Different Types Of Datasets Research Articles

Reconstruction error based implicit regularization method and its engineering application to lung cancer diagnosis

The automatic diagnosis of lung cancer via artificial intelligence faces two hotspot issues: (1) insufficient data and (2) excessive redundant information, which make it difficult for convolutional neural networks (CNNs) to learn discriminative information of lung cancer. In this paper, we present the reconstruction error based implicit regularization method (REbIRM) that regularizes CNNs at the loss layer. During each training iteration, the reconstruction errors introduced by the two-stage discriminative auto-encoder are used to sharpen the generalization ability of deep CNNs by improving the decision boundary. In the application process, the trained deep CNN is used for completing computed tomography (CT) diagnostics. The main clinical benefit of our approach is that it is domain independent, requiring no specialized knowledge, and can therefore be applied to different types of datasets. To the best of our knowledge, this is the first attempt to implicitly regularize CNNs based on the reconstruction errors. Finally, experimental results on three CT image classification datasets show that REbIRM can achieve impressive results and that, in conjunction with Dropout, it obtains the state-of-the-art performance. REbIRM is also robust to the selection of hyper-parameters and only has the sublinear influence on the convergence of deep CNNs. Besides, empirical and theoretical evidence are provided to indicate that REbIRM prefers to converges in a constrained parameter space with flatter minima, which explains why it can generalize to new data. Finally, the nature of REbIRM is further explored through visualization techniques to analyze how it works in training deep CNNs.

Camellia oleifera Tree Detection and Counting Based on UAV RGB Image and YOLOv8

The detection and counting of Camellia oleifera trees are important parts of the yield estimation of Camellia oleifera. The ability to identify and count Camellia oleifera trees quickly has always been important in the context of research on the yield estimation of Camellia oleifera. Because of their specific growing environment, it is a difficult task to identify and count Camellia oleifera trees with high efficiency. In this paper, based on a UAV RGB image, three different types of datasets, i.e., a DOM dataset, an original image dataset, and a cropped original image dataset, were designed. Combined with the YOLOv8 model, the detection and counting of Camellia oleifera trees were carried out. By comparing YOLOv9 and YOLOv10 in four evaluation indexes, including precision, recall, mAP, and F1 score, Camellia oleifera trees in two areas were selected for prediction and compared with the real values. The experimental results show that the cropped original image dataset was better for the recognition and counting of Camellia oleifera, and the mAP values were 8% and 11% higher than those of the DOM dataset and the original image dataset, respectively. Compared to YOLOv5, YOLOv7, YOLOv9, and YOLOv10, YOLOv8 performed better in terms of the accuracy and recall rate, and the mAP improved by 3–8%, reaching 0.82. Regression analysis was performed on the predicted and measured values, and the average R2 reached 0.94. This research shows that a UAV RGB image combined with YOLOv8 provides an effective solution for the detection and counting of Camellia oleifera trees, which is of great significance for Camellia oleifera yield estimation and orchard management.

Pest Detection Based on Lightweight Locality-Aware Faster R-CNN

Accurate and timely monitoring of pests is an effective way to minimize the negative effects of pests in agriculture. Since deep learning-based methods have achieved good performance in object detection, they have been successfully applied for pest detection and monitoring. However, the current pest detection methods fail to balance the relationship between computational cost and model accuracy. Therefore, this paper proposes a lightweight, locality-aware faster R-CNN (LLA-RCNN) method for effective pest detection and real-time monitoring. The proposed model uses MobileNetV3 to replace the original backbone, reduce the computational complexity, and compress the size of the model to speed up pest detection. The coordinate attention (CA) blocks are utilized to enhance the locality information for highlighting the objects under complex backgrounds. Furthermore, the generalized intersection over union (GIoU) loss function and region of interest align (RoI Align) technology are used to improve pest detection accuracy. The experimental results on different types of datasets validate that the proposed model not only significantly reduces the number of parameters and floating-point operations (FLOPs), but also achieves better performance than some popular pest detection methods. This demonstrates strong generalization capabilities and provides a feasible method for pest detection on resource-constrained devices.

Cognitive activity analysis of Parkinson's patients using artificial intelligence techniques.

