Inference Strategy Research Articles

A Distributed Fuzzy Optimal Decision Making Strategy for Task Offloading in Edge Computing Environment

With the technological evolution of mobile devices, 5G and 6G communication and users’ demand for new generation applications viz. face recognition, image processing, augmented reality, etc., has accelerated the new computing paradigm of Mobile Edge Computing (MEC). It operates in close proximity to users by facilitating the execution of computational-intensive tasks from devices through offloading. However, the offloading decision at the device level faces many challenges due to uncertainty in various profiling parameters in modern communication technologies. Further, with the increase in the number of profiling parameters, the fuzzy-based approaches suffer inference searching overheads. In this context, a fuzzy-based approach with an optimal inference strategy is proposed to make suitable offloading decision. The proposed approach utilizes Classification and Regression Tree (CART) mechanism at the inference engine with reduced time complexity of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> (| <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">V</i> | <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">log</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> | <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</i> |)), as compared to <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> (| <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</i> | <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">|V |</sup> ) of state-of-the-art, conventional fuzzy-based offloading approaches, and has been proved to be more efficient. The performance of the proposed approach is evaluated and compared with contemporary offloading algorithms in a python-based fog and edge simulator, YAFS. The simulation results show the reduction in average task processing time, average task completion time, energy consumption, improved server utilization, and tolerance to latency and delay sensitivity for the offloaded tasks in terms of reduced task failure rates.

SAR Despeckling Using a Denoising Diffusion Probabilistic Model

Speckle is a type of multiplicative noise that affects all coherent imaging modalities including Synthetic Aperture Radar (SAR) images. The presence of speckle degrades the image quality and can adversely affect the performance of SAR image applications such as automatic target recognition and change detection. Thus, SAR despeckling is an important problem in remote sensing. In this paper, we introduce SAR-DDPM, a denoising diffusion probabilistic model for SAR despeckling. The proposed method employs a Markov chain that transforms clean images to white Gaussian noise by successively adding random noise. The despeckled image is obtained through a reverse process that predicts the added noise iteratively, using a noise predictor conditioned on the speckled image. Additionally, we propose a new inference strategy based on cycle spinning to improve the despeckling performance. Our experiments on both synthetic and real SAR images demonstrate that the proposed method leads to significant improvements in both quantitative and qualitative results over the state-of-the-art despeckling methods. The code is available at: https://github.com/malshaV/SAR_DDPM.

CODet: Component Object Detector Extracting Structural Features Based on Target Characteristics

Deep learning technology has promoted the object detection task in the remote sensing (RS) field to move toward better performance and more demanding requirements. Except for rigid body objects, component objects (COs) with more complex characteristics remain a detection challenge. Its “partial rules and overall disorder” characteristic limits the model learning ability to the structural features. And the internal noise and relatively sparse arrangement are not conducive to optimizing the model by the existing sample assignment strategies. We propose CODet to detect COs in RS scenes. It consists of a cross-hierarchy feature fusion module (CFM) and a noise-sparse sample assignment (NSA) strategy. CFM learns the potential representation and relative position relationship of components by fusing different level features. NSA redefines the optimization process of sample assignment. It aims to alleviate the problems of classification–localization misalignment (CLM) and the positive–negative sample imbalance (PNI) caused by the object’s internal noise and sparse arrangement. The method is verified on the proposed COD dataset of six categories of COs, reaching an average mAP/mAP <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">50</sup> of 54.3/86.0. To be closer to the task requirements of the practical RS scene, we also propose a RS large-scale images inference framework. It includes a dataset (APRoI, labeled with COs and rigid body objects), a large-scale image inference strategy, and a set of evaluation metrics. With CODet as the core, the framework can effectively reduce the inference time by three to four times on images with an average of more than 100 million pixels.

