Abstract:Early detection and accurate diagnosis can predict the risk of malignant disease transformation, thereby increasing the probability of effective treatment. A mild syndrome with small infected regions is an ominous warning and is foremost in the early diagnosis of diseases. Deep learning algorithms, such as convolutional neural networks (CNNs), have been used to segment natural or medical objects, showing promising results. However, analyzing medical objects of small areas in images remains a challenge due to information losses and compression defects caused by convolution and pooling operations in CNNs. These losses and defects become increasingly significant as the network deepens, particularly for small medical objects. To address these challenges, we propose a novel scale-variant attention-based network (SvANet) for accurate small-scale object segmentation in medical images. The SvANet consists of Monte Carlo attention, scale-variant attention, and vision transformer, which incorporates cross-scale features and alleviates compression artifacts for enhancing the discrimination of small medical objects. Quantitative experimental results demonstrate the superior performance of SvANet, achieving 96.12%, 96.11%, 89.79%, 84.15%, 80.25%, 73.05%, and 72.58% in mean Dice coefficient for segmenting kidney tumors, skin lesions, hepatic tumors, polyps, surgical excision cells, retinal vasculatures, and sperms, which occupy less than 1% of the image areas in KiTS23, ISIC 2018, ATLAS, PolypGen, TissueNet, FIVES, and SpermHealth datasets, respectively.
Abstract:Objective: Cortico-muscular communication patterns are instrumental in understanding movement control. Estimating significant causal relationships between motor cortex electroencephalogram (EEG) and surface electromyogram (sEMG) from concurrently active muscles presents a formidable challenge since the relevant processes underlying muscle control are typically weak in comparison to measurement noise and background activities. Methodology: In this paper, a novel framework is proposed to simultaneously estimate the order of the autoregressive model of cortico-muscular interactions along with the parameters while enforcing stationarity condition in a convex program to ensure global optimality. The proposed method is further extended to a non-convex program to account for the presence of measurement noise in the recorded signals by introducing a wavelet sparsity assumption on the excitation noise in the model. Results: The proposed methodology is validated using both simulated data and neurophysiological signals. In case of simulated data, the performance of the proposed methods has been compared with the benchmark approaches in terms of order identification, computational efficiency, and goodness of fit in relation to various noise levels. In case of physiological signals our proposed methods are compared against the state-of-the-art approaches in terms of the ability to detect Granger causality. Significance: The proposed methods are shown to be effective in handling stationarity and measurement noise assumptions, revealing significant causal interactions from brain to muscles and vice versa.
Abstract:Class-incremental learning (CIL) aims to train a model to learn new classes from non-stationary data streams without forgetting old ones. In this paper, we propose a new kind of connectionist model by tailoring neural unit dynamics that adapt the behavior of neural networks for CIL. In each training session, it introduces a supervisory mechanism to guide network expansion whose growth size is compactly commensurate with the intrinsic complexity of a newly arriving task. This constructs a near-minimal network while allowing the model to expand its capacity when cannot sufficiently hold new classes. At inference time, it automatically reactivates the required neural units to retrieve knowledge and leaves the remaining inactivated to prevent interference. We name our model AutoActivator, which is effective and scalable. To gain insights into the neural unit dynamics, we theoretically analyze the model's convergence property via a universal approximation theorem on learning sequential mappings, which is under-explored in the CIL community. Experiments show that our method achieves strong CIL performance in rehearsal-free and minimal-expansion settings with different backbones.
Abstract:This paper presents a new approach to the recovery of a spectrally sparse signal (SSS) from partially observed entries, focusing on challenges posed by large-scale data and heavy noise environments. The SSS reconstruction can be formulated as a non-convex low-rank Hankel recovery problem. Traditional formulations for SSS recovery often suffer from reconstruction inaccuracies due to unequally weighted norms and over-relaxation of the Hankel structure in noisy conditions. Moreover, a critical limitation of standard proximal gradient (PG) methods for solving the optimization problem is their slow convergence. We overcome this by introducing a more accurate formulation and a Low-rank Projected Proximal Gradient (LPPG) method, designed to efficiently converge to stationary points through a two-step process. The first step involves a modified PG approach, allowing for a constant step size independent of signal size, which significantly accelerates the gradient descent phase. The second step employs a subspace projection strategy, optimizing within a low-rank matrix space to further decrease the objective function. Both steps of the LPPG method are meticulously tailored to exploit the intrinsic low-rank and Hankel structures of the problem, thereby enhancing computational efficiency. Our numerical simulations reveal a substantial improvement in both the efficiency and recovery accuracy of the LPPG method compared to existing benchmark algorithms. This performance gain is particularly pronounced in scenarios with significant noise, demonstrating the method's robustness and applicability to large-scale SSS recovery tasks.
Abstract:We consider minimizing a function consisting of a quadratic term and a proximable term which is possibly nonconvex and nonsmooth. This problem is also known as scaled proximal operator. Despite its simple form, existing methods suffer from slow convergence or high implementation complexity or both. To overcome these limitations, we develop a fast and user-friendly second-order proximal algorithm. Key innovation involves building and solving a series of opportunistically majorized problems along a hybrid Newton direction. The approach directly uses the precise Hessian of the quadratic term, and calculates the inverse only once, eliminating the iterative numerical approximation of the Hessian, a common practice in quasi-Newton methods. The algorithm's convergence to a critical point is established, and local convergence rate is derived based on the Kurdyka-Lojasiewicz property of the objective function. Numerical comparisons are conducted on well-known optimization problems. The results demonstrate that the proposed algorithm not only achieves a faster convergence but also tends to converge to a better local optimum compare to benchmark algorithms.
