To see the other types of publications on this topic, follow the link: ENet.
Journal articles on the topic 'ENet'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'ENet.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Yadav, Shital Sanjay, and Anup S. Vibhute. "Emotion Detection Using Deep Learning Algorithm." International Journal of Computer Vision and Image Processing 11, no. 4 (2021): 30–38. http://dx.doi.org/10.4018/ijcvip.2021100103.
Full textAbstract:
Automatic emotion detection is a prime task in computerized human behaviour analysis. The proposed system is an automatic emotion detection using convolution neural network. The proposed end-to-end CNN is therefore named as ENet. Keeping in mind the computational efficiency, the deep network makes use of trained weight parameters of the MobileNet to initialize the weight parameters of ENet. On top of the last convolution layer of ENet, the authors place global average pooling layer to make it independent of the input image size. The ENet is validated for emotion detection using two benchmark datasets: Cohn-Kanade+ (CK+) and Japanese female facial expression (JAFFE). The experimental results show that the proposed ENet outperforms the other existing methods for emotion detection.
2
Oh, Dongpin, and Bonggun Shin. "Improving Evidential Deep Learning via Multi-Task Learning." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (2022): 7895–903. http://dx.doi.org/10.1609/aaai.v36i7.20759.
Full textAbstract:
The Evidential regression network (ENet) estimates a continuous target and its predictive uncertainty without costly Bayesian model averaging. However, it is possible that the target is inaccurately predicted due to the gradient shrinkage problem of the original loss function of the ENet, the negative log marginal likelihood (NLL) loss. In this paper, the objective is to improve the prediction accuracy of the ENet while maintaining its efficient uncertainty estimation by resolving the gradient shrinkage problem. A multi-task learning (MTL) framework, referred to as MT-ENet, is proposed to accomplish this aim. In the MTL, we define the Lipschitz modified mean squared error (MSE) loss function as another loss and add it to the existing NLL loss. The Lipschitz modified MSE loss is designed to mitigate the gradient conflict with the NLL loss by dynamically adjusting its Lipschitz constant. By doing so, the Lipschitz MSE loss does not disturb the uncertainty estimation of the NLL loss. The MT-ENet enhances the predictive accuracy of the ENet without losing uncertainty estimation capability on the synthetic dataset and real-world benchmarks, including drug-target affinity (DTA) regression. Furthermore, the MT-ENet shows remarkable calibration and out-of-distribution detection capability on the DTA benchmarks.
3
Fu, Guang-Hui, Min-Jie Zong, Feng-Hua Wang, and Lun-Zhao Yi. "A Comparison of Sparse Partial Least Squares and Elastic Net in Wavelength Selection on NIR Spectroscopy Data." International Journal of Analytical Chemistry 2019 (August 1, 2019): 1–12. http://dx.doi.org/10.1155/2019/7314916.
Full textAbstract:
Elastic net (Enet) and sparse partial least squares (SPLS) are frequently employed for wavelength selection and model calibration in analysis of near infrared spectroscopy data. Enet and SPLS can perform variable selection and model calibration simultaneously. And they also tend to select wavelength intervals rather than individual wavelengths when the predictors are multicollinear. In this paper, we focus on comparison of Enet and SPLS in interval wavelength selection and model calibration for near infrared spectroscopy data. The results from both simulation and real spectroscopy data show that Enet method tends to select less predictors as key variables than SPLS; thus it gets more parsimony model and brings advantages for model interpretation. SPLS can obtain much lower mean square of prediction error (MSE) than Enet. So SPLS is more suitable when the attention is to get better model fitting accuracy. The above conclusion is still held when coming to performing the strongly correlated NIR spectroscopy data whose predictors present group structures, Enet exhibits more sparse property than SPLS, and the selected predictors (wavelengths) are segmentally successive.
4
Salvaggio, Giuseppe, Giuseppe Cutaia, Antonio Greco, et al. "Deep Learning Networks for Automatic Retroperitoneal Sarcoma Segmentation in Computerized Tomography." Applied Sciences 12, no. 3 (2022): 1665. http://dx.doi.org/10.3390/app12031665.
