Autoregressive Method Research Articles

Deep Learning and Handcrafted Features for Thyroid Nodule Classification

ABSTRACTIn this research, we present a refined image‐based computer‐aided diagnosis (CAD) system for thyroid cancer detection using ultrasound imagery. This system integrates a specialized convolutional neural network (CNN) architecture designed to address the unique aspects of thyroid image datasets. Additionally, it incorporates a novel statistical model that utilizes a two‐dimensional random coefficient autoregressive (2D‐RCA) method to precisely analyze the textural characteristics of thyroid images, thereby capturing essential texture‐related information. The classification framework relies on a composite feature vector that combines deep learning features from the CNN and handcrafted features from the 2D‐RCA model, processed through a support vector machine (SVM) algorithm. Our evaluation methodology is structured in three phases: initial assessment of the 2D‐RCA features, analysis of the CNN‐derived features, and a final evaluation of their combined effect on classification performance. Comparative analyses with well‐known networks such as VGG16, VGG19, ResNet50, and AlexNet highlight the superior performance of our approach. The outcomes indicate a significant enhancement in diagnostic accuracy, achieving a classification accuracy of 97.2%, a sensitivity of 84.42%, and a specificity of 95.23%. These results not only demonstrate a notable advancement in the classification of thyroid nodules but also establish a new standard in the efficiency of CAD systems.

Electric Vehicle Sentiment Analysis Using Large Language Models

Sentiment analysis is a technique used to understand the public’s opinion towards an event, product, or organization. For example, sentiment analysis can be used to understand positive or negative opinions or attitudes towards electric vehicle (EV) brands. This provides companies with valuable insight into the public’s opinion of their products and brands. In the field of natural language processing (NLP), transformer models have shown great performance compared to traditional machine learning algorithms. However, these models have not been explored extensively in the EV domain. EV companies are becoming significant competitors in the automotive industry and are projected to cover up to 30% of the United States light vehicle market by 2030 In this study, we present a comparative study of large language models (LLMs) including bidirectional encoder representations from transformers (BERT), robustly optimised BERT (RoBERTa), and a generalised autoregressive pre-training method (XLNet) using Lucid Motors and Tesla Motors YouTube datasets. Results evidenced that LLMs like BERT and her variants are off-the-shelf algorithms for sentiment analysis, specifically when fine-tuned. Furthermore, our findings present the need for domain adaptation whilst utilizing LLMs. Finally, the experimental results showed that RoBERTa achieved consistent performance across the EV datasets with an F1 score of at least 92%.

Effects of foreign direct investment on climate change in the Asian region

Purpose ― This research aims to empirically investigate and compare the effects of foreign direct investment on climate change in five South Asian nations.Methodology ― This research uses yearly data covering 1980–2020 in five South Asian nations: Bangladesh, India, Nepal, Pakistan, and Sri Lanka. Vector Autoregressive (VAR) methods with variance decomposition and impulse response function provide the basis of the empirical data for comparison analysis. Findings ― This research shows that foreign direct investment's impact on pollution ranges from 1% to 10% in four countries and 16.13% in Pakistan. This indicates that in five South Asian states, there is little endogenous correlation between foreign direct investment and pollution. Furthermore, a shock to foreign investment improves the environmental conditions in Bangladesh and India while harming the growth of other nations.Implications ― The impact of foreign direct investment on pollution may vary based on each country's economic situation. Public efforts to enhance capital goods, education, health, and infrastructure are essential for reducing pollution and attracting foreign investment. Therefore, improved transparency and governance are essential for a positive relationship between growth and foreign investment.Value/Originality ― This research contributes to analyzing and comparing the effects of foreign direct investment on climate change in five South Asian nations using Vector Autoregressive (VAR) methods.

