Effect Of Augmentation Research Articles

The Effects of Light Treatments on Growth and Flowering Characteristics of Oncidesa Gower Ramsey ‘Honey Angel’ at Different Growth Stages

In our previous work, we observed that Oncidesa Gower Ramsey ‘Honey Angel’ (HA) plants became stunned on hot summer afternoons, and the seasonal trend in solar radiation affected its production schedule by limiting flower yield and quality. The objective of this work was to study the growth and flowering characteristics of HA pseudobulbs at three stages of growth (G2–G4) in response to three types of light-emitting diode (LED) lighting treatments, including full spectrum (FS), deep red/white-medium blue (DR/W-MB), and deep red/white-low blue (DR/W-LB), for two additional time intervals. The supplementary LED lighting time intervals (S) applied daily were carried out for 1 h (4:00~5:00 a.m., as S-1) or 2 h (4:00~6:00 a.m., as S-2) from March to September, 2022. Natural light without supplemental lighting was the control. The length of pseudobulb (PL), width of pseudobulb (PW), thickness of pseudobulb (PT), length of inflorescence (FL), number of branches (FB), number of florets (FN), and days to flowering (FD) per plant were recorded andcalculated when 80% of florets became mature. Light treatments significantly affected all pseudobulb growth and flower quality traits at different Gs, especially pseudobulb length (PL) and flower number (FN) under different LED types and lighting time intervals. MB-1 treatment promoted PT at both G3 and G4, whereas MB-2 treatment increased PW at both G2 and G4. Both MB-1 and LB-1 treatments had augmented effects on PL, respectively, at G2 and G3. The PW, FL, FB, and FN increased with additional light time and reached maxima under MB-2 treatment at G4 compared to other treatments and controls. Early flowering and an increased number of flowers at G4 were observed in plants grown under MB-2 treatment. Controlling light quality and supplementary light time intervals enables the production of HA plants with the desired growth and flowering quality characteristics of the pseudobulbs.

ARIAS: An AR-based interactive advertising system.

In this paper, we present an interactive advertising system based on augmented reality(AR) called ARIAS, which is manipulated with gestures for displaying advertising videos. Two-dimensional markers are defined in the system. The system captures the frame data through the camera in real time, uses OpenCV library to identify the predefined markers, and calculates the pose of markers captured by the camera. With OpenGL library, a virtual cubic model is created at the position of the marker, and thus videos or images are displayed on the six faces of the cube. The virtual cube, together with the original frame data collected by the camera, is displayed in the interactive window to achieve the augmented reality effect. Customers are accessible to various advertising content by observing the marker from different positions. The system, meanwhile, supports gesture operation in order to make the customers pay attention to the content they are interested in with one hand. The MediaPipe Hand framework is used to extract the landmarks of hands, based on which, a series of gestures are designed for interactive operation. The efficiency and accuracy of the system are tested and analyzed with the result, indicating that the system has high reliability and good interactiveness. This system is open at https://github.com/wanzhuxie/ARIAS/tree/PLOS-ONE.

Effects of data augmentation by replicating instances : Classification performance by Decision trees

Numerous medical data have classification problems for it has unbalanced instances. This means the medical data has less number of positive instances because it refers to disease diagnosis. Even the world's common disease diabetes data is unbalanced. We have the machine learning algorithms to combat the imbalanced classification. Among them, resampling is a useful technique that helps to balance the instance based on the classes’ majority and minority by under-sampling and oversampling methods. However, in spite of its circulation, the sampling has issues in the efficient evaluation of small-sized data. This study measured sampling methods and machine learning classifiers of different split percentages using a diabetes dataset which waver units of imbalance and produce better accuracy. The evaluation measure for each replication percentage is calculated and the same is interpreted in the Discussion.