Full textAbstract:
The volume estimation of retroperitoneal sarcoma (RPS) is often difficult due to its huge dimensions and irregular shape; thus, it often requires manual segmentation, which is time-consuming and operator-dependent. This study aimed to evaluate two fully automated deep learning networks (ENet and ERFNet) for RPS segmentation. This retrospective study included 20 patients with RPS who received an abdominal computed tomography (CT) examination. Forty-nine CT examinations, with a total of 72 lesions, were included. Manual segmentation was performed by two radiologists in consensus, and automatic segmentation was performed using ENet and ERFNet. Significant differences between manual and automatic segmentation were tested using the analysis of variance (ANOVA). A set of performance indicators for the shape comparison (namely sensitivity), positive predictive value (PPV), dice similarity coefficient (DSC), volume overlap error (VOE), and volumetric differences (VD) were calculated. There were no significant differences found between the RPS volumes obtained using manual segmentation and ENet (p-value = 0.935), manual segmentation and ERFNet (p-value = 0.544), or ENet and ERFNet (p-value = 0.119). The sensitivity, PPV, DSC, VOE, and VD for ENet and ERFNet were 91.54% and 72.21%, 89.85% and 87.00%, 90.52% and 74.85%, 16.87% and 36.85%, and 2.11% and −14.80%, respectively. By using a dedicated GPU, ENet took around 15 s for segmentation versus 13 s for ERFNet. In the case of CPU, ENet took around 2 min versus 1 min for ERFNet. The manual approach required approximately one hour per segmentation. In conclusion, fully automatic deep learning networks are reliable methods for RPS volume assessment. ENet performs better than ERFNet for automatic segmentation, though it requires more time.
5
Hendricks, M. "ENet President's Problem." American Journal of Evaluation 6, no. 1 (1985): 56–57. http://dx.doi.org/10.1177/109821408500600115.
Full text
6
Comelli, Albert, Navdeep Dahiya, Alessandro Stefano, et al. "Deep Learning-Based Methods for Prostate Segmentation in Magnetic Resonance Imaging." Applied Sciences 11, no. 2 (2021): 782. http://dx.doi.org/10.3390/app11020782.
Full textAbstract:
Magnetic Resonance Imaging-based prostate segmentation is an essential task for adaptive radiotherapy and for radiomics studies whose purpose is to identify associations between imaging features and patient outcomes. Because manual delineation is a time-consuming task, we present three deep-learning (DL) approaches, namely UNet, efficient neural network (ENet), and efficient residual factorized convNet (ERFNet), whose aim is to tackle the fully-automated, real-time, and 3D delineation process of the prostate gland on T2-weighted MRI. While UNet is used in many biomedical image delineation applications, ENet and ERFNet are mainly applied in self-driving cars to compensate for limited hardware availability while still achieving accurate segmentation. We apply these models to a limited set of 85 manual prostate segmentations using the k-fold validation strategy and the Tversky loss function and we compare their results. We find that ENet and UNet are more accurate than ERFNet, with ENet much faster than UNet. Specifically, ENet obtains a dice similarity coefficient of 90.89% and a segmentation time of about 6 s using central processing unit (CPU) hardware to simulate real clinical conditions where graphics processing unit (GPU) is not always available. In conclusion, ENet could be efficiently applied for prostate delineation even in small image training datasets with potential benefit for patient management personalization.
7
Abas, Mohamad Ilyas, Syafruddin Syarif, Ingrid Nurtanio, and Zulkifli Tahir. "Comparison of Convolutional Neural Network Methods for the Classification of Maize Plant Diseases." Register: Jurnal Ilmiah Teknologi Sistem Informasi 10, no. 1 (2024): 46–59. http://dx.doi.org/10.26594/register.v10i1.3656.
Full textAbstract:
The focus of this study is the classification of maize images with common rust, gray leaf spot, blight, and healthy diseases. Various models, including ResNet50, ResNet101, Xception, VGG16, and ENet, were tested for this purpose. The dataset used for corn plant diseases is publicly available, and the data were split into separate sets for training, validation, and testing. After processing the data, the following models were identified: the Xception model epoch with an accuracy of 83.74%, the ResNet model with an accuracy of 97.19% at epoch 8/10, the ResNet101 model with an accuracy of 97.55% at epoch 10/10, and the ENet model with an accuracy of 98.69% at epoch 9/1000. ENet exhibited the highest accuracy among the five models at 98.69%. Additionally, ENet achieved an average accuracy of 95.45%, the highest among all tested models, based on the average accuracy in the confusion matrix. This research indicates that ENet performs best at processing data related to maize plant diseases. Consequently, the analysis of maize plant diseases is expected to evolve as a result of this research. Following the implementation of the system's generated model, this research will continue to explore its impact. The intention is to provide a summary of the comparative classification performance of CNN algorithms.
