Automated strabismus detection and classification using deep learning analysis of facial images

BackgroundAntimicrobial peptides (AMPs) are short peptides with diverse biological activities and playing a crucial role in various biological processes. Due to the widespread misuse of traditional antibiotics and the increasing resistance of microorganisms to these drugs, AMPs have emerged as a promising alternative. Consequently, the identification of AMPs has garnered significant research interest. Numerous computational methods based on machine learning algorithms have been developed to facilitate AMP recognition. However, some existing AMPs recognition models only focus on binary classification tasks or only identify the functional activity of a limited number of AMPs categories in multi-class classification tasks. To address this limitation, this study proposes a two-stage AMPs recognition model, iAMP-SeE.MethodsThe iAMP-SeE model extracts features from protein sequences using ESM2, employs a Convolutional Neural Network (CNN) module to capture local patterns from ESM features and utilizes a Bidirectional Long Short-Term Memory (BiLSTM) network to capture long-term dependencies. Furthermore, it incorporates Squeeze-and-Excitation (SE) and Efficient Channel Attention (ECA) mechanisms, which focus on global and local channel relationships, respectively. These two attention mechanisms are complementary, as they enhance features across various dimensions and granularities while simultaneously suppressing irrelevant or redundant features, thereby boosting the model’s performance. Additionally, to address the issue of imbalanced datasets, the Synthetic Minority Over-sampling Technique (SMOTE) is incorporated into the multi-classification task. This method balances the number of AMP categories and ensures that minority classes are not overlooked during model training.ResultsEvaluation across a range of classification thresholds demonstrated the stability of the model’s performance metrics in both binary and multi-class tasks. Furthermore, comparative experiments with existing AMP recognition models confirmed the superior performance of iAMP-SeE.ConclusionsRigorous experimental comparisons and ablation studies demonstrate the effectiveness of iAMP-SeE for both binary and multi-class AMP classification tasks. The source code is publicly available at: https://github.com/cqw0715/iAMP-SeE.git.

Convolutional Neural Networks (CNNs) demonstrate state-of-the-art performance in large-scale multi-class image classification tasks. CNNs consist of convolution layers that progressively construct features and a classification layer. Typically, a softmax function is used in the classification layer to learn joint probabilities for the classes, which are subsequently used for class prediction. We refer to such an approach as the joint approach to multi-class classification. There exists another approach in the literature which determines the multi-class prediction outcome through a sequence of binary decisions, and is christened the class binarization approach. A popular type of class binarization is error-correcting output codes. In this paper, we propose to incorporate error-correcting output codes into convolutional neural networks by inserting a latent binarization layer in a CNN classification layer. This approach encapsulates both encoding and decoding steps of error-correcting output codes into a single CNN architecture that is capable of discovering an optimal coding matrix during training. The latent binarization layer is motivated by the family of latent-trait and latent-class models used in behavioral research. We call the proposed convolutional neural networks with Latent Binarization as LB-CNNs, and develop algorithms combining expectation maximization algorithms and back-propagation to train LB-CNNs. The proposed models and algorithms are applied to several image recognition tasks, producing excellent results. Furthermore, our model enhances the interpretability of the decision process of standard convolutional neural networks.

A deep learning fusion network trained with clinical and high-frequency ultrasound images in the multi-classification of skin diseases in comparison with dermatologists: a prospective and multicenter study

