Classification of Slow and Fast Learners Using a Deep Learning Model

Diabetic Retinopathy (DR), a diabetes-related eye condition, damages retinal blood vessels and can lead to vision loss if undetected early. Precise diagnosis is challenging due to subtle, varied symptoms. While classical deep learning (DL) models like CNNs and ResNet's are widely used, they face resource and accuracy limitations. Quantum computing, leveraging quantum mechanics, offers revolutionary potential for faster problem-solving across fields like cryptography, optimization, and medicine. This research introduces QuantumNet, a hybrid model combining classical DL and quantum transfer learning to enhance DR detection. QuantumNet demonstrates high accuracy and resource efficiency, providing a transformative solution for DR detection and broader medical imaging applications. The method is as follows:•Evaluate three classical deep learning models-CNN, ResNet50, and MobileNetV2-using the APTOS 2019 blindness detection dataset on Kaggle to identify the best-performing model for integration.•QuantumNet combines the best-performing classical DL model for feature extraction with a variational quantum classifier, leveraging quantum transfer learning for enhanced diagnostics, validated statistically and on Google Cirq using standard metrics.•QuantumNet achieves 94.11 % accuracy, surpassing classical DL models and prior research by 11.93 percentage points, demonstrating its potential for accurate, efficient DR detection and broader medical imaging applications.

This research analyzes gender equality in cognitive learning approaches among students in schools in Multan, Pakistan, and assesses their educational futures. The study seeks to evaluate how these variations affect students' educational prospects and suggests recommendations to cater this gap. The study examines gender differences in learning strategies influenced by access to resources, culture, and teaching styles by applying Vygotsky’s sociocultural theory of cognitive development and learning strategies among male and female students. Structural data analysis tools such as standardized cognitive assessment tests, questionnaires, and interviews with urban and rural school students, teachers, and academic administrators are employed. These tools provide a comprehensive view of the cognitive approaches used by male and female students. The findings reveal that female students tend to engage more in cooperative learning and verbal communication, while male students demonstrate stronger inclination towards visual thinking. These gender-based cognitive differences highlight the need for gender-sensitive teaching models acclimating diverse cognitive patterns in educational access and cultural influences. The study suggests that effective interventions and policies in the Pakistani education system should address gender disparities in education and cognitive achievement.

According to the control-value theory of achievement emotions, the influence of cognitive activation teaching strategies on students’ effective use of Cognitive and Meta-Cognitive (CMC) learning strategies is mediated by control appraisals (e.g. self-efficacy) and achievement emotions (i.e. enjoyment and boredom). However, there is limited and contrasting empirical evidence to support this assertion despite claims of cross-cultural and domain consistency. The present study was aimed at examining the multiple mediational roles of self-efficacy and achievement emotions on the relationship between perceived cognitive activation during instruction and four CMC learning strategies among Ugandan biology students. Data were collected using anonymous questionnaires from 587 (50.6% females) tenth grade students with a mean age of 17 years (SD = 1.16) from 10 secondary schools in Uganda. We tested the mediation hypothesis in separate models with each CMC learning strategy. Indirect effects from cognitive activation through self-efficacy and/or enjoyment to CMC learning strategies were all significant confirming their mediational roles. There were significant (p < 0.001) direct effects from cognitive activation to: self-efficacy (β = 0.41), enjoyment (β = 0.26) and cognitive learning strategies, i.e. rehearsal (β = 0.30), organisation (β = 0.30) and elaboration (β = 0.33). Self-efficacy and enjoyment fully mediated the relationship between cognitive activation and metacognition. Except for self-efficacy, direct effects to or from boredom were not significant. Clearly, instructional strategies in biology that stimulate thought among learners are relevant for increasing effective use of any one of CMC learning strategies.

Deep Learning has dramatically improved the accuracy of image recognition. Image recognition is considered to be one of the most challenging problems in imaging science. This paper briefly surveys the application of Deep Learning in classification, object detection, semantic segmentation and instance segmentation of objects in digitized images. The paper reviews widely used Deep Learning models, in classifying, detecting and segmenting objects based on convolutional neural networks (CNN). It provides a summary and presents some discussion about the performance of each model, including training time and accuracy.

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.

Detection of COVID-19 using deep learning techniques and classification methods

See the forest and the trees: Effective machine and deep learning algorithms for wood filtering and tree species classification from terrestrial laser scanning

Liver cancer (LC) is a globally known issue. It is one of the most common cancers that can cause human beings. It is a fatal disease spreading especially in developing countries. Many algorithms have been used to perform the detection of liver cancer with the help of both traditional machine learning classifiers and deep learning classifiers. To analyze the performance of commonly used algorithms, this paper attempts a comparative study on LC detection. It includes both machine learning and deep learning techniques; and several methods for liver and tumor detection from CT images are used. With the advances in Artificial Intelligence (AI) and convolution neural networks algorithms, the methods included in this comparative study achieved great results. The best accuracy among traditional machine learning classifiers reaches 90.46% using Support Vector Machine (RBF). Inception V4 pre-trained model obtained 93.15% in terms of testing accuracy, and it is the best classifier among deep learning models. The performance of deep learning models is very promising to take place in medical decisions.

