Discrete Fourier Transform (DFT) based beam-formers provide N beams with a uniform linear array having N antennas. Despite low-complexity, DFT beamformers cannot generate deep nulls at arbitrary directions of arrivals (DOAs) in the beam pattern to attenuate interferences. On the other hand, data-dependent adaptive beamformers can achieve deep nulls at arbitrary DOAs, however, at higher complexity due to an inversion of a matrix in deriving optimum weights. In this paper, we propose a combined approximate DFT (ADFT) and adaptive beamformer for a uniform linear array consisting of P subarrays, each consisting of M antennas. Here, we first employ P ADFT beamformers to process signals received by subarrays, and the P outputs of these subarrays are then processed by an adaptive beamformer. Simulation results confirm that the proposed beamformer provides the benefits of both DFT and adaptive beamformers. Furthermore, we present preliminary results of an experimental antenna array operating at 5.75 GHz, where a Howells-Applebaum beamformer is employed as the adaptive beamformer.

The combined use of algorithms for approximate discrete cosine transform (DCT) with approximate computing is examined toward area-efficient field programmable gate array (FPGA) hardware architectures. The performance of previously reported, multiplierless approximate DCT transforms are explored in the presence of non-exact hardware adders which provide better utilisation of FPGA resources in terms of look-up-tables (LUTs). In the context of 2D image compression, provided examples are demonstrating a 20% LUT reduction in FPGA utilization compared to accurate adders, with a corresponding image quality degradation of 0.6 dB in terms of PSNR. The potential benefit of such area-efficient FPGA hardware designs is explored on 3D (video compression), 4D (static light field compression), and 5D (light field video compression) cases where significant FPGA resource savings are obtained at the cost of marginal degradation of output quality.

Machine-learning-assisted cancer subtyping is a promising avenue in digital pathology. Cancer subtyping models however require careful training using expert annotations, so that they can be inferred with a degree of known certainty (or uncertainty). To this end, we introduce the concept of uncertainty awareness into a self-supervised contrastive learning model. This is achieved by computing an evidence vector at every epoch, which assesses the model's confidence in its predictions. The derived uncertainty score is then utilized as a metric to selectively label the most crucial images that require further annotation, thus iteratively refining the training process. With just 1-10% of strategically selected annotations, we attain state-of-the-art performance in cancer subtyping on benchmark datasets. Our method not only strategically guides the annotation process to minimize the need for extensive labeled datasets, but also improve the precision and efficiency of classifications. This development is particularly beneficial in settings where the availability of labeled data is limited, offering a promising direction for future research and application in digital pathology. Our code is available at https://github.com/Nirhoshan/AI-for-histopathology

We propose a minimax design method for multi-dimensional (M-D) interpolated finite-support impulse response (IFIR) filters. As a result of the cascade structure of an MD IFIR filter, the optimization problem of the minimax design is nonconvex. In order to solve this nonconvex optimization problem, we employ a convex-concave procedure, where each iteration solves a convex constrained optimization problem. We present experimental results to confirm the effectiveness and the superior performance of the proposed method compared to previously proposed minimax designs of M-D IFIR filters. Furthermore, we present an implementation of M-D IFIR filter on the Xilinx Kintex UltraScale KCU105 field-programmable gate array, where a quantization error of −60.59 dB is achieved with the coefficient word length of 24 bits.

Chromatic derivatives (CDs) and associated chromatic approximations (CAs) provide a numerically robust and powerful framework for digital processing of continuous-time/space signals, using not only the discrete signal amplitudes, but also higher order derivatives. Acquisition of CDs has so far been limited to software implementations. This paper presents field-programmable gate array (FPGA)-based digital hardware architectures suitable for the real-time acquisition of CDs, thus enabling CDs to be used for practical signal processing algorithm development in embedded systems. With 24 bits of fixed-point precision, the proposed hardware architectures provide approximate 116 dB accuracy in the frequency responses of FIR filters capturing the CDs, and 76.85 dB and 75.09 dB accuracy in signal reconstruction with synthetic and real audio signals using CDs up to order 28 degrees. The designs have been verified on an AMD Kintex UltraScale KCU105 FGPA device using bit-true cycle-accurate hardware co-simulation.