The field of histopathological image analysis has evolved significantly with the advent of digital pathology, leading to the development of automated models capable of classifying tissues and structures within diverse pathological images. Artificial intelligence algorithms, such as convolutional neural networks, have shown remarkable capabilities in pathology image analysis tasks, including tumor identification, metastasis detection, and patient prognosis assessment. However, traditional manual analysis methods have generally shown low accuracy in diagnosing colorectal cancer using histopathological images. This study investigates the use of AI in image classification and image analytics using histopathological images using the histogram of oriented gradients method. The study develops an AI-based architecture for image classification using histopathological images, aiming to achieve high performance with less complexity through specific parameters and layers. In this study, we investigate the complicated state of histopathological image classification, explicitly focusing on categorizing nine distinct tissue types. Our research used open-source multi-centered image datasets that included records of 100.000 non-overlapping images from 86 patients for training and 7180 non-overlapping images from 50 patients for testing. The study compares two distinct approaches, training artificial intelligence-based algorithms and manual machine learning models, to automate tissue classification. This research comprises two primary classification tasks: binary classification, distinguishing between normal and tumor tissues, and multi-classification, encompassing nine tissue types, including adipose, background, debris, stroma, lymphocytes, mucus, smooth muscle, normal colon mucosa, and tumor. Our findings show that artificial intelligence-based systems can achieve 0.91 and 0.97 accuracy in binary and multi-class classifications. In comparison, the histogram of directed gradient features and the Random Forest classifier achieved accuracy rates of 0.75 and 0.44 in binary and multi-class classifications, respectively. Our artificial intelligence-based methods are generalizable, allowing them to be integrated into histopathology diagnostics procedures and improve diagnostic accuracy and efficiency. The CNN model outperforms existing machine learning techniques, demonstrating its potential to improve the precision and effectiveness of histopathology image analysis. This research emphasizes the importance of maintaining data consistency and applying normalization methods during the data preparation stage for analysis. It particularly highlights the potential of artificial intelligence to assess histopathological images.

In the recent era, the growth of deep learning is inevitable. Various models such as convolutional neural networks (CNNs) and transformers are used widely in images for high classification accuracy. Since the invention of transformers, researchers have widely used novel approaches using transformers to achieve an impressive accuracy. In spite of this, this paper proposes a novel custom lightweight CNN model called Attentive and Lightweight Network (ALNet). ALNet consists of three major blocks: stem, core, and head. The core part is the novel classifier built as an inspiration from various pre-trained models such as ResNet, SENet (Squeeze and Excitation Network), EfficientNet, SqueezeNet, and ShuffleNet. The main objective is to build a model that has a high classification accuracy while reducing the number of parameters. This reduces the size of the model and hence makes it easy to deploy on cloud platforms and use in edge devices. The model was evaluated using 5-fold cross-validation on three different datasets. The primary dataset was a grapevine dataset with an accuracy of 99.78 percent and 100 percent in multi-class and binary classification respectively. To test the robustness of the model, a multi-class classification using the apple dataset achieved an accuracy of 99.95 percent and a binary classification with the cherry dataset achieved an accuracy of 100 percent. ALNet uses only 0.17 million parameters which is 18 times less parameters than the lightest model (SqueezeNet) and it takes only 14 seconds to train each epoch while pretrained models take 17-31 seconds. ALNet requires only 151.98 MFLOPs with a model size of 677.20 KB, making it approximately 18 times smaller than SqueezeNet. On the whole, ALNet is a highly accurate, lightweight model for plant leaf diseases prediction.

Multi-label fundus disease classification using dual-branch deep learning: an intelligent diagnosis framework inspired by traditional Chinese medicine Five Wheels theory

Digital systems are changing to security systems in contemporary days. It is time for the digital system to have sufficient security to defend against threats and attacks. The intrusion detection system can identify an anomaly from an external or internal source in the network system. Many kinds of threats are present, that is, active and passive. These dangers could lead to anomalies in the system by which data can be attacked and taken by attackers from the beginning to the destination. Machine learning nowadays is a developing topic; its applications are wide. We can forecast the future through machine learning and classify the right class. In this paper, we employed the new binary and multiclass classification model of Convolutional Neural Networks (CNNs) to identify the anomaly of the network system. In this respect, we used the NSLKDD dataset. Our model uses a Convolutional Neural Network (CNN) to conduct binary and multiclass classification. In both datasets, we build a DL-based DoS detection model. We focus on the DoS category in the most extensively used IDS dataset, KDD. As the name implies, CNN is the most extensively used the DL model for image recognition. Adding a pooling layer to the convolution layer minimizes the size of the feature data extracted from the image while maintaining I/O and spatial information. The CNN model has shown the promising results of multiclass and binary classification in terms of validation loss of 0.0012 at 11th epochs and validation accuracy of 98% and 99%, respectively.