Splitting strategies for post-selection inference

Summary We consider the problem of providing valid inference for a selected parameter in a sparse regression setting. It is well known that classical regression tools can be unreliable in this context because of the bias generated in the selection step. Many approaches have been proposed in recent years to ensure inferential validity. In this article we consider a simple alternative to data splitting based on randomizing the response vector, which allows for higher selection and inferential power than the former, and is applicable with an arbitrary selection rule. We perform a theoretical and empirical comparison of the two methods and derive a central limit theorem for the randomization approach. Our investigations show that the gain in power can be substantial.

A Little Bit More: Bitplane-Wise Bit-Depth Recovery.

Imaging sensors digitize incoming scene light at a dynamic range of 10-12 bits (i.e., 1024-4096 tonal values). The sensor image is then processed onboard the camera and finally quantized to only 8 bits (i.e., 256 tonal values) to conform to prevailing encoding standards. There are a number of important applications, such as high-bit-depth displays and photo editing, where it is beneficial to recover the lost bit depth. Deep neural networks are effective at this bit-depth reconstruction task. Given the quantized low-bit-depth image as input, existing deep learning methods employ a single-shot approach that attempts to either (1) directly estimate the high-bit-depth image, or (2) directly estimate the residual between the high- and low-bit-depth images. In contrast, we propose a training and inference strategy that recovers the residual image bitplane-by-bitplane. Our bitplane-wise learning framework has the advantage of allowing for multiple levels of supervision during training and is able to obtain state-of-the-art results using a simple network architecture. We test our proposed method extensively on several image datasets and demonstrate an improvement from 0.5dB to 2.3dB PSNR over prior methods depending on the quantization level.

Unsupervised Grouped Axial Data Modeling via Hierarchical Bayesian Nonparametric Models With Watson Distributions.

This paper aims at proposing an unsupervised hierarchical nonparametric Bayesian framework for modeling axial data (i.e., observations are axes of direction) that can be partitioned into multiple groups, where each observation within a group is sampled from a mixture of Watson distributions with an infinite number of components that are allowed to be shared across different groups. First, we propose a hierarchical nonparametric Bayesian model for modeling grouped axial data based on the hierarchical Pitman-Yor process mixture model of Watson distributions. Then, we demonstrate that by setting the discount parameters of the proposed model to 0, another hierarchical nonparametric Bayesian model based on hierarchical Dirichlet process can be derived for modeling axial data. To learn the proposed models, we systematically develop a closed-form optimization algorithm based on the collapsed variational Bayes (CVB) inference. Furthermore, to ensure the convergence of the proposed learning algorithm, an annealing mechanism is introduced to the framework of CVB inference, leading to an averaged collapsed variational Bayes inference strategy. The merits of the proposed models for modeling grouped axial data are demonstrated through experiments on both synthetic data and real-world applications involving gene expression data clustering and depth image analysis.

Financial Market Correlation Analysis and Stock Selection Application Based on TCN-Deep Clustering

It is meaningful to analyze the market correlations for stock selection in the field of financial investment. Since it is difficult for existing deep clustering methods to mine the complex and nonlinear features contained in financial time series, in order to deeply mine the features of financial time series and achieve clustering, a new end-to-end deep clustering method for financial time series is proposed. It contains two modules: an autoencoder feature extraction network based on TCN (temporal convolutional neural) networks and a temporal clustering optimization algorithm with a KL (Kullback–Leibler) divergence. The features of financial time series are represented by the causal convolution and the dilated convolution of TCN networks. Then, the pre-training results based on the KL divergence are fine-tuned to make the clustering results discriminative. The experimental results show that the proposed method outperforms existing deep clustering and general clustering algorithms in the CSI 300 and S&amp;P 500 index markets. In addition, the clustering results combined with an inference strategy can be used to select stocks that perform well or poorly, thus guiding actual stock market trades.

