Classification of Dermoscopic Images Using CNN-SVM

Mobile fitness applications provide the opportunity to show users real-time feedback on their current fitness activity. For such applications, it is essential to accurately track the user's current fitness activity using available mobile sensors, such as inertial measurement units (IMUs). Convolutional neural networks (CNNs) have been shown to produce strong results in different time series classification tasks, including the recognition of daily living activities. However, fitness activities can present unique challenges to the human activity recognition task (HAR), including greater similarity between individual activities and fewer available data for model training. In this paper, we evaluate the applicability of CNNs to the fitness activity recognition task (FAR) using IMU data and determine the impact of input data size and sensor count on performance. For this purpose, we adapted three existing CNN architectures to the FAR task and designed a fourth CNN variant, which we call the scaling fully convolutional network (Scaling-FCN). We designed a preprocessing pipeline and recorded a running exercise data set with 20 participants, in which we evaluated the respective recognition performances of the four networks, comparing them with three traditional machine learning (ML) methods commonly used in HAR. Although CNN architectures achieve at least 94% test accuracy in all scenarios, two traditional ML architectures surpass them in the default scenario, with support vector machines (SVMs) achieving 99.00 ± 0.34% test accuracy. The removal of all sensors except one foot sensor reduced the performance of traditional ML architectures but improved the performance of CNN architectures on our data set, with our Scaling-FCN reaching the highest accuracy of 99.86 ± 0.11% on the test set. Our results suggest that CNNs are generally well suited for fitness activity recognition, and noticeable performance improvements can be achieved if sensors are dropped selectively, although traditional ML architectures can still compete with or even surpass CNNs when favorable input data are utilized.

Because bacterial blight (BB) disease seriously affects the yield and quality of rice, breeding BB resistant rice is an important priority for plant breeders but the process is time-consuming. The feasibility of using terahertz imaging technology and near-infrared hyperspectral imaging technology to identify BB resistant seeds has therefore been studied. The two-dimensional (2D) spectral images and one-dimensional (1D) spectra provided by both imaging methods were used to build discriminant models based on a deep learning method, the convolutional neural network (CNN), and traditional machine learning methods, support vector machine (SVM), random forest (RF), and partial least squares discriminant analysis (PLS-DA). The highest classification accuracy was achieved by the discriminate model based on CNN using the terahertz absorption spectra. Confusion matrixes were pictured to show the identification details. The t-distributed stochastic neighbor embedding (t-SNE) method was used to visualize the process of CNN data processing. Terahertz imaging technology combined with CNN has great potential to quickly identify BB resistant rice seeds and is more accurate than using near-infrared hyperspectral imaging.

Mild cognitive impairment (MCI) is a clinical condition characterized by a decline in cognitive ability and progression of cognitive impairment. It is often considered a transitional stage between normal aging and Alzheimer's disease (AD). This study aimed to compare deep learning (DL) and traditional machine learning (ML) methods in predicting MCI using plasma proteomic biomarkers. A total of 239 adults were selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort along with a pool of 146 plasma proteomic biomarkers. We evaluated seven traditional ML models (support vector machines (SVMs), logistic regression (LR), naïve Bayes (NB), random forest (RF), k-nearest neighbor (KNN), gradient boosting machine (GBM), and extreme gradient boosting (XGBoost)) and six variations of a deep neural network (DNN) model-the DL model in the H2O package. Least Absolute Shrinkage and Selection Operator (LASSO) selected 35 proteomic biomarkers from the pool. Based on grid search, the DNN model with an activation function of "Rectifier With Dropout" with 2 layers and 32 of 35 selected proteomic biomarkers revealed the best model with the highest accuracy of 0.995 and an F1 Score of 0.996, while among seven traditional ML methods, XGBoost was the best with an accuracy of 0.986 and an F1 Score of 0.985. Several biomarkers were correlated with the APOE-ε4 genotype, polygenic hazard score (PHS), and three clinical cerebrospinal fluid biomarkers (Aβ42, tTau, and pTau). Bioinformatics analysis using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) revealed several molecular functions and pathways associated with the selected biomarkers, including cytokine-cytokine receptor interaction, cholesterol metabolism, and regulation of lipid localization. The results showed that the DL model may represent a promising tool in the prediction of MCI. These plasma proteomic biomarkers may help with early diagnosis, prognostic risk stratification, and early treatment interventions for individuals at risk for MCI.