Stacking of multiple Machine Learning (ML) classifiers have gained popularity in addressing anomalous data classification along with Deep Learning (DL) algorithms. This study compares traditional ML classifiers, multi-layer stacking ML classifiers, and DL classifiers using an open-source malware dataset-containing equal numbers of benign and malware samples. The results on the realistic dataset indicate that the DL classifier, utilizing a Bidirectional Long Short-Term Memory (BiLSTM) model, outperformed the stacked classifiers with Logistic Regression (LR) and Support Vector Machine (SVM) as Meta learners by 36.78% and 39.69%, respectively, in terms of classification accuracy and performance. The research work was extended to study the impact of Generative Adversarial Network (GAN) based synthetic dataset of relatively smaller size on deep learning models. It was observed that the Deep Learning Multi-Layer Perceptron (DLMLP) Model had relatively superior performance as compared to complex deep learning models like Long Short-Term Memory LSTM and BiLSTM

sleep apnea (SA) detection has popularly been performed using the gold standard polysomnography (PSG). This method is complex, time-consuming, and essentially requires a skilled person to record multi-channel sleep data. PSG data acquisition to detect OSA requires a dedicated sleep laboratory and hence it is expensive. The main aim of this paper is to select the most suitable modality single-channel electrocardiogram (ECG) and heart rate variability (HRV) to detect OSA using machine learning and deep learning classifiers. This paper includes selected articles written in the English language and published during the last decade. A total of 273 papers were found and 25 were selected using the preferred reporting items for systematic literature reviews and meta-analyses (PRISMA) approach. It includes articles compiled by searching in google scholar, PubMed, and Web of Science databases. The main contribution of this systematic literature review (SLR) is to identify the research gap and to Adhoc novel, methodologies to fill the gap for sleep apnea detection using ECG and HRV in machine learning (ML) and deep learning (DL) classifiers. The study concludes that DL algorithms for SA using ECG and HRV modalities are easy and robust. It was reported in this review that during the year 2021, most of the research work was carried out in DL for SA detection which establishes its significance. This SLR also provides important information to choose an efficient model for SA detection and characterization using a single-channel modality.

Software-defined networking (SDN) is becoming a predominant architecture for managing diverse networks. However, recent research has exhibited the susceptibility of SDN architectures to cyberattacks, which increases its security challenges. Many researchers have used machine learning (ML) and deep learning (DL) classifiers to mitigate cyberattacks in SDN architectures. Since SDN datasets could suffer from class imbalance issues, the classification accuracy of predictive classifiers is undermined. Therefore, this research conducts a comparative analysis of the impact of utilizing oversampling and principal component analysis (PCA) techniques on ML and DL classifiers using publicly available SDN datasets. This approach combines mitigating the class imbalance issue and maintaining the effectiveness of the performance when reducing data dimensionality. Initially, the oversampling techniques are used to balance the classes of the SDN datasets. Then, the classification performance of ML and DL classifiers is evaluated and compared to observe the effectiveness of each oversampling technique on each classifier. PCA is applied to the balanced dataset, and the classifier’s performance is evaluated and compared. The results demonstrated that Random Oversampling outperformed the other balancing techniques. Furthermore, the XGBoost and Transformer classifiers were the most sensitive models when using oversampling and PCA algorithms. In addition, macro and weighted averages of evaluation metrics were calculated to show the impact of imbalanced class datasets on each classifier.

Nowadays, science and technology has rapidly increasing due to the specific requirements of education. The main aim of this technique is to enhance the physical education activities and helps sports man to finest teaching facilities of these activities. Moreover, the body changes with sports activities based on Deep Learning (DL) frameworks and classifier technology are examined to promote the practical application. Therefore, this paper Deep Reinforcement Learning based Chimp optimization (DRLbCO) algorithm was developed to improve the teaching efficiency of physical education system through the intelligent computer aided assessment models. Also, this model improving the performance, enhancing coaching effectiveness, and gaining competitive advantages in sports. Consequently, the proposed system is based on DL based image detection model DRL, which can analyse and provides proper actions in teaching students and enhance the ability of motion analysis in sports video training quality. Moreover, the DL model is integrated with optimization algorithm to optimize the performance. This could involve reinforcement learning, and other classifiers such as Support Vector Machine (SVM). Based on this provides feedback to students and teachers during physical education classes. The developed model is significantly enhances the physical education teaching student action in virtual sports instruction. Overall intention of the video assessment system of the sports training performance in analyzed.

