Stochastic Gradient Descent Optimization Research Articles

Class-Incremental Learning Method With Fast Update and High Retainability Based on Broad Learning System.

Machine learning aims to generate a predictive model from a training dataset of a fixed number of known classes. However, many real-world applications (such as health monitoring and elderly care) are data streams in which new data arrive continually in a short time. Such new data may even belong to previously unknown classes. Hence, class-incremental learning (CIL) is necessary, which incrementally and rapidly updates an existing model with the data of new classes while retaining the existing knowledge of old classes. However, most current CIL methods are designed based on deep models that require a computationally expensive training and update process. In addition, deep learning based CIL (DCIL) methods typically employ stochastic gradient descent (SGD) as an optimizer that forgets the old knowledge to a certain extent. In this article, a broad learning system-based CIL (BLS-CIL) method with fast update and high retainability of old class knowledge is proposed. Traditional BLS is a fast and effective shallow neural network, but it does not work well on CIL tasks. However, our proposed BLS-CIL can overcome these issues and provide the following: 1) high accuracy due to our novel class-correlation loss function that considers the correlations between old and new classes; 2) significantly short training/update time due to the newly derived closed-form solution for our class-correlation loss without iterative optimization; and 3) high retainability of old class knowledge due to our newly derived recursive update rule for CIL (RULL) that does not replay the exemplars of all old classes, as contrasted to the exemplars-replaying methods with the SGD optimizer. The proposed BLS-CIL has been evaluated over 12 real-world datasets, including seven tabular/numerical datasets and six image datasets, and the compared methods include one shallow network and seven classical or state-of-the-art DCIL methods. Experimental results show that our BIL-CIL can significantly improve the classification performance over a shallow network by a large margin (8.80%-48.42%). It also achieves comparable or even higher accuracy than DCIL methods, but greatly reduces the training time from hours to minutes and the update time from minutes to seconds.

An efficient method for disaster tweets classification using gradient-based optimized convolutional neural networks with BERT embeddings

Event of the disastrous scenarios are actively discussed on microblogging platforms like Twitter which can lead to chaotic situations. In the era of machine learning and deep learning, these chaotic situations can be effectively controlled by developing efficient methods and models that can assist in classifying real and fake tweets. In this research article, an efficient method named BERT Embedding based CNN model with RMSProp Optimizer is proposed to effectively classify the tweets related disastrous scenario. Tweet classification is carried out via some of the popular the machine learning algorithms such as logistic regression and decision tree classifiers. Noting the low accuracy of machine learning models, Convolutional Neural Network (CNN) based deep learning model is selected as the primary classification method. CNNs performance is improved via optimization of the parameters with gradient based optimizers. To further elevate accuracy and to capture contextual semantics from the text data, BERT embeddings are included in the proposed model. The performance of proposed method - BERT Embedding based CNN model with RMSProp Optimizer achieved an F1 score of 0.80 and an Accuracy of 0.83. The methodology presented in this research article is comprised of the following key contributions:•Identification of suitable text classification model that can effectively capture complex patterns when dealing with large vocabularies or nuanced language structures in disaster management scenarios.•The method explores the gradient based optimization techniques such as Adam Optimizer, Stochastic Gradient Descent (SGD) Optimizer, AdaGrad, and RMSprop Optimizer to identify the most appropriate optimizer that meets the characteristics of the dataset and the CNN model architecture.•“BERT Embedding based CNN model with RMSProp Optimizer” – a method to classify the disaster tweets and capture semantic representations by leveraging BERT embeddings with appropriate feature selection is presented and models are validated with appropriate comparative analysis.