The Army Rapid Capabilities Office (RCO) sponsored a Blind Signal Classification Competition seeking algorithms to automatically identify the modulation schemes of RF signal from complex-valued IQ (in-phase quadrature) samples. Traditional spectrum sensing technology uses energy detection to detect the existence of RF signals but the RCO competition further aimed to detect the modulation scheme of signals without prior information. Machine Learning (ML) technologies have been widely used for blind signal classification problem. Traditional ML methods usually have two stages where the first stage is to manually extract the features of the IQ symbols by subject matter experts and the second stage is to feed the features to an ML algorithm (e.g., a support vector machine) to develop the classifier. The state-of-art technology is to apply deep learning technologies such as Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) directly to the complex-value IQ symbols to train a multi-class classifier. Our team, dubbed Deep Dreamers, participated in the RCO competition and placed 3rd out of 42 active teams across industry, academia, and government. In this work we share our experience and lessons learned from the competition. Deep learning methods such as CNN, Residual Neural Network (ResNet), and Long Short-Term Memory (LSTM) are the fundamental neural network layers we used to develop a multi-class classifier. None of our individual models were able to achieve a competitively high ranking in the competition. The key to our success was to use ensemble learning to average the outputs of multiple diverse classifiers. In order for ensemble methods to be more accurate than any of its base models; the base learners have to be as accurate as possible. We found that while ResNet was more accurate than the LSTM; the LSTM was less sensitive to deviations in the test set.

We address the Lithuanian author profiling task in two dimensions (AGE and GENDER) using two deep learning methods (i.e., Long Short-Term Memory - LSTM) and Convolutional Neural Network - CNN) applied on the top of Lithuanian neural word embeddings. We also investigate an impact of the training dataset size on the author profiling accuracy. The best results are achieved with the largest datasets, containing 5,000 instances in each class. Besides, LSTM was more effective on the smaller datasets, and CNN - on the larger ones. We compare the deep learning methods with the traditional machine learning methods (in particular, Naive Bayes Multinomial and Support Vector Machine), and frequencies of elements as the feature representation). The comparison revealed that the deep learning is not the best solution for our author profiling task.

Deep learning algorithms can be used to design systems that report data on patients and deliver warnings to medical applications or electronic health information if there are changes in the patient's health. These systems could be created using deep Learning. This helps verify that patients get the proper effective care at the proper time for each specific patient. A healthcare decision support system was presented using the Internet of Things and deep learning methods. In the proposed system, we examined the capability of integrating deep learning technology into automatic diagnosis and IoT capabilities for faster message exchange over the Internet. We have selected the suitable Neural Network structure (number of best-hidden layers and activation function classes) to construct the e-health system. In addition, the e-health system relied on data from doctors to understand the Neural Network. In the validation method, the total evaluation of the proposed healthcare system for diagnostics provides dependability under various patient conditions. Based on evaluation and simulation findings, a dual hidden layer of feed-forward NN and its neurons store the tanh function more effectively than other NN. To overcome challenges, this study will integrate artificial intelligence with IoT. This study aims to determine the NN's optimal layer counts and activation function variations.

Diabetic retinopathy (DR) is one of the leading causes of vision loss in adults and is one of the detrimental side effects of the mass prevalence of Diabetes Mellitus (DM). It is crucial to have an efficient screening method for early diagnosis of DR to prevent vision loss. This paper compares and analyzes the various Machine Learning (ML) techniques, from traditional ML to advanced Deep Learning models. We compared and analyzed the efficacy of Convolutional Neural Networks (CNNs), Capsule Networks (CapsNet), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), decision trees, and Random Forests. This paper also considers determining factors in the evaluation, including contrast enhancements, noise reduction, grayscaling, etc We analyze recent research studies and compare methodologies and metrics, including accuracy, precision, sensitivity, and specificity. The findings highlight the advanced performance of Deep Learning (DL) models, with CapsNet achieving a remarkable accuracy of up to 97.98% and a high precision rate, outperforming other traditional ML methods. The Contrast Limited Adaptive Histogram Equalization (CLAHE) preprocessing technique substantially enhanced the model’s efficiency. Each ML method’s computational requirements are also considered. While most advanced deep learning methods performed better according to the metrics, they are more computationally complex, requiring more resources and data input. We also discussed how datasets like MESSIDOR could be more straightforward and contribute to highly evaluated performance and that there is a lack of consistency regarding benchmark datasets across papers in the field. Using the DL models facilitates accurate early detection for DR screening, can potentially reduce vision loss risks, and improves accessibility and cost-efficiency of eye screening. Further research is recommended to extend our findings by building models with public datasets, experimenting with ensembles of DL and traditional ML models, and considering testing high-performing models like CapsNet.