ARST: auto-regressive surgical transformer for phase recognition from laparoscopic videos

ABSTRACT Phase recognition plays an essential role for surgical workflow analysis in computer assisted intervention. Transformer, originally proposed for sequential data modelling in natural language processing, has been successfully applied to surgical phase recognition. Existing works based on transformer mainly focus on modeling attention dependency, without introducing auto-regression. In this work, an Auto-Regressive Surgical Transformer, referred as ARST, is first proposed for on-line surgical phase recognition from laparoscopic videos, modeling the inter-phase correlation implicitly by conditional probability distribution. To reduce inference bias and to enhance phase consistency, we further develop a consistency constraint inference strategy based on auto-regression. We conduct comprehensive validations on a well-known public dataset Cholec80. Experimental results show that our method outperforms the state-of-the-art methods both quantitatively and qualitatively, and achieves an inference rate of 66 frames per second (fps).

Mixed-UNet: Refined class activation mapping for weakly-supervised semantic segmentation with multi-scale inference

Deep learning techniques have shown great potential in medical image processing, particularly through accurate and reliable image segmentation on magnetic resonance imaging (MRI) scans or computed tomography (CT) scans, which allow the localization and diagnosis of lesions. However, training these segmentation models requires a large number of manually annotated pixel-level labels, which are time-consuming and labor-intensive, in contrast to image-level labels that are easier to obtain. It is imperative to resolve this problem through weakly-supervised semantic segmentation models using image-level labels as supervision since it can significantly reduce human annotation efforts. Most of the advanced solutions exploit class activation mapping (CAM). However, the original CAMs rarely capture the precise boundaries of lesions. In this study, we propose the strategy of multi-scale inference to refine CAMs by reducing the detail loss in single-scale reasoning. For segmentation, we develop a novel model named Mixed-UNet, which has two parallel branches in the decoding phase. The results can be obtained after fusing the extracted features from two branches. We evaluate the designed Mixed-UNet against several prevalent deep learning-based segmentation approaches on our dataset collected from the local hospital and public datasets. The validation results demonstrate that our model surpasses available methods under the same supervision level in the segmentation of various lesions from brain imaging.

A novel Boolean network inference strategy to model early hematopoiesis aging

Hematopoietic stem cell (HSC) aging is a multifactorial event leading to changes in HSC properties and functions, which are intrinsically coordinated and affect the early hematopoiesis. To better understand the mechanisms and factors controlling these changes, we developed an original strategy to construct a Boolean model of HSC differentiation. Based on our previous scRNA-seq data, we exhaustively characterized active transcription modules or regulons along the differentiation trajectory and constructed an influence graph between 15 selected components involved in the dynamics of the process. Then we defined dynamical constraints between observed cellular states along the trajectory and using answer set programming with in silico perturbation analysis, we obtained a Boolean model explaining the early priming of HSCs. Finally, perturbations of the model based on age-related changes revealed important deregulations, such as the overactivation of Egr1 and Junb or the loss of Cebpa activation by Gata2. These new regulatory mechanisms were found to be relevant for the myeloid bias of aged HSC and explain the decreased transcriptional priming of HSCs to all mature cell types except megakaryocytes.

대학생 학습자의 영어 관용어 이해 과정에서의 어려움

Objectives Using the theoretical viewpoint of lexical transfer, this study investigates what causes Korean (L1) undergraduates’ difficulties in making sense of English (L2) idioms. Methods In order to achieve this research objective, ninety undergraduates in a metropolitan city area participated in a questionnaire-based study using four-type English idioms. The research participants translated twenty English idioms into Korean, which were selected by a Korean reference group depending on the perceived form and meaning similarity between L1 and L2. Then the participants listened to the explanations and answers on them and completed a questionnaire asking the most difficult idiom, the inference process of it, and what they realized about L2 idiom comprehension. Results There are three main findings. First, the idioms perceived the most difficult in translation were in the order of cognate idioms &lt; pragmatic idioms &lt; false friends idioms &lt; L2-only idioms. This shows a tendency that the research participants had difficulty in understanding construal-opaque idioms including false friends idioms and L2-only idioms, whereas they did not have difficulty in understanding construal-transparent idioms including cognate idioms and pragmatic idioms. Second, when the participants did not perceive crosslinguistic meaning similarity on the construal-transparent idioms, they tended to make an arbitrary L1-based inference on them, resulting in translation errors. Third, crosslinguistic form difference could interact with crosslinguistic meaning similarity in the process of perceiving crosslinguistic similarity; nevertheless, the finding that they perceived more difficulty in understanding false friends idioms than pragmatic idioms signifies that the mechanism of lexical transfer is the perceived similarity of meaning between L1 and L2 idioms. Conclusions This study shows that construal opacity is the main cause of the research participants’ difficulties in understanding L2 idioms because their persistent meaning system is rooted in L1. This finding suggests that the popular teaching method of using inference strategy on L2 idiom comprehension is only valid for construal-transparent idioms as universal cognition operates on them, and that conscious effort to broaden L2 idiom repertoire is needed for construal-opaque idioms on which relative cognition operates. In the same vein, raising student consciousness on the crosslinguistic universals and linguistic relativity is also expected.