8
Katzenmeyer, C. "Final ENet Board Meeting." American Journal of Evaluation 7, no. 1 (1986): 106. http://dx.doi.org/10.1177/109821408600700117.
Full text
9
Katzenmeyer, Conrad. "Final ENet board meeting." Evaluation Practice 7, no. 1 (1986): 106. http://dx.doi.org/10.1016/s0886-1633(86)80085-x.
Full text
10
Jabbour, Georges, Melanie Henderson, Angelo Tremblay, and Marie Eve Mathieu. "Aerobic Fitness Indices of Children Differed Not by Body Weight Status but by Level of Engagement in Physical Activity." Journal of Physical Activity and Health 12, no. 6 (2015): 854–60. http://dx.doi.org/10.1123/jpah.2013-0337.
Full textAbstract:
Objective:Moderate-to-vigorous physical activity (MVPA) improves aerobic fitness in children, which is usually assessed by maximal oxygen consumption. However, other indices of aerobic fitness have been understudied.Methods:To compare net oxygen (VO2net), net energy consumption (Enet), net mechanical efficiency (MEnet), and lipid oxidation rate in active and inactive children across body weight statuses.Design:The sample included normal-weight, overweight, and obese children of whom 44 are active (≥30 min of MVPA/d) and 41 are inactive (<30 min of MVPA/d). VO2net, Enet, MEnet and lipid oxidation rate were determined during an incremental maximal cycling test.Results:Active obese participants had significantly lower values of VO2net and Enet and higher MEnet than inactive obese participants at all load stages. In addition, active obese participants showed a significantly higher lipid oxidation rate compared with inactive obese and active overweight and normal-weight participants. VO2net, Enet, and MEnet were similar across active children, regardless of body weight status.Conclusion:Thirty minutes or more of MVPA per day is associated with a potentiation of aerobic fitness indicators in obese prepubertal children. Moreover, the indices of aerobic fitness of inactive obese children are significantly different from those of active obese and nonobese ones.
11
Gao, Xiaofei, Qi Lizhe, Ma Chuangjia, and Yunquan Sun. "Research on real-time cloth edge extraction method based on ENet semantic segmentation." Journal of Engineered Fibers and Fabrics 17 (January 2022): 155892502211318. http://dx.doi.org/10.1177/15589250221131890.
Full textAbstract:
A vision-based sewing trajectory extraction method aims at the difficulty of adaptive generation of sewing trajectory in garment automatic processing. Firstly, the ENet model is improved and the I-ENet semantic segmentation algorithm is proposed; Then, based on the semantic segmentation results, a dynamic edge extraction method based on the GaussMod fitting method is proposed. Based on segmented images, curve fitting, median filtering, and edge-preserving filtering are used. Finally, the Canny operator is used to find the sewing edge trajectory curve. At last, the sewing trajectory curve of the robot is generated. Through experimental verification, the MIoU and PA of the semantic segmentation algorithm I-ENet proposed in this paper reach 95.06% and 97.80% respectively. Compared with the MIoU of the original model of ENet, the MIoU is improved by 2.78%, the pixel accuracy is improved by 1.18%, and the frame rate is 30 FPS. It can realize cloth segmentation and extraction in an unstructured environment. The maximum error between the sewing edge trajectory and the actual edge is 1.35 mm, the mean error is 0.61 mm, and the mean value of dynamic variance is 0.57 mm. This method meets the practical application requirements.
12
Prema, K., and J. Visumathi. "Parallel Mirrors Based Marine Predator Optimization Algorithm with Deep Learning Model for Quality and Shelf-Life Prediction of Shrimp." International Journal of Electrical and Electronics Research 11, no. 2 (2023): 262–71. http://dx.doi.org/10.37391/ijeer.110204.