The development of modern Artificial Intelligence (AI) based models for the early diagnosis of Parkinson's disease (PD) has been gaining deep attention by researchers recently. In particular, the use of different types of datasets (voice, hand movements, gait, etc.) increases the variety of up-to-date models. Movement disorders and tremors are also among the most prominent symptoms of PD. The usage of drawings in the detection of PD can be a crucial decision-support approach that doctors can benefit from. A dataset was created by asking 40 PD and 40 Healthy Controls (HC) to draw spirals with and without templates using a special tablet. The patient-healthy distinction was achieved by classifying drawings of individuals using Support Vector Machine (SVM), Random Forest (RF), and Naive Bayes (NB) algorithms. Prior to classification, the data were normalized by applying the min-max normalization method. Moreover, Leave-One-Subject-Out (LOSO) Cross-Validation (CV) approach was utilized to eliminate possible overfitting scenarios. To further improve the performances of classifiers, Principal Component Analysis (PCA) dimension reduction technique were also applied to the raw data and the results were compared accordingly. The highest accuracy among machine learning based classifiers was obtained as 90% with SVM classifier using non-template drawings with PCA application. The model can be used as a pre-evaluation system in the clinic as a non-invasive method that also minimizes environmental and educational level differences by using simple hand gestures such as hand drawing, writing numbers, words, and syllables. As a result of our study, preliminary preparation has been made so that hand drawing analysis can be used as an auxiliary system that can save time for health professionals. We plan to work on more comprehensive data in the future.

Kernel-based iVAT with adaptive cluster extraction

AbstractVisual Assessment of cluster Tendency (VAT) is a popular method that visually represents the possible clusters found in a dataset as dark blocks along the diagonal of a reordered dissimilarity image (RDI). Although many variants of the VAT algorithm have been proposed to improve the visualisation quality on different types of datasets, they still suffer from the challenge of extracting clusters with varied densities. In this paper, we focus on overcoming this drawback of VAT algorithms by incorporating kernel methods and also propose a novel adaptive cluster extraction strategy, named CER, to effectively identify the local clusters from the RDI. We examine their effects on an improved VAT method (iVAT) and systematically evaluate the clustering performance on 18 synthetic and real-world datasets. The experimental results reveal that the recently proposed data-dependent dissimilarity measure, namely the Isolation kernel, helps to significantly improve the RDI image for easy cluster identification. Furthermore, the proposed cluster extraction method, CER, outperforms other existing methods on most of the datasets in terms of a series of dissimilarity measures.

Multi-modal contrastive learning of subcellular organization using DICE.

The data deluge in biology calls for computational approaches that can integrate multiple datasets of different types to build a holistic view of biological processes or structures of interest. An emerging paradigm in this domain is the unsupervised learning of data embeddings that can be used for downstream clustering and classification tasks. While such approaches for integrating data of similar types are becoming common, there is scarcer work on consolidating different data modalities such as network and image information. Here, we introduce DICE (Data Integration through Contrastive Embedding), a contrastive learning model for multi-modal data integration. We apply this model to study the subcellular organization of proteins by integrating protein-protein interaction data and protein image data measured in HEK293 cells. We demonstrate the advantage of data integration over any single modality and show that our framework outperforms previous integration approaches. Availability: https://github.com/raminass/protein-contrastive Contact: raminass@gmail.com.

Comparative Analysis of Machine-Learning Model Performance in Image Analysis: The Impact of Dataset Diversity and Size.

This study presents an analysis of machine-learning model performance in image analysis, with a specific focus on videolaryngoscopy procedures. The research aimed to explore how dataset diversity and size affect the performance of machine-learning models, an issue vital to the advancement of clinical artificial intelligence tools. A total of 377 videolaryngoscopy videos from YouTube were used to create 6 varied datasets, each differing in patient diversity and image count. The study also incorporates data augmentation techniques to enhance these datasets further. Two machine-learning models, YOLOv5-Small and YOLOv8-Small, were trained and evaluated on metrics such as F1 score (a statistical measure that combines the precision and recall of the model into a single metric, reflecting its overall accuracy), precision, recall, mAP@50, and mAP@50-95. The findings indicate a significant impact of dataset configuration on model performance, especially the balance between diversity and quantity. The Multi-25 × 10 dataset, featuring 25 images from 10 different patients, demonstrates superior performance, highlighting the value of a well-balanced dataset. The study also finds that the effects of data augmentation vary across different types of datasets. Overall, this study emphasizes the critical role of dataset structure in the performance of machine-learning models in medical image analysis. It underscores the necessity of striking an optimal balance between dataset size and diversity, thereby illuminating the complexities inherent in data-driven machine-learning development.