Analyzing recurrent and nonrecurrent terminal events data in discrete time.

Joint analysis of recurrent and nonrecurrent terminal events has attracted substantial attention in literature. However, there lacks formal methodology for such analysis when the event time data are on discrete scales, even though some modeling and inference strategies have been developed for discrete-time survival analysis. We propose a discrete-time joint modeling approach for the analysis of recurrent and terminal events where the two types of events may be correlated with each other. The proposed joint modeling assumes a shared frailty to account for the dependence among recurrent events and between the recurrent and the terminal terminal events. Also, the joint modeling allows for time-dependent covariates and rich families of transformation models for the recurrent and terminal events. A major advantage of our approach is that it does not assume a distribution for the frailty, nor does it assume a Poisson process for the analysis of the recurrent event. The utility of the proposed analysis is illustrated by simulation studies and two real applications, where the application to the biochemists' rank promotion data jointly analyzes the biochemists' citation numbers and times to rank promotion, and the application to the scleroderma lung study data jointly analyzes the adverse events and off-drug time among patients with the symptomatic scleroderma-related interstitial lungdisease.

Deep Learning of Latent Variable Models for Industrial Process Monitoring

Data-driven process monitoring based on latent variable models are widely employed in industry. This article proposes a novel monitoring framework for latent variable models using hierarchical feature extraction, Bayesian inference, and weighting strategy. We first establish a deep structure to implement hierarchical latent variables extraction, the extracted features are used to construct diverse monitoring statistics. Then, we utilize Bayesian inference and proper weighting strategy to fuse various useful information. In line with the different characteristics of principal component analysis (PCA) and independent component analysis (ICA), we construct a deep PCA-ICA model for process monitoring according to the proposed framework. The deep PCA-ICA model performs hierarchical feature extraction, which can simultaneously extract deep Gaussian information and deep non-Gaussian information. The features extracted by different layers are then transformed to posterior probabilities through Bayesian inference. After that, different posterior probabilities are combined through appropriate weighting strategy to build new probabilistic statistic, which can give more synthetic monitoring results. Moreover, the Bayesian inference and weighting strategy are further used to integrate the advantages of different models by transforming various probabilistic statistics into an overall monitoring index, which can comprehensively indicate the process status. The Tennessee Eastman process is used to validate the superiority of the proposed model over the existing methods. Besides, the extracted features are further analyzed to show the effectiveness and benefits of the deep hierarchical feature extraction structure.

ADS-B-Based Spatiotemporal Alignment Network for Airport Video Object Segmentation

Video object segmentation (VOS) is the fundamental problem of vision-based intelligent transportation, and many VOS algorithms relying on inference from reference masks have been proposed. Due to the inherent defects of the inference strategy and the complex changes of targets, VOS methods that perform well on public datasets are usually ineffective in airport scenarios. We propose a spatiotemporal alignment network (STA-Net) that makes use of Automatic Dependent Surveillance-Broadcast (ADS-B) data as prior information to guide the long-term segmentation of aircraft. ADS-B is an airport-specific signal, which indicates the location of aircraft in real time. Based on ADS-B, we continuously generate new reference masks instead of using previous masks for inference, which greatly reduces the accumulation of inference errors. To achieve this, previous masks of each aircraft are aligned on the temporal domain based on the position information in ADS-B. All temporally-aligned masks are compared, and the one most similar to the current instant is reserved. This mask is both temporally and spatially aligned; hence it is a better reference mask for inference. Aligned masks are updated every time new ADS-B data arrive, so that they can support long-term inference. With the selected mask as a reference, aircraft of interest are segmented within a unified encoder-decoder framework over the long term. Experiments on a benchmark dataset and in a real airport scenario verify the effectiveness of the presented method.