Mixed-curvature knowledge-enhanced graph contrastive learning for recommendation

Contrastive learning has recently triggered a series of valuable studies in the recommendation field, as it can extract supervised information from large-scale unsupervised data, reducing interference from unrelated entities. However, in real scenarios, supervised data is often sparse and challenging to fully leverage, inevitably leading to decreased accuracy in recommendation algorithms based on contrastive learning. Although knowledge graphs can offer abundant facts and serve as a rich source for supervised signals, achieving data augmentation effects, knowledge graph embedding heightens sensitivity to changes in graph node information. Moreover, the Euclidean space is not entirely suitable for accommodating varying degrees of graph structure expansion. To fill this research gap, we propose a mixed-curvature knowledge-enhanced graph contrastive learning for recommendation (MKGCL). Specifically, we design a knowledge-enhanced approach to generate knowledge-enhanced global views, which combines user–item interaction views with knowledge-augmented semantic views, resulting in more reliable and comprehensive regulatory signals. In particular, based on the characteristics of the curvature space, we construct multiple product manifolds of a single curvature space, thereby constructing a comprehensive mixed-curvature space, which ensures better scalability for the expansion of the graph structure. Extensive experiments on four benchmark datasets, results show that MKGCL significantly outperforms other state-of-the-art algorithms in comparison.

Effectiveness of data augmentation to predict students at risk using deep learning algorithms

The academic intervention to predict at-risk higher education (HE) students requires effective data model development. Such data modelling projects in the HE context may have common issues related to (a) adopting small-scale modelling that gives limited options for early intervention and (b) using imbalanced data that hinders capturing effective details of poorly performing students. We address the issues going beyond the distribution-based algorithm, using a multilayer perceptron classifier which shows better on confusion metric, recall, and precision measures for identifying at-risk students. Our proposed deep learning-based model, which uses data augmentation techniques to supplement the data instances and balance the dataset, aims to improve the prediction accuracy of whether the student will fail or not based on their interaction with the learning management systems to prevent struggling students from evasion.

Lift Augmentation on a Tiltrotor Wing Using the Combination of Vortex Generators and Gurney’s Flap

Recently, flow control using vortex generators (VGs) and a Gurney flap (GF) has received considerable attention, but independently. The purpose of this study is to perform a numerical investigation into the lift augmentation effects of a tiltrotor wing with the combination of VGs and GF. The numerical results were obtained with the Reynolds-averaged Navier-Stokes (RANS) equations, and the turbulence was solved by the Spalart-Allmaras one-equation turbulence model. The separate and joint performances of these two control devices at different angles of attack are determined. It is shown that the combined configuration can provide greater lift augmentation than either device individually. Compared with the baseline wing, the implementation of both devices increases the stall angle of attack from 10° to 22°, and the maximum lift coefficient is improved by 82.33%.

5-Fluorouracil and Anti-EGFR antibody scaffold chitosan-stabilized Pickering emulsion: Formulations, physical characterization, in-vitro studies in NCL-H226 cells, and in-vivo investigations in Wistar rats for the augmented therapeutic effects against squamous cell carcinoma

This research seeks to optimize a chitosan-stabilized Pickering emulsion (PE) containing 5-fluorouracil (5-FU) as a potential Squamous Cell Carcinoma therapy. The 5-Fluorouracil was also thoroughly analysed using UV spectrophotometry and RP-HPLC, demonstrating exceptional linearity, sensitivity, precision, and robustness. The techniques of characterization revealed Pickering emulsion (PE) morphology, solid-like gel properties, successful encapsulation, and promising anticancer effects. FTIR was used to validate the efficacy of encapsulation, and DSC was used to confirm the post-encapsulation drug stability. The 0.6 % chitosan-stabilized PE showed exceptional stability and drug loading efficiency. Anti-EGFR-5-FU-CS-PE gel was developed for sustained drug release in the treatment of Squamous Cell Carcinoma. Anti-EGFR-5-FU-CS-PE demonstrated potent anticancer effects in vitro, with a lower IC50 than 5-FU and 5-FU-CS-PE. Anti-EGFR-5-FU-PE Pickering emulsions based on chitosan were investigated for their rheological properties, cellular interactions, and therapeutic potential. Both emulsions and gel exhibited sustained in vitro drug release after successful encapsulation. Anti-EGFR-5-FU-CS-PE induced apoptosis, decreased mitochondrial membrane potential, and inhibited the migration of cancer cells. Wistar mice were tested for safety and tumour growth inhibition. All formulations exhibited exceptional six-month stability. Anti-EGFR-5-FU-CS-PE emerges as a viable therapeutic option, necessitating additional research.