The paper presents a solution to the multiclass classification problem based on the Convolutional Fuzzy Neural Networks. The proposed model includes a fuzzy self-organization layer for data clustering (in addition to convolutional, pooling and fully-connected layers). The model combines the power of convolutional neural networks and fuzzy logic, it is capable of handling uncertainty and imprecision in the input pattern representation. The Convolutional Fuzzy Neural Networks could provide better accuracy in multiclass classification tasks when classified objects are often characterized by uncertainty and inaccuracy in their representation.

As security threats become more complex, the need for effective intrusion detection systems (IDSs) has grown. Traditional machine learning methods are limited by the need for extensive feature engineering and data preprocessing. To overcome this, we propose two enhanced hybrid deep learning models, an autoencoder–convolutional neural network (Autoencoder–CNN) and a transformer–deep neural network (Transformer–DNN). The Autoencoder reshapes network traffic data, addressing class imbalance, and the CNN performs precise classification. The transformer component extracts contextual features, which the DNN uses for accurate classification. Our approach utilizes an enhanced hybrid adaptive synthetic sampling–synthetic minority oversampling technique (ADASYN-SMOTE) for binary classification and enhanced SMOTE for multi-class classification, along with edited nearest neighbors (ENN) for further class imbalance handling. The models were designed to minimize false positives and negatives, improve real-time detection, and identify zero-day attacks. Evaluations based on the CICIDS2017 dataset showed 99.90% accuracy for Autoencoder–CNN and 99.92% for Transformer–DNN in binary classification, and 99.95% and 99.96% in multi-class classification, respectively. On the NF-BoT-IoT-v2 dataset, the Autoencoder–CNN achieved 99.98% in binary classification and 97.95% in multi-class classification, while the Transformer–DNN reached 99.98% and 97.90%, respectively. These results demonstrate the superior performance of the proposed models compared with traditional methods for handling diverse network attacks.

Determining environmental chemical carcinogenicity is urgently needed as humans are increasingly exposed to these chemicals. In this study, we developed a hybrid neural network (HNN) method called HNN-Cancer to predict potential carcinogens of real-life chemicals. The HNN-Cancer included a new SMILES feature representation method by modifying our previous 3D array representation of 1D SMILES simulated by the convolutional neural network (CNN). We developed binary classification, multiclass classification, and regression models based on diverse non-congeneric chemicals. Along with the HNN-Cancer model, we developed models based on the random forest (RF), bootstrap aggregating (Bagging), and adaptive boosting (AdaBoost) methods for binary and multiclass classification. We developed regression models using HNN-Cancer, RF, support vector regressor (SVR), gradient boosting (GB), kernel ridge (KR), decision tree with AdaBoost (DT), KNeighbors (KN), and a consensus method. The performance of the models for all classifications was assessed using various statistical metrics. The accuracy of the HNN-Cancer, RF, and Bagging models were 74%, and their AUC was ~0.81 for binary classification models developed with 7994 chemicals. The sensitivity was 79.5% and the specificity was 67.3% for the HNN-Cancer, which outperforms the other methods. In the case of multiclass classification models with 1618 chemicals, we obtained the optimal accuracy of 70% with an AUC 0.7 for HNN-Cancer, RF, Bagging, and AdaBoost, respectively. In the case of regression models, the correlation coefficient (R) was around 0.62 for HNN-Cancer and RF higher than the SVM, GB, KR, DTBoost, and NN machine learning methods. Overall, the HNN-Cancer performed better for the majority of the known carcinogen experimental datasets. Further, the predictive performance of HNN-Cancer on diverse chemicals is comparable to the literature-reported models that included similar and less diverse molecules. Our HNN-Cancer could be used in identifying potentially carcinogenic chemicals for a wide variety of chemical classes.