FastSpeechStyle: Fast, Emotion Controllable, and High-Quality Speech Synthesis

Non-autoregressive text-to-speech models such as Fastspeech2 can fast synthesize high-quality speech. This model also allows explicit control of the speech signal’s pitch, energy, and speed. However, controlling emotion while maintaining natural human-like speech is still a problem. In this work, we propose an expressive speech synthesis model that can synthesize high-quality speech with desired emotion. The proposed model includes two main components (1) Mel Emotion Encoder extracts emotion embedding from the Mel-spectrogram of audio, (2) the FastSpeechStyle, a non-autoregressive model, which is modified from vanilla Fastspeech2. The FastSpeechStyle used an Improved Conformer block, which replaces normal LayerNorm with Style Adaptive LayerNorm to “shift” and “scale” hidden features according to emotion embedding, instead of vanilla FFTBlock [Y. Ren, Y. Ruan, X. Tan, T. Qin, S. Zhao, Z. Zhao and T.-Y. Liu, Fastspeech: Fast, robust and controllable text to speech, Adv. Neural Inf. Process. Syst. 32 (2019)] to better model the local and global dependency in the acoustic model. We also propose a specific inference strategy to control the desired emotion of speech. The experimental results show that (1) The proposed model with improved Conformer achieved higher scores than the baseline model in all naturalness and emotion similarity scores; (2) The proposed model still maintains fast inference speed like the baseline model.

Streamlined Variational Inference for Linear Mixed Models with Crossed Random Effects

We derive streamlined mean field variational Bayes algorithms for fitting linear mixed models with crossed random effects. In the most general situation, where the dimensions of the crossed groups are arbitrarily large, streamlining is hindered by lack of sparseness in the underlying least squares system. Because of this fact we also consider a hierarchy of relaxations of the mean field product restriction. The least stringent product restriction delivers a high degree of inferential accuracy. However, this accuracy must be mitigated against its higher storage and computing demands. Faster sparse storage and computing alternatives are also provided, but come with the price of diminished inferential accuracy. This article provides full algorithmic details of three variational inference strategies, presents detailed empirical results on their pros and cons and, thus, guides the users on their choice of variational inference approach depending on the problem size and computing resources. Supplementary materials for this article are available online.

Highly scalable maximum likelihood and conjugate Bayesian inference for ERGMs on graph sets with equivalent vertices.

The exponential family random graph modeling (ERGM) framework provides a highly flexible approach for the statistical analysis of networks (i.e., graphs). As ERGMs with dyadic dependence involve normalizing factors that are extremely costly to compute, practical strategies for ERGMs inference generally employ a variety of approximations or other workarounds. Markov Chain Monte Carlo maximum likelihood (MCMC MLE) provides a powerful tool to approximate the maximum likelihood estimator (MLE) of ERGM parameters, and is generally feasible for typical models on single networks with as many as a few thousand nodes. MCMC-based algorithms for Bayesian analysis are more expensive, and high-quality answers are challenging to obtain on large graphs. For both strategies, extension to the pooled case—in which we observe multiple networks from a common generative process—adds further computational cost, with both time and memory scaling linearly in the number of graphs. This becomes prohibitive for large networks, or cases in which large numbers of graph observations are available. Here, we exploit some basic properties of the discrete exponential families to develop an approach for ERGM inference in the pooled case that (where applicable) allows an arbitrarily large number of graph observations to be fit at no additional computational cost beyond preprocessing the data itself. Moreover, a variant of our approach can also be used to perform Bayesian inference under conjugate priors, again with no additional computational cost in the estimation phase. The latter can be employed either for single graph observations, or for observations from graph sets. As we show, the conjugate prior is easily specified, and is well-suited to applications such as regularization. Simulation studies show that the pooled method leads to estimates with good frequentist properties, and posterior estimates under the conjugate prior are well-behaved. We demonstrate the usefulness of our approach with applications to pooled analysis of brain functional connectivity networks and to replicated x-ray crystal structures of hen egg-white lysozyme.