Full textAbstract:
Automatic classification and assessment of shrimp freshness plays a major role in aquaculture industry. Shrimp is one of the highly perishable seafood, because of its flavor and excellent nutritional content. Given the high amount of industrial production, determining the freshness of shrimp quickly and precisely is difficult. Instead of using feature-engineering-based techniques, a novel hybrid classification approach is proposed by combining the strength of convolutional neural networks (CNN) and Marine Predators Algorithm (MPA) for shrimp freshness diagnosis. In order to choose the best hyperparameter values, marine predator algorithm is improved using Parallel Mirrors Technique (PMPA). The proposed methodology employs a pretrained CNN model termed EfficientNet (ENet), which is combined with the PMPA algorithm to form the PMPA-ENet architecture. The proposed approach yields high performance while also reducing computational complexity. The result showed that proposed model achieved an accuracy and F-score of 98.62% and 97.25% for assessment of freshness in shrimp. PMPA's effectiveness in determining optimal values is compared to four different meta-heuristic algorithms hybridized with ENet including Particle Swarm Optimization (PSO), Simple Genetic Algorithm (SGA), Whale Optimization Algorithm (WOA), and traditional Marine Predator Algorithm (MPA). The results indicated that PMPA-ENet algorithm provides better classification compared with other algorithms
13
TASSIGNON, MJ. "EBO, ENET and accredited courses." Acta Ophthalmologica 87 (September 2009): 0. http://dx.doi.org/10.1111/j.1755-3768.2009.2372.x.
Full text
14
Silva, Maguino Santos da, Francisco José Gondim Pitanga, Jorge Medeiros Gomes, Úrsula Paula Renó Soci, and Alex Cleber Improta Caria. "Eletroestimulação e treinamento físico: uma revisão narrativa." Research, Society and Development 9, no. 12 (2020): e4691211528. http://dx.doi.org/10.33448/rsd-v9i12.11528.
Full textAbstract:
A Eletroestimulação é uma técnica utilizada por profissionais da área da saúde em tratamentos para diversas doenças e treinamentos esportivos. Pode ser aplicada em academias de ginástica, clínicas de fisioterapia e ambientes esportivos como clubes de futebol, corridas, entre outros. Existem diversas nomenclaturas no mercado relacionando a eletroestimulação, mas todas elas são tecnicamente conhecidas como estimulação neuromuscular elétrica transcutânea (ENET). A ENET de corpo inteiro é uma técnica relativamente nova, e entrou no mercado para potencializar o tratamento e treinamento que já eram utilizados por estimuladores elétricos locais, como a corrente russa, galvânica e outras. Os resultados dos estudos relacionados ao tema divergem bastante, portanto, percebe-se a necessidade de mais pesquisas relacionadas ao tema. Assim, o objetivo da presente revisão é, identificar e discutir os efeitos benéficos da ENET no tratamento de doenças cardiovasculares e neuromusculares, inclusive no auxílio do treinamento físico convencional e os potenciais riscos para saúde humana.
15
Ahmed, Shouket Abdulrahman, Hazry Desa, Abadal-Salam T. Hussain, and Taha A. Taha. "Implementation of deep neural networks learning on unmanned aerial vehicle based remote-sensing." IAES International Journal of Artificial Intelligence (IJ-AI) 13, no. 1 (2024): 941. http://dx.doi.org/10.11591/ijai.v13.i1.pp941-947.
Full textAbstract:
Due to efficient and adaptable data collecting, unmanned aerial vehicle (UAV) has been a popular topic in computer vision (CV) and remote sensing (RS) in recent years. Inspiring by the recent success of deep learning (DL), several enhanced object identification and tracking methods have been broadly applied to a variety of UAV-related applications, including environmental monitoring, precision agriculture, and traffic management. In this research, we present efficient neural network (ENet), a unique deep neural network architecture designed exclusively for jobs demanding low latency operation. ENet is up to quicker, takes fewer floating-point operations per second (FLOPs), has fewer parameters, and offers accuracy comparable to or superior to that of previous models. We have tested it on the street and cityscapes reports on comparisons with current state-of-the-art approaches and the tradeoffs between a network's processing speed and accuracy. We give measurements of the proposed architecture's performance on embedded devices and offer software enhancements that might make ENet even quicker.
16
Abdulrahman, Ahmed Shouket, Hazry Desa, Hussain Abadal-Salam T., and Taha Taha A. "Implementation of deep neural networks learning on unmanned aerial vehicle based remote-sensing." IAES International Journal of Artificial Intelligence (IJ-AI) 13, no. 1 (2024): 941–47. https://doi.org/10.11591/ijai.v13.i2.pp941-947.