Comparative Effectiveness of Data Augmentation Using Traditional Approaches versus StyleGANs in Automated Sewer Defect Detection

Comparative Effectiveness of Data Augmentation Using Traditional Approaches versus StyleGANs in Automated Sewer Defect Detection

Data augmentation by using gans and image transformation in facial emotion classification

We propose different approach combinations including GANs and image transformation in facial emotion classification especially for FER-2013 dataset. Our goal is not to reach the highest accuracy for this dataset, but to compare and verify the data augmentation effects for several main GAN methods such as Vanilla GAN, CGAN, DCGAN and BiGAN. We used these GAN models to generate fake images and put them to our train dataset. And the data together was through image transformation to train in the CNN model that we designed to perform facial emotion classification. Base on the result when we used some GANs (BiGAN/DCGAN) and image transformation, the accuracy of the model indeed has been improved. The best combination data augmentation approaches in this paper are using image transformation and DCGAN.

Effects of Data Augmentation on the Nine-Axis IMU-Based Orientation Estimation Accuracy of a Recurrent Neural Network.

The nine-axis inertial and measurement unit (IMU)-based three-dimensional (3D) orientation estimation is a fundamental part of inertial motion capture. Recently, owing to the successful utilization of deep learning in various applications, orientation estimation neural networks (NNs) trained on large datasets, including nine-axis IMU signals and reference orientation data, have been developed. During the training process, the limited amount of training data is a critical issue in the development of powerful networks. Data augmentation, which increases the amount of training data, is a key approach for addressing the data shortage problem and thus for improving the estimation performance. However, to the best of our knowledge, no studies have been conducted to analyze the effects of data augmentation techniques on estimation performance in orientation estimation networks using IMU sensors. This paper selects three data augmentation techniques for IMU-based orientation estimation NNs, i.e., augmentation by virtual rotation, bias addition, and noise addition (which are hereafter referred to as rotation, bias, and noise, respectively). Then, this paper analyzes the effects of these augmentation techniques on estimation accuracy in recurrent neural networks, for a total of seven combinations (i.e., rotation only, bias only, noise only, rotation and bias, rotation and noise, and rotation and bias and noise). The evaluation results show that, among a total of seven augmentation cases, four cases including 'rotation' (i.e., rotation only, rotation and bias, rotation and noise, and rotation and bias and noise) occupy the top four. Therefore, it may be concluded that the augmentation effect of rotation is overwhelming compared to those of bias and noise. By applying rotation augmentation, the performance of the NN can be significantly improved. The analysis of the effect of the data augmentation techniques presented in this paper may provide insights for developing robust IMU-based orientation estimation networks.

Augmentation of Apis mellifera for Fruit Yield Enhancement in Capparis decidua (Forssk.) Edgew (Kair)

Capparis decidua (Family: Capparidaceae) is a very nutritious shrub of arid region. Its fruits are utilized in famous Rajasthani Panchkutta and Tricutta vegetable and pickle making. The present paper deals with the effect of augmentation of Apis mellifera beehives on the fruit setting and fruit quality parameters. It was found that the average numbers of fruit setting raceme-1 were found 4.36, 3.77 and 2.2 in natural pollination with augmentation of honey bees, pollination by honey bees only and natural pollination respectively. Germination percentages, total sugar, average fruit weight, shoot length and seedling length was higher in case of natural pollination with augmentation of honey bees among all the treatments.

Augmented antitumor effects of erlotinib and cabozantinib on A549 non-small cell lung cancer: In vitro and in vivo studies

Non-small cell lung carcinoma is a challenging disease worldwide. This study aims to determine whether combining erlotinib, an epidermal growth factor receptor (EGFR) inhibitor, with cabozantinib, a mesenchymal-epithelial transition factor (c-Met) inhibitor, would have an augmented therapeutic benefit on A549 cells. The combination of erlotinib and cabozantinib (5 µM) inhibited A549 cell viability compared to each monotherapy at ≥ 10 µM as confirmed by the MTT assay. Combination therapy also has a more potent inhibition of cellular migration than monotherapy using the wound-healing assay. Furthermore, mRNA expression analyses for assessing apoptosis, metastasis, and cell cycle-related genes, the results showed that combination therapy significantly inhibits levels of BCL-2, MMP-9, VEGF, and TGF-β while inducing p53, p21, and BAX expression. In terms of oncogenic markers, western blotting analysis showed a significant reduction of BCl-2 expression and elevation in caspase3, p53, and p21 proteins as indicators of cell death via apoptosis. The antitumor in vivo effect of the combination therapy showed significant tumor inhibition compared to monotherapy. In conclusion, combination therapy could be a potential promising strategy to treat non-small cell lung carcinoma.