The neonatal period is the most vulnerable time for the development of seizures. Seizures in the immature brain lead to detrimental consequences, therefore require early diagnosis. The gold -standard for neonatal seizure detection currently relies on continuous video-EEG monitoring; which involves recording multi-channel electroencephalogram (EEG) alongside real-time video monitoring within a neonatal intensive care unit (NICU). However, video-EEG monitoring technology requires clinical expertise and is often limited to technologically advanced and resourceful settings. Cost-effective new techniques could help the medical fraternity make an accurate diagnosis and advocate treatment without delay. In this work, a novel explainable deep learning model to automate the neonatal seizure detection process with a reduced EEG montage is proposed, which employs convolutional nets, graph attention layers, and fully connected layers. Beyond its ability to detect seizures in real time with a reduced montage, this model offers the unique advantage of real-time interpretability. By evaluating the performance on the Zenodo dataset with 10-fold cross-validation, the presented model achieves an absolute improvement of 8.31% and 42.86% in area under curve (AUC) and recall, respectively.

Sleep plays a crucial role in the well-being of human lives. Traditional sleep studies using Polysomnography are associated with discomfort and often lower sleep quality caused by the acquisition setup. Previous works have focused on developing less obtrusive methods to conduct high-quality sleep studies, and ear- EEG is among popular alternatives. However, the performance of sleep staging based on ear-EEG is still inferior to scalp- EEG based sleep staging. In order to address the performance gap between scalp-EEG and ear- EEG based sleep staging, we propose a cross-modal knowledge distillation strategy1†https://github.com/Mithunjha/EarEEG_KnowledgeDistillation, which is a domain adaptation approach. We employ model architectures from the transformer and convolutional neural network families to demonstrate the model-agnostic nature of the method. Our experiments and analysis validate the effectiveness of the proposed approach with existing architectures, where it enhances the accuracy of the ear-EEG based sleep staging by 3.46% and Cohen's kappa coefficient by a margin of 0.038. Furthermore, our findings indicate that our approach is not limited to a specific model architecture and can be applied to a wide range of deep learning models.

Human behavioral monitoring during sleep is essential for various medical applications. Majority of the contactless human pose estimation algorithms are based on RGB modality, causing ineffectiveness in in-bed pose estimation due to occlusions by blankets and varying illumination conditions. Long-wavelength infrared (LWIR) modality based pose estimation algorithms overcome the aforementioned challenges; however, ground truth pose generations by a human annotator under such conditions are not feasible. A feasible solution to address this issue is to transfer the knowledge learned from images with pose labels and no occlusions, and adapt it towards real world conditions (occlusions due to blankets). In this paper, we propose a novel learning strategy comprises of two-fold data augmentation to reduce the cross-domain discrepancy and knowledge distillation to learn the distribution of unlabeled images in real world conditions. Our experiments and analysis show the effectiveness of our approach over multiple standard human pose estimation baselines1.

We propose a weighted least-square (WLS) method to design autoregressive moving average (ARMA) graph filters. We first express the WLS design problem as a numerically-stable optimization problem using Chebyshev polynomial bases. We then formulate the optimization problem with a non-convex objective function and linear constraints for stability. We employ a relaxation technique and convert the non-convex optimization problem into an iterative second-order cone programming problem. Experimental results confirm that ARMA graph filters designed using the proposed WLS method have significantly improved frequency responses compared to those designed using previously proposed WLS design methods.

Two-dimensional (2-D) infinite-extent impulse response (IIR) filter design is a challenging problem due to the difficulty in verifying stability. optimization methods proposed so far predominantly consider the design of 2-D IIR filters having quadrantally-symmetric frequency responses, where the transfer functions have separable denominators. In this paper, we propose a weighted least-squares (WLS) design method for 2-D IIR filters having arbitrary frequency response and stable in the practical bounded-input bounded-output (P-BIBO) sense. Our design considers transfer functions with nonseparable numerators and denominators having complex-and real-valued coefficients, respectively. We formulate the WLS design as an iterative second-order cone programming problem, which includes constraints to guarantee the P-BIBO stability. Design examples confirm that the proposed WLS method leads to P-BIBO stable 2-D IIR filters.

Mostly-online teaching experiences in circuits and systems (CAS) during 2020-2021 COVID-19 pandemic are presented. Three case studies are shared summarizing course details, tools and platforms, best practices and limitations across three universities representing different continents. The presented approaches attempt to address several limitations of passive online delivery of CAS courses via interactive simulations, formative assessments via interactive web content and slide-embedded polls, at-home labs with student acquired hardware and instructor-lead and student-centered activity based learning.

Three-dimensional space-time velocity filters may be used to enhance dynamic passband objects of interest in videos while attenuating moving interfering objects based on their velocities. In this paper, we show that the attenuation of interfering stopband objects may be significantly improved using recently proposed shifted-velocity filters. It is shown that an improvement of approximately 20 dB in signal-to-interference ratio may be achieved for stopband to passband velocity differences of only 1 pixels/frame. More importantly, this improvement is achieved without increasing the computational complexity.