Full textAbstract:
Due to efficient and adaptable data collecting, unmanned aerial vehicle (UAV) has been a popular topic in computer vision (CV) and remote sensing (RS) in recent years. Inspiring by the recent success of deep learning (DL), several enhanced object identification and tracking methods have been broadly applied to a variety of UAV-related applications, including environmental monitoring, precision agriculture, and traffic management. In this research, we present efficient neural network (ENet), a unique deep neural network architecture designed exclusively for jobs demanding low latency operation. ENet is up to quicker, takes fewer floating-point operations per second (FLOPs), has fewer parameters, and offers accuracy comparable to or superior to that of previous models. We have tested it on the street and cityscapes reports on comparisons with current state-of-the-art approaches and the tradeoffs between a network's processing speed and accuracy. We give measurements of the proposed architecture's performance on embedded devices and offer software enhancements that might make ENet even quicker.
17
Stefano, Alessandro, and Albert Comelli. "Customized Efficient Neural Network for COVID-19 Infected Region Identification in CT Images." Journal of Imaging 7, no. 8 (2021): 131. http://dx.doi.org/10.3390/jimaging7080131.
Full textAbstract:
Background: In the field of biomedical imaging, radiomics is a promising approach that aims to provide quantitative features from images. It is highly dependent on accurate identification and delineation of the volume of interest to avoid mistakes in the implementation of the texture-based prediction model. In this context, we present a customized deep learning approach aimed at addressing the real-time, and fully automated identification and segmentation of COVID-19 infected regions in computed tomography images. Methods: In a previous study, we adopted ENET, originally used for image segmentation tasks in self-driving cars, for whole parenchyma segmentation in patients with idiopathic pulmonary fibrosis which has several similarities to COVID-19 disease. To automatically identify and segment COVID-19 infected areas, a customized ENET, namely C-ENET, was implemented and its performance compared to the original ENET and some state-of-the-art deep learning architectures. Results: The experimental results demonstrate the effectiveness of our approach. Considering the performance obtained in terms of similarity of the result of the segmentation to the gold standard (dice similarity coefficient ~75%), our proposed methodology can be used for the identification and delineation of COVID-19 infected areas without any supervision of a radiologist, in order to obtain a volume of interest independent from the user. Conclusions: We demonstrated that the proposed customized deep learning model can be applied to rapidly identify, and segment COVID-19 infected regions to subsequently extract useful information for assessing disease severity through radiomics analyses.
18
Zhang, Teng, Shang Gao, Shao-wu Zhang, and Xiao-dong Cui. "m6Aexpress-enet: Predicting the regulatory expression m6A sites by an enet-regularization negative binomial regression model." Methods 226 (June 2024): 61–70. http://dx.doi.org/10.1016/j.ymeth.2024.04.011.
Full text
19
Leblanc, N., X. Wan, and P. M. Leung. "Physiological role of Ca(2+)-activated and voltage-dependent K+ currents in rabbit coronary myocytes." American Journal of Physiology-Cell Physiology 266, no. 6 (1994): C1523—C1537. http://dx.doi.org/10.1152/ajpcell.1994.266.6.c1523.
Full textAbstract:
The properties and function of Ca(2+)-activated K+ (KCa) and voltage-dependent K+ (IK) currents of rabbit coronary myocytes were studied under whole cell voltage-clamp conditions (22 degrees C). Inhibition of KCa by tetraethylammonium chloride (1-10 mM) or charybdotoxin (50-100 nM) suppressed noisy outward rectifying current elicited by 5-s voltage steps or ramp at potentials > 0 mV, reduced the hump of the biphasic ramp current-voltage relation, and shifted by less than +5 mV the potential at which no net steady-state current is recorded (Enet; index of resting membrane potential). Inhibition of steady-state inward Ca2+ currents [ICa(L)] by nifedipine (1 microM) displaced Enet by -11 mV. Analysis of steady-state voltage dependence of IK supported the existence of a "window" current between -50 and 0 mV. 4-Aminopyridine (2 mM) blocked a noninactivating component of IK evoked between -30 and -40 mV, abolished the hump current during ramps, and shifted Enet by more than +15 mV; hump current persisted during 2-min ramp depolarizations and peaked near the maximum overlap of the steady-state activation and inactivation curves of IK (about -22 mV). A threefold rise in extracellular Ca2+ concentration (1.8-5.4 mM) enhanced time-dependent outward K+ current (6.7-fold at +40 mV) and shifted Enet by -30 mV. It is concluded that, under steady-state conditions, IK and ICa(L) play a major role in regulating resting membrane potential at a physiological level of intracellular Ca2+ concentration, with a minor contribution from KCa. However, elevation of intracellular Ca2+ concentration enhances KCa and hyperpolarizes the myocyte to limit Ca2+ entry through ICa(L).