Action-aware Linguistic Skeleton Optimization Network for Non-autoregressive Video Captioning

Non-autoregressive video captioning methods generate visual words in parallel but often overlook semantic correlations among them, especially regarding verbs, leading to lower caption quality. To address this, we integrate action information of highlighted objects to enhance semantic connections among visual words. Our proposed Action-aware Language Skeleton Optimization Network (ALSO-Net) tackles the challenge of extracting action information across frames, improving understanding of complex context-dependent video actions and reducing sentence inconsistencies. ALSO-Net incorporates a linguistic skeleton tag generator to refine semantic correlations and a video action predictor to enhance verb prediction accuracy in video captions. We also address issues of unsatisfactory caption length and quality by jointly optimizing different levels of motion prediction loss. Experimental evaluation on prominent video captioning datasets demonstrates that ALSO-Net outperforms baseline methods by a significant margin and achieves competitive performance compared to state-of-the-art autoregressive methods with smaller model complexity and faster inference time.

Modeling the occupancy rate and nights spent at tourism accommodations of Spain using autoregressive deep learning networks

Purpose The purpose of this paper is to autoregressively model the net occupancy rate of beds and bedrooms in hotels and similar accommodations and the nights spent at these accommodations of Spain for the period of 1990–2023 using monthly data. Design/methodology/approach The monthly occupancy rate of hotels and the total number of hotel nights data of Spain for the 1990M01–2023M09 range is considered. An autoregressive deep learning network is developed for the modeling of both metrics. Moreover, the results of the proposed autoregressive deep learning method are compared to those of a classical artificial neural network. Findings The actual occupancy rate, total night data and the deep learning model results are compared showing the accuracy of the developed model. Moreover, the R2, mean absolute error, root mean square error and mean absolute percentage error of the models are calculated further demonstrating the high performance of the developed model. The R2 values higher than 0.9 are achieved for both occupancy rate and total number of hotel nights data. Practical implications The modeling results given in this paper demonstrate that the previous values of the net occupancy rate and the total number of nights can be used as inputs of a deep learning network model by which accurate forecasts can be made for the future values of the occupancy rate and the total number of hotel nights. This modeling approach possesses importance from the practical viewpoint considering that the accurate planning and forecast of the net occupancy rate and the total number of nights affect the tourism income. Originality/value This study differs from existing literature by attempting to model the occupancy rate and the total number of hotel nights data autoregressively using deep learning networks.

Generative adversarial networks for whispered to voiced speech conversion: a comparative study

AbstractGenerative Adversarial Networks (GANs) have demonstrated promising results as end-to-end models for whispered to voiced speech conversion. Leveraging non-autoregressive systems like GANs capable of performing conditional waveform generation eliminates the need for separate models to estimate voiced speech features, and leads to faster inference compared to autoregressive methods. This study aims to identify the optimal GAN architecture for the whispered to voiced speech conversion task by comparing six state-of-the-art models. Furthermore, we present a method for evaluating the preservation of speaker identity and local accent, using embeddings obtained from speaker- and language identification systems. Our experimental results show that building the speech conversion system based on the HiFi-GAN architecture yields the best objective evaluation scores, outperforming the baseline by $$\sim$$ ∼ 9% relative using frequency-weighted Signal-to-Noise Ratio and Log Likelihood Ratio, as well as by $$\sim$$ ∼ 29% relative using Root Mean Squared Error. In subjective tests, HiFi-GAN yielded a mean opinion score of 2.9, significantly outperforming the baseline with a score of 1.4. Furthermore, HiFi-GAN enhanced ASR performance and preserved speaker identity and accent, with correct language detection rates of up to $$\sim$$ ∼ 98%.

Multi-fidelity Gaussian process surrogate modeling for regression problems in physics

Abstract One of the main challenges in surrogate modeling is the limited availability of data due to resource constraints associated with computationally expensive simulations. Multi-fidelity methods provide a solution by chaining models in a hierarchy with increasing fidelity, associated with lower error, but increasing cost. In this paper, we compare different multi-fidelity methods employed in constructing Gaussian process surrogates for regression. Non-linear autoregressive methods in the existing literature are primarily confined to two-fidelity models, and we extend these methods to handle more than two levels of fidelity. Additionally, we propose enhancements for an existing method incorporating delay terms by introducing a structured kernel. We demonstrate the performance of these methods across various academic and real-world scenarios. Our findings reveal that multi-fidelity methods generally have a smaller prediction error for the same computational cost as compared to the single-fidelity method, although their effectiveness varies across different scenarios.