Bayesian Multivariate Mixed Poisson Models with Copula-Based Mixture

It is common practice to use multivariate count modeling in actuarial literature when dealing with claim counts from insurance policies with multiple covers. One possible way to construct such a model is to implement copula directly on discrete margins. However, likelihood inference under this construction involves the computation of multidimensional rectangle probabilities, which could be computationally expensive, especially in the elliptical copula case. Another potential approach is based on the multivariate mixed Poisson model. The crucial work under this method is to find an appropriate multivariate continuous distribution for mixing parameters. By virtue of the copula, this issue could be easily addressed. Under such a framework, the Markov chain Monte Carlo (MCMC) method is a feasible strategy for inference. The usefulness of our model is then illustrated through a real-life example. The empirical analysis demonstrates the superiority of adopting a copula-based mixture over other types of mixtures. Finally, we demonstrate how those fitted models can be applied to the insurance ratemaking problem in a Bayesian context.

Intelligent Single-Board Computer for Industry 4.0: Efficient Real-Time Monitoring System for Anomaly Detection in CNC Machines

The Industry 4.0 technology relies on Single-board computers and the Internet of Things (IOT) and Machine Learning (ML). In addition, sensory detectors, controllers, and a communication interface are employed to address the demands of distant supervision and operational management. In today's industrial environment, understanding machines and giving effective interpretation and prognostics is a challenging issue. This paper presents an effective on-process identification tool for monitoring and advising the operator based on sensor parameters. The data is analysed with the Fast Fourier Transform (FFT) inference and machine learning strategies to detect the production calibre of an industrial Computer Numerical Control (CNC) machine, including vibration, temperature, humidity, and operating temperatures. The vibration parameter is provided to the FFT algorithm to produce frequency, and the diameter dataset is also provided manually from the hole diameter in the job piece to correctly monitor and inspect the product quality to prognostics to the fault in machines. Improper machine settings cause varied vibrations and changes in parameters, whereas our Industry 4.0 module detects and warns about faulty parameters. The device is put through its trials using three distinct machine learning approaches, and the results are collected. ML combines the outcomes of many baseline estimators to provide better results. This research work utilizes the Linear regression model since it has a high-power detection ability and minimizes variance as well as bias. The Single board computer using FFT and linear regression monitoring gives greater data accuracy of 97.6 percent on comparing the outcomes of 5.4%improved efficiency than K-Nearest Neighbourhood (KNN), 95.5% Random Forest Network (RN), and 95% Support Vector Machine (SVM) algorithms. The proposed system was validated via the deployment of suitable test scenarios, illustrating the technique's effectiveness in manufacturing environments.

High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics

AbstractIn Neural Machine Translation, it is typically assumed that the sentence with the highest estimated probability should also be the translation with the highest quality as measured by humans. In this work, we question this assumption and show that model estimates and translation quality only vaguely correlate. We apply Minimum Bayes Risk (MBR) decoding on unbiased samples to optimize diverse automated metrics of translation quality as an alternative inference strategy to beam search. Instead of targeting the hypotheses with the highest model probability, MBR decoding extracts the hypotheses with the highest estimated quality. Our experiments show that the combination of a neural translation model with a neural reference-based metric, Bleurt, results in significant improvement in human evaluations. This improvement is obtained with translations different from classical beam-search output: These translations have much lower model likelihood and are less favored by surface metrics like Bleu.