Image Data Acquisition and Classification of Vannamei Shrimp Cultivation Results Based on Deep Learning

This research aimed to employ deep learning techniques to address the classification of Litopenaeus vannamei cultivation results in land ponds and tarpaulin ponds. Despite their similar appearance, distinguishable differences exist in various aspects such as color, shape, size, and market price between the two cultivation methods, often leading to consumer confusion and potential exploitation by irresponsible sellers. To mitigate this challenge, the research proposed a classification method utilizing two Convolutional Neural Network (CNN) architectures: Visual Geometry Group-16 (VGG-16) and Residual Network-50 (ResNet-50), renowned for their success in various image recognition applications. The dataset comprised 2,080 images per class of vannamei shrimp from both types of ponds. Augmentation techniques enhanced the dataset’s diversity and sample size, reinforcing the model’s ability to discern shrimp morphology variations. Experiments were conducted with learning rates of 0.001 and 0.0001 on the Stochastic Gradient Descent (SGD) and Adaptive Moment Estimation (ADAM) optimizers to evaluate their effectiveness in model training. The VGG-16 and ResNet-50 models were trained with a learning rate parameter of 0.0001, leveraging the flexibility and reasonable control provided by the SGD optimizer. Lower learning rate values were chosen to prevent overfitting and enhance training stability. The model evaluation demonstrated promising results, with both architectures achieving 100% accuracy in classifying vannamei shrimp from soil ponds and tarpaulin ponds. Furthermore, experimental findings highlight the superiority of using SGD with a learning rate of 0.0001 over 0.001 on both architectures, underscoring the significant impact of optimizer and learning rate selection on model training effectiveness in image classification tasks.

An Improved Reacceleration Optimization Algorithm Based on the Momentum Method for Image Recognition

The optimization algorithm plays a crucial role in image recognition by neural networks. However, it is challenging to accelerate the model’s convergence and maintain high precision. As a commonly used stochastic gradient descent optimization algorithm, the momentum method requires many epochs to find the optimal parameters during model training. The velocity of its gradient descent depends solely on the historical gradients and is not subject to random fluctuations. To address this issue, an optimization algorithm to enhance the gradient descent velocity, i.e., the momentum reacceleration gradient descent (MRGD), is proposed. The algorithm utilizes the point division of the current momentum and the gradient relationship, multiplying it with the gradient. It can adjust the update rate and step size of the parameters based on the gradient descent state, so as to achieve faster convergence and higher precision in training the deep learning model. The effectiveness of this method is further proven by applying the reacceleration mechanism to the Adam optimizer, resulting in the MRGDAdam algorithm. We verify both algorithms using multiple image classification datasets, and the experimental results show that the proposed optimization algorithm enables the model to achieve higher recognition accuracy over a small number of training epochs, as well as speeding up model implementation. This study provides new ideas and expansions for future optimizer research.

Deep learning–based urban energy forecasting model for residential building energy efficiency

Sustainable and inventive city design is becoming more and more dependent on the use of cutting-edge technology as smart cities develop further. Energy efficiency optimization in residential structures is an essential part of the puzzle as it helps conserve resources and keeps the planet habitable. An enhanced Deep Neural Network (DNN) model for household energy efficiency predictions is presented in this research. Our model uses a large dataset of building features, weather, occupancy patterns and energy usage histories. Data is preprocessed, features are engineered and hyperparameters are tweaked to improve DNN prediction. Scalable, easy-to-understand models are essential, as are shifting urban areas and energy landscapes. In this work, the authors have evaluated the proposed model with basic model with different optimizers. Initially, the Stochastic Gradient Descent optimizer applied that gained 91.02% Recall, 93.47% Precision, 93.28% F1-Score, 0.0153 MSE, 0.0166 RMSE and 0.0165 MAE. The proposed model gained 99.52% Recall, 98.91% Precision, 99.09% F1-Score, 0.0140 MSE, 0.0137 RMSE and 0.0139 MAE. By monitoring, analyzing and making decisions in real time, smart city systems can help planners understand energy usage trends. The optimized DNN model advances smart city development by promoting sustainability and resource optimization. Predicting residential buildings’ energy efficiency provides proactive energy savings, cost reduction and environmental impact mitigation. The suggested DNN model shows how smart cities use cutting-edge urban planning to become more sustainable, efficient and resilient.