Automatic driving image matching via Random Sample Consensus (RANSAC) and Spectral Clustering (SC) with monocular camera.

In today's big data era, with the development of the Internet of Things (IoT) technology and the trend of autonomous driving prevailing, visual information has shown a blowout increase, but most image matching algorithms have problems such as low accuracy and low inlier rates, resulting in insufficient information. In order to solve the problem of low image matching accuracy and low inlier rate in the field of autonomous driving, this research innovatively applies spectral clustering (SC) in the field of data analysis to image matching in the field of autonomous driving, and a new image matching algorithm "SC-RANSAC" based on SC and Random Sample Consensus (RANSAC) is proposed. The datasets in this research are collected based on the monocular cameras of autonomous driving cars. We use RANSAC to obtain the initial inlier set and the SC algorithm to filter RANSAC's outliers and then use the filtered inliers as the final inlier set. In order to verify the effectiveness of the algorithm, it shows the matching effect from three angles: camera translation, rotation, and rotation and translation. SC-RANSAC is also compared with RANSAC, graph-cut RANSAC, and marginalizing sample consensus by using two different types of datasets. Finally, we select three representative pictures to test the robustness of the SC-RANSAC algorithm. The experimental results show that SC-RANSAC can effectively and reliably eliminate mismatches in the initial matching results; has a high inlier rate, real-time performance, and robustness; and can be effectively applied in the environment of autonomous driving.

Research on the performance of hybrid vision models based on ViT

ViT is a model proposed by the Google team in 2020 to apply a transformer in image classification, although it is not the first paper to apply a transformer in visual tasks, because of its model is simple and effective, and scalable, it has become a milestone work in the application of transformer in CV field, and has also triggered the subsequent related research. The core conclusion of the original ViT paper is that when there is enough data for pre-training, ViT outperforms CNN, breaks through the limitation of the transformer's lack of inductive bias, and can achieve better migration results in downstream tasks. However, when the training dataset is not large enough, ViT usually performs worse than ResNets of the same size, because Transformer lacks inductive bias, a kind of a priori knowledge, assumptions made in advance, compared with CNN. Through its innovative architecture and powerful performance, the visual representation transform (ViT) model continues to advance the field of computer vision, while facing some challenges and room for improvement. With the deepening of research and the continuous development of technology, ViT is expected to play a greater role in more practical applications. The article aims to explore the advantages and applicability of the ViT model and tries to construct a hybrid visual model to improve its generalization ability for different types of datasets, demonstrating the hybrid model's significance in improving the performance of the ViT model.

Predicting single-cell cellular responses to perturbations using cycle consistency learning.

Phenotype-based drug screening emerges as a powerful approach for identifying compounds that actively interact with cells. Transcriptional and proteomic profiling of cell lines and individual cells provide insights into the cellular state alterations that occur at the molecular level in response to external perturbations, such as drugs or genetic manipulations. In this paper, we propose cycleCDR, a novel deep learning framework to predict cellular response to external perturbations. We leverage the autoencoder to map the unperturbed cellular states to a latent space, in which we postulate the effects of drug perturbations on cellular states follow a linear additive model. Next, we introduce the cycle consistency constraints to ensure that unperturbed cellular state subjected to drug perturbation in the latent space would produces the perturbed cellular state through the decoder. Conversely, removal of perturbations from the perturbed cellular states can restore the unperturbed cellular state. The cycle consistency constraints and linear modeling in the latent space enable to learn transferable representations of external perturbations, so that our model can generalize well to unseen drugs during training stage. We validate our model on four different types of datasets, including bulk transcriptional responses, bulk proteomic responses, and single-cell transcriptional responses to drug/gene perturbations. The experimental results demonstrate that our model consistently outperforms existing state-of-the-art methods, indicating our method is highly versatile and applicable to a wide range of scenarios. The source code is available at: https://github.com/hliulab/cycleCDR.

