Robust Stochastic Gradient Descent With Student-t Distribution Based First-Order Momentum

The role of artificial intelligence in the management of liver diseases

Universal neonatal hepatitis B virus (HBV) vaccination and the advent of direct-acting antivirals (DAA) against hepatitis C virus (HCV) have reshaped the epidemiology of chronic liver diseases. However, some aspects of the management of chronic liver diseases remain unresolved. Nucleotide analogs can achieve sustained HBV DNA suppression but rarely lead to a functional cure. Despite the high efficacy of DAAs, successful antiviral therapy does not eliminate the risk of hepatocellular carcinoma (HCC), highlighted the need for cost-effective identification of high-risk populations for HCC surveillance and tailored HCC treatment strategies for these populations. The accessibility of high-throughput genomic data has accelerated the development of precision medicine, and the emergence of artificial intelligence (AI) has led to a new era of precision medicine. AI can learn from complex, non-linear data and identify hidden patterns within real-world datasets. The combination of AI and multi-omics approaches can facilitate disease diagnosis, biomarker discovery, and the prediction of treatment efficacy and prognosis. AI algorithms have been implemented in various aspects, including non-invasive tests, predictive models, image diagnosis, and the interpretation of histopathology findings. AI can support clinicians in decision-making, alleviate clinical burdens, and curtail healthcare expenses. In this review, we introduce the fundamental concepts of machine learning and review the role of AI in the management of chronic liver diseases.

Investigating the closure stress and crack initiation stress in fractured rocks using the student t distribution and Monte Carlo simulation method

Traditional method of determining closure and initiation stress of fractured rocks by analyzing the stress-strain curve has problems such as strong subjectivity and large errors. This study utilized the rock closure stress values and onset stress values determined by three traditional methods, namely, axial strain method, fracture volume method and empirical value taking method, as the base database. The Student t distribution theory was used to obtain a confidence interval based on its overall distribution of values and to achieve a combination of the advantages of multiple methods. Within confidence interval, the Monte Carlo stochastic simulation was used to determine the convergence interval of the second stage to further improve the accuracy. Finally, mean value of the randomly sampled values after reaching the convergence stage was taken as the probability value of rock closure and crack initiation stress. The results showed that the 3 traditional methods for calculating rock closure and initiation stresses are significantly different. In contrast, the proposed method biases more towards multi-numerical distribution intervals and also considers the preference effects of different calculation methods. In addition, this method does not show any extreme values that deviate from the confidence intervals, and it has strong accuracy and stability compared to other methods.

GPS-Free Wireless Precise Positioning System for Automatic Flying and Landing Application of Shipborne Unmanned Aerial Vehicle

This research is dedicated to developing an automatic landing system for shipborne unmanned aerial vehicles (UAVs) based on wireless precise positioning technology. The application scenario is practical for specific challenging and complex environmental conditions, such as the Global Positioning System (GPS) being disabled during wartime. The primary objective is to establish a precise and real-time dynamic wireless positioning system, ensuring that the UAV can autonomously land on the shipborne platform without relying on GPS. This work addresses several key aspects, including the implementation of an ultra-wideband (UWB) circuit module with a specific antenna design and RF front-end chip to enhance wireless signal reception. These modules play a crucial role in achieving accurate positioning, mitigating the limitations caused by GPS inaccuracy, thereby enhancing the overall performance and reception range of the system. Additionally, the study develops a wireless positioning algorithm to validate the effectiveness of automatic landing on the shipborne platform. The platform's wave vibration is considered to provide a realistic landing system for shipborne UAVs. The UWB modules are practically installed on the shipborne platform, and the UAV and the autonomous three-body vessel are tested simultaneously in the outdoor open water space to verify the functionality, precision, and adaptability of the proposed UAV landing system. Results demonstrate that the UAV can autonomously fly from 200 m, approach, and automatically land on the moving shipborne platform without relying on GPS.

The WuC-Adam algorithm based on joint improvement of Warmup and cosine annealing algorithms

The Adam algorithm is a common choice for optimizing neural network models. However, its application often brings challenges, such as susceptibility to local optima, overfitting and convergence problems caused by unstable learning rate behavior. In this article, we introduce an enhanced Adam optimization algorithm that integrates Warmup and cosine annealing techniques to alleviate these challenges. By integrating preheating technology into traditional Adam algorithms, we systematically improved the learning rate during the initial training phase, effectively avoiding instability issues. In addition, we adopt a dynamic cosine annealing strategy to adaptively adjust the learning rate, improve local optimization problems and enhance the model's generalization ability. To validate the effectiveness of our proposed method, extensive experiments were conducted on various standard datasets and compared with traditional Adam and other optimization methods. Multiple comparative experiments were conducted using multiple optimization algorithms and the improved algorithm proposed in this paper on multiple datasets. On the MNIST, CIFAR10 and CIFAR100 datasets, the improved algorithm proposed in this paper achieved accuracies of 98.87%, 87.67% and 58.88%, respectively, with significant improvements compared to other algorithms. The experimental results clearly indicate that our joint enhancement of the Adam algorithm has resulted in significant improvements in model convergence speed and generalization performance. These promising results emphasize the potential of our enhanced Adam algorithm in a wide range of deep learning tasks.