Leveraging YOLOv5s with optimization‐based effective anomaly detection in pedestrian walkways

AbstractCurrently, video surveillance is generally used to safeguard safety in public places like railway stations, traffic signals, malls, and so on. Video anomaly recognition and localization are the main components of the intelligent video surveillance method. Video anomaly recognition refers to the procedure of spatiotemporal localization of the abnormal design existing in the video. A main task in video surveillance is the classification of anomalies that occur in it like thefts, crimes, and so forth. Also, anomaly recognition in pedestrian walkways has enlarged major attention among the computer vision (CV) groups to improve pedestrian protection. The current developments in Deep Learning (DL) methods have great attention to dissimilar procedures like image classification, object recognition, and so forth. This study designs an Optimal Deep Learning for Effective Anomaly Detection in Pedestrian Walkways (ODL‐EADPW) model. The ODL‐EADPW technique employs a fine‐tuned DL model for the identification of pedestrians and anomalies in the walkways. In the ODL‐EADPW technique, the image pre‐processing is primarily involved in two stages median filtering (MF) based noise removal and adaptive histogram equalization (AHE)‐based contrast enhancement. For anomaly detection in pedestrian walkways, the ODL‐EADPW technique uses the YOLOv5s model with EfficientRep as a backbone network. To enhance the detection results of the ODL‐EADPW technique, a stochastic gradient descent (SGD) optimizer was employed to perfect the hyperparameters of the EfficientRep model. The performance evaluation of the ODL‐EADPW methodology is implemented on the UCSD Anomaly detection dataset. An extensive comparison study stated that the ODL‐EADPW technique gains effectual detection results over other DL models in terms of different measures.

Real-time decomposition technique for compressive light field display using the multiplex correlations

How to compress and decompose the high-dimensional light field information in real time is still a challenging task for compressive light field display. Traditional iterative algorithms suffer from slow convergence speed and limited image quality. Therefore, a real-time decomposition technique for compressive light field display using multiplex correlations is proposed. Firstly, the iteration initial value of the algorithm is optimized, by utilizing the spatial correlations of pixel multiplex light fields, which significantly improves the convergence speed and reduces noise. Secondly, the iterative task of high-dimensional matrix in the non-negative matrix factorization (NMF) algorithm is divided into highly parallel linear iterative tasks. A stochastic gradient descent (SGD) optimizer and GPU are used to parallel compress and decompose the light fields. Thirdly, addresses of light field data are reordered using the sign distance field (SDF) transformation in sheared camera frustum space, making the addressing process of compression and decomposition more efficient. A rendering pipeline is constructed that renders the compressive light fields using 3D model data directly. For a light field containing 5 × 5 viewpoints and 1024 × 1024 × 2 pixels, only 2-3 iterations are needed to approach the optimal solution. The decomposition efficiency is increased by 15.24 times. The frame rate of decomposition exceeds 30 frames per second (fps). A compressive light field display system has been built to realize 3D display, verifying the feasibility of the technique.

A deep learning-based quantitative prediction model for the processing potentials of soybeans as soymilk raw materials

Current technologies as correlation analysis, regression analysis and classification model, exhibited various limitations in the evaluation of soybean possessing potentials, including single, vague evaluation and failure of quantitative prediction, and thereby hindering more efficient and profitable soymilk industry. To solve this problem, 54 soybean cultivars and their corresponding soymilks were subjected to chemical, textural, and sensory analyses to obtain the soybean physicochemical nature (PN) and the soymilk profit and quality attribute (PQA) datasets. A deep-learning based model was established to quantitatively predict PQA data using PN data. Through 45 rounds of training with the stochastic gradient descent optimization, 9 remaining pairs of PN and PQA data were used for model validation. Results suggested that the overall prediction performance of the model showed significant improvements through iterative training, and the trained model eventually reached satisfying predictions (|relative error| ≤ 20%, standard deviation of relative error ≤ 40%) on 78% key soymilk PQAs. Future model training using big data may facilitate better prediction on soymilk odor qualities.