Diagnosing pre-existing heart diseases early in life is important as it helps prevent complications such as pulmonary hypertension, heart rhythm problems, blood clots, heart failure and sudden cardiac arrest. To identify such diseases, phonocardiogram (PCG) and electrocardiogram (ECG) waveforms convey important information. Therefore, effectively using these two modalities of data has the potential to improve the disease screening process. We evaluate this hypothesis on a subset of the PhysioNet Challenge 2016 Dataset which contains simultaneously acquired PCG and ECG recordings. Our novel dual-convolutional neural network based approach uses transfer learning to tackle the problem of having limited amounts of simultaneous PCG and ECG data that is publicly available, while having the potential to adapt to larger datasets. In addition, we introduce two main evaluation frameworks named record-wise and sample-wise evaluation which leads to a rich performance evaluation for the transfer learning approach. Comparisons with methods which used single or dual modality data show that our method can lead to better performance. Furthermore, our results show that individually collected ECG or PCG waveforms are able to provide transferable features which could effectively help to make use of a limited number of synchronized PCG and ECG waveforms and still achieve significant classification performance.

We propose a weighted least-squares (WLS) design method for multi-dimensional (M-D) complex-coefficient finite- extent impulse response (FIR) filters. We consider the general form of M-D FIR filters having arbitrary frequency responses and low group delays. We formulate the proposed WLS design as a second-order cone programming problem. Design examples confirm that the proposed method provides the state-of-the-art M-D FIR filter designs with almost constant group delay.

Geometric information of scenes available with four-dimensional (4-D) light fields (LFs) paves the way for post-capture refocusing. Light field refocusing methods proposed so far have been limited to a single planar or a volumetric region of a scene. In this letter, we demonstrate simultaneous refocusing of multiple volumetric regions in LFs. To this end, we employ a 4-D sparse finite-extent impulse response (FIR) filter consisting of multiple hyperfan-shaped passbands. We design the 4-D sparse FIR filter as an optimal filter in the least-squares sense. Experimental results confirm that the proposed filter provides 63% average reduction in computational complexity with negligible degradation in the fidelity of multi-volumetric refocused LFs compared to a 4-D nonsparse FIR filter.

A minimax design for 2-D complex-coefficient FIR filters having asymmetric frequency responses is proposed in this paper. We consider the general form of 2-D FIR filters with low group delay and formulate the minimax design as a semidefinite programming problem. The 2-D linear-phase FIR filters with conjugate-symmetric coefficients are a special case of the proposed design. Example filter designs having near-equiripple magnitude responses are presented to verify the effectiveness of the proposed design method.

A low-complexity codec and a hardware architecture are proposed for achieving real-time compression of four-dimensional (4-D) light field (LF) signals captured from camera/lenslet arrays. The proposed system employs the 4-D extension of the two-dimensional (2-D) 8×8 approximate discrete cosine transform (ADCT) that has recently appeared in the literature. Motivated by the partial separability of the multidimensional spectrum of LFs, the proposed 4-D ADCT is obtained by cascading 2-D inter-view and 2-D intra-view transform stages. Software simulations are provided to confirm the performance of the 4-D ADCT based compression and comparisons are made with respect to 2-D inter-view only and 2-D intra-view only ADCT-based compression. Proposed digital architectures are validated using stepped hardware co-simulation on a Xilinx Virtex-7 VC-707 FPGA platform verifying 597 MHz maximum possible clock frequency, implying an ideal throughput of 18×103LFs/sec for performing 4-D ADCT on (8× 8×432×624×3) size LFs. When 10% of the ADCT coefficients per each (8×8×8×8) hypercube are retained sub aperture images show 38 dB average PSNR and 0.95 average SSIM.

A multi-port spatio-temporal noise-shaping ADC is proposed to process plane waves received by spatially-oversampled antenna arrays. In the proposed multi-port ADC, the desired plane waves are processed with a spatial low-pass frequency response whereas the noise and distortion are shaped with a spatial high-pass frequency response. By employing a first-order Butterworth filter, approximately circular passbands and stopbands are achieved for the signal and the noise transfer functions, respectively. The proposed noise-shaping system is designed in the TSMC 180 nm CMOS process, with ADCs and DACs modeled as noise sources. Circuit simulation results show that the proposed system can achieve a bandwidth of 50 MHz.

A combined approach of low-complexity light field depth filtering and deep learning is proposed for object classification in the presence of partial occlusions. The proposed approach exploits depth information embedded in multi-perspective four-dimensional (4-D) light fields via low-complexity 4-D sparse depth filtering and deep-learning. The proposed 4-D depth filter, designed using numerical optimization techniques by formulating as an ℓ1- ℓ∞minimization problem, is shown to outperform typical light field refocusing based on 4-D shift-sum averaging filters. Experiments conducted using a light field dataset acquired by a Lytro camera verify 45% and 27% better performance in terms of object classification accuracy compared to the cases when no depth filtering is employed and standard shift-sum refocusing is employed, respectively.

