Hyperparameter optimized deep learning models for multiclass oral lesion classification in proprietary histopathological image Data

In the task of music genre classification, feature extraction and classifier modeling are the two key parts that directly affect the classification accuracy. In the traditional classification method, the feature extraction and classification processes are designed separately. First, the features are extracted manually from the original music signal, and then a reasonable classifier is selected to build a model and classify the extracted features. Although the traditional methods have achieved good results in many classification tasks, the feature extraction process is complex and difficult to achieve, and the features required for different classification tasks need to be specially designed, and the extracted features lack of universality. With the successful application and continuous development of deep learning models in other fields, more and more studies begin to use music spectra as the input of deep learning models to classify music genres. However, so far, the accuracy of existing classification methods based on deep learning is not ideal, so this paper mainly studies a classification method based on deep learning to improve the classification accuracy of music genre classification model. In this paper, a parallel structured deep attention classification model is proposed. By training BRNN, it can automatically learn music features from samples. The linear attention model calculates the attention probability distribution on this feature according to the learned features, and reassigns it to the feature representation. Finally, the classification is realized according to the eigenvectors with different weights. Besides the linear attention model with simple structure, a CNN attention model with stronger learning ability is also designed. In order to verify the feasibility and validity of the model, validation experiments were conducted on two standard datasets, GTZAN and Extended Ballroom. The experimental results show that the classification model based on deep parallel attention mechanism has good classification robustness, and the accuracy of classification based on BRNN and parallel CNN attention model reaches 92.7% on Extended Ballroom data set, which is better than the existing classification method based on deep learning. The validity and feasibility of the classification model are proved.

Improving classification accuracy of motor imagery-based brain computer interface (MI-BCI) systems has been discussed widely in the BCI research community. Analyses of multi-class MI data are challenging because feature extraction and classification of these data are more difficult as compared with those applied to binary-class data. This paper introduces a new model for multi-class MI-BCI data classification. The approach encompasses two main stages: feature extraction and fuzzy classification. In the feature extraction phase, a common spatial pattern algorithm is employed to extract significant discriminant features from the multi-class data. The obtained features serve as inputs to a fuzzy classifier that is designed by fusing the fuzzy standard additive model and particle swarm optimization method. The proposed fuzzy model aims to handle uncertainty, noise, and outliers existed in MI-BCI data. Experimental studies are carried out using two benchmark BCI competition data sets. Our results show the effectiveness of the fuzzy classifier against its competing techniques. The proposed model paths the way for paralysed or disordered patients to use movement imagery to control different assistive devices in their daily activities.

To review studies on deep learning (DL) models for classification, detection, and segmentation of rib fractures in CT data, to determine their risk of bias (ROB), and to analyse the performance of acute rib fracture detection models. Research articles written in English were retrieved from PubMed, Embase, and Web of Science in April 2023. A study was only included if a DL model was used to classify, detect, or segment rib fractures, and only if the model was trained with CT data from humans. For the ROB assessment, the Quality Assessment of Diagnostic Accuracy Studies tool was used. The performance of acute rib fracture detection models was meta-analysed with forest plots. A total of 27 studies were selected. About 75% of the studies have ROB by not reporting the patient selection criteria, including control patients or using 5-mm slice thickness CT scans. The sensitivity, precision, and F1-score of the subgroup of low ROB studies were 89.60% (95%CI, 86.31%-92.90%), 84.89% (95%CI, 81.59%-88.18%), and 86.66% (95%CI, 84.62%-88.71%), respectively. The ROB subgroup differences test for the F1-score led to a p-value below 0.1. ROB in studies mostly stems from an inappropriate patient and data selection. The studies with low ROB have better F1-score in acute rib fracture detection using DL models. This systematic review will be a reference to the taxonomy of the current status of rib fracture detection with DL models, and upcoming studies will benefit from our data extraction, our ROB assessment, and our meta-analysis.