Exchange Rate Pass-Through on Prices in Nigeria—A Threshold Analysis

Persistent exchange rate depreciation and its debilitating effects on rising inflation have remained a concern in Nigeria. This article explores the effects of exchange rate pass-through on producer prices, consumer prices, export prices, import prices and the Taylor rule from 2000 to 2023, using quarterly data and adopting threshold autoregression and self-exciting smooth threshold regression methods. The findings suggest that there are non-linearities in the way that exchange rate depreciation affects prices in Nigeria. Furthermore, the findings suggest a threshold of 5 percent depreciation. Two sub-sample analyses corroborate the main findings, showing that a threshold of 5 percent is the optimum benchmark if demand and supply are not to be weakened. At this level or below, the effects of exchange rate depreciation on inflation are much lower, even though prices will rise. However, above this benchmark, the effects of depreciation on inflation are much larger, weakening consumer demand for both imported and domestic goods as well as producer supply of both exported and domestic goods and services in the economy. This result implies that an average exchange rate depreciation not higher than 5 percent within a quarter is reasonable if the Nigerian economy is to remain competitive both domestically and globally. Finally, the results suggest that the exchange rate pass-through to prices is considerably higher in Nigeria below the threshold, while it overshoots for producer prices, export prices, and import prices above the threshold. To keep inflation in check, this paper suggests that the monetary authorities should try to keep exchange rate depreciation below the established thresholds, while also considering adjusting the policy rate to take into account the exchange rate depreciation thresholds in order to keep domestic prices stable.

Harbor in the storm: How Bitcoin navigates challenges of climate change and global uncertainties

Understanding Bitcoin's (BTC) performance and hedging effects under various uncertainties is crucial. This study combines time-varying Granger causality (TVGC) tests and wavelet time-varying parameter vector autoregression (TVP-VAR) methods to examine the relationship between Bitcoin (BTC) and climate uncertainty (SOI), geopolitical risk (GPR), economic policy uncertainty (EPU), crude oil volatility (OVX), and market volatility (VIX) across both time and frequency domains, from December 19, 2017, to October 16, 2023. The results show that in recent years, the long-term impact of SOI on BTC, as well as political and economic uncertainties, is hard to ignore, but BTC cannot serve as a safe-haven asset against SOI. Wavelet decomposition indicates that during extreme events, BTC exhibits a leading positive co-movement with EPU, GPR, VIX, and OVX in the long term, showing potential as a hedging asset. However, TVGC and wavelet decomposition spillover results further suggest that BTC's hedging capacity against different economic and political uncertainties may be limited during certain extreme events.

Generative adversarial network for semi-supervised image captioning

Traditional supervised image captioning methods usually rely on a large number of images and paired captions for training. However, the creation of such datasets necessitates considerable temporal and human resources. Therefore, we propose a new semi-supervised image captioning algorithm to solve this problem. The proposed method uses a generative adversarial network to generate images that match captions, and uses these generated images and captions as new training data. This avoids the error accumulation problem when generating pseudo captions with autoregressive method and the network can directly perform backpropagation. At the same time, in order to ensure the correlation between the generated images and captions, we introduced the CLIP model for constraints. The CLIP model has been pre-trained on a large amount of image–text data, so it shows excellent performance in semantic alignment of images and text. To verify the effectiveness of our method, we validate on MSCOCO offline “Karpathy” test split. Experiment results show that our method can significantly improve the performance of the model when using 1% paired data, with the CIDEr score increasing from 69.5% to 77.7%. This shows that our method can effectively utilize unlabeled data for image caption tasks.