Weapon Detection Using FRCNN

Abstract: Due to the increase in crime in remote and congested places, security is a top priority in all fields. Computer vision is having numerous uses for abnormal objects recognition and monitoring to deal with an array of scenarios. It's necessary for video surveillance systems to be employed as a way to fulfil the growing need and the protection of individual's financial assets, safety, and security, and to enhance having the capacity to detect and assess unusual events, is necessary for intelligence monitoring.This enables the utilization of FRCNN machine learning that autonomously identify weapons. Two different types of datasets will be utilized in the provided implementation. A pair of datasets can be downloaded, one with labelled photos and the second with a combination of manually labelled photos. In almost all of the aforementioned scenarios, algorithms gather precise data; nevertheless, how well speed and precision coincide could impact how algorithms are used in real-life instances

An Update of the NeQuick-Corr Topside Ionosphere Modeling Based on New Datasets

A new analytical formula for H0, one of the three parameters (H0, g, and r) on which the NeQuick model is based to describe the altitude profile of the electron density above the F2-layer peak height hmF2, has recently been proposed. This new analytical representation of H0, called H0,corr, relies on numerical grids based on two different types of datasets. On one side, electron density observations by the Swarm satellites over Europe from December 2013 to September 2018, and on the other side, IRI UP (International Reference Ionosphere UPdate) maps over Europe of the critical frequency of the ordinary mode of propagation associated with the F2 layer, foF2, and hmF2, at 15 min cadence for the same period. The new NeQuick topside representation based on H0,corr, hereafter referred to as NeQuick-corr, improved the original NeQuick topside representation. This work updates the numerical grids of H0,corr by extending the underlying Swarm and IRI UP datasets until December 2021, thus allowing coverage of low solar activity levels, as well. Moreover, concerning Swarm, besides the original dataset, the calibrated one is considered, and corresponding grids of H0,corr calculated. At the same time, the role of g is investigated, by considering values different from the reference one, equal to 0.125, currently adopted. To understand what are the best H0,corr grids to be considered for the NeQuick-corr topside representation, vertical total electron content data for low, middle, and high latitudes, recorded from five low-Earth-orbit satellite missions (COSMIC/FORMOSAT-3, GRACE, METOP, TerraSAR-X, and Swarm) have been analyzed. The updated H0,corr grids based on the original Swarm dataset with a value for g = 0.15, and the updated H0,corr grids based on the calibrated Swarm dataset with a value for g = 0.14, are those for which the best results are obtained. The results show that the performance of the different NeQuick-corr models is reliable also for low latitudes, even though these are outside the spatial domain for which the H0,corr grids were obtained, and are dependent on solar activity.

Traffic prediction for diverse edge IoT data using graph network

AbstractMore researchers are proposing artificial intelligence algorithms for Internet of Things (IoT) devices and applying them to themes such as smart cities and smart transportation. In recent years, relevant research has mainly focused on data processing and algorithm modeling, and most have shown good prediction results. However, many algorithmic models often adjust parameters for the corresponding datasets, so the robustness of the models is weak. When different types of data face other model parameters, the prediction performance often varies a lot. Thus, this work starts from the perspective of data processing and algorithm models. Taking traffic data as an example, we first propose a new data processing method that processes traffic data with different attributes and characteristics into a dataset that is more common for most models. Then we will compare different types of datasets from the perspective of multiple model parameters, and further analyze the precautions and changing trends of different traffic data in machine learning. Finally, different types of data and ranges of model parameters are explored, together with possible reasons for fluctuations in forecast results when data parameters change.

