Deep Learning Classification Model Research Articles

Development of a classification model for Cynanchum wilfordii and Cynanchum auriculatum using convolutional neural network and local interpretable model-agnostic explanation technology.

Cynanchum wilfordii is a perennial tuberous root in the Asclepiadaceae family that has long been used medicinally. Although C. wilfordii is distinct in origin and content from Cynancum auriculatum, a genus of the same species, it is difficult for the public to recognize because the ripe fruit and root are remarkably similar. In this study, images were collected to categorize C. wilfordii and C. auriculatum, which were then processed and input into a deep-learning classification model to corroborate the results. By obtaining 200 photographs of each of the two cross sections of each medicinal material, approximately 800 images were employed, and approximately 3200 images were used to construct a deep-learning classification model via image augmentation. For the classification, the structures of Inception-ResNet and VGGnet-19 among convolutional neural network (CNN) models were used, with Inception-ResNet outperforming VGGnet-19 in terms of performance and learning speed. The validation set confirmed a strong classification performance of approximately 0.862. Furthermore, explanatory properties were added to the deep-learning model using local interpretable model-agnostic explanation (LIME), and the suitability of the LIME domain was assessed using cross-validation in both situations. Thus, artificial intelligence may be used as an auxiliary metric in the sensory evaluation of medicinal materials in future, owing to its explanatory ability.

D-HRSP: Dataset of helpful reviews for service providers

Most common services are now provided through mobile applications; thus, the importance of mobile application reviews has increased. Service providers and developers seek helpful reviews to find useful information to improve their services. However, with currently existing indicators, e.g., star rating systems, it is difficult to identify reviews that are directly related to the quality of the service. Thus, in this study, we defined helpful mobile application reviews for service providers and developers based on the components of an existing service quality evaluation model. We also provide the D-HRSP (dataset of helpful reviews for service providers), which is a labeled dataset that can be used to examine helpful reviews. We also report the experimental results obtained with simple natural language processing techniques and machine learning and deep learning classification models. The experimental results demonstrate that the proposed definition can help address real-life problems and create opportunities for additional research into the identification of helpful mobile application reviews.

Development of a deep-learning model for classification of LI-RADS major features by using subtraction images of MRI: a preliminary study.

Liver Imaging Reporting and Data System (LI-RADS) is limited by interreader variability. Thus, our study aimed to develop a deep-learning model for classifying LI-RADS major features using subtraction images using magnetic resonance imaging (MRI). This single-center retrospective study included 222 consecutive patients who underwent resection for hepatocellular carcinoma (HCC) between January, 2015 and December, 2017. Subtraction arterial, portal venous, and transitional phase images of preoperative gadoxetic acid-enhanced MRI were used to train and test the deep-learning models. Initially, a three-dimensional (3D) nnU-Net-based deep-learning model was developed for HCC segmentation. Subsequently, a 3D U-Net-based deep-learning model was developed to assess three LI-RADS major features (nonrim arterial phase hyperenhancement [APHE], nonperipheral washout, and enhancing capsule [EC]), utilizing the results determined by board-certified radiologists as reference standards. The HCC segmentation performance was assessed using the Dice similarity coefficient (DSC), sensitivity, and precision. The sensitivity, specificity, and accuracy of the deep-learning model for classifying LI-RADS major features were calculated. The average DSC, sensitivity, and precision of our model for HCC segmentation were 0.884, 0.891, and 0.887, respectively, across all the phases. Our model demonstrated a sensitivity, specificity, and accuracy of 96.6% (28/29), 66.7% (4/6), and 91.4% (32/35), respectively, for nonrim APHE; 95.0% (19/20), 50.0% (4/8), and 82.1% (23/28), respectively, for nonperipheral washout; and 86.7% (26/30), 54.2% (13/24), and 72.2% (39/54) for EC, respectively. We developed an end-to-end deep-learning model that classifies the LI-RADS major features using subtraction MRI images. Our model exhibited satisfactory performance in classifying LI-RADS major features.

Deep survival modeling of longitudinal retinal OCT volumes for predicting the onset of atrophy in patients with intermediate AMD.