Automatic depression classification from multimodal input data is a challenging task. Modern methods use paralinguistic information such as audio and video signals. Using linguistic information such as speech signals and text data for depression classification is a complicated task in deep learning models. Best audio and video features are built to produce a dependable depression classification system. Textual signals related to depression classification are analyzed using text-based content data. Moreover, to increase the achievements of the depression classification system, audio, visual, and text descriptors are used. So, a deep learning-based depression classification model is developed to detect the person with depression from multimodal data. The EEG signal, Speech signal, video, and text are gathered from standard databases. Four stages of feature extraction take place. In the first stage, the features from the decomposed EEG signals are attained by the empirical mode decomposition (EMD) method, and features are extracted by means of linear and nonlinear feature extraction. In the second stage, the spectral features of the speech signals from the Mel-frequency cepstral coefficients (MFCC) are extracted. In the third stage, the facial texture features from the input video are extracted. In the fourth stage of feature extraction, the input text data are pre-processed, and from the pre-processed data, the textual features are extracted by using the Transformer Net. All four sets of features are optimally selected and combined with the optimal weights to get the weighted fused features using the enhanced mountaineering team-based optimization algorithm (EMTOA). The optimal weighted fused features are finally given to the hybrid attention-based dilated network (HADN). The HDAN is developed by combining temporal convolutional network (TCN) with bidirectional long short-term memory (Bi-LSTM). The parameters in the HDAN are optimized with the assistance of the developed EMTOA algorithm. At last, the classified output of depression is obtained from the HDAN. The efficiency of the developed deep learning HDAN is validated by comparing it with various traditional classification models.

Distinguishing between a dangerous audio event like a gun firing and other non-life-threatening events, such as a plastic bag bursting, can mean the difference between life and death and, therefore, the necessary and unnecessary deployment of public safety personnel. Sounds generated by plastic bag explosions are often confused with real gunshot sounds, by either humans or computer algorithms. As a case study, the research reported in this paper offers insight into sounds of plastic bag explosions and gunshots. An experimental study in this research reveals that a deep learning-based classification model trained with a popular urban sound dataset containing gunshot sounds cannot distinguish plastic bag pop sounds from gunshot sounds. This study further shows that the same deep learning model, if trained with a dataset containing plastic pop sounds, can effectively detect the non-life-threatening sounds. For this purpose, first, a collection of plastic bag-popping sounds was recorded in different environments with varying parameters, such as plastic bag size and distance from the recording microphones. The audio clips’ duration ranged from 400 ms to 600 ms. This collection of data was then used, together with a gunshot sound dataset, to train a classification model based on a convolutional neural network (CNN) to differentiate life-threatening gunshot events from non-life-threatening plastic bag explosion events. A comparison between two feature extraction methods, the Mel-frequency cepstral coefficients (MFCC) and Mel-spectrograms, was also done. Experimental studies conducted in this research show that once the plastic bag pop sounds are injected into model training, the CNN classification model performs well in distinguishing actual gunshot sounds from plastic bag sounds.

Rapid improvements in the world of information technology have resulted in a demand for data collecting and the act of storing data for future retrieval. As a result, many businesses and organisations are driven to collect and store massive amounts of data in the data warehouse, a recently built database module. Data classification is a strategy for building a data classifier model that describes the relevant data classes and allows for a better comprehension of the data. It is important to highlight that this data classification approach is not well defined and is a non-deterministic process because there is no guarantee that the data classifier model constructed from past data would work better for future data. In the light of these facts, this chapter discusses the data classification method and its usefulness in the engineering and science fields. The significance and need for a research contribution for data classification using various machine learning models with optimization methods are highlighted, bringing the research work’s aims to light. In this chapter, the various approaches used for designing and developing classifier models, as well as their benefits and drawbacks, are discussed, as well as the hybrid support vector machine with grey wolf optimization (HSVMGWO) used to classify the various datasets. After a thorough evaluation, the proposed HSVMGWO method outperformed the four types of conventional methods: random forest, support vector machine, ada boost algorithm, and finally decision tree, with an efficiency of 95.3 percent, sensitivity of 97.08 percent, specificity of 95.68 percent, and time responsibility of 13.186 M.sec. Statistical study of accuracy values and calculation time shows that the proposed schemes outperform existing approaches.KeywordsGrey wolf optimizationSupport vector machineMultivariate datasetRandom forestAda boost algorithmDecision tree