Prediction of the stage of cancer plays an important role in planning the course of treatment and has been largely reliant on imaging tools which do not capture molecular events that cause cancer progression. Gene-expression data-based analyses are able to identify these events, allowing RNA-sequence and microarray cancer data to be used for cancer analyses. Breast cancer is the most common cancer worldwide, and is classified into four stages - stages 1, 2, 3, and 4 [2]. While machine learning models have previously been explored to perform stage classification with limited success, multi-class stage classification has not had significant progress. There is a need for improved multi-class classification models, such as by investigating deep learning models. Gene-expression-based cancer data is characterised by the small size of available datasets, class imbalance, and high dimensionality. Class balancing methods must be applied to the dataset. Since all the genes are not necessary for stage prediction, retaining only the necessary genes can improve classification accuracy. The breast cancer samples are to be classified into 4 classes of stages 1 to 4. Invasive ductal carcinoma breast cancer samples are obtained from The Cancer Genome Atlas (TCGA) and Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) datasets and combined. Two class balancing techniques are explored, synthetic minority oversampling technique (SMOTE) and SMOTE followed by random undersampling. A hybrid feature selection pipeline is proposed, with three pipelines explored involving combinations of filter and embedded feature selection methods: Pipeline 1 - minimum-redundancy maximum-relevancy (mRMR) and correlation feature selection (CFS), Pipeline 2 - mRMR, mutual information (MI) and CFS, and Pipeline 3 - mRMR and support vector machine-recursive feature elimination (SVM-RFE). The classification is done using deep learning models, namely deep neural network, convolutional neural network, recurrent neural network, a modified deep neural network, and an AutoKeras generated model. Classification performance post class-balancing and various feature selection techniques show marked improvement over classification prior to feature selection. The best multiclass classification was found to be by a deep neural network post SMOTE and random undersampling, and feature selection using mRMR and recursive feature elimination, with a Cohen-Kappa score of 0.303 and a classification accuracy of 53.1%. For binary classification into early and late-stage cancer, the best performance is obtained by a modified deep neural network (DNN) post SMOTE and random undersampling, and feature selection using mRMR and recursive feature elimination, with an accuracy of 81.0% and a Cohen-Kappa score (CKS) of 0.280. This pipeline also showed improved multiclass classification performance on neuroblastoma cancer data, with a best area under the receiver operating characteristic (auROC) curve score of 0.872, as compared to 0.71 obtained in previous work, an improvement of 22.81%. The results and analysis reveal that feature selection techniques play a vital role in gene-expression data-based classification, and the proposed hybrid feature selection pipeline improves classification performance. Multi-class classification is possible using deep learning models, though further improvement particularly in late-stage classification is necessary and should be explored further.

In the rapidly changing field of cybersecurity, strong and efficient Intrusion Detection Systems (IDS) are essential for spotting malicious activities on the network traffic. However, traditional IDS models often face challenges such as too many irrelevant features (high-dimensional data), uneven class distributions (imbalanced datasets), and constantly evolving threats (shifting attack patterns). To overcome these issues, we introduce a hybrid framework called WGAN-GP_IMOA_DA_Ensemble. It combines: (i) a new bio-inspired Indian Millipede Optimization Algorithm (IMOA), based on the movement and foraging behavior of Indian millipedes, for selecting the most relevant features; (ii) an enhanced Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) that uses attention layers, layer normalization, and skip connections in the discriminator, producing more realistic synthetic samples for rare attack types; and (iii) a dynamic attention-based ensemble, DA_Ensemble, which integrates three deep learning models namely Feedforward Neural Network (FNN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), and adaptively weights their predictions in real time, emphasizing the most accurate model for a specific type of traffic. The model was tested on benchmark datasets such as UNSW-NB15, H23Q, and CIC-IDS2017 under multiclass and binary settings. In binary classification, the model achieved 100% “accuracy, precision, recall, and F1-score” on the UNSW-NB15 dataset, surpassing the best benchmark method, Optimized Hybrid Deep Neural Network + Enhanced Conditional Random Field (OHDNN+ECRF), by nearly 2%. On CIC-IDS2017 and H23Q, it attained about 99% across all four metrics, improving previous baselines by 2% to 3%. In multiclass classification, it reached 99% in all four metrics on UNSW-NB15 and CIC-IDS2017, and about 98% on H23Q, demonstrating a steady 2% to 4% improvement over current leading methods. These results, confirmed through five-fold cross-validation and ablation studies, show that the proposed approach reliably delivers statistically significant improvements in both binary and multiclass intrusion detection tasks.