Time Series Econometric Analysis of ODOP's Contribution to State-Level GDP Growth in India

This study examines the economic impact of the One District One Product (ODOP) scheme on state-level GDP growth in India using time-series econometric models from 2011 to 2023. The ODOP initiative, launched by the Indian government, aims to promote regional economic development by fostering unique local products from each district. By employing Vector Autoregression (VAR) and Johansen Co-Integration methods, the research quantitatively assesses the causal relationship between the ODOP scheme and GDP growth across various states. Preliminary findings suggest that ODOP significantly contributes to regional GDP, particularly through enhancing local production and market reach, thereby integrating regional economies into national and global value chains. This study underscores the importance of targeted regional policies in achieving broader economic objectives and fostering sustainable development. It also highlights the ODOP scheme’s role in promoting traditional products and skills, which aligns with the government's larger goals of a self-reliant India.

البرمجة الضبابية وتحسين أداء الخوارزميات في بيئة متعددة المتغيرات الرتيبة

In many situations of daily life, when we start statistical analysis, we encounter data that we suffer from inaccuracy in its measurement, either due to observation or measurement errors or the lack of appropriate conditions for collecting this data, such as failure times of machines, equipment, electrical devices, medical, engineering and economic data. In many medical studies, the researcher may have a strong conviction that the regression function used to describe the relationship between two variables has a certain form or formula that can be characterized by certain ordering restrictions such as monotonicity; monotonic regression has important applications in statistics, operations research, and signal processing, and these applications are often characterized by a very large value of n. For such large-scale problems, it is of great practical importance to develop algorithms whose complexity does not increase rapidly with increasing n. It is a nonparametric regression technique that preserves order. In this thesis, the proposed fuzzy autoregressive monotonic method, fuzzy autoregressive monotonic least squares (FILSR), fuzzy autoregressive M estimator (FIM), and fuzzy autoregressive maximum likelihood estimator (FIML) were proposed. The best method for estimating the autoregressive function is the fuzzy autoregressive maximum likelihood method with a mean square error of (0.51455).

Polar Motion Ultra-Short-Term Prediction of Least-Squares+Multivariate Autoregressive Hybrid Method by Using the Kalman Filter.

The polar motion (PM, including two parameters PMx and PMy) ultra-short-term prediction (1-10 days) is demanded in the real-time navigation of satellites and spacecrafts. Improving the PMx and PMy ultra-short-term predictions accuracies are a key to optimize the performance of these related applications. Currently, the least squares (LS)+autoregressive (AR) hybrid method is regarded as one of the most capable approaches for ultra-short-term predictions of PMx and PMy. The Kalman filter has proven to be effective in improving the ultra-short-term prediction performance of the LS+AR hybrid method, but the PMx and PMy ultra-short-term predictions accuracies are still not able to satisfy some related applications. In order to improve the performance of PM ultra-short-term prediction, it is worth exploring the combinations of existing methods. Throughout the existing predicted methods, the LS+multivariate autoregressive (MAR) hybrid method by using the Kalman filter has the potential to improve the accuracy of PM ultra-short-term prediction. In addition, a PM prediction performance analysis of the LS+MAR hybrid method by using the Kalman filter, namely the LS+MAR+Kalman hybrid method, is still missing. In this contribution, we proposed the LS+MAR+Kalman hybrid method for PM ultra-short-term prediction. The data sets for PM predictions, which range from 1 to 10 days, have been tested based on the International Earth Rotation and Reference Systems Service Earth Orientation Parameter (IERS EOP) 14 C04 series to assess the performance of the LS+MAR+Kalman hybrid model. The experimental results illustrated that the LS+MAR+Kalman hybrid method can effectively execute PMy ultra-short-term predictions. The improvement of PMy prediction accuracy can rise up to 12.69% for 10-day predictions, and the improvement of ultra-short-term predictions is 7.64% on average.