In patients with age-related macular degeneration (AMD), the risk of progression to late stages is highly heterogeneous, and the prognostic imaging biomarkers remain unclear. We propose a deep survival model to predict the progression towards the late atrophic stage of AMD. The model combines the advantages of survival modelling, accounting for time-to-event and censoring, and the advantages of deep learning, generating prediction from raw 3D OCT scans, without the need for extracting a predefined set of quantitative biomarkers. We demonstrate, in an extensive set of evaluations, based on two large longitudinal datasets with 231 eyes from 121 patients for internal evaluation, and 280 eyes from 140 patients for the external evaluation, that this model improves the risk estimation performance over standard deep learning classification models.

Data Fusion Algorithm For Wireless Sensor Networks Based On Cluster Routing And Deep Learning

In order to make full use of node energy and extend the network’s lifetime, a data fusion algorithm for wireless sensor networks is proposed in this paper. The algorithm improves the traditional clustering routing protocol and introduces a deep learning model to build the data fusion algorithm based on the optimized clustering architecture. When optimizing cluster routing protocol, the cluster head is selected by comprehensively considering such factors as node density, residual energy of nodes and the reasonable cluster size. The deep learning model and classification model are introduced in the data fusion process. The optimal parameters of the network are obtained by training the deep learning model of the sink node, then the sink nodes transfer these parameters to the corresponding sensor nodes. The cluster head extracts, classifies and fuses similar features of the data. The nodes in the cluster use the deep learning model to fit the collected raw data. Simulation results show that the data fusion algorithm proposed in this paper can reduce the redundant data transmitted to the sink node of wireless sensor networks, reduce the network energy consumption and prolong the network’s life. The overall performance of the network is improved.

Ischemia and Hemorrhage detection in CT images with Hyper parameter optimization of classification models and Improved UNet Segmentation Model

Deep learning is a powerful technique that has been applied to the task of stroke detection using medical imaging. Stroke is a medical condition that occurs when the blood supply to the brain is interrupted, which can cause brain damage and other serious complications. Detection of stroke is important in order to minimize damage and improve patient outcomes. One of the most common imaging modalities used for stroke detection is CT(Computed Tomography). CT can provide detailed images of the brain and can be used to identify the presence and location of a stroke. Deep learning models, particularly convolutional neural networks (CNNs), have shown promise for the task of stroke detection using CT images. These models can learn to automatically identify patterns in the images that are indicative of a stroke, such as the presence of an infarct or hemorrhage. Some examples of deep learning models used for stroke detection in CT images are U-Net, which is commonly used for medical image segmentation tasks, and CNNs, which have been trained to classify brain CT images into normal or abnormal.
 The purpose of this study is to identify the type of stroke from brain CT images taken without the administration of a contrast agent, i.e. occlusive (ischemic) or hemorrhagic (hemorrhagic). Stroke images were collected and a dataset was constructed with medical specialists. Deep learning classification models were evaluated with hyperparameter optimization techniques. And the result segmented with improved Unet model to visualize the stroke in CT images. Classification models were compared and VGG16 achieved %94 success. Unet model was achieved %60 IOU and detected the ischemia and hemorrhage differences.

Music Recommendation System Using Deep Learning

Abstract: As part of this study, we present a music recommendation system that makes use of deep learning. The system learns a neural network that can anticipate the user's musical preferences and provide personalised playlist suggestions based on the user's listening habits. The proposed method considers both the user's explicit tastes and those that may be deduced from their listening patterns. The technology is able to adapt to a user's evolving preferences over time and provide more relevant recommendations. Software that predicts what a user will wish to buy based on their tastes and prior purchases is called a recommendation system. Although the emphasis of this paper is on improving music recommendation systems, the approach outlined here might be applied to a broad range of other platforms and domains as well, including video sharing sites like YouTube and Netflix as well as online retailers like Amazon. System efficiency decreases as complexity increases. Our technique, Tunes Recommendation System (T-RECSYS), provides an efficient recommendation system that can make predictions in real time by integrating data from both content-based and collaborative filtering into a deep learning classification model. By applying our strategy to the Spotify Recsys Challenge dataset, we find a threshold that provides an optimal trade-off between false positives and false negatives, increasing accuracy to 88%