Epilepsy is a brain disorder that causes patients to suffer from convulsions, which affects their behavior and way of life. Epilepsy can be detected with electroencephalograms (EEGs), which record brain neural activity. Traditional approaches for detecting epileptic seizures from an EEG signal are time-consuming and annoying. To supersede these traditional methods, a myriad of automated seizure detection frameworks based on machine learning techniques have recently been developed. Feature extraction and classification are the two essential phases for seizure detection. The classifier assigns the proper class label after feature extraction lowers the input pattern space while maintaining useful features. This paper proposes a new feature extraction method based on calculating nonlinear features from the most relevant EEG frequency bands. The EEG signal is first decomposed into smaller time segments from which a vector of nonlinear features is computed and supplied to machine learning (ML) and deep learning (DL) classifiers. Experiments on the Bonn dataset reveals an accuracy of 99.7% reached in classifying normal and ictal EEG signals; and an accuracy of 98.8% in the discrimination of ictal and interictal EEG signals. Furthermore, a performance of 100% is achieved on the Hauz Khas dataset. The classification results of the proposed approach were compared to those from published state of the art techniques. Our results are equivalent to or better than some recent studies appeared in the literature.

Artificial intelligence (AI)-based approaches are crucial in computer-aided diagnosis (CAD) for various medical applications. Their ability to quickly and accurately learn from complex data is remarkable. Deep learning (DL) models have shown promising results in accurately classifying Alzheimer's disease (AD) and its related cognitive states, Early Mild Cognitive Impairment (EMCI) and Late Mild Cognitive Impairment (LMCI), along with the healthy conditions known as Cognitively Normal (CN). This offers valuable insights into disease progression and diagnosis. However, certain traditional machine learning (ML) classifiers perform equally well or even better than DL models, requiring less training data. This is particularly valuable in CAD in situations with limited labeled datasets. In this paper, we propose an ensemble classifier based on ML models for magnetic resonance imaging (MRI) data, which achieved an impressive accuracy of 96.52%. This represents a 3-5% improvement over the best individual classifier. We evaluated popular ML classifiers for AD classification under both data-scarce and data-rich conditions using the Alzheimer's Disease Neuroimaging Initiative and Open Access Series of Imaging Studies datasets. By comparing the results to state-of-the-art CNN-centric DL algorithms, we gain insights into the strengths and weaknesses of each approach. This work will help users to select the most suitable algorithm for AD classification based on data availability.

Deep learning is one machine learning method based on the layers used in artificial neural networks. The breakthrough of deep learning in classification led to its rapid application in speech recognition, natural language understanding, and image processing and recognition. In the field of biodiversity informatics, deep learning efforts are being applied in rapid species identification and counts of individuals identified based on image, audio, video, and other data types. However, deep learning methods hold great potential for application in all aspects of biodiversity informatics. We present a case study illustrating how to increase data collection quality and efficiency using well-established technology such as optical character recognition (OCR) and some image classification. Our goal is to image data from the scanned documents of various butterfly atlases, add species, specimens, collections, photographs and other relevant information, and build a database of butterfly images. Information collection involves image annotation and text-based descritpion input. Although the work of image annotation is simple, this process can be accelerated by deep learning-based target segmentation to make the selection process easier, such as changing box select to a double click. The process of information collection is complicated, involving input of species names, specimen collection, specimen description, and other information. Generally, there are many images in atlases, the text layout is rather messy, and overall OCR success is poor. Therefore, the measures we take are as follows: Step A: select the screenshot of the text and then call the OCR interface to generate the text material; Step B: proceed with NLP- (natural language processing) related processing; Step C: perform manual operations on the results, and introduce the NLP function again to this process; Step D: submit the result. The deep learning applications we integrated in our client tool include: target segmentation of the annotated image for automatic positioning and background removal, etc. to improve the quality of the image used for identification; making a preliminary judgment on various attributes of the labeled image and using the results to assist the automatic filling of relevant information in step B, including species information, specimen attributes (specimen image, nature photo, hand drawing pictures, etc.), insect stage (egg, adult, etc.); OCR in step A. target segmentation of the annotated image for automatic positioning and background removal, etc. to improve the quality of the image used for identification; making a preliminary judgment on various attributes of the labeled image and using the results to assist the automatic filling of relevant information in step B, including species information, specimen attributes (specimen image, nature photo, hand drawing pictures, etc.), insect stage (egg, adult, etc.); OCR in step A. Some simple machine learning methods such as k-nearest neighbor can be used to automatically determine gender, pose, and so on. While complex information such as collection place, time, and collector can be analyzed by deep learning-based NLP methods in the future. In our infomation collection process, ten fields are required to submit one single record. Of those, about 4-5 input fields can be dealt with the AI-assistant. It can thus be seen from the above process that deep learning has reduced the workload of manual information annotation by at least 30%. With improvements in accuracy, the era of using automatic information extraction robots to replace manual information annotation and collection is just around the corner.