In the digital era, machine learning and deep learning have become indispensable tools for bioinformatics, particularly in analyzing high-dimensional gene expression data for cancer diagnosis and classification. This study leverages the CuMiDa brain cancer dataset, a curated microarray database with 54,676 genes and 130 samples, to evaluate the effectiveness of deep learning models integrated with dimensionality reduction techniques. Principal Component Analysis (PCA) and Truncated Singular Value Decomposition (TruncatedSVD) were employed to address the challenges of high-dimensional data, reducing noise and computational complexity. Three deep learning models—DNN, MLP, and TabNet—were implemented with various optimizers, including ADAM, RMSprop, and SGD. Results showed that TruncatedSVD outperformed PCA in minimizing loss, especially for MLP with LBFGS optimizers, achieving near-zero loss. TabNet demonstrated the highest classification accuracy (96%) with ADAM and RMSprop. Conversely, SGD exhibited suboptimal performance across models. These findings highlight the critical role of dimensionality reduction and optimizer selection in enhancing the efficiency and accuracy of deep learning models for cancer classification. This research provides a robust framework for improving diagnostic tools in computational oncology.

The significant role of emotion in human daily interaction cannot be over-emphasized, however, the pressing demand for a cutting-edge and highly efficient model for the classification of speech emotion in effective computing has remained a challenging task. Researchers have proposed several approaches for speech emotion classification (SEC) in recent times, but the lingering challenge of the insufficient dataset, which has been limiting the performances of these approaches, is still of major concern. Therefore, this work proposes a deep transfer learning model, a technique that has been yielding tremendous and state-of-the-art results in computer vision, for SEC. Our approach used a pre-trained and optimized model of Visual Geometry Group (VGGNet) convolutional neural network architecture with appropriate fine-tuning for optimal performance. The speech signal is converted to a mel-Spectrogram image suitable for deep learning model input (224\(\,\times \,\)244 x 3) using filterbanks and Fast Fourier transform (FFT) on the speech samples. Multi-layer perceptron (MLP) algorithm is adopted as a classifier after feature extraction is carried out by the deep learning model. Speech pre-processing was carried out on Toronto English Speech Set (TESS) speech emotional corpus used for the study to prevent the low performance of our proposed model. The result of our experiment after evaluation using the TESS dataset shows an improved result in SEC with an accuracy rate of 96.1% and specificity of 97.4%.KeywordsDeep learningSpeech emotionClassificationDeep convolutional neural network

The development of brain-computer interface (BCI) applications has recently piqued the interest of researchers because it can help physically handicapped people to communicate with their brain electroencephalogram (EEG) signal. The automatic classification of mental workload tasks from multi-channel EEG signal analysis is critical for BCI applications. In this paper, we propose an end-to-end deep learning (DL) model for the classification of the mental arithmetic task (MAT) from multi-channel EEG signals. As an end-to-end DL model, a residual-based temporal attention network (RTA-Net) is developed to achieve optimal performance for MAT classification. We have mainly considered two MAT: before mental arithmetic calculation and during mental arithmetic calculation. The RTA-Net model is validated on a freely available MAT-based EEG dataset. The results show that our proposed model yield the best performance with classification accuracy: 99.32%, F1-score: 99.20%, and Cohen’s Kappa: 98.15%, which defeat the performance of all existing methods for MAT classification. For real-world applications, our automated MAT system is ready to be tested with additional datasets.