Research progress of computer vision tasks based on deep learning and SAE network

Abstract In recent years, artificial intelligence has gradually become the core driving force of a new round of scientific and technological revolution and industrial transformation, and is exerting a profound impact on all aspects of human life. With the rapid development of Internet big data and high-performance parallel computing, relevant research in computer vision has made significant progress in the past few years, becoming one of the important application branches in the field of artificial intelligence. The exercise of image classification forming part of computer vision tasks involves a large amount of computation, and training based on traditional deep learning (DL) classification models typically involves slow training and low accuracy in many parameters. Thus, in order to solve these problems, an image classification model based on DL and SAE network was proposed. Firstly, the main research of computer vision task-image classification is introduced in detail. Then, the combination framework of deep neural network and SAE network is built. At the same time, the deep neural network was used to carry out convolution operation of the parameters learned by SAE and extract each feature of the image with neurons, so as to improve the training accuracy of the deep neural network. Finally, the traditional deep neural network and SAE network were used for comparative experiment and analysis. Experimental results show that the proposed method has a certain degree of improvement in image classification accuracy compared with traditional deep neural network and SAE network, and the accuracy reaches 97.13%.

Abstract 5440: Deep-learning model for tumor type classification enables enhanced clinical decision support in cancer diagnosis

Abstract Background: Knowledge of a patient’s tumor type is essential for guiding clinical treatment decisions in cancer, but histologically-based diagnosis remains challenging for a subset of cancers. Genomic alterations are highly indicative of tumor type and can be used to build classifiers that predict diagnoses, but most genomic-based classification methods use whole genome sequencing (WGS) data which is not feasible for widespread clinical implementation at present. Clinical sequencing is typically performed using cancer gene panels that target individual mutations, often drivers, but previous tumor type classifiers developed using driver-based features alone perform poorly. We hypothesize that a classifier developed using state-of-the-art deep-learning methods and a sufficiently large training cohort would be able to overcome previous accuracy limitations and support the development of a clinically-relevant tumor type prediction model. Methods: We present Deep Genome-Derived Diagnosis (GDD-ENS), an ensemble-based deep-learning tumor type classification method trained using data from cancer gene panel sequencing. We specifically use data from MSK-IMPACT, an FDA-authorized clinical sequencing assay that reports genomic alterations including mutations, indels, copy number alterations, and gene fusions across 505 cancer-associated genes. We aggregated a discovery cohort of 35,372 patients with solid tumors profiled with MSK-IMPACT across 38 common cancer types and used this set to generate 4,487 somatic mutation features for development. Results: GDD-ENS achieves 78.8% accuracy on a held out validation cohort of 6971 patients. For the 71.9% of predictions assigned a high confidence by the model, accuracy increases to 92.7%, rivaling WGS-based models. We use Shapley Values to report prediction-specific feature importance, and aggregate them across cancer types to show GDD-ENS identifies known cancer type-genomic alteration trends. GDD-ENS also, with high accuracy, identifies patients with cancer types not included in the 38 common types using metrics derived from ensemble statistics. For patients where non-genomic information could further guide predictions, we implement a customizable prediction-specific adaptive prior distribution and report improved accuracy after adjusting predictions to account for features such as metastatic sample biopsy site. Finally, we apply GDD-ENS to a set of 1,123 patients with Cancers of Unknown Primary (CUP) and return high confidence predictions for 49% of these patients, in some cases matching predictions on CUP samples with diagnoses that were later confirmed through additional sampling and disease progression. Conclusions: Integrating GDD-ENS into prospective clinical sequencing workflows will enable clinically-relevant tumor type predictions that can guide treatment decisions in real-time. Citation Format: Madison Darmofal, Shalabh Suman, Gurnit Atwal, Jie-Fu Chen, Anna Varghese, Jason C. Chang, Anoop Balakrishnan Rema, Aijazuddin Syed, Quaid Morris, Michael Berger. Deep-learning model for tumor type classification enables enhanced clinical decision support in cancer diagnosis. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5440.