A clinical decision support system using rough set theory and machine learning for disease prediction

ObjectiveTechnological advances have led to drastic changes in daily life, and particularly healthcare, while traditional diagnosis methods are being replaced by technology-oriented models and paper-based patient healthcare records with digital files. Using the latest technology and data mining techniques, we aimed to develop an automated clinical decision support system (CDSS), to improve patient prognoses and healthcare delivery. Our proposed approach placed a strong emphasis on improvements that meet patient, parent, and physician expectations. We developed a flexible framework to identify hepatitis, dermatological conditions, hepatic disease, and autism in adults and provide results to patients as recommendations. The novelty of this CDSS lies in its integration of rough set theory (RST) and machine learning (ML) techniques to improve clinical decision-making accuracy and effectiveness. MethodsData were collected through various web-based resources. Standard preprocessing techniques were applied to encode categorical features, conduct min-max scaling, and remove null and duplicate entries. The most prevalent feature in the class and standard deviation were used to fill missing categorical and continuous feature values, respectively. A rough set approach was applied as feature selection, to remove highly redundant and irrelevant elements. Then, various ML techniques, including K nearest neighbors (KNN), linear support vector machine (LSVM), radial basis function support vector machine (RBF SVM), decision tree (DT), random forest (RF), and Naive Bayes (NB), were employed to analyze four publicly available benchmark medical datasets of different types from the UCI repository and Kaggle. The model was implemented in Python, and various validity metrics, including precision, recall, F1-score, and root mean square error (RMSE), applied to measure its performance. ResultsFeatures were selected using an RST approach and examined by RF analysis and important features of hepatitis, dermatology conditions, hepatic disease, and autism determined by RST and RF exhibited 92.85 %, 90.90 %, 100 %, and 80 % similarity, respectively. Selected features were stored as electronic health records and various ML classifiers, such as KNN, LSVM, RBF SVM, DT, RF, and NB, applied to classify patients with hepatitis, dermatology conditions, hepatic disease, and autism. In the last phase, the performance of proposed classifiers was compared with that of existing state-of-the-art methods, using various validity measures. RF was found to be the best approach for adult screening of: hepatitis with accuracy 88.66 %, precision 74.46 %, recall 75.17 %, F1-score 74.81 %, and RMSE value 0.244; dermatology conditions with accuracy 97.29 %, precision 96.96 %, recall 96.96 %, F1-score 96.96 %, and RMSE value, 0.173; hepatic disease, with accuracy 91.58 %, precision 81.76 %, recall 81.82 %, F1-Score 81.79 %, and RMSE value 0.193; and autism, with accuracy 100 %, precision 100 %, recall 100 %, F1-score 100 %, and RMSE value 0.064. ConclusionThe overall performance of our proposed framework may suggest that it could assist medical experts in more accurately identifying and diagnosing patients with hepatitis, dermatology conditions, hepatic disease, and autism.

Performance Evaluation of Deep Learning in Detection COVID-19 Based on Different Types of Datasets

Performance Evaluation of Deep Learning in Detection COVID-19 Based on Different Types of Datasets

Intelligent Fault Diagnosis of Rolling Bearing Based on Gramian Angular Difference Field and Improved Dual Attention Residual Network.

With the rapid development of smart manufacturing, data-driven deep learning (DL) methods are widely used for bearing fault diagnosis. Aiming at the problem of model training crashes when data are imbalanced and the difficulty of traditional signal analysis methods in effectively extracting fault features, this paper proposes an intelligent fault diagnosis method of rolling bearings based on Gramian Angular Difference Field (GADF) and Improved Dual Attention Residual Network (IDARN). The original vibration signals are encoded as 2D-GADF feature images for network input; the residual structures will incorporate dual attention mechanism to enhance the integration ability of the features, while the group normalization (GN) method is introduced to overcome the bias caused by data discrepancies; and then the model is trained to complete the classification of faults. In order to verify the superiority of the proposed method, the data obtained from Case Western Reserve University (CWRU) bearing data and bearing fault experimental equipment were compared with other popular DL methods, and the proposed model performed optimally. The method eventually achieved an average identification accuracy of 99.2% and 97.9% on two different types of datasets, respectively.

