challenges that need immediate attention. Therefore, in this Letter, the authors present a mental task classification model based on the notion of transfer learning that addresses the issue of data scarcity, model selection and misclassification ratio. In the framework, the proposed model uses pre-trained network for the extraction of diverse feature and classify using support vector machine. The authors employed four pre-trained networks to identify the optimal network for the proposed framework: Vgg16, Vgg19, Resnet18 and Resnet50. The highest classification accuracy of 86.85% (using Resnet50) was achieved using transfer learning. Comparison results showed that convolutional neural network-based approach outperformed conventional machine learning approaches and hence it can be concluded that the EEG-based classification of the mental task using transfer learning model could be used in developing a superior model despite the limited data availability.
TL;DR: In this article, a compact dual-band bandpass filter (BPF) based on parallel coupled lines and shorted stubs has been presented and the transmission and reflection coefficients were straightforwardly derived via the input impedances using odd-and even-mode analysis methods.
Abstract: A compact dual-band bandpass filter (BPF) based on parallel coupled lines and shorted stubs has been presented in this Letter. The transmission and reflection coefficients of the proposed dual-band BPF are straightforwardly derived via the input impedances using odd- and even-mode analysis methods. Four transmission poles in the two passbands and nine deep transmission zeros (TZs) in the stopband can be realised. The centre frequencies and bandwidths of the two passbands can be tuned by controlling the impedance parameters of the coupled lines and shorted stubs. For demonstration, a prototype example of this dual-band BPF with a small size is experimentally characterised. The measured results show that it has high-frequency selectivity with multiple TZs at the stopband.