Natural language based malicious domain detection using machine learning and deep learning

Cyberattacks are still challenging since they are increasing day by day. Cybercriminals employ a variety of strategies to manipulate and exploit their targets vulnerabilities. Malicious URLs are one such strategy which is used to target large groups on various social media platforms. To draw internet users, these web addresses are disguised as being safe. Deliberate or inadvertent use of such URLs exposes the user or the organization in the cyberspace and opens the way for further attacks. Systems that use rules-based or machine learning algorithms to find malicious URLs usually rely on feature engineering. This requires domain expertise and experience. Sometimes, even after extracting features from a dataset, it may not completely leverage the potential of the dataset. The proposed method employs Natural Language Processing (NLP) approaches to vectorize the words in the URLs and applies machine learning and deep learning models for classification. Vectorization technique in NLP reduces the effort of feature engineering and maximizing the use of the dataset. For the experiment, two separate datasets are used. To vectorize the URL text, three different vectorization methods are used. To evaluate the performance of the proposed method, two different datasets (D1 and D2) that are regularly utilized in the research domain were used. The results demonstrate that the superior accuracy of 92.4 % with the D1 dataset is achieved by the Decision Tree (DT) with count vectorizer and the Random Forest (RF) with Term Frequency-Inverse Document Frequency (TF-IDF) vectorizer. With the D2 dataset, DT with TF-IDF vectorizer obtains a greater accuracy of 99.5 %. The Artificial Neural Network (ANN) model achieves 89.6 % accuracy with the D1 dataset and 99.2 % accuracy with the D2 dataset.

Predicting Breast Cancer Events in Ductal Carcinoma In Situ (DCIS) Using Generative Adversarial Network Augmented Deep Learning Model.

Standard clinicopathological parameters (age, growth pattern, tumor size, margin status, and grade) have been shown to have limited value in predicting recurrence in ductal carcinoma in situ (DCIS) patients. Early and accurate recurrence prediction would facilitate a more aggressive treatment policy for high-risk patients (mastectomy or adjuvant radiation therapy), and simultaneously reduce over-treatment of low-risk patients. Generative adversarial networks (GAN) are a class of DL models in which two adversarial neural networks, generator and discriminator, compete with each other to generate high quality images. In this work, we have developed a deep learning (DL) classification network that predicts breast cancer events (BCEs) in DCIS patients using hematoxylin and eosin (H & E) images. The DL classification model was trained on 67 patients using image patches from the actual DCIS cores and GAN generated image patches to predict breast cancer events (BCEs). The hold-out validation dataset (n = 66) had an AUC of 0.82. Bayesian analysis further confirmed the independence of the model from classical clinicopathological parameters. DL models of H & E images may be used as a risk stratification strategy for DCIS patients to personalize therapy.

Classification of metastatic hepatic carcinoma and hepatocellular carcinoma lesions using contrast-enhanced CT based on EI-CNNet.

For hepatocellular carcinoma and metastatic hepatic carcinoma, imaging is one of the main diagnostic methods. In clinical practice, diagnosis mainly relied on experienced imaging physicians, which was inefficient and cannot met the demand for rapid and accurate diagnosis. Therefore, how to efficiently and accurately classify the two types of liver cancer based on imaging is an urgent problem to be solved at present. The purpose of this study was to use the deep learning classification model to help radiologists classify the single metastatic hepatic carcinoma and hepatocellular carcinoma based on the enhanced features of enhanced CT (Computer Tomography) portal phase images of the liver site. In this retrospective study, 52 patients with metastatic hepatic carcinoma and 50 patients with hepatocellular carcinoma were among the patients who underwent preoperative enhanced CT examinations from 2017-2020. A total of 565 CT slices from these patients were used to train and validate the classification network (EI-CNNet, training/validation: 452/113). First, the EI block was used to extract edge information from CT slices to enrich fine-grained information and classify them. Then, ROC (Receiver Operating Characteristic) curve was used to evaluate the performance, accuracy, and recall of the EI-CNNet. Finally, the classification results of EI-CNNet were compared with popular classification models. By utilizing 80% data for model training and 20% data for model validation, the average accuracy of this experiment was 98.2% ± 0.62 (mean ± standard deviation (SD)), the recall rate was 97.23%±2.77, the precision rate was 98.02%±2.07, the network parameters were 11.83 MB, and the validation time was 9.83s/sample. The classification accuracy was improved by 20.98% compared to the base CNN network and the validation time was10.38s/sample. Compared with other classification networks, the InceptionV3 network showed improved classification results, but the number of parameters was increased and the validation time was 33s/sample, and the classification accuracy was improved by 6.51% using this method. EI-CNNet demonstrated promised diagnostic performance and has potential to reduce the workload of radiologists and may help distinguish whether the tumor is primary or metastatic in time; otherwise, it may be missed or misjudged. This article is protected by copyright. All rights reserved.