20
Zhang, Jie, and Mingyuan He. "Methodology for Severe Convective Cloud Identification Using Lightweight Neural Network Model Ensembling." Remote Sensing 16, no. 12 (2024): 2070. http://dx.doi.org/10.3390/rs16122070.
Full textAbstract:
This study introduces an advanced ensemble methodology employing lightweight neural network models for identifying severe convective clouds from FY-4B geostationary meteorological satellite imagery. We have constructed a FY-4B based severe convective cloud dataset by a combination of algorithms and expert judgment. Through the ablation study of a model ensembling combination of multiple specialized lightweight architectures—ENet, ESPNet, Fast-SCNN, ICNet, and MobileNetV2—the optimal EFNet (ENet- and Fast-SCNN-based network) not only achieves real-time processing capabilities but also ensures high accuracy in severe weather detection. EFNet consistently outperformed traditional, heavier models across several key performance indicators: achieving an accuracy of 0.9941, precision of 0.9391, recall of 0.9201, F1 score of 0.9295, and computing time of 18.65 s over the test dataset of 300 images (~0.06 s per 512 × 512 pic). ENet shows high precision but misses subtle clouds, while Fast-SCNN has high sensitivity but lower precision, leading to misclassifications. EFNet’s ensemble approach balances these traits, enhancing overall predictive accuracy. The ensemble method of lightweight models effectively aggregates the diverse strengths of the individual models, optimizing both speed and predictive performance.
21
Wiedenmann, B. "From ENET to ENETS: A Long Odyssey in the Land of Small and Rare Tumors." Neuroendocrinology 80, no. 1 (2004): 1–2. http://dx.doi.org/10.1159/000080730.
Full text
22
Vemulapalli, Teja Ram Mohan Sai. "Predicting Crop Yields in Indian Agriculture Using Machine Learning." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 05 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem33602.
Full textAbstract:
Agriculture provides the backbone of India's economy both within and between. The paper below provides a brief insight into the creation of a fresh model is currently in progress to estimate the variability in the crop yields across various regions in India. Via this simple setting-based approach, such parameters as year, district, season and area can be used to predict the amounts of crop outputs for certain years. By employing sophisticated regression techniques, Kernel Ridge, Lasso, and ENet algorithms are used, to improve the yield prediction precision. Additionally, it implies a technique of Scaled Regression which is specifically designed to improve the accuracy of the data resulting as long-term predictions. Key terms: Crop yield forecasting, Lasso algorithm, Kernel Ridge algorithm, ENet algorithm, Stacked Regression.
23
Kim, Sangwon, Jaeyeal Nam, and Byoungchul Ko. "Fast Depth Estimation in a Single Image Using Lightweight Efficient Neural Network." Sensors 19, no. 20 (2019): 4434. http://dx.doi.org/10.3390/s19204434.
Full textAbstract:
Depth estimation is a crucial and fundamental problem in the computer vision field. Conventional methods re-construct scenes using feature points extracted from multiple images; however, these approaches require multiple images and thus are not easily implemented in various real-time applications. Moreover, the special equipment required by hardware-based approaches using 3D sensors is expensive. Therefore, software-based methods for estimating depth from a single image using machine learning or deep learning are emerging as new alternatives. In this paper, we propose an algorithm that generates a depth map in real time using a single image and an optimized lightweight efficient neural network (L-ENet) algorithm instead of physical equipment, such as an infrared sensor or multi-view camera. Because depth values have a continuous nature and can produce locally ambiguous results, pixel-wise prediction with ordinal depth range classification was applied in this study. In addition, in our method various convolution techniques are applied to extract a dense feature map, and the number of parameters is greatly reduced by reducing the network layer. By using the proposed L-ENet algorithm, an accurate depth map can be generated from a single image quickly and, in a comparison with the ground truth, we can produce depth values closer to those of the ground truth with small errors. Experiments confirmed that the proposed L-ENet can achieve a significantly improved estimation performance over the state-of-the-art algorithms in depth estimation based on a single image.