Introducing bidirectional attention for autoregressive models in abstractive summarization

Abstractive summarization methods typically follow the autoregressive paradigm using the causal masks in the decoder for training and inference efficiency. However, this approach leads to a constant context throughout the generation process, which conflicting with the bidirectional characteristics of natural language. Although previous attempts have been made to incorporate bidirectional attention in the decoding process through non-autoregressive approach, the evaluation results are not comparable to the autoregressive methods. To bring bidirectional attention to the autoregressive process while maintaining superior performance, we propose the global autoregressive paradigm, which takes the outputs of the autoregressive process as additional inputs in the subsequent global iteration. Specifically, we build a bidirectional decoder alongside the original encoder and decoder to capture the bidirectional context of the outputs. This context is updated after each autoregressive decoding iteration. The decoder then integrates the updated context into subsequent autoregressive decoding steps, enhancing the generative process with a more comprehensive and authentic context. Additionally, we use contrastive learning to train the model to extract reliable features from the bidirectional context and apply reinforcement learning to improve the model's utilization of this context. We evaluate our method on CNN/DM, XSum, and NYT datasets, and the results highlight the significance of the bidirectional context. Our method achieves the best performance in terms of ROUGE-2 on CNN/DM (23.96), and performs comparably on XSum (25.45) and NYT (27.91). It also outperforms all the baselines in terms of BERTScore, with a score of 89.96 on CNN/DM, 92.70 on XSum, and 90.04 on NYT. Furthermore, our method can perform better with a larger beam size.

Dynamic features and wind-resistant strategy of suspended monorail vehicle-track beam systems subjected to turbulent wind

Suspended monorail vehicles (SMV), hung beneath box beams with open bottoms, exhibit significant transverse wobble when exposed to turbulent winds, markedly impacting passenger comfort. This study presents an effective methodology for comprehensively evaluating the dynamical behavior of suspended monorail vehicle-track beam systems (SMVTBS) under wind action. First, based on the multi-rigid body dynamics theory and finite element method, an integrated vehicle-track beam interaction model is established. Then, by applying the auto-regressive (AR) linear filtering method, a turbulent wind velocity field with inherent correlations is adequately simulated through a stochastic process, which is later converted into wind force acting on both the track beam and vehicles. On this basis, the vibration responses of the SMVTBS with and without wind actions are compared, and the effects of the wind load on the vehicle-track beam dynamical behavior are revealed. Furthermore, to improve the wind-resistant performance of the SMV, several crucial design parameters are reasonably selected and effective wind-resistant strategies are proposed. Finally, the dynamic performance of the SMV is evaluated under wind action, and suitable train running speeds were recommended at different wind velocities to guarantee vehicle riding comfort. The research results can provide useful guidance for the design and operation of SMVTBS against crosswinds.

Novel Methods to Calculate and Estimate the Factors Influencing the Ecological Footprints of Pakistan

Increasing demand for natural resources has exacerbated the scarcity of natural resources. Shortage of natural resources for timely needs is raising some significant environmental issues for the fast-growing population. It is argued that there is a trade-off between economic growth and environmental quality but it is debatable. To expand this debate, this article examines the short-run and long-run relationship between ecological footprints and income growth accompanied by other macroeconomic indicators. This study investigated the validity of the Environmental Kuznets curve between income growth and environmental pressure in Pakistan. This paper is based on secondary data for the period (1970 to 2021). The Auto-Regressive Distributive lag-bound testing method is utilized to determine the short-run and long-run links between income growth and ecological footprints per capita. The study found that a larger proportion of Pakistan’s imports are contaminated with high embodied emissions. An increase in economic prosperity has dynamic implications for the environment across international borders. The products embodied emissions imported in Pakistan are greater than the emissions exported to other economies. The net effect of trade is negative on the environment in Pakistan. The study confirms that there exists a significant statistical relationship between ecological footprints and economic growth. This validates the evidence of the Environmental Kuznets Curve in the case of Pakistan.