Identification and Classification of Small Sample Desert Grassland Vegetation Communities Based on Dynamic Graph Convolution and UAV Hyperspectral Imagery.

Desert steppes are the last barrier to protecting the steppe ecosystem. However, existing grassland monitoring methods still mainly use traditional monitoring methods, which have certain limitations in the monitoring process. Additionally, the existing deep learning classification models of desert and grassland still use traditional convolutional neural networks for classification, which cannot adapt to the classification task of irregular ground objects, which limits the classification performance of the model. To address the above problems, this paper uses a UAV hyperspectral remote sensing platform for data acquisition and proposes a spatial neighborhood dynamic graph convolution network (SN_DGCN) for degraded grassland vegetation community classification. The results show that the proposed classification model had the highest classification accuracy compared to the seven classification models of MLP, 1DCNN, 2DCNN, 3DCNN, Resnet18, Densenet121, and SN_GCN; its OA, AA, and kappa were 97.13%, 96.50%, and 96.05% in the case of only 10 samples per class of features, respectively; The classification performance was stable under different numbers of training samples, had better generalization ability in the classification task of small samples, and was more effective for the classification task of irregular features. Meanwhile, the latest desert grassland classification models were also compared, which fully demonstrated the superior classification performance of the proposed model in this paper. The proposed model provides a new method for the classification of vegetation communities in desert grasslands, which is helpful for the management and restoration of desert steppes.

Automated Monkeypox Skin Lesion Detection Using Deep Learning and Transfer Learning Techniques.

The current outbreak of monkeypox (mpox) has become a major public health concern because of the quick spread of this disease across multiple countries. Early detection and diagnosis of mpox is crucial for effective treatment and management. Considering this, the purpose of this research was to detect and validate the best performing model for detecting mpox using deep learning approaches and classification models. To achieve this goal, we evaluated the performance of five common pretrained deep learning models (VGG19, VGG16, ResNet50, MobileNetV2, and EfficientNetB3) and compared their accuracy levels when detecting mpox. The performance of the models was assessed with metrics (i.e., the accuracy, recall, precision, and F1-score). Our experimental results demonstrate that the MobileNetV2 model had the best classification performance with an accuracy level of 98.16%, a recall of 0.96, a precision of 0.99, and an F1-score of 0.98. Additionally, validation of the model with different datasets showed that the highest accuracy of 0.94% was achieved using the MobileNetV2 model. Our findings indicate that the MobileNetV2 method outperforms previous models described in the literature in mpox image classification. These results are promising, as they show that machine learning techniques could be used for the early detection of mpox. Our algorithm was able to achieve a high level of accuracy in classifying mpox in both the training and test sets, making it a potentially valuable tool for quick and accurate diagnosis in clinical settings.

Abstract P6-04-10: Recurrence Prediction in Ductal Carcinoma In Situ (DCIS) Patients from Tissue Microarrays (TMAs)