Comparison of Data Visualization, Outlier Detection and Data Dimensionality Reduction Methods

With the deepening of the digital age of information, people's daily data is getting larger and larger, and it is more and more difficult to quantify and process. At this time, the data processing means becomes particularly important. This paper compares and analyzes some methods from data visualization to data dimensionality reduction to outlier detection. In this paper, two different types of datasets, ModelNet40, and red wine quality, are used to introduce the visualization method of the Farthest Point Sampling (FPS). This method can have a clear visual effect on the data dimension and scale, and allow users to observe the structure, type, and scale of the data. In data dimensionality reduction, the study uses Principal Component Analysis (PCA), T-Distributed Stochastic Neighbor Embedding (t-SNE), Triplets Manifold Approximation and Projection (TriMAP), Uniform Manifold Approximation and Projection (UMAP), Pairwise Controlled Manifold Approximation Projection (PaCMAP), and Autoencoder to compare their dimensionality reduction effects. Through these methods, this paper finds that different methods have different effects on different datasets. Therefore, in data dimensionality reduction, it can get twice the result with half the effort by choosing the appropriate method. Finally, this paper also detects outliers. Outliers in datasets will make it difficult for people to process data and make subsequent results inaccurate, so it is necessary to identify outliers. This paper involves methods such as isolation forest and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). Through this paper, the methods of different datasets are analyzed and summarized.

Multigrade brain tumor classification in MRI images using Fine tuned efficientnet

Medical imaging plays a vital role in detecting and treating brain tumors. Malignant or non-malignant brain tissue’s abnormal growth causes long-term brain damage. It is crucial to detect and properly categorize the kind of brain tumor. Specialists normally use MRI to create high-contrast grayscale brain images to segment them. Convolutional neural networks (CNN) driven by deep learning (DL) have transformed computer-assisted testing systems by producing good results in a wide range of medical imaging analytics applications, including tumor diagnosis in the brain. The paper introduces a lightweight fine-tuned Convolutional Neural Network EfficientNet ’ECNN’ to detect brain tumors. In this study, we provide a transfer learning-based measurement strategy for grouping cerebrum growths in three distinct datasets with different classifications, such as meningioma, glioma, and pituitary growth, using fine-tuned EfficientNets. The findings of this research rely on Efficient Nets to classify brain tumors in three different types of datasets utilizing a fine-tuned transfer learning mechanism. With EfficientNetV2S as the system’s foundation, our proposed way of fine-tunned pre-trained EfficientNetV2S model outperformed for all datasets over state of the art methods. The effectiveness of the suggested model has been assessed using performance metrics, and outcomes were compared to those produced using state-of-the-art approaches. The average test accuracy, recall, precision, and sensitivity score are 98.48%, 98%, 98.5%, and 98.71%, respectively.

One-Dimensional LSTM-Regulated Deep Residual Network for Data-Driven Fault Detection in Electric Machines

Achieving a model which accurately diagnoses faults in electric machines is a vital step in data-driven fault detection approaches. To this aim, this paper proposes a Long Short-Term Memory (LSTM) regulated deep residual network for data-driven fault diagnosis purposes in electric machines. The advantages of the proposed network are that it is more general in terms of fault type and measurement, results in a more accurate model for fault classification, and has faster convergence compared with other networks, such as conventional deep residual networks. In order to prove these advantages of the proposed network, it is evaluated by two different types of datasets. One is the Inter-Turn Short Circuit (ITSC) fault in a Permanent Magnet Synchronous Motor (PMSM) with the data of measured three-phase current. The second one is the Case Western Reverse University (CWRU) bearing fault dataset with the vibration measurements. The performance of the network is also compared with other networks. Results reveal that the model can accurately detect both types of faults by two different measurements with a test accuracy of 100%. Furthermore, it converges faster than other networks in the training procedure.

Medical image segmentation based on dynamic positioning and region-aware attention

Transformer has already proven its ability to model long-distance dependencies. However, medical images have strong local structures. Directly using Transformer to extract features would not only contain redundant information increasing the computational effort, but also be detrimental to extracting local details. Given these issues, we propose a network based on dynamic positioning and region-aware attention, which adopts a two-stage feature extraction strategy. In the shallow layer, we design Dynamic Positioning Attention (DPA). It will localize to the key feature information and construct a variable window for it, then perform attention calculation. DPA improves the learning ability of local details, reduces the amount of computation. At the deep level, Bi-Level Routing Attention (BRA) is used to discard irrelevant key–value pairs, achieve content-aware sparse attention for the deep dispersed semantic information, and improve computational efficiency. After several experiments, the results show that our method achieves advanced performance on different types of datasets.