Artificial intelligence predicts direct-acting antivirals failure among hepatitis C virus patients: A nationwide hepatitis C virus registry program

BACKGROUND/AIMS

Despite the high efficacy of direct-acting antivirals (DAAs), approximately 1-3% of hepatitis C virus (HCV) patients fail to achieve a sustained virological response. We conducted a nationwide study to investigate risk factors associated with DAA treatment failure. Machine-learning algorithms have been applied to discriminate subjects who may fail to respond to DAA therapy.

METHODS

We analyzed the Taiwan HCV Registry Program database to explore predictors of DAA failure in HCV patients. Fifty-five host and virological features were assessed using multivariate logistic regression, decision tree, random forest, eXtreme Gradient Boosting (XGBoost), and artificial neural network. The primary outcome was undetectable HCV RNA at 12 weeks after the end of treatment.

RESULTS

The training (n=23,955) and validation (n=10,346) datasets had similar baseline demographics, with an overall DAA failure rate of 1.6% (n=538). Multivariate logistic regression analysis revealed that liver cirrhosis, hepatocellular carcinoma, poor DAA adherence, and higher hemoglobin A1c were significantly associated with virological failure. XGBoost outperformed the other algorithms and logistic regression models, with an area under the receiver operating characteristic curve of 1.000 in the training dataset and 0.803 in the validation dataset. The top five predictors of treatment failure were HCV RNA, body mass index, α-fetoprotein, platelets, and FIB-4 index. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the XGBoost model (cutoff value=0.5) were 99.5%, 69.7%, 99.9%, 97.4%, and 99.5%, respectively, for the entire dataset.

CONCLUSION

Machine learning algorithms effectively provide risk stratification for DAA failure and additional information on the factors associated with DAA failure.

A Hybrid Localization Algorithm for an Adaptive Strategy-Based Distance Vector-Hop and Improved Sparrow Search for Wireless Sensor Networks

Wireless sensor networks (WSNs) are applied in many fields, among which node localization is one of the most important parts. The Distance Vector-Hop (DV-Hop) algorithm is the most widely used range-free localization algorithm, but its localization accuracy is not high enough. In this paper, to solve this problem, a hybrid localization algorithm for an adaptive strategy-based distance vector-hop and improved sparrow search is proposed (HADSS). First, an adaptive hop count strategy is designed to refine the hop count between all sensor nodes, using a hop count correction factor for secondary correction. Compared with the simple method of using multiple communication radii, this mechanism can refine the hop counts between nodes and reduce the error, as well as the communication overhead. Second, the average hop distance of the anchor nodes is calculated using the mean square error criterion. Then, the average hop distance obtained from the unknown nodes is corrected according to a combination of the anchor node trust degree and the weighting method. Compared with the single weighting method, both the global information about the network and the local information about each anchor node are taken into account, which reduces the average hop distance errors. Simulation experiments are conducted to verify the localization performance of the proposed HADSS algorithm by considering the normalized localization error. The simulation results show that the accuracy of the proposed HADSS algorithm is much higher than that of five existing methods.

The Synergy between Deep Learning and Organs-on-Chips for High-Throughput Drug Screening: A Review

Organs-on-chips (OoCs) are miniature microfluidic systems that have arguably become a class of advanced in vitro models. Deep learning, as an emerging topic in machine learning, has the ability to extract a hidden statistical relationship from the input data. Recently, these two areas have become integrated to achieve synergy for accelerating drug screening. This review provides a brief description of the basic concepts of deep learning used in OoCs and exemplifies the successful use cases for different types of OoCs. These microfluidic chips are of potential to be assembled as highly potent human-on-chips with complex physiological or pathological functions. Finally, we discuss the future supply with perspectives and potential challenges in terms of combining OoCs and deep learning for image processing and automation designs.

An Improved Adam Optimization Algorithm Combining Adaptive Coefficients and Composite Gradients Based on Randomized Block Coordinate Descent

An improved Adam optimization algorithm combining adaptive coefficients and composite gradients based on randomized block coordinate descent is proposed to address issues of the Adam algorithm such as slow convergence, the tendency to miss the global optimal solution, and the ineffectiveness of processing high-dimensional vectors. The adaptive coefficient is used to adjust the gradient deviation value and correct the search direction firstly. Then, the predicted gradient is introduced, and the current gradient and the first-order momentum are combined to form a composite gradient to improve the global optimization ability. Finally, the random block coordinate method is used to determine the gradient update mode, which reduces the computational overhead. Simulation experiments on two standard datasets for classification show that the convergence speed and accuracy of the proposed algorithm are higher than those of the six gradient descent methods, and the CPU and memory utilization are significantly reduced. In addition, based on logging data, the BP neural networks optimized by six algorithms, respectively, are used to predict reservoir porosity. Results show that the proposed method has lower system overhead, higher accuracy, and stronger stability, and the absolute error of more than 86% data is within 0.1%, which further verifies its effectiveness.