Abstract Recurrence Prediction in Ductal Carcinoma In Situ (DCIS) Patients Using Generative Adversarial Network (GAN) Augmented Deep Learning Model Background: DCIS patients have an excellent overall survival rate and over-treatment is always a cause for concern due to potential side-effects. Standard clinicopathological factors (age, growth pattern, tumor size, margin status and grade) have been shown to have limited value in predicting recurrence and segregation of high and low risk patients. Early and accurate recurrence prediction would facilitate a more aggressive treatment policy for high-risk patients (mastectomy or adjuvant radiation therapy), and simultaneously reduce over-treatment of low-risk patients. In this work, we have developed a deep learning (DL) classification framework that predicts recurrence in DCIS patients from Tissue microarrays (TMAs) hematoxylin and eosin (H&E) images using a generative adversarial network (GAN) augmented deep learning (DL) classification model. A GAN is a class of DL models, in which two adversarial neural networks, generator and discriminator contest among each other to generate high quality images. During the adversarial training process, the generator learns to synthesize realistic images similar to those in the training set while the discriminator learns to distinguish between real and generated images. In recent years, high quality medical images have been generated by GAN models. To the best of our knowledge, this is the first time a GAN model has been used to generate H&E images to train a DL classification model to predict recurrence in DCIS patients. Materials and methods: The cohort was comprised of 68 DCIS patients, aged between 35-89 years, lesion size of 5-90 mm, with a mix of low (15%), intermediate (35%) and 50% high grade cases. Patients were treated with mastectomy and/or a combination of lumpectomy, radiation and hormone therapy. TMAs were constructed from 2mm cores (1-3 cores per patient) in consultation with a breast pathologist to create hematoxylin and eosin (H&E) images for further analysis. The cohort was split into independent training (n=50 patients, 10 with recurrences at 5years) and validation groups (n=18 patients, 6 with recurrences at 5years). TMA (H&E) images were divided into smaller image patches of size 256x256 to train a GAN to generate image patches. A DL classification network (Resnet-Inception v2) was trained using TMA image patches and aggressive image patches generated by GAN to predict recurrence. The ability to generate synthetic image patches of aggressive lesions permitted training of a large DL classification network and predict recurrence in DCIS patients. Importantly, manual annotation was not necessary for the process. Results: The DL classification model trained with both TMA and GAN generated image patches predicted recurrence with an AUC of 0.87, sensitivity of 0.83 and specificity of 0.91 in the validation dataset. The DL classification model trained with image patches from TMAs only predicted recurrence with an AUC of 0.81. Conclusions: The use of a GAN model to generate H&E images circumvents the needs for a large cohort and accurate labor-intensive manual annotation of histopathological images, which is often required for training a large DL classification model. The use of GAN generated aggressive image patches during training significantly improves recurrence prediction accuracy of the DL classification model. Validation in independent larger cohorts is ongoing, and if successful, could provide a novel assay for risk prediction that does not waste precious tissue samples. Citation Format: Ghose Soumya, Yesim Gokmen-Polar, Sanghee Cho, Elizabeth McDonough, Cynthia Davis, Jhimli Mitra, Zhanpan Zhang, Fiona Ginty, Sunil Badve. Recurrence Prediction in Ductal Carcinoma In Situ (DCIS) Patients from Tissue Microarrays (TMAs) [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P6-04-10.

Prediction of Drug Demand Based on Deep Learning Approach and Classification Model

The high demand for drugs in the last period has caused problems with drug shortages in several pharmacies. Almost all pharmacies experience the same problem, causing many people who do not to get their drug needs during the current pandemic. To overcome this, analyzing the process of predicting drug demand in the next period is necessary. The prediction process can be used as an initial solution in solving problems to see the number of drug demand numbers that will occur. This study aims to develop a predictive analysis model for drug demand using a deep learning approach and a classification model. Deep learning is an approach that does well in the case of prediction. The classification model also includes the right concept for solving the problem. The prediction and classification analysis methods include K-Means clustering, Multiple Linear Regression (MRL), Artificial Neural Network (ANN), and Decision Tree algorithms C.45. This method can provide better performance results in the prediction process to get precise and accurate output. Prediction results obtained from the learning process provide an accuracy rate of 99.99%. The output of the classification model also provides an overview of the knowledge base in the form of a decision tree. The level of classification model testing carried out gives the accuracy of the classification pattern of 97.05% so that the analytical model developed can predict future drug demand.