ABSTRACTDue to the ever-expanding volume of observed spectroscopic data from surveys such as SDSS and LAMOST, it has become important to apply artificial intelligence (AI) techniques for analysing stellar spectra to solve spectral classification and regression problems like the determination of stellar atmospheric parameters Teff, $\rm {\log g}$, and [Fe/H]. We propose an automated approach for the classification of stellar spectra in the optical region using convolutional neural networks (CNNs). Traditional machine learning (ML) methods with ‘shallow’ architecture (usually up to two hidden layers) have been trained for these purposes in the past. However, deep learning methods with a larger number of hidden layers allow the use of finer details in the spectrum which results in improved accuracy and better generalization. Studying finer spectral signatures also enables us to determine accurate differential stellar parameters and find rare objects. We examine various machine and deep learning algorithms like artificial neural networks, Random Forest, and CNN to classify stellar spectra using the Jacoby Atlas, ELODIE, and MILES spectral libraries as training samples. We test the performance of the trained networks on the Indo-U.S. Library of Coudé Feed Stellar Spectra (CFLIB). We show that using CNNs, we are able to lower the error up to 1.23 spectral subclasses as compared to that of two subclasses achieved in the past studies with ML approach. We further apply the trained model to classify stellar spectra retrieved from the SDSS data base with SNR > 20.

Medical images classification is a challenging research topic in the field of computer vision, especially when applied to diagnosis of breast cancer (BC). Nowadays, histopathological image is marked as the gold standard for diagnosing BC. However, such diagnosis is heavily dependent on the clinician's experience, which is extremely time consuming and is subjected to human error even for experienced doctors. To address those problems, this paper implements an automated method for distinguishing the benign from the malignant tumor based on a convolutional neural network (CNN). Traditional deep CNN and machine learning methods not only lead to poor performance, but also fail to make full use of the long-term dependence between some key features and image tags. To further meet the high accuracy requirement of diagnosis, according to the characteristics of histopathological images, we propose a novel CNN framework. Firstly, a normal image is augmented to solve the problem about having a limited database. Secondly, we introduce transfer learning to obtain more accurate weight parameters that were pre-trained on the ImageNet. Thirdly, we combine various features extracted by many individual models to obtain comprehensive features. Finally, random forest is introduced to enforce classification. The experimental results show that novel CNN frameworks have better performance compared with individual models, including DenseNet and ResNet. Experimental results are able to prove the effectiveness of our strategy.

The coronavirus COVID-19 pandemic has caused a global health crisis. According to According to the World Health Assembly, one of the best preventative measures is to wear a face mask while out outdoors (WHO). This work presents a hybrid model for face mask identification that combines deep and traditional machine learning. I have trained the proposed system, which consists of convolutional neural networks (ConNN), support vector machines (SVM), and random forests (RF), in three stages, the first stage, used ConNN, the second stage, used the same ConNN with the SVM method, and in the third stage, used ConNN and RF. This paper suggests three different kinds of masked face recognition datasets: the Incorrectly Masked Face Dataset (IMFD), the Correctly Masked Face Dataset (CMFD), and the combination for MaskedFace-Net, a worldwide masked face detection system. Two objectives are presented for the realistic masked face datasets: i) to identify individuals whose faces are covered or not covered, ii) to identify faces whose masks are put on properly or improperly (for example, at airport entrances or among crowds). The suggested model is made up of two parts. The first part is designed for feature extraction using a convolutional neural networks. In contrast, the second section is made to classify face masks using SVM and RF methods. The ConNN achieved 99.92%. and achieved for ConNN and SVM 99.94%. ConNN and RF 98.79%. Moreover,The system has been tested in real world scenarios and can recognize and classify any image selected by Google with high accuracy. we a comparison and the results aim to evaluate the proposed model.

Epilepsy is a common neurological disorder that severely impairs the quality of life of patients. Accurate detection of epileptic seizures is crucial for diagnosis and treatment. This paper reviews the application of machine learning in epilepsy diagnosis, with a specific focus on two core tasks: classifying seizure types based on electroencephalograms (EEG) and detecting interictal epileptiform discharges (IEDs). Machine learning methods are mainly divided into two categories: one is traditional machine learning methods, such as support vector machines and random forests, which rely on manual extraction of EEG features. Although they exhibit stable performance on small sample data, feature engineering is complex and dependent on expert experience. The second is deep learning methods (such as CNN, RNN, and their variants), which can automatically learn the spatiotemporal features of EEG and have significant advantages in multi-type seizure classification, but they have high requirements for data quality and scale. In IEDs detection, although methods such as tensor decomposition can achieve high accuracy by integrating multi-dimensional information, they still face problems such as difficulty in distinguishing artifacts in template matching. Future research needs to optimize algorithm performance and address challenges such as data scarcity to further improve detection effectiveness.