Leaves are one of the plant components that play a crucial role in plant productivity. Leaf disease in lemon plants can negatively impact both productivity and plant health. Therefore, a computer-based system for auto-matic classification was developed to efficiently and accurately identify dis-eases in lemon leaves. The automatic disease classification process in lemon leaves plays an important role for farmers, supporting timely and accurate decision-making. This study compared several deep learning and transformer models for disease classification of lemon leaves based on their images. The main objective of this study was to determine the performance of each deep learning and transformer architecture for disease classification in lemon leaves using image-based features. In evaluating various experiments, two deep learning models performed well: InceptionV3 and Xception, with accu-racies of 99.85% and 99.63%, respectively, and minimum loss values of 0.017% and 0.0018%, respectively. Then, the transformer model using the Vision Transformer architecture outperformed the two best deep learning models, achieving 99.89% accuracy and a loss of 0.0013. Overall, the experiment comparing the deep learning model and the transformer shows that the Vision Transformer outperforms the CNN. Consequently, the Vision Trans-former presents strong potential as an effective and robust approach for im-age-based leaf disease detection in lemon plants.

Data classification is an important area of data mining. Several well known techniques such as Decision tree, Neural Network, etc. are available for this task. In this paper we propose a Particle Swarm Optimized Polynomial equation for classification of several well known data sets. Our proposed method is derived from some of the findings of the valuable information like number of terms, number and combination of features in each term, degree of the polynomial equation etc. of our earlier work on data classification using Polynomial Neural Network. The PSO optimizes these polynomial equations. The polynomial equation that gives the best performance is considered as the model for classification. Our simulation result shows that the proposed approach is able to give competitive classification accuracy compared to PNN in many datasets.

BACKGROUND : Deep learning models have previously been established to predict the histopathology and invasion depth of gastric lesions using endoscopic images. This study aimed to establish and validate a deep learning-based clinical decision support system (CDSS) for the automated detection and classification (diagnosis and invasion depth prediction) of gastric neoplasms in real-time endoscopy. METHODS : The same 5017 endoscopic images that were employed to establish previous models were used for the training data. The primary outcomes were: (i) the lesion detection rate for the detection model, and (ii) the lesion classification accuracy for the classification model. For performance validation of the lesion detection model, 2524 real-time procedures were tested in a randomized pilot study. Consecutive patients were allocated either to CDSS-assisted or conventional screening endoscopy. The lesion detection rate was compared between the groups. For performance validation of the lesion classification model, a prospective multicenter external test was conducted using 3976 novel images from five institutions. RESULTS : The lesion detection rate was 95.6 % (internal test). On performance validation, CDSS-assisted endoscopy showed a higher lesion detection rate than conventional screening endoscopy, although statistically not significant (2.0 % vs. 1.3 %; P = 0.21) (randomized study). The lesion classification rate was 89.7 % in the four-class classification (advanced gastric cancer, early gastric cancer, dysplasia, and non-neoplastic) and 89.2 % in the invasion depth prediction (mucosa confined or submucosa invaded; internal test). On performance validation, the CDSS reached 81.5 % accuracy in the four-class classification and 86.4 % accuracy in the binary classification (prospective multicenter external test). CONCLUSIONS : The CDSS demonstrated its potential for real-life clinical application and high performance in terms of lesion detection and classification of detected lesions in the stomach.

Given the significance and potential risks associated with Ocular Surface Squamous Neoplasia (OSSN) and the importance of its differentiation from other conditions, we aimed to develop a Deep Learning (DL) model differentiating OSSN from pterygium (PTG) using slit photographs. A dataset comprising slit photographs of 162 patients including 77 images of OSSN and 85 images of PTG was assembled. After manual segmentation of the images, a Python-based transfer learning approach utilizing the EfficientNet B7 network was employed for automated image segmentation. GoogleNet, a pre-trained neural network was used to categorize the images into OSSN or PTG. To evaluate the performance of our DL model, K-Fold 10 Cross Validation was implemented, and various performance metrics were measured. There was a statistically significant difference in mean age between the OSSN (63.23 ± 13.74 years) and PTG groups (47.18 ± 11.53) (P-value =.000). Furthermore, 84.41% of patients in the OSSN group and 80.00% of the patients in the PTG group were male. Our classification model, trained on automatically segmented images, demonstrated reliable performance measures in distinguishing OSSN from PTG, with an Area Under Curve (AUC) of 98%, sensitivity, F1 score, and accuracy of 94%, and a Matthews Correlation Coefficient (MCC) of 88%. This study presents a novel DL model that effectively segments and classifies OSSN from PTG images with a relatively high accuracy. In addition to its clinical use, this model can be potentially used as a telemedicine application.