Abstract:This paper investigates signal estimation in wireless transmission from the perspective of statistical machine learning, where the transmitted signals may be from an integrated sensing and communication system; that is, 1) signals may be not only discrete constellation points but also arbitrary complex values; 2) signals may be spatially correlated. Particular attention is paid to handling various uncertainties such as the uncertainty of the transmitting signal covariance, the uncertainty of the channel matrix, the uncertainty of the channel noise covariance, the existence of channel impulse noises (i.e., outliers), and the limited sample size of pilots. To proceed, a distributionally robust machine learning framework that is insensitive to the above uncertainties is proposed for beamforming (at the receiver) and estimation of wireless signals, which reveals that channel estimation is not a necessary operation. For optimal linear estimation, the proposed framework includes several existing beamformers as special cases such as diagonal loading and eigenvalue thresholding. For optimal nonlinear estimation, estimators are limited in reproducing kernel Hilbert spaces and neural network function spaces, and corresponding uncertainty-aware solutions (e.g., kernelized diagonal loading) are derived. In addition, we prove that the ridge and kernel ridge regression methods in machine learning are distributionally robust against diagonal perturbation in feature covariance.
Abstract:Data-driven soft sensors provide a potentially cost-effective and more accurate modeling approach to measure difficult-to-measure indices in industrial processes compared to mechanistic approaches. Artificial intelligence (AI) techniques, such as deep learning, have become a popular soft sensors modeling approach in the area of machine learning and big data. However, soft sensors models based deep learning potentially lead to complex model structures and excessive training time. In addition, industrial processes often rely on distributed control systems (DCS) characterized by resource constraints. Herein, guided by spatial geometric, a lightweight geometric constructive neural network, namely LightGCNet, is proposed, which utilizes compact angle constraint to assign the hidden parameters from dynamic intervals. At the same time, a node pool strategy and spatial geometric relationships are used to visualize and optimize the process of assigning hidden parameters, enhancing interpretability. In addition, the universal approximation property of LightGCNet is proved by spatial geometric analysis. Two versions algorithmic implementations of LightGCNet are presented in this article. Simulation results concerning both benchmark datasets and the ore grinding process indicate remarkable merits of LightGCNet in terms of small network size, fast learning speed, and sound generalization.
Abstract:In the context of deep learning research, where model introductions continually occur, the need for effective and efficient evaluation remains paramount. Existing methods often emphasize accuracy metrics, overlooking stability. To address this, the paper introduces the Accuracy-Stability Index (ASI), a quantitative measure incorporating both accuracy and stability for assessing deep learning models. Experimental results demonstrate the application of ASI, and a 3D surface model is presented for visualizing ASI, mean accuracy, and coefficient of variation. This paper addresses the important issue of quantitative benchmarking metrics for deep learning models, providing a new approach for accurately evaluating accuracy and stability of deep learning models. The paper concludes with discussions on potential weaknesses and outlines future research directions.
Abstract:Integrated sensing and communication (ISAC), which enables hardware, resources (e.g., spectra), and waveforms sharing, is becoming a key feature in future-generation communication systems. This paper investigates robust waveform design for ISAC systems when the underlying true communication channels (e.g. time-selective ones) are not accurately known. With uncertainties in nominal communication channel models, the nominally-estimated communication performance may be not achievable in practice; i.e., the communication performance of ISAC systems cannot be guaranteed. Therefore, we formulate robust waveform design problems by studying the worst-case channels and prove that the robustly-estimated performance is guaranteed to be attainable in real-world operation. As a consequence, the reliability of ISAC systems in terms of communication performance is improved. The robust waveform design problems are shown to be non-convex, non-differentiable, and high-dimensional, which cannot be solved using existing optimization techniques. Therefore, we develop a computationally-efficient and globally-optimal algorithm to solve them. Simulation results show that the robustly-estimated communication performance can be ensured to be practically reachable while the nominally-estimated performance cannot, which validates the value of robust design.
Abstract:As aliasing artefacts are highly structural and non-local, many MRI reconstruction networks use pooling to enlarge filter coverage and incorporate global context. However, this inadvertently impedes fine detail recovery as downsampling creates a resolution bottleneck. Moreover, real and imaginary features are commonly split into separate channels, discarding phase information particularly important to high frequency textures. In this work, we introduce an efficient multi-scale reconstruction network using dilated convolutions to preserve resolution and experiment with a complex-valued version using complex convolutions. Inspired by parallel dilated filters, multiple receptive fields are processed simultaneously with branches that see both large structural artefacts and fine local features. We also adopt dense residual connections for feature aggregation to efficiently increase scale and the deep cascade global architecture to reduce overfitting. The real-valued version of this model outperformed common reconstruction architectures as well as a state-of-the-art multi-scale network whilst being three times more efficient. The complex-valued network yielded better qualitative results when more phase information was present.