Millimeter-wave radar is widely used in intelligent vehicle infrastructure cooperative systems (IVICS) because of its long detection distance, high integration and less affected by weather conditions. The target recognition and classification technology based on millimeter wave radar is a research hotspot. However, traditional recognition methods require a complex feature extraction process. In this paper, a millimeter-wave radar classification method based on deep learning is proposed, which uses the ability of convolutional neural networks (CNN) method to automatically extract feature data, so as to replace most of the complex processes of traditional radar signal processing chain. It solves the four classification tasks of bus, cars, electromobile and pedestrians. Taking the selected feature data as the RV spectrum, a seven layer convolution neural network is built to classify the target. Compared with traditional machine learning methods, CNN greatly reduces the workload of feature engineering, and its classification effect is better than traditional machine learning methods. Then, from the perspective of redundancy of the convolution kernels, we simplify the CNN architecture. As a result, final classification accuracy of the CNN is 93.16%. After simplifying the structure of the CNN, the computational complexity and storage consumption of the network are reduced by 74.67% and 73.71%, respectively, while ensuring that the classification accuracy does not decline.

Due to the complexity of medical images, traditional medical image classification methods have been unable to meet actual application needs. In recent years, the rapid development of deep learning theory has provided a technical approach for solving medical image classification tasks. However, deep learning has the following problems in medical image classification. First, it is impossible to construct a deep learning model hierarchy for medical image properties; second, the network initialization weights of deep learning models are not well optimized. Therefore, this paper starts from the perspective of network optimization and improves the nonlinear modeling ability of the network through optimization methods. A new network weight initialization method is proposed, which alleviates the problem that existing deep learning model initialization is limited by the type of the nonlinear unit adopted and increases the potential of the neural network to handle different visual tasks. Moreover, through an in‐depth study of the multicolumn convolutional neural network framework, this paper finds that the number of features and the convolution kernel size at different levels of the convolutional neural network are different. In contrast, the proposed method can construct different convolutional neural network models that adapt better to the characteristics of the medical images of interest and thus can better train the resulting heterogeneous multicolumn convolutional neural networks. Finally, using the adaptive sliding window fusion mechanism proposed in this paper, both methods jointly complete the classification task of medical images. Based on the above ideas, this paper proposes a medical classification algorithm based on a weight initialization/sliding window fusion for multilevel convolutional neural networks. The methods proposed in this study were applied to breast mass, brain tumor tissue, and medical image database classification experiments. The results show that the proposed method not only achieves a higher average accuracy than that of traditional machine learning and other deep learning methods but also is more stable and more robust.

In Cassini ISS (Imaging Science Subsystem) images, contour detection is often performed on disk-resolved objects to accurately locate their center. Thus, contour detection is a key problem. Traditional edge detection methods, such as Canny and Roberts, often extract the contour with too much interior details and noise. Although the deep convolutional neural network has been applied successfully in many image tasks, such as classification and object detection, it needs more time and computer resources. In this paper, a contour detection algorithm based on H-ELM (Hierarchical Extreme Learning Machine) and DenseCRF (Dense Conditional Random Field) is proposed for Cassini ISS images. The experimental results show that this algorithm’s performance is better than both traditional machine learning methods, such as Support Vector Machine, Extreme Learning Machine and even deep Convolutional Neural Network. The extracted contour is closer to the actual contour. Moreover, it can be trained and tested quickly on the general configuration of PC, and thus can be applied to contour detection for Cassini ISS images.

Despite advances in diagnostics, the objective and repeatable assessment of patients with neurological deficits (e.g., stroke) remains a major challenge. Modern methods based on artificial intelligence (AI) are of interest to researchers and clinicians in this area. This study presents a comparative analysis of different AI approaches used to analyze gait of stroke patients using a retrospective dataset of 120 individuals. The main objective is to evaluate the effectiveness, accuracy, and clinical relevance of machine learning (ML) and deep learning (DL) models in identifying gait abnormalities and predicting rehabilitation outcomes. Multiple AI techniques—including support vector machines (SVM), random forests (RF), k-nearest neighbors (k-NN), and convolutional neural networks (CNN)—were trained and tested on time-series gait data with spatiotemporal parameters. Performance metrics such as accuracy, precision, recall, and area under the curve (AUC) were used to compare model results. Initial results indicate that DL models, particularly CNNs, outperform traditional ML methods in capturing complex gait patterns and providing reliable classification. However, simpler models showed advantages in interpretability and computational efficiency. This study highlights the potential and shortcomings of AI-based gait analysis tools in supporting clinical decision-making and planning personalized stroke rehabilitation.