Evaluation of deep learning models for classification of asphalt pavement distresses

ABSTRACT Transfer learning (TL) offers a convenient methodology for exploiting the capability of deep convolutional neural networks (DCNNs) for many image classification tasks including the classification of pavement distresses. Seven state-of-the-art DCNNs were retrained to classify asphalt pavement distresses grouped into eight classes using TL techniques. The aim was to evaluate the predictive performances of the selected DCNNs in order to provide some guidelines on selection of DCNNs for pavement application. The results show some existing DCNN’s are better than others for developing pavement distress classification models using the specific TL approach adopted in the study. The predictive ability of each model varied depending on distress class as some models with very low overall accuracy showed excellent results for individual distress class(s). Based on a combination of various performance metrics including F1-score, area under ROC curve, optimal operating threshold, training time, and model size, the best performing network had a relative score that was found to be significantly higher than the next two top-performing models. The best-performing networks were characterised by lower proportions of false negative values, low ambiguity scores, and well-defined t-SNE clusters that showed clear separation between the eight different pavement distress classes considered.

Classification of deep-sea cold seep bacteria by transformer combined with Raman spectroscopy

Raman spectroscopy is a rapid analysis method of biological samples without labeling and destruction. At present, the commonly used Raman spectrum classification models include CNN, RNN, etc. The transformer has not been used for Raman spectrum identification. This paper introduces a new method of transformer combined with Raman spectroscopy to identify deep-sea cold seep microorganisms at the single-cell level. We collected the Raman spectra of eight cold seep bacteria, each of which has at least 500 spectra for the training of transformer model. We compare the transformer classification model with other deep learning classification models. The experimental results show that this method can improve the accuracy of microbial classification. Our average isolation level accuracy is more than 97%.

Diabetic retinopathy detection using principal component analysis multi-label feature extraction and classification

Diabetic Retinopathy (DR) is the most common cause of eyesight loss that affects millions of people worldwide. Although there are recognized screening procedures for detecting the condition, such as fluorescein angiography and optical coherence tomography, the majority of patients are unaware and fail to have such tests at the proper time. Prompt identification of the condition is critical in avoiding vision loss, which occurs when Diabetes Mellitus (DM) is left untreated for an extended length of time. Several Machine Learning (ML) and Deep Learning (DL) algorithms have been used on DR datasets for disease prediction and classification, however, the majority of them have ignored the element of data pre-processing and dimensionality reduction, which are known as a major gap resulting in biased findings. In the first line of this research, data preprocessing was performed on the color Fundus Photographs (CFPs). Subsequently, we performed feature extraction with Principal Component Analysis (PCA). A Deep Learning Multi-Label Feature Extraction and Classification (ML-FEC) model based on pre-trained Convolutional Neural Network (CNN) architecture was proposed. Then, transfer learning was applied to train a subset of the images using three state-of-the-art CNN architectures, namely, ResNet50, ResNet152, and SqueezeNet1 with parameter-tuning to identify and classify the lesions. The experimental findings revealed an accuracy of 93.67% with a hamming loss of 0.0603 for ResNet 50, an accuracy of 91.94%, and Hamming Loss of 0.0805 for Squeezenet1 and an accuracy of 94.40% with Hamming loss of 0.0560 was achieved by ResNet 152 which demonstrates the suitability of the model for implementation in daily clinical practice and to support large scale DR screening programs.

Motivational Impact and Promotion of Research Culture Through the Development of Deep Learning Models

The professional training model in Colombia is moving from a competency-based approach to learning outcomes. This path is enriched with contributions both at the level of national policies and each institution, as well as the teaching experiences and interests of the students. In this environment, this research presents the impact on the motivational level, and on the development of research skills, in undergraduate students of the electrical area generated by implementing a training scheme that involves developing research formulated and guided by the students themselves. The students come from a model based on labor competencies, and the current curricular reform proposes a new model based on learning outcomes that demands a closer follow-up of the training process of each individual. The experimental group consisted of students in a new academic space in artificial intelligence (AI), for which specific instructional material was designed so that students could build deep learning classification models for real problems while implementing a scientific development scheme that includes the generation of scientific publications. The control group maintained a traditional training scheme based on content tracking and periodic written evaluations. The results showed that although both groups achieved a high level of learning effectiveness, the experimental group demonstrated more remarkable development in their creative thinking and more significant appropriation of the academic space and the training process, with a solid self-critical position. The research concluded that the follow-up model, as well as the material developed, manages to increase the student’s commitment to their training process and to generate positions on how this process is developed.