Classification of plug seedling quality by improved convolutional neural network with an attention mechanism

The classification of plug seedling quality plays an active role in enhancing the quality of seedlings. The EfficientNet-B7-CBAM model, an improved convolutional neural network (CNN) model, was proposed to improve classification efficiency and reduce high cost. To ensure that the EfficientNet-B7 model simultaneously learns crucial channel and spatial location information, the convolutional block attention module (CBAM) has been incorporated. To improve the model's ability to generalize, a transfer learning strategy and Adam optimization algorithm were introduced. A system for image acquisition collected 8,109 images of pepper plug seedlings, and data augmentation techniques improved the resulting data set. The proposed EfficientNet-B7-CBAM model achieved an average accuracy of 97.99% on the test set, 7.32% higher than before the improvement. Under the same experimental conditions, the classification accuracy increased by 8.88-20.05% to classical network models such as AlexNet, VGG16, InceptionV3, ResNet50, and DenseNet121. The proposed method had high accuracy in the plug seedling quality classification task. It was well-adapted to numerous types of plug seedlings, providing a reference for developing a fast and accurate algorithm for plug seedling quality classification.

Concrete Cracks Detection and Monitoring Using Deep Learning-Based Multiresolution Analysis

In this paper, we propose a new methodology for crack detection and monitoring in concrete structures. This approach is based on a multiresolution analysis of a sample or a specimen of concrete material subjected to several types of solicitation. The image obtained by ultrasonic investigation and processed by a customized wavelet is analyzed at various scales in order to detect internal cracks and crack initiation. The ultimate objective of this work is to propose an automatic crack type identification scheme based on convolutional neural networks (CNN). In this context, crack propagation can be monitored without access to the concrete surface and the goal is to detect cracks before they are visible. This is achieved through the combination of two major data analysis tools which are wavelets and deep learning. This original procedure is shown to yield a high accuracy close to 90%. In order to evaluate the performance of the proposed CNN architectures, we also used an open access database, SDNET2018, for the automatic detection of external cracks.

HyAdamC: A New Adam-Based Hybrid Optimization Algorithm for Convolution Neural Networks

As the performance of devices that conduct large-scale computations has been rapidly improved, various deep learning models have been successfully utilized in various applications. Particularly, convolution neural networks (CNN) have shown remarkable performance in image processing tasks such as image classification and segmentation. Accordingly, more stable and robust optimization methods are required to effectively train them. However, the traditional optimizers used in deep learning still have unsatisfactory training performance for the models with many layers and weights. Accordingly, in this paper, we propose a new Adam-based hybrid optimization method called HyAdamC for training CNNs effectively. HyAdamC uses three new velocity control functions to adjust its search strength carefully in term of initial, short, and long-term velocities. Moreover, HyAdamC utilizes an adaptive coefficient computation method to prevent that a search direction determined by the first momentum is distorted by any outlier gradients. Then, these are combined into one hybrid method. In our experiments, HyAdamC showed not only notable test accuracies but also significantly stable and robust optimization abilities when training various CNN models. Furthermore, we also found that HyAdamC could be applied into not only image classification and image segmentation tasks.

t-soft update of target network for deep reinforcement learning

This paper proposes a new robust update rule of target network for deep reinforcement learning (DRL), to replace the conventional update rule, given as an exponential moving average. The target network is for smoothly generating the reference signals for a main network in DRL, thereby reducing learning variance. The problem with its conventional update rule is the fact that all the parameters are smoothly copied with the same speed from the main network, even when some of them are trying to update toward the wrong directions. This behavior increases the risk of generating the wrong reference signals. Although slowing down the overall update speed is a naive way to mitigate wrong updates, it would decrease learning speed. To robustly update the parameters while keeping learning speed, a t-soft update method, which is inspired by Student-t distribution, is derived with reference to the analogy between the exponential moving average and the normal distribution. Through the analysis of the derived t-soft update, we show that it takes over the properties of the Student-t distribution. Specifically, with a heavy-tailed property of the Student-t distribution, the t-soft update automatically excludes extreme updates that differ from past experiences. In addition, when the updates are similar to the past experiences, it can mitigate the learning delay by increasing the amount of updates. In PyBullet robotics simulations for DRL, an online actor-critic algorithm with the t-soft update outperformed the conventional methods in terms of the obtained return and/or its variance. From the training process by the t-soft update, we found that the t-soft update is globally consistent with the standard soft update, and the update rates are locally adjusted for acceleration or suppression.