The Impact of AI on Organizational Employees: A Literature Review

The quick advancement of artificial intelligence technologies represents a backdrop that cannot be disregarded in contemporary organizational management practice and research. Based on the field of human resource management, the study reviews and summarizes the impact of AI on the subject of human resource decision-making—employees—from the viewpoint of organizational management. This study takes two important research directions of AI and organizational management research at the individual level, and summarizes the research on employees' adoption of AI technology and the impact of AI on them individually in organizations. The adoption of AI technology by employees is influenced by technological, organizational and personal factors. AI technology shows the advantage of augmentation effect on employees on the one hand, and the phenomenon of automation, i.e. substitution effect on the other. Organizations should place a high value on the new changes that AI has made to the workplaces, attach importance to employees' attitudes, psychological and behavioral responses to new intelligent technologies. Utilize AI technologies to support decisions and promote the development of the new model of "AI+HRM".

Modelling the Effects of Wolbachia-Carrying Male Augmentation and Mating Competition on the Control Of Dengue Fever

Modelling the Effects of Wolbachia-Carrying Male Augmentation and Mating Competition on the Control Of Dengue Fever

Advanced effect of curcumin and resveratrol on mitigating hepatic steatosis in metabolic associated fatty liver disease via the PI3K/AKT/mTOR and HIF-1/VEGF cascade

Metabolic associated fatty liver disease (MAFLD) is the most common chronic liver disease that has no viable treatment. Curcumin (Cur) and resveratrol (Res) are two natural products that have been studied for their potential to ameliorate MAFLD. However, while these compounds have been investigated individually, their combined use and the potential for a synergistic or augmented effect remain unexplored. This study aims to investigate the effect of curcumin (Cur) and resveratrol (Res) as a potential combination therapy on MAFLD. Cur, Res and Cur+Res were tested in palmitic acid (PA)-induced-HepG2 cells. MAFLD model was established using Goto-Kakizaki rats. The animals were treated with vehicle control (model group), Cur (150 mg/kg), Res (150 mg/kg), Cur+Res (150 mg/kg, 8:2, w/w), or metformin (Met, positive control, 400 mg/kg/day) via oral gavage for 4 weeks. Wistar rats were used as the control group. Network pharmacology was conducted to elucidate the molecular actions of Cur and Res, followed by q-PCR and immunoblotting in vivo. Cur+Res exhibited synergistic effects in reducing triglyceride, total cholesterol and lipid accumulation in PA-induced HepG2 cells. The combination also markedly attenuated hepatic steatosis in the MAFLD rats. Network pharmacology illustrated that the interaction of Cur and Res was associated with the modulation of multiple molecular targets associated with the PI3K/AKT/mTOR and HIF-1 signaling pathways. Experimental results confirmed that Cur+Res nomalised the gene targets and protein expressions in the PI3K/AKT/mTOR and HIF-1 signaling pathways, including PI3K, mTOR, STAT-3, HIF-1α, and VEGF. The present study demonstrated an advanced effect of Cur and Res in combination to attenuate MAFLD, and the mechanism is at least partly associated with the modulation of the PI3K/AKT/mTOR and HIF-1 signaling pathways.

Triple Therapy with Metformin, Ketogenic Diet, and Metronomic Cyclophosphamide Reduced Tumor Growth in MYCN-Amplified Neuroblastoma Xenografts.

Neuroblastoma (NB) is a childhood cancer in which amplification of the MYCN gene is the most acknowledged marker of poor prognosis. MYCN-amplified NB cells rely on both glycolysis and mitochondrial oxidative phosphorylation (OXPHOS) for energy production. Previously, we demonstrated that a ketogenic diet (KD) combined with metronomic cyclophosphamide (CP) delayed tumor growth in MYCN-amplified NB xenografts. The anti-diabetic drug metformin (MET) also targets complex I of the OXPHOS system. Therefore, MET-induced disruptions of mitochondrial respiration may enhance the anti-tumor effect of CP when combined with a KD. In this study, we found that MET decreased cell proliferation and mitochondrial respiration in MYCN-amplified NB cell lines, while the combination of KD, MET, and low-dose CP (triple therapy) also reduced tumor growth and improved survival in vivo in MYCN-amplified NB xenografts. Gene ontology enrichment analysis revealed that this triple therapy had the greatest effect on the transcription of genes involved in fatty acid ß-oxidation, which was supported by the increased protein expression of CPT1A, a key mitochondrial fatty acid transporter. We suspect that alterations to ß-oxidation alongside the inhibition of complex I may hamper mitochondrial energy production, thus explaining these augmented anti-tumor effects, suggesting that the combination of MET and KD is an effective adjuvant therapy to CP in MYCN-amplified NB xenografts.