Oral cancer is the sixth most frequent type of cancer worldwide, and it is one of the main causes of mortality. Although early detection during precancerous phases can greatly increase survival rates, late-stage diagnoses are the cause of its high mortality rate. Using image analysis of oral lesions, this study suggests an effective diagnosis technique. The lightweight MobileNetV2 CNN architecture is used to classify the texture and color properties that are extracted from photos by exploring five color spaces. This model enhances accuracy while still being appropriate for resource-constrained, mobile applications by fusing deep learning with handmade features. The approach performs well in binary and multi-class classification tasks, differentiating between benign, malignant, and precancerous lesions. Particularly in underprivileged areas, its scalability and affordable design make it perfect for early oral cancer screening. Keywords: Oral Cancer Detection, Pre-Cancerous Lesions, MobileNetV2, Convolutional Neural Network (CNN), Color and Texture Features, Medical Image Classification, Deep Learning, Lightweight Architecture, Real-Time Diagnosis, Resource-Constrained Devices

Machine learning involves the task of training systems to be able to make decisions without being explicitly programmed. Important among machine learning tasks is classification involving the process of training machines to make predictions from predefined labels. Classification is broadly categorized into three distinct groups: single-label (SL), multi-class, and multi-label (ML) classification. This research work presents an application of a multi-label classification (MLC) technique in automating Quranic verses labeling. MLC has been gaining attention in recent years. This is due to the increasing amount of works based on real-world classification problems of multi-label data. In traditional classification problems, patterns are associated with a single-label from a set of disjoint labels. However, in MLC, an instance of data is associated with a set of labels. In this paper, three standard <em>MLC</em> methods: <span>binary relevance (BR), classifier chain (CC), and label powerset (LP) algorithms are implemented with four baseline classifiers: support vector machine (SVM), naïve Bayes (NB), k-nearest neighbors (k-NN), and J48. The research methodology adopts the multi-label problem transformation (PT) approach. The results are validated using six conventional performance metrics. These include: hamming loss, accuracy, one error, micro-F1, macro-F1, and avg. precision. From the results, the classifiers effectively achieved above 70% accuracy mark. Overall, SVM achieved the best results with CC and LP algorithms.</span>

We argue that citations, as they have different reasons and functions, should not all be treated in the same way. Using the large, annotated dataset of about 10K citation contexts annotated by human experts, extracted from the Association for Computational Linguistics repository, we present a deep learning–based citation context classification architecture. Unlike all existing state-of-the-art feature-based citation classification models, our proposed convolutional neural network (CNN) with fastText-based pre-trained embedding vectors uses only the citation context as its input to outperform them in both binary- (important and non-important) and multi-class (Use, Extends, CompareOrContrast, Motivation, Background, Other) citation classification tasks. Furthermore, we propose using focal-loss and class-weight functions in the CNN model to overcome the inherited class imbalance issues in citation classification datasets. We show that using the focal-loss function with CNN adds a factor of [Formula: see text] to the cross-entropy function. Our model improves on the baseline results by achieving an encouraging 90.6 F1 score with 90.7% accuracy and a 72.3 F1 score with a 72.1% accuracy score, respectively, for binary- and multi-class citation classification tasks.