24
Summers, Lucia, Alyssa N. Shallenberger, John Cruz, and Lawrence V. Fulton. "A Multi-Input Machine Learning Approach to Classifying Sex Trafficking from Online Escort Advertisements." Machine Learning and Knowledge Extraction 5, no. 2 (2023): 460–72. http://dx.doi.org/10.3390/make5020028.
Full textAbstract:
Sex trafficking victims are often advertised through online escort sites. These ads can be publicly accessed, but law enforcement lacks the resources to comb through hundreds of ads to identify those that may feature sex-trafficked individuals. The purpose of this study was to implement and test multi-input, deep learning (DL) binary classification models to predict the probability of an online escort ad being associated with sex trafficking (ST) activity and aid in the detection and investigation of ST. Data from 12,350 scraped and classified ads were split into training and test sets (80% and 20%, respectively). Multi-input models that included recurrent neural networks (RNN) for text classification, convolutional neural networks (CNN, specifically EfficientNetB6 or ENET) for image/emoji classification, and neural networks (NN) for feature classification were trained and used to classify the 20% test set. The best-performing DL model included text and imagery inputs, resulting in an accuracy of 0.82 and an F1 score of 0.70. More importantly, the best classifier (RNN + ENET) correctly identified 14 of 14 sites that had classification probability estimates of 0.845 or greater (1.0 precision); precision was 96% for the multi-input model (NN + RNN + ENET) when only the ads associated with the highest positive classification probabilities (>0.90) were considered (n = 202 ads). The models developed could be productionalized and piloted with criminal investigators, as they could potentially increase their efficiency in identifying potential ST victims.
25
Kayanan, Manickavasagar, and Pushpakanthie Wijekoon. "Stochastic Restricted LASSO-Type Estimator in the Linear Regression Model." Journal of Probability and Statistics 2020 (March 30, 2020): 1–7. http://dx.doi.org/10.1155/2020/7352097.
Full textAbstract:
Among several variable selection methods, LASSO is the most desirable estimation procedure for handling regularization and variable selection simultaneously in the high-dimensional linear regression models when multicollinearity exists among the predictor variables. Since LASSO is unstable under high multicollinearity, the elastic-net (Enet) estimator has been used to overcome this issue. According to the literature, the estimation of regression parameters can be improved by adding prior information about regression coefficients to the model, which is available in the form of exact or stochastic linear restrictions. In this article, we proposed a stochastic restricted LASSO-type estimator (SRLASSO) by incorporating stochastic linear restrictions. Furthermore, we compared the performance of SRLASSO with LASSO and Enet in root mean square error (RMSE) criterion and mean absolute prediction error (MAPE) criterion based on a Monte Carlo simulation study. Finally, a real-world example was used to demonstrate the performance of SRLASSO.
26
Reyes, Juan Rufino. "Nowcasting domestic liquidity in the Philippines using machine learning algorithms." Philippine Review of Economics 59, no. 2 (2022): 1–40. http://dx.doi.org/10.37907/1erp2202d.
Full textAbstract:
This study utilizes a number of algorithms used in machine learning to nowcast domestic liquidity growth in the Philippines. It employs regularization (i.e., Ridge Regression, Least Absolute Shrinkage and Selection Operator (LASSO), Elastic Net (ENET)) and tree-based (i.e., Random Forest, Gradient Boosted Trees) methods in order to support the BSP’s current suite of macroeconomic models used to forecast and analyze liquidity. Hence, this study evaluates the accuracy of time series models (e.g., Autoregressive, Dynamic Factor), regularization, and tree-based methods through an expanding window. The results indicate that Ridge Regression, LASSO, ENET, Random Forest, and Gradient Boosted Trees provide better estimates than the traditional time series models, with month-ahead nowcasts yielding lower Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). Furthermore, regularization and tree-based methods facilitate the identification of macroeconomic indicators that are significant to specify parsimonious nowcasting models.
27
Chen, Feng Qin. "Research on the Network Safety Loophole of Enet." Applied Mechanics and Materials 687-691 (November 2014): 1942–44. http://dx.doi.org/10.4028/www.scientific.net/amm.687-691.1942.
Full textAbstract:
With the continuous development and popularization of computer network information technology, many colleges all have set up campus network. At present, campus network has been the important project in college base installation. However, information security issue of campus network would directly affect college to launch various pedagogical practices and refer to students’ individual privacy security issue. This paper has pointed out many safety loopholes existing in university campus network, and attempted to explore improvement measure and corresponding countermeasure of domestic university campus network information security.