Augmentation Pathways Network for Visual Recognition

Data augmentation is practically helpful for visual recognition, especially at the time of data scarcity. However, such success is only limited to quite a few light augmentations (e.g., random crop, flip). Heavy augmentations are either unstable or show adverse effects during training, owing to the big gap between the original and augmented images. This paper introduces a novel network design, noted as Augmentation Pathways (AP), to systematically stabilize training on a much wider range of augmentation policies. Notably, AP tames various heavy data augmentations and stably boosts performance without a careful selection among augmentation policies. Unlike traditional single pathway, augmented images are processed in different neural paths. The main pathway handles the light augmentations, while other pathways focus on the heavier augmentations. By interacting with multiple paths in a dependent manner, the backbone network robustly learns from shared visual patterns among augmentations, and suppresses the side effect of heavy augmentations at the same time. Furthermore, we extend AP to high-order versions for high-order scenarios, demonstrating its robustness and flexibility in practical usage. Experimental results on ImageNet demonstrate the compatibility and effectiveness on a much wider range of augmentations, while consuming fewer parameters and lower computational costs at inference time.

The Efficiency of Transfer Learning and Data Augmentation in Lemon Leaf Image Classification

Leaf diseases in trees and plants are important factors that directly affect the yield of agricultural products. This problem may cause a decrease in the production capacity and profitability of farmers. For this reason, computer-aided detection and classification systems are needed to accurately detect plant diseases. In recent years, learning algorithms and image-processing techniques have been used effectively in the agricultural sector. In this study, the efficiency of transfer learning and data augmentation methods on a dataset consisting of lemon leaf images is examined and the classification of diseased and healthy lemon leaf images is performed. In our study, VGG16, ResNet50, and DenseNet201 transfer learning methods were applied both with and without data increment, and the effect of data augmentation on performance was evaluated. Among the deep transfer learning methods used, DenseNet201 gave the highest accuracy rate with 98.29%. This study shows that transfer learning methods can effectively distinguish between diseased and healthy lemon leaves. It has also been observed that data augmentation does not always provide performance improvement. In future studies, it is predicted that it will be appropriate to evaluate the effect of data augmentation more effectively by applying deep transfer learning methods to plants with different class numbers.

The Effect of Data Augmentation in Deep Learning with Drone Object Detection

Drone object detection is one of the main applications of image processing technology and pattern recognition using deep learning. However, the limited drone image data that can be accessed for training detection algorithms is a challenge in the development of drone object detection technology. Therefore, many studies have been conducted to increase the amount of drone image data using data augmentation techniques. This study aims to evaluate the effect of data augmentation on deep learning accuracy in drone object detection using the YOLOv5 algorithm. The methods used in this research include collecting drone image data, augmenting data with rotate, crop and cutout, training the YOLOv5 algorithm with and without data augmentation, as well as testing and analyzing training results.The results of the study show that data augmentation can't improve the accuracy of the YOLOv5 algorithm in drone object detection. Evidenced by the decreasing value of precision and mAP@0.5 and the relatively constant value of recall and F-1 score. This is caused by too much augmentation can cause loss of important information in the data and improper augmentation can cause noise or distortion in the data.

Experimental Comparison of the Effect of Image Augmentation Technique to Raw Data for Image Classification

Deep Learning models advance the methodology of image classification. But, the performance of the model depends on the diversity of the image used for training. This study examines the effect of image augmentation on the performance of ResNet50 as a baseline model with an SVM classifier for feature extraction. Two parallel experiments were conducted based on 30 raw images and with image augmentation from 8 class representations. The evaluation metrics showcase a remarkable increase of 31% in f1-score and 7.6% in ROC-AUC. The findings enhancement in F1-score ad ROC-AUC underscores the role of image augmentation as a powerful tool to reinforce the model's performance for image classification