8034 Background: The histopathological prediction of malignant lung nodules is crucial for preoperative planning, but it always remains not precise until the detailed pathological evaluation is performed after the surgery. Thus, to define the histology types (in situ adenocarcinoma (AIS), microinvasive adenocarcinoma (MIA), and invasive adenocarcinoma (IA)) of pulmonary adenocarcinoma appearing as lung nodules before the operation and reduce unnecessary invasive diagnosis and treatment operations, we developed a classification model of based on CT images. Methods: Patients who were diagnosed with pulmonary adenocarcinoma (tumor diameter ≤ 3cm) at Nanfang Hospital, Southern Medical University, China, were retrospectively enrolled, including detailed pathology results, computed tomography (CT) images, and basic information. Through training the model proposed in our previous study, we proposed a new model for defining histopathological types. Then, we used this data to train and compare the diagnostic efficacy of our model with another previously reported deep learning (DL) model (that was a segmentation - classification model with the 3D Unet++ - ResNet-50 combined model) and machine learning (ML) model (that was a traditional model Grey Level Co-occurrence Matrices (GLCM) as the feature extractor and the support vector machine (SVM) as the classifier) in the same method. Results: A total of 2061 patients (with 395 of AIS, 334 of MIA and 1332 of IA) were retrospectively enrolled from January 2019 to April 2022. The data from 2/3 of the patients were randomly selected for training and another 1/3 for verifying. Through training and verifying, our model shows much better diagnostic efficacy, with areas under receiver operating characteristic (ROC) curves with 95% confidence interval (CI) of 0.97(0.96, 0.98), comparing with those of the ML model of 0.77(0.73, 0.81) and the DL model of (0.90(0.88, 0.92). The heatmap visualization of the proposed model shows the classification ability with prediction probabilities of our model clearly and understandably. Conclusions: In this study, we developed a novel artificial intelligence multi-task learning model to precisely predict the pathology type of malignant lung nodules with satisfying diagnostic efficacy, which might provide a new and reliable way for preoperative planning of lung nodules. Further external verifying should be done in the future. In addition, prediction of the growth patterns of pulmonary adenocarcinoma could be more helpful in addition to predicting histopathological types.

This research presents approaches for combined classification by using attribute filtering with data classification. The performance comparisons of single and combined classification algorithms were used for classifying the conduct disorder of vocational students in Thailand. Single classification included the performance comparisons of four classifiers: 1) Naive Bayes 2) Bayesian Belief Network 3) C4.5 algorithm and 4) RIPPER algorithm. Combined classification included two steps: attributes filtration and data classification. First step was the attribute selection technique named genetic search. Then, results were assessed by using three evaluators: 1) Correlation-based Feature Selection (CFS) 2) Consistency-based Subset Evaluation and 3) Wrapper Subset Evaluation. Second step was the classification of data set by using selected attributed from the first step and four classification algorithms used for single classification. Next, the measurements of classification accuracy had been performed by using the k-fold Cross Validation technique for both single and combined classifications. The outperformed classification model from single and combined classifications was identified. The model was named Conduct Disorder Classification Model (CDCM). It was found that combined classification using genetic search and wrapper subset evaluator with Decision Tree (C4.5) algorithm, had the highest accuracy rate at 83.01%. As well, results from CDCM evaluation showed that factors associated with conduct disorders of students included (1) grade point average of high school, (2) gender, (3) age, (4) father income, (5) grade of typing I subject, (6) height, (7) blood group and (8) grade of business subject. Future works were also suggested.