A low-complexity wideband transmit beamformer is proposed using a digitally-fed uniform linear array of broadband Vivaldi antennas operating in the S-band. The proposed transmit beamformer employs a novel DSP feeding network based on a transmit-mode 2-D sparse finite-extent impulse response (FIR) filter having a planar passband in the 2-D frequency-wavenumber space. Electronic beam steering is achieved by changing the filter coefficients defined in closed-form and hard-thresholding (HT) is employed to obtain a sparse 2-D impulse responses of the filter. Full-wave electromagnetic simulations are used to obtain the far-field beam patterns produced by the 2-D sparse FIR filter in the frequency range 2-2.8 GHz for wideband signals with 33% fractional bandwidth. Computational complexity, beam directionality and side-lobe performance are investigated with varying HT along with quantitative comparisons with an equally selective wideband frequency-domain phased array.

Application of depth-selective filtering to modulated-sparse light fields towards reducing the DSP and memory complexities in real-time light field processing is investigated. A modulated-sparse light field is obtained by spatially windowing an original 4-D light-field signal, which is subsequently processed by 4-D depth-selective filters to achieve planar focus and occlusion suppression. Multidimensional spectral properties of modulated-sparse light fields are explored and demonstrative examples with real light fields are provided to show that almost similar depth filtering and occlusion suppression performance can be achieved by processing such modulated-sparse light fields, leading to significant reduction in DSP hardware and memory complexities.

Human gait analysis, the study of human locomotion, is possible with low-cost RGBD sensors such as the Kinect sensor. However, due to the inherent depth sensing accuracy limitations of these sensors as the distance from the sensor increases, the distance range of gait analysis too becomes small and inefficient for clinical use. We present a system that uses two independent Kinects in a data fusion framework that increases the distance range of gait analysis from 2.5 m to 4 m with three gait cycles. Our gait parameters are reasonably accurate and comparable with existing systems with 4% error in length measurements and 5° error in flexion measurements. The system is extensible to have several Kinects.

Light field signal processing allows manipulation of a rich set of information captured from a scene to achieve real-time depth filtering and occlusion suppression. Low-complexity four-dimensional infinite impulse response digital filters for simultaneous depth filtering and occlusion suppression over multiple depths in light fields are proposed. A low-complexity two-dimensional separable approach is employed to design the proposed filters having multiple frequency-planar pass-bands/stopbands in the four-dimensional spatial frequency domain, that can be electronically tuned to enhance/reject planar objects at multiple depths in a light field. Filter synthesis details are provided with specific design examples corresponding to 2-passband and 1-stopband cases. Numerically generated and Lytro camera captured light fields are used to verify the effectiveness of the proposed multi-depth-pass and multi-depth-reject filters. For synthetic light field inputs these filters confirm an average denoising, depth filtering and occlusion suppression performance of 20 dB, 20 dB, and 30 dB, respectively.

There are several systems that use one or several Kinect sensors for human gait analysis, particularly for diagnosis of patients. However, due to the limited depth sensing range of the Kinect—a sensor manufactured for video gaming—the depth measurement accuracy reduces with distance from the Kinect. In addition, self-occlusion of the subject limits the accuracy and utility of such systems. We overcome these limitations by using a two-Kinect gait analysis system and mechanically moving the Kinects in synchronization with the test subject and each other. This increases the practical measurement range of the Kinect-based system whilst maintaining the measurement accuracy. Results of the comparison of knee flexion, step length, and stride length with a software based method show that our moving Kinect system can accurately analyse these gait parameters.

A 5-D IIR depth-velocity filter is proposed for enhancing objects moving on linear trajectories, with constant velocity and at constant depth, in light field videos (also known as plenoptic videos). The passband of the proposed filter is a plane in the 5-D frequency domain and is realized by cascading three first-order 5-D IIR filters having 4-D hyperplanar passbands of appropriate orientations. Numerical simulation results are presented to confirm the performance of the proposed filter.

A low-complexity 3D FIR filter is proposed for selectively enhancing severely corrupted linear trajectory spatio-temporal signals. The proposed 3D FIR filter is separable and consists of a 3D spatio-temporal wide-angle FIR cone filter between two 2D spatial variable-shift filters. Low complexity of the 3D spatio-temporal wide-angle FIR cone filter is achieved by exploiting the spatial-symmetry of the passband and by employing maximal decimation in the temporal dimension. Compared to existing techniques, the proposed 3D FIR filter provides significant reduction of the computational complexity for similar SINR improvement.