Stream salinity prediction in data-scarce regions: Application of transfer learning and uncertainty quantification

Scarcity of stream salinity data poses a challenge to understanding salinity dynamics and its implications for water supply management in water-scarce salt-prone regions around the world. This paper introduces a framework for generating continuous daily stream salinity estimates using instance-based transfer learning (TL) and assessing the reliability of the synthetic salinity data through uncertainty quantification via prediction intervals (PIs). The framework was developed using two temporally distinct specific conductance (SC) datasets from the Upper Red River Basin (URRB) located in southwestern Oklahoma and Texas Panhandle, United States. The instance-based TL approach was implemented by calibrating Feedforward Neural Networks (FFNNs) on a source SC dataset of around 1200 instantaneous grab samples collected by United States Geological Survey (USGS) from 1959 to 1993. The trained FFNNs were subsequently tested on a target dataset (1998-present) of 220 instantaneous grab samples collected by the Oklahoma Water Resources Board (OWRB). The framework's generalizability was assessed in the data-rich Bird Creek watershed in Oklahoma by manipulating continuous SC data to simulate data-scarce conditions for training the models and using the complete Bird Creek dataset for model evaluation. The Lower Upper Bound Estimation (LUBE) method was used with FFNNs to estimate PIs for uncertainty quantification. Autoregressive SC prediction methods via FFNN were found to be reliable with Nash Sutcliffe Efficiency (NSE) values of 0.65 and 0.45 on in-sample and out-of-sample test data, respectively. The same modeling scenario resulted in an NSE of 0.54 for the Bird Creek data using a similar missing data ratio, whereas a higher ratio of observed data increased the accuracy (NSE = 0.84). The relatively narrow estimated PIs for the North Fork Red River in the URRB indicated satisfactory stream salinity predictions, showing an average width equivalent to 25 % of the observed range and a confidence level of 70 %.

Structure-Based Drug Design with a Deep Hierarchical Generative Model.

Recently, the remarkable growth of available crystal structure data and libraries of commercially available or readily synthesizable molecules have unlocked previously inaccessible regions of chemical space for drug development. Paired with improvements in virtual ligand screening methods, these expanded libraries are having a notable impact on early drug design efforts. Yet screening-based methods still face scalability limits, due to computational constraints and the sheer scale of drug-like space. Machine learning approaches are overcoming these limitations by learning the fundamental intra- and intermolecular relationships in drug-target systems from existing data. Here, we introduce DrugHIVE, a deep hierarchical variational autoencoder that outperforms state-of-the-art autoregressive and diffusion-based methods in both speed and performance on common generative benchmarks. DrugHIVE's hierarchical design enables improved control over molecular generation. Its capabilities include dramatically increasing virtual screening efficiency and accelerating a wide range of common drug design tasks, including de novo generation, molecular optimization, scaffold hopping, linker design, and high-throughput pattern replacement. Our highly scalable method can even be applied to receptors with high-confidence AlphaFold-predicted structures, extending the ability to generate high-quality drug-like molecules to a majority of the unsolved human proteome.

Transient road signals simulation strategy in a Stewart platform

In this article, a transient road signals simulation strategy in a Stewart platform is presented. Real world road signals are transient signals and thus the accurate simulation of its frequency, amplitude and damping components is key for further simulation of comfort. This simulation strategy combines a kinematic model and a transient signal reconstruction strategy using an autoregressive method. First, the developed experimental kinematic model on a Stewart platform is presented. Then, the procedure to simulate real-world transient road signals in the driving simulator is explained. Finally, the developed strategy has been validated under real road signals combined in the 6 degrees-of-freedom to prove the accuracy between the real world experimental measured signal and the simulated signal in the hexapod. The final goal of the presented transient road signals simulation strategy is to perform further vehicle dynamics and ride and comfort studies in the simulation phase using electric Stewart platforms.

Mitigating digital market risk with conventional, green, and Islamic bonds: Fresh insights from new hybrid deep learning models

We examine the impact of conventional, green, and Islamic bonds on the long-term memory of cryptocurrency market risk. Utilizing a time-varying parameter vector autoregressive deep learning model, we integrate time-varying parameter vector autoregressive methods with advanced deep learning sequence modeling architectures, including temporal convolutional network, gated recurrent unit, and long short-term memory for December 18, 2017, to April 19, 2024. Results indicate that incorporating all fixed-income securities reduces digital market risk. However, conventional and green bonds have a particularly strong impact on improving the long-term memory of digital market risk, while this is not the case for Sukuk.