28
Gburzynski, P., and P. Rudnicki. "A note on the performance of ENET II." IEEE Journal on Selected Areas in Communications 7, no. 3 (1989): 424–27. http://dx.doi.org/10.1109/49.16875.
Full text
29
Bou Zerdan, Morgan, Jeffrey Andrew How, Larissa Alejandra Meyer, Mark Munsell, and Pamela T. Soliman. "Clinicopathological features and survival outcomes in women with endometrial neuroendocrine tumors." Journal of Clinical Oncology 43, no. 16_suppl (2025): 5604. https://doi.org/10.1200/jco.2025.43.16_suppl.5604.
Full textAbstract:
5604 Background: Endometrial neuroendocrine tumors (ENET) are rare, representing about 0.8% of endometrial cancers. Due to their aggressive nature, they are often diagnosed at an advanced stage with no standardized treatment guidelines. This study provides data on the clinicopathological features and survival outcomes of ENETs. Methods: This IRB-approved retrospective cohort study evaluated patients with ENETs seen at MD Anderson Cancer Center between 1994 and 2024. All patients with a histology-confirmed diagnosis of ENET were included. Descriptive statistics was used to summarize patients’ clinicopathologic features. Event-free survival (EFS) was defined as the time from 1st treatment to recurrence, progression, or death. Overall survival (OS) was defined as the time from start of 1st treatment to death. Kaplan-Meier was used to estimate OS and EFS, and Cox regression was used to estimate hazard ratios for prognostic factors. Results: A total of 97 patients were included. Median age at diagnosis was 60 years (range: 30–85). Median BMI was 30.3 kg/m2 (range: 17.1 - 76.7). 87% were white. FIGO stage at diagnosis was 31% stage I/II, 62% stage III/IV, and 5% unknown. 84% underwent primary surgery and 16% had neoadjuvant chemotherapy. For those who underwent surgery, 59% had chemotherapy and 39% had radiotherapy. 39% of patients were NED after completion of primary treatment, 38% progressed and 23% recurred. Median follow-up was 1.4 years (range 6 days to 15.7 years). Median EFS was 0.8 years (95% CI: 0.6–1.3). On multivariate analysis, patients treated with carboplatin/paclitaxel (C/P) (HR= 0.43, 95% CI: 0.24–0.79, p =0.006), or cisplatin/etoposide (C/E) (HR = 0.35, 95% CI: 0.20–0.62, p = 0.001) had a decreased risk of recurrence compared to no adjuvant therapy. Among Stage I/II patients treated with C/E had a decreased risk of recurrence compared to patients treated with C/P (HR= 0.16 (95% CI: 0.03–0.80), p=0.025). Median OS was 1.6 years (95% CI: 1.2–3.0). Multivariate analysis showed stage III/IV disease had almost 3 times the risk of death (p=0.0008). Treatment with C+P (HR =0.40, 95% CI: 0.22–0.74, p=0.003) or C+E had a HR= 0.35 (95% CI: 0.20–0.63), p= 0.0005, compared to patients receiving other or no chemotherapy. Conclusions: This study highlights the aggressive nature of ENETs, often diagnosed at advanced stage. Adjuvant therapy with cisplatin/etoposide was associated with reduced the risk of death compared to other treatments. Despite chemotherapy, median EFS was short, highlighting the need for improved treatment strategies.
30
Natanzon, Yanina, Madalene Earp, Julie M. Cunningham, et al. "Genomic Analysis Using Regularized Regression in High-Grade Serous Ovarian Cancer." Cancer Informatics 17 (January 1, 2018): 117693511875534. http://dx.doi.org/10.1177/1176935118755341.
Full textAbstract:
High-grade serous ovarian cancer (HGSOC) is a complex disease in which initiation and progression have been associated with copy number alterations, epigenetic processes, and, to a lesser extent, germline variation. We hypothesized that, when summarized at the gene level, tumor methylation and germline genetic variation, alone or in combination, influence tumor gene expression in HGSOC. We used Elastic Net (ENET) penalized regression method to evaluate these associations and adjust for somatic copy number in 3 independent data sets comprising tumors from more than 470 patients. Penalized regression models of germline variation, