Noisy Information Research Articles

DynaSTI: Dynamics modeling with sequential temporal information for reinforcement learning in Atari

Deep reinforcement learning (DRL) has shown remarkable capabilities in solving sequential decision-making problems. However, DRL requires extensive interactions with image-based environments. Existing methods have combined self-supervised learning or data augmentation to improve sample efficiency. While understanding the temporal information dynamics of the environment is important for effective learning, many methods do not consider these factors. To address the sample efficiency problem, we propose dynamics modeling with sequential temporal information (DynaSTI) that incorporates environmental dynamics and leverages the correlation among trajectories to improve sample efficiency. DynaSTI uses an effective learning strategy for state representation as an auxiliary task, using gated recurrent units to capture temporal information. It also integrates forward and inverse dynamics modeling in a hierarchical configuration, enhancing the learning of environmental dynamics compared to using each model separately. The hierarchical structure of DynaSTI enhances the stability of inverse dynamics modeling during training by using inputs derived from forward dynamics modeling, which focuses on feature extraction related to controllable state. This approach effectively filters out noisy information. Consequently, using denoised inputs from forward dynamics modeling results in improved stability when training inverse dynamics modeling, rather than using inputs directly from the encoder. We demonstrate the effectiveness of DynaSTI through experiments on the Atari game benchmark, limiting the environment interactions to 100k steps. Our extensive experiments confirm that DynaSTI significantly improves the sample efficiency of DRL, outperforming comparison methods in terms of statistically reliable metrics and nearing human-level performance.

Threatening language detection from Urdu data with deep sequential model

The Urdu language is spoken and written on different social media platforms like Twitter, WhatsApp, Facebook, and YouTube. However, due to the lack of Urdu Language Processing (ULP) libraries, it is quite challenging to identify threats from textual and sequential data on the social media provided in Urdu. Therefore, it is required to preprocess the Urdu data as efficiently as English by creating different stemming and data cleaning libraries for Urdu data. Different lexical and machine learning-based techniques are introduced in the literature, but all of these are limited to the unavailability of online Urdu vocabulary. This research has introduced Urdu language vocabulary, including a stop words list and a stemming dictionary to preprocess Urdu data as efficiently as English. This reduced the input size of the Urdu language sentences and removed redundant and noisy information. Finally, a deep sequential model based on Long Short-Term Memory (LSTM) units is trained on the efficiently preprocessed, evaluated, and tested. Our proposed methodology resulted in good prediction performance, i.e., an accuracy of 82%, which is greater than the existing methods.

DSTAN: A Deformable Spatial-temporal Attention Network with Bidirectional Sequence Feature Refinement for Speckle Noise Removal in Thyroid Ultrasound Video.

Thyroid ultrasound video provides significant value for thyroid diseases diagnosis, but the ultrasound imaging process is often affected by the speckle noise, resulting in poor quality of the ultrasound video. Numerous video denoising methods have been proposed to remove noise while preserving texture details. However, existing methods still suffer from the following problems: (1) relevant temporal features in the low-contrast ultrasound video cannot be accurately aligned and effectively aggregated by simple optical flow or motion estimation, resulting in the artifacts and motion blur in the video; (2) fixed receptive field in spatial features integration lacks the flexibility of aggregating features in the global region of interest and is susceptible to interference from irrelevant noisy regions. In this work, we propose a deformable spatial-temporal attention denoising network to remove speckle noise in thyroid ultrasound video. The entire network follows the bidirectional feature propagation mechanism to efficiently exploit the spatial-temporal information of the whole video sequence. In this process, two modules are proposed to address the above problems: (1) a deformable temporal attention module (DTAM) is designed after optical flow pre-alignment to further capture and aggregate relevant temporal features according to the learned offsets between frames, so that inter-frame information can be better exploited even with the imprecise flow estimation under the low contrast of ultrasound video; (2) a deformable spatial attention module (DSAM) is proposed to flexibly integrate spatial features in the global region of interest through the learned intra-frame offsets, so that irrelevant noisy information can be ignored and essential information can be precisely exploited. Finally, all these refined features are rectified and merged through residual convolution blocks to recover the clean video frames. Experimental results on our thyroid ultrasound video (US-V) dataset and the DDTI dataset demonstrate that our proposed method exceeds 1.2 1.3dB on PSNR and has clearer texture detail compared to other state-of-the-art methods. In the meantime, the proposed model can also assist thyroid nodule segmentation methods to achieve more accurate segmentation effect, which provides an important basis for thyroid diagnosis. In the future, the proposed model can be improved and extended to other medical image sequence datasets, including CT and MRI slice denoising. The code and datasets are provided at https://github.com/Meta-MJ/DSTAN .

Fusing multiple interval-valued fuzzy monotonic decision trees

As a powerful knowledge mining technique for ordinal classification tasks, dominance-based rough set theory has many advantages but also some issues. Sensitivity to noisy information means that even a single mislabeled sample can lead to substantial fluctuations in the approximation calculations. Another issue is that most monotonic classifiers can only handle real-valued data and cannot directly deal with interval-valued data, which is common in practical applications. To address these issues, a tree-based fusion learning method for monotonic classification of interval-valued attributes, named FM-IFMDT, has been proposed. Its functional structure comprises three components: (i) The proposed robust β-precision interval-valued fuzzy dominance neighborhood rough set model (β-IFDNRS) can adaptively identify and filter noise samples. (ii) The interval dominance discernibility matrix based on β-IFDNRS is developed for feature selection and can generate a set of complete and diverse feature subsets. (iii) The novel interval-valued fuzzy monotonic decision tree (IFMDT) based on the probability distribution is trained on each feature subset and is used as the base classifier of the weighted voting fusion model. Extensive experiments show the proposed fusion learning method has significant advantages.

Selecting EEG channels and features using multi-objective optimization for accurate MCI detection: validation using leave-one-subject-out strategy

Effective management of dementia requires the timely detection of mild cognitive impairment (MCI). This paper introduces a multi-objective optimization approach for selecting EEG channels (and features) for the purpose of detecting MCI. Firstly, each EEG signal from each channel is decomposed into subbands using either variational mode decomposition (VMD) or discrete wavelet transform (DWT). A feature is then extracted from each subband using one of the following measures: standard deviation, interquartile range, band power, Teager energy, Katz's and Higuchi's fractal dimensions, Shannon entropy, sure entropy, or threshold entropy. Different machine learning techniques are used to classify the features of MCI cases from those of healthy controls. The classifier's performance is validated using leave-one-subject-out (LOSO) cross-validation (CV). The non-dominated sorting genetic algorithm (NSGA)-II is designed with the aim of minimizing the number of EEG channels (or features) and maximizing classification accuracy. The performance is evaluated using a publicly available online dataset containing EEGs from 19 channels recorded from 24 participants. The results demonstrate a significant improvement in performance when utilizing the NSGA-II algorithm. By selecting only a few appropriate EEG channels, the LOSO CV-based results show a significant improvement compared to using all 19 channels. Additionally, the outcomes indicate that accuracy can be further improved by selecting suitable features from different channels. For instance, by combining VMD and Teager energy, the SVM accuracy obtained using all channels is 74.24%. Interestingly, when only five channels are selected using NSGA-II, the accuracy increases to 91.56%. The accuracy is further improved to 95.28% when using only 8 features selected from 7 channels. This demonstrates that by choosing informative features or channels while excluding noisy or irrelevant information, the impact of noise is reduced, resulting in improved accuracy. These promising findings indicate that, with a limited number of channels and features, accurate diagnosis of MCI is achievable, which opens the door for its application in clinical practice.

Biological computations: Limitations of attractor-based formalisms and the need for transients

Living systems, from single cells to higher vertebrates, receive a continuous stream of non-stationary inputs that they sense, for e.g. via cell surface receptors or sensory organs. By integrating these time-varying, multi-sensory, and often noisy information with memory using complex molecular or neuronal networks, they generate a variety of responses beyond simple stimulus-response association, including avoidance behavior, life-long-learning or social interactions. In a broad sense, these processes can be understood as a type of biological computation. Taking as a basis generic features of biological computations, such as real-time responsiveness or robustness and flexibility of the computation, we highlight the limitations of the current attractor-based framework for understanding computations in biological systems. We argue that frameworks based on transient dynamics away from attractors are better suited for the description of computations performed by neuronal and signaling networks. In particular, we discuss how quasi-stable transient dynamics from ghost states that emerge at criticality have a promising potential for developing an integrated framework of computations, that can help us understand how living system actively process information and learn from their continuously changing environment.

Dictionary-Based Multi-View Learning With Privileged Information

Multi-view learning can improve classification performance by combining information between different views. Due to the similarity in different views of the dataset, sometimes the features obtained are highly limited and redundant. At the same time, different views accumulate a large amount of noisy information, which will affect the classification performance of the model. To solve these problems, we embed privileged information in the model and introduce dictionary learning, and proposed a new dictionary-based multi-view learning method with privileged information (MVDL-PI). First, two sets of dictionaries (synthetic dictionary and analysis dictionary) and sparse representation matrices of different information domains are obtained for each view information and privilege information through dictionary learning. Then, we obtain consistency information from the regularization terms of the two different sets of synthetic dictionaries and construct a LUPI (Learning using privileged information) classifier by the sparse representation. In addition, we use alternating convex optimization and Lagrange multiplier methods to optimize the model and prove its convergence. In the experiment, we did a number of experiments comparing this method with similar recent methods. The experimental results show that the MVDL-PI method is superior to other methods in terms of stability and classification accuracy.

A Heterogeneous Directed Graph Attention Network for inductive text classification using multilevel semantic embeddings

In the current study, a novel network model is proposed for text classification based on Graph Attention Networks (GATs) and sentence-transformer embeddings. Most existing methods with a pretraining model as an input layer still treat words as the minimum processing unit. However, word embedding is not an efficient and appropriate solution when dealing with long texts containing many professional words. This study aims to design a model capable of handling text classification tasks at multilevel semantic segmentation. The main contribution of this study is that a novel GAT variant is designed using global nodes and Squeeze-and-Excitation Networks (SENet) to capture semantic information. Moreover, a novel unidirectional attention mechanism is introduced for our model to avoid the message passing of irrelevant noisy information within global nodes. The numerical results show that according to the characteristics of datasets, specific semantic information combinations can effectively improve the accuracy and performance of text classification. Without fine-tuning of the pretrained encoder, the new state-of-the-art performance is achieved on three benchmark datasets. In addition, a comprehensive analysis of the graph attention mechanism in the model for specific cases suggests that the unidirectional attention mechanism and the use of global nodes are key contributing factors to multilevel semantic fusion.

Formation of recurring transient Ca2+-based intercellular communities during Drosophila hematopoiesis

Tissue development occurs through a complex interplay between many individual cells. Yet, the fundamental question of how collective tissue behavior emerges from heterogeneous and noisy information processing and transfer at the single-cell level remains unknown. Here, we reveal that tissue scale signaling regulation can arise from local gap-junction mediated cell-cell signaling through the spatiotemporal establishment of an intermediate-scale of transient multicellular communication communities over the course of tissue development. We demonstrated this intermediate scale of emergent signaling using Ca2+ signaling in the intact, ex vivo cultured, live developing Drosophila hematopoietic organ, the lymph gland. Recurrent activation of these transient signaling communities defined self-organized signaling "hotspots" that gradually formed over the course of larva development. These hotspots receive and transmit information to facilitate repetitive interactions with nonhotspot neighbors. Overall, this work bridges the scales between single-cell and emergent group behavior providing key mechanistic insight into how cells establish tissue-scale communication networks.

A Handwriting Recognition System With WiFi

Handwriting recognition systems are a convenient and alternative way of writing in the air with fingers rather than typing on keyboards. However, existing recognition systems are limited by their low accuracy and the requirement to wear dedicated devices. To address these issues, we propose WiWrite, an accurate contactless handwriting recognition system that allows users to write in the air without wearing any wearable devices. Specifically, we employ a novel <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CSI division scheme</i> to process the noisy raw WiFi channel state information (CSI), which stabilizes the CSI phase and reduces noise in CSI amplitude. To automatically retain low noise data for identification in the LOS scenario, we propose a self-paced dense convolutional network (SPDCN), which is a self-paced loss function based on a modified convolutional neural network coupled with a dense convolutional network. Furthermore, to achieve accurate handwriting recognition in the NLOS scenario, we combine ADOA and PCA algorithms to remove location-induced interference and extract action features. Comprehensive experiments show the merits of WiWrite, revealing that the recognition accuracy for the same-size input and different-size input are 93.6% and 89.0%, respectively. Moreover, WiWrite can achieve accurate recognition regardless of environment and target diversity in LOS and NLOS scenarios.

When Are Two Lists Better than One?: Benefits and Harms in Joint Decision-Making

Historically, much of machine learning research has focused on the performance of the algorithm alone, but recently more attention has been focused on optimizing joint human-algorithm performance. Here, we analyze a specific type of human-algorithm collaboration where the algorithm has access to a set of n items, and presents a subset of size k to the human, who selects a final item from among those k. This scenario could model content recommendation, route planning, or any type of labeling task. Because both the human and algorithm have imperfect, noisy information about the true ordering of items, the key question is: which value of k maximizes the probability that the best item will be ultimately selected? For k=1, performance is optimized by the algorithm acting alone, and for k=n it is optimized by the human acting alone. Surprisingly, we show that for multiple of noise models, it is optimal to set k in [2, n-1] - that is, there are strict benefits to collaborating, even when the human and algorithm have equal accuracy separately. We demonstrate this theoretically for the Mallows model and experimentally for the Random Utilities models of noisy permutations. However, we show this pattern is *reversed* when the human is anchored on the algorithm's presented ordering - the joint system always has strictly worse performance. We extend these results to the case where the human and algorithm differ in their accuracy levels, showing that there always exist regimes where a more accurate agent would strictly benefit from collaborating with a less accurate one, but these regimes are asymmetric between the human and the algorithm's accuracy.

Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective

Graph contrastive learning is a general learning paradigm excelling at capturing invariant information from diverse perturbations in graphs. Recent works focus on exploring the structural rationale from graphs, thereby increasing the discriminability of the invariant information. However, such methods may incur in the mis-learning of graph models towards the interpretability of graphs, and thus the learned noisy and task-agnostic information interferes with the prediction of graphs. To this end, with the purpose of exploring the intrinsic rationale of graphs, we accordingly propose to capture the dimensional rationale from graphs, which has not received sufficient attention in the literature. The conducted exploratory experiments attest to the feasibility of the aforementioned roadmap. To elucidate the innate mechanism behind the performance improvement arising from the dimensional rationale, we rethink the dimensional rationale in graph contrastive learning from a causal perspective and further formalize the causality among the variables in the pre-training stage to build the corresponding structural causal model. On the basis of the understanding of the structural causal model, we propose the dimensional rationale-aware graph contrastive learning approach, which introduces a learnable dimensional rationale acquiring network and a redundancy reduction constraint. The learnable dimensional rationale acquiring network is updated by leveraging a bi-level meta-learning technique, and the redundancy reduction constraint disentangles the redundant features through a decorrelation process during learning. Empirically, compared with state-of-the-art methods, our method can yield significant performance boosts on various benchmarks with respect to discriminability and transferability. The code implementation of our method is available at https://github.com/ByronJi/DRGCL.

MSDRA-NET: A MULTI-SCALE ATTENTION-GUIDED NETWORK FOR MAGNETIC RESONANCE IMAGE RESTORATION

The acquisition and transmission of magnetic resonance (MR) images are frequently affected by random noise pollution, which hampers the diagnosis of diseases by doctors or automated systems. Hence, the search for advanced denoising methods is of great research interest, particularly in magnetic resonance imaging (MRI) denoising models, which are based on deep learning networks and achieve satisfactory results. However, the mining of noisy contextual information and effective information-guided transfer are often neglected in the denoising process, which leads to poor extraction of information at different scales, and poor retention of details. This greatly hinders the further development of MR image denoising methods. Here, we propose a denoising method, MSDRA-Net, for the mining and exploitation of different hierarchical noise features and construct a multi-scale dilated residual (MSDR) structure to transfer and retain noise information at different levels across the layer. Next, a contextual guidance attention (CGA) module guides and transfers contextual information, utilizing the features learnt from different layers of the model as weights. A reconstruction refinement block (RRB) is utilized to construct clean images from the obtained noise bias and the given noisy images. Experiments on simulated and clinical MRI data validated the effectiveness of our method, which demonstrated a superior performance compared to several state-of-the-art methods.

Finite difference-embedded UNet for solving transcranial ultrasound frequency-domain wavefield.

Transcranial ultrasound imaging assumes a growing significance in the detection and monitoring of intracranial lesions and cerebral blood flow. Accurate solution of partial differential equation (PDE) is one of the prerequisites for obtaining transcranial ultrasound wavefields. Grid-based numerical solvers such as finite difference (FD) and finite element methods have limitations including high computational costs and discretization errors. Purely data-driven methods have relatively high demands on training datasets. The fact that physics-informed neural network can only target the same model limits its application. In addition, compared to time-domain approaches, frequency-domain solutions offer advantages of reducing computational complexity and enabling stable and accurate inversions. Therefore, we introduce a framework called FD-embedded UNet (FEUNet) for solving frequency-domain transcranial ultrasound wavefields. The PDE error is calculated using the optimal 9-point FD operator, and it is integrated with the data-driven error to jointly guide the network iterations. We showcase the effectiveness of this approach through experiments involving idealized skull and brain models. FEUNet demonstrates versatility in handling various input scenarios and excels in enhancing prediction accuracy, especially with limited datasets and noisy information. Finally, we provide an overview of the advantages, limitations, and potential avenues for future research in this study.

The autocorrelated Bayesian sampler: A rational process for probability judgments, estimates, confidence intervals, choices, confidence judgments, and response times.

Normative models of decision-making that optimally transform noisy (sensory) information into categorical decisions qualitatively mismatch human behavior. Indeed, leading computational models have only achieved high empirical corroboration by adding task-specific assumptions that deviate from normative principles. In response, we offer a Bayesian approach that implicitly produces a posterior distribution of possible answers (hypotheses) in response to sensory information. But we assume that the brain has no direct access to this posterior, but can only sample hypotheses according to their posterior probabilities. Accordingly, we argue that the primary problem of normative concern in decision-making is integrating stochastic hypotheses, rather than stochastic sensory information, to make categorical decisions. This implies that human response variability arises mainly from posterior sampling rather than sensory noise. Because human hypothesis generation is serially correlated, hypothesis samples will be autocorrelated. Guided by this new problem formulation, we develop a new process, the Autocorrelated Bayesian Sampler (ABS), which grounds autocorrelated hypothesis generation in a sophisticated sampling algorithm. The ABS provides a single mechanism that qualitatively explains many empirical effects of probability judgments, estimates, confidence intervals, choice, confidence judgments, response times, and their relationships. Our analysis demonstrates the unifying power of a perspective shift in the exploration of normative models. It also exemplifies the proposal that the "Bayesian brain" operates using samples not probabilities, and that variability in human behavior may primarily reflect computational rather than sensory noise. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Adaptive and fuzzy locality discriminant analysis for dimensionality reduction

Linear discriminant analysis (LDA) uses labeled samples for acquiring a discriminant projection direction, by which data of different categories are separated into distinct groups in a lower-dimensional subspace. In response to the issue that LDA lacks robustness to non-Gaussian data with rich local information, improvements on LDA explore the subspace manifold structure by building a fully connected similarity graph. However, these methods are vulnerable to the interference of noisy and redundant information. In this paper, we propose a new local LDA method, named adaptive and fuzzy locality discriminant analysis (AFLDA), which aims at extracting precise and compact features. Firstly, an adaptive and fuzzy k-means strategy is adopted, where the membership between data and corresponding subclass centers for each class is learned to establish a hybrid bipartite graph and capture local information. Secondly, we design a discrete and probability constraint imposed on the membership matrix to explore the intricate structure of multimodal data. Moreover, the subblock partition for each class makes data accommodate to multimodal subclasses. Thirdly, the maximum total scatter regularization term is introduced, which amply disperses the data to enhance the recognition of local structure and avoid trivial solutions. Finally, to eliminate the interference of noisy and redundant information, AFLDA learns an optimized subspace, where cluster centers and the membership matrix are updated alternately. Promising results in experiments illustrate the efficacy of the model.

WITHDRAWN: Extracting key topics from massive COVID-19 information on social networks: An integrated deep learning and LDA framework

Quickly discovering and processing unmeaningful information is especially important in the current social network, where public opinion is rapidly fermenting. In this study, a novel topic extraction framework is proposed to extract key topics for the special event of COVID-19 on social networks. First, huge and noisy COVID-19 information is pre-processed for our framework. Second, a model of key information identification is designed for COVID-19 information, which combines the deep learning model of Text Convolutional Neural Networks (TextCNN) with Bi-directional Long Short-Term Memory (BiLSTM) to perform a multi-class classification task. Finally, a model of key topic extraction is developed with the Latent Dirichlet Allocation (LDA) model, which is able to summarize topics and keywords from a large amount of information. we crawled the public opinion information of the COVID-19 on weibo as our dataset. experimental results demonstrate that our model outperforms the other benchmark models in identifying important information related to COVID-19. the key topic extraction model based on LDA can further divide key information into multiple topics ►And describe the topics through keywords for fast tracking of COVID-19 pandemic on social networks.

Exploiting sparsity for localisation of large‐scale wireless sensor networks

AbstractWireless Sensor Network (WSN) localisation refers to the problem of determining the position of each of the agents in a WSN using noisy measurement information. In many cases, such as in distance and bearing‐based localisation, the measurement model is a non‐linear function of the agents' positions, leading to pairwise interconnections between the agents. As the optimal solution for the WSN localisation problem is known to be computationally expensive in these cases, an efficient approximation is desired. The authors show that the inherent sparsity in this problem can be exploited to greatly reduce the computational effort of using an Extended Kalman Filter (EKF) for large‐scale WSN localisation. In the proposed method, which the authors call the L‐Banded Extended Kalman Filter (LB‐EKF), the measurement information matrix is converted into a banded matrix by relabelling (permuting the order of) the vertices of the graph. Using a combination of theoretical analysis and numerical simulations, it is shown that typical WSN configurations (which can be modelled as random geometric graphs) can be localised in a scalable manner using the proposed LB‐EKF approach.

Lightweight Cross-Modal Information Mutual Reinforcement Network for RGB-T Salient Object Detection.

RGB-T salient object detection (SOD) has made significant progress in recent years. However, most existing works are based on heavy models, which are not applicable to mobile devices. Additionally, there is still room for improvement in the design of cross-modal feature fusion and cross-level feature fusion. To address these issues, we propose a lightweight cross-modal information mutual reinforcement network for RGB-T SOD. Our network consists of a lightweight encoder, the cross-modal information mutual reinforcement (CMIMR) module, and the semantic-information-guided fusion (SIGF) module. To reduce the computational cost and the number of parameters, we employ the lightweight module in both the encoder and decoder. Furthermore, to fuse the complementary information between two-modal features, we design the CMIMR module to enhance the two-modal features. This module effectively refines the two-modal features by absorbing previous-level semantic information and inter-modal complementary information. In addition, to fuse the cross-level feature and detect multiscale salient objects, we design the SIGF module, which effectively suppresses the background noisy information in low-level features and extracts multiscale information. We conduct extensive experiments on three RGB-T datasets, and our method achieves competitive performance compared to the other 15 state-of-the-art methods.

Nonparametric Bayesian functional clustering with applications to racial disparities in breast cancer

AbstractAs we have easier access to massive data sets, functional analyses have gained more interest. However, such data sets often contain large heterogeneities, noises, and dimensionalities. When generalizing the analyses from vectors to functions, classical methods might not work directly. This paper considers noisy information reduction in functional analyses from two perspectives: functional clustering to group similar observations and thus reduce the sample size and functional variable selection to reduce the dimensionality. The complicated data structures and relations can be easily modeled by a Bayesian hierarchical model due to its flexibility. Hence, this paper proposes a nonparametric Bayesian functional clustering and peak point selection method via weighted Dirichlet process mixture (WDPM) modeling that automatically clusters and provides accurate estimations, together with conditional Laplace prior, which is a conjugate variable selection prior. The proposed method is named WDPM‐VS for short, and is able to simultaneously perform the following tasks: (1) Automatic cluster without specifying the number of clusters or cluster centers beforehand; (2) Cluster for heterogeneously behaved functions; (3) Select vibrational peak points; and (4) Reduce noisy information from the two perspectives: sample size and dimensionality. The method will greatly outperform its comparison methods in root mean squared errors. Based on this proposed method, we are able to identify biological factors that can explain the breast cancer racial disparities.