An automated learning model for twitter sentiment analysis using Ranger AdaBelief optimizer based Bidirectional Long Short Term Memory

AbstractSentiment analysis is an automated approach which is utilized in process of analysing textual data to describe public opinion. The sentiment analysis has major role in creating impact in the day‐to‐day life of individuals. However, a precise interpretation of text still relies as a major concern in classifying sentiment. So, this research introduced Bidirectional Long Short Term Memory with Ranger AdaBelief Optimizer (Bi‐LSTM RAO) to classify sentiment of tweets. Initially, data is obtained from Twitter API, Sentiment 140 and Stanford Sentiment Treebank‐2 (SST‐2). The raw data is pre‐processed and it is subjected to feature extraction which is performed using Bag of Words (BoW) and Term Frequency‐Inverse Document Frequency (TF‐IDF). The feature selection is performed using Gazelle Optimization Algorithm (GOA) which removes the irrelevant or redundant features that maximized model performance and classification is performed using Bi LSTM–RAO. The RAO optimizes the loss function of Bi‐LSTM model that maximized accuracy. The classification accuracy of proposed method for Twitter API, Sentiment 140 and SST 2 dataset is obtained as 909.44%, 99.71% and 99.86%, respectively. These obtained results are comparably higher than ensemble framework, Robustly Optimized BERT and Gated Recurrent Unit (RoBERTa‐GRU), Logistic Regression‐Long Short Term Memory (LR‐LSTM), Convolutional Bi‐LSTM, Sentiment and Context Aware Attention‐based Hybrid Deep Neural Network (SCA‐HDNN) and Stochastic Gradient Descent optimization based Stochastic Gate Neural Network (SGD‐SGNN).

A modified time adaptive self-organizing map with stochastic gradient descent optimizer for automated food recognition system

Numerous decades of study have been devoted to associating artificial intelligence and culinary type recognition. Automated food identification systems are significant in many disciplines, comprising dietary valuation, menu analysis, and nutritional tracking. In the past, traditional image analysis algorithms caused in poor classification accuracy, but deep learning methods have enabled the identification of food types and its constituents. This study proposed a novel method to develop food recognition competence and accuracy by connecting a Stochastic Gradient Descent (SGD) optimizer to a Modified Time Adaptive Self-Organizing Map (MTA-SOM). Food arrival differences subsequent from lighting, changing perspectives, and occlusions sometimes provide challenges to traditional food recognition algorithms. In this research, propose an MTA-SOM that learns and adapts to changing food item appearances by dynamically changing its topology over time. This research leverages the self-organizing possessions of SOMs and the fine-tuning properties of SGD by relating the MTA-SOM and the SGD optimizer, thereby maximizing the advantages of both techniques. The research method includes collecting a large number of food images from a difference of cuisines and presentation styles in order to assess the effectiveness of the proposed method. This proposed method performs an extensive test and connect MTA-SOM and SGD to present approaches of food recognition. Important advances in precision and robustness are produced as the system learns to recognize food items more precisely and adapts to changes in food appearance. By automating food detection with high precision and adaptability, our method could revolutionize our capability to interact with food-related data and offer important insights into dietary practices and nutritious decisions.

Deep Learning Model for Colon Cancer Classification using InceptionV3

Colon cancer is a significant global public health concern, necessitating an accurate and timely diagnosis for effective treatment. Leveraging advancements in deep learning, this study proposes a novel approach to colon cancer classification using InceptionV3 convolutional neural network architecture. A dataset comprising 1600 colonoscopy images divided into colon_aca (adenocarcinoma) and colon_n (normal) classes was utilized. The model demonstrated promising performance, achieving a training accuracy of 98.86% and a validation accuracy of 99.74% after 100 epochs. This success was accomplished by employing a Stochastic Gradient Descent (SGD) optimizer with a learning rate of 0.0001 and momentum of 0.9, along with categorical cross-entropy loss. Our findings underscore the importance of deep learning models, specifically InceptionV3, in facilitating the precise classification of colon cancer, thus offering a valuable tool for assisting clinicians in early detection and treatment decision-making. Future research may explore the integration of additional clinical data and the evaluation of alternative deep learning architectures to further enhance diagnostic accuracy.

SDGMNet: Statistic-Based Dynamic Gradient Modulation for Local Descriptor Learning

Rescaling the backpropagated gradient of contrastive loss has made significant progress in descriptor learning. However, current gradient modulation strategies have no regard for the varying distribution of global gradients, so they would suffer from changes in training phases or datasets. In this paper, we propose a dynamic gradient modulation, named SDGMNet, for contrastive local descriptor learning. The core of our method is formulating modulation functions with dynamically estimated statistical characteristics. Firstly, we introduce angle for distance measure after deep analysis on backpropagation of pair-wise loss. On this basis, auto-focus modulation is employed to moderate the impact of statistically uncommon individual pairs in stochastic gradient descent optimization; probabilistic margin cuts off the gradients of proportional triplets that have achieved enough optimization; power adjustment balances the total weights of negative pairs and positive pairs. Extensive experiments demonstrate that our novel descriptor surpasses previous state-of-the-art methods in several tasks including patch verification, retrieval, pose estimation, and 3D reconstruction.

An Improved Skin Lesion Classification Using a Hybrid Approach with Active Contour Snake Model and Lightweight Attention-Guided Capsule Networks.

Skin cancer is a prevalent type of malignancy on a global scale, and the early and accurate diagnosis of this condition is of utmost importance for the survival of patients. The clinical assessment of cutaneous lesions is a crucial aspect of medical practice, although it encounters several obstacles, such as prolonged waiting time and misinterpretation. The intricate nature of skin lesions, coupled with variations in appearance and texture, presents substantial barriers to accurate classification. As such, skilled clinicians often struggle to differentiate benign moles from early malignant tumors in skin images. Although deep learning-based approaches such as convolution neural networks have made significant improvements, their stability and generalization continue to experience difficulties, and their performance in accurately delineating lesion borders, capturing refined spatial connections among features, and using contextual information for classification is suboptimal. To address these limitations, we propose a novel approach for skin lesion classification that combines snake models of active contour (AC) segmentation, ResNet50 for feature extraction, and a capsule network with a fusion of lightweight attention mechanisms to attain the different feature channels and spatial regions within feature maps, enhance the feature discrimination, and improve accuracy. We employed the stochastic gradient descent (SGD) optimization algorithm to optimize the model's parameters. The proposed model is implemented on publicly available datasets, namely, HAM10000 and ISIC 2020. The experimental results showed that the proposed model achieved an accuracy of 98% and AUC-ROC of 97.3%, showcasing substantial potential in terms of effective model generalization compared to existing state-of-the-art (SOTA) approaches. These results highlight the potential for our approach to reshape automated dermatological diagnosis and provide a helpful tool for medical practitioners.

The Investigation of Multiple Optimization Methods on Convolutional Neural Network

In this study, the optimization of a Convolutional Neural Network (CNN) was conducted using the Fruits 360 dataset, with a specific emphasis on the impacts of Spatial Transformer Network (STN) and Stochastic Gradient Descent (SGD) optimization methods. Firstly, a baseline CNN model is built, which achieves 97.84% accuracy with a loss of 0.0999 after 50 epochs. Then, the impact of integrating STN and SGD into CNN models separately is investigated. The addition of STN slightly increased the accuracy to 97.92%, reduced the loss to 0.0994, and decreased the validation accuracy. This result suggests that while STN enhances the model's generalization ability, it may slightly reduce the maximum accuracy achievable on the validation set. After SGD optimization, the verification accuracy is increased to 98.19%, the loss is reduced to 0.0537, and the verification accuracy is increased to 98.40%. These results highlight the effectiveness of SGD in fine-tuning model parameters, resulting in more accurate models and improved generalization capabilities. A comparative analysis of these methods highlights their respective advantages. The effectiveness of the STN is rooted in its capacity to improve model generalization and mitigate overfitting, which is particularly beneficial in situations that demand robustness against varied data sets. In contrast, SGD stands out for its ability to significantly improve model accuracy and reduce loss, making it a balanced choice for comprehensive model optimization. Future research directions include exploring these optimization techniques on various datasets and investigating the potential of combining STN and SGD to achieve higher performance in CNN models.

Hybrid learning of predictive mobile-edge computation offloading under differently-aged network states

By offloading computationally demanding applications to edge servers, mobile edge computing (MEC) can alleviate the stringent hardware requirements and save energy consumption of resource-restrained devices. Mobile edge computation offloading (MECO, i.e., optimizing computation offloading and resource allocation) is critical to the performance of MEC. However, the existing study typically assumed the availability of all the network states for the upcoming time slot, not applicable in practical MECO with differently-aged network states (e.g., fast-changing practical wireless channels and instantly observable local task arrivals). This paper proposes a novel hybrid learning approach that optimizes the instantaneous local processing and predictive computation offloading decisions. We establish a new hybrid learning approach for instantaneous local processing and predictive computation offloading decisions by integrating the learning techniques of stochastic gradient descent (SGD) and online convex optimization (OCO). By decomposing the primal problems, the proposed approach can be implemented in a decentralized manner. We prove that the optimality loss resulting from the differently-aged network states can diminish with the decreasing stepsizes of SGD and OCO. Simulation results validate the asymptotic optimality and superiority of the proposed hybrid learning approach, as compared to state-of-the-art (e.g., based on OCO techniques).

TrioConvTomatoNet: A robust CNN architecture for fast and accurate tomato leaf disease classification for real time application

Tomato leaf diseases are a common threat to long-term tomato protection that affects many farmers worldwide. Computer-assisted technology is more prevalent for early and accurate diagnosis of tomato leaf diseases, which may reduce the likelihood that the plant will suffer further harm. The advancement of deep learning techniques has a lot of potential for accurate classification of leaf diseases through an automated feature extraction topology. By changing the network layers and their parameters in the feature extraction topology, it is possible to extract the exact features and improve the classification accuracy. In this study, TrioConvTomatoNet, novel deep convolutional neural network architecture, is proposed, which includes a 3-series convolution layer under each stage of the feature extraction topology to capture and integrate the information from the leaf images efficiently. To improve the network's learning ability and perform accurate classifications, the proposed method incorporates the stochastic gradient descent optimizer. In order to facilitate proper learning, a separate dataset preparation strategy was followed for tomato leaf image dataset collection, which includes existing and real-time images. This research is carried out with varying the number of convolution layers to express the effectiveness of the proposed method in capturing and integrating information from the leaf images. Also, the extensive experiments on an unseen dataset collection with and without augmentation express the superiority and robustness of TrioConvTomatoNet in terms of both accuracy and speed when compared to state-of-the-art methods. The proposed method achieves remarkable accuracy of about 99.39% in disease classification while processing both existing database and real-time images, making it suitable for practical deployment in agricultural settings.

An ensemble deep learning model for automatic classification of cotton leaves diseases

<p>Cotton plant (Gossypium herbaceum), is one of the significant fiber crop grown worldwide. However, the crop is quite prone to leaves diseases, for which deep learning (DL) techniques can be utilized for early disease prediction and prevent stakeholders from losing the harvest. The objective of this paper is to develop a novel ensemble based deep convolutional neural network (DCNN) model developed on two base pretrained models named: VGG16 and InceptionV3 for early detection of cotton leaves diseases. The proposed ensemble model trained on cotton leaves dataset reports higher training and testing prediction accuracies as compared to the base pretrained models. Given that, deep learning architectures have hyper-parameters, this paper presents exhaustive experimental evaluations on ensemble model to tune hyper-parameters named learning rate, optimizer and no of epochs. The suggested hyper-parameter settings can be directly utilized while employing the ensemble model for cotton plant leaves disease detection and prediction. With suggested hyper-parameters settings of learning rate 0.0001, 20 epochs and stochastic gradient descent (SGD) optimizer, ensemble model reported training and testing accuracies of 98% and 95% respectively, which was higher than the training and testing accuracies of VGG16 and InceptionV3 pretrained DCNN models.</p>

Telugu letters dataset and parallel deep convolutional neural network with a SGD optimizer model for TCR

<p>Because of the rapid growth in technology breakthroughs, including multimedia and cell phones, Telugu character recognition (TCR) has recently become a popular study area. It is still necessary to construct automated and intelligent online TCR models, even if many studies have focused on offline TCR models. The Telugu character dataset construction and validation using an Inception and ResNet-based model are presented. The collection of 645 letters in the dataset includes 18 Achus, 38 Hallus, 35 Othulu, 34×16 Guninthamulu, and 10 Ankelu. The proposed technique aims to efficiently recognize and identify distinctive Telugu characters online. This model's main pre-processing steps to achieve its goals include normalization, smoothing, and interpolation. Improved recognition performance can be attained by using stochastic gradient descent (SGD) to optimize the model's hyperparameters.</p>

Performance analysis of data resampling on class imbalance and classification techniques on multi-omics data for cancer classification.

Cancer, in any of its forms, remains a significant public health concern worldwide. Advances in early detection and treatment could lead to a decline in the overall death rate from cancer in recent decades. Therefore, tumor prediction and classification play an important role in fighting cancer. This study built computational models for a joint analysis of RNA seq, copy number variation (CNV), and DNA methylation to classify normal and tumor samples across liver cancer, breast cancer, and colon adenocarcinoma from The Cancer Genome Atlas (TCGA) dataset. Total of 18 machine learning methods were evaluated based on the AUC, precision, recall, and F-measure. Besides, five techniques were compared to ameliorate problems of class imbalance in the cancer datasets. Synthetic Minority Oversampling Technique (SMOTE) demonstrated the best performance. The results indicate that the model applying Stochastic Gradient Descent (SGD) for learning binary class SVM with hinge loss has the highest classification results on liver cancer and breast cancer datasets, with accuracy over 99% and AUC greater than or equal to 0.999. For colon adenocarcinoma dataset, both SGD and Sequential Minimal Optimization (SMO) that implements John Platt's sequential minimal optimization algorithm for training a support vector machine shows an outstanding classification performance with accuracy of 100%, AUC, precision, recall, and F-measure all at 1.000.

Artificial intelligence-based model for predicting pulmonary arterial hypertension on chest x-ray images.

Pulmonary arterial hypertension is a serious medical condition. However, the condition is often misdiagnosed or a rather long delay occurs from symptom onset to diagnosis, associated with decreased 5-year survival. In this study, we developed and tested a deep-learning algorithm to detect pulmonary arterial hypertension using chest X-ray (CXR) images. From the image archive of Chiba University Hospital, 259 CXR images from 145 patients with pulmonary arterial hypertension and 260 CXR images from 260 control patients were identified; of which 418 were used for training and 101 were used for testing. Using the testing dataset for each image, the algorithm outputted a numerical value from 0 to 1 (the probability of the pulmonary arterial hypertension score). The training process employed a binary cross-entropy loss function with stochastic gradient descent optimization (learning rate parameter, α = 0.01). In addition, using the same testing dataset, the algorithm's ability to identify pulmonary arterial hypertension was compared with that of experienced doctors. The area under the curve (AUC) of the receiver operating characteristic curve for the detection ability of the algorithm was 0.988. Using an AUC threshold of 0.69, the sensitivity and specificity of the algorithm were 0.933 and 0.982, respectively. The AUC of the algorithm's detection ability was superior to that of the doctors. The CXR image-derived deep-learning algorithm had superior pulmonary arterial hypertension detection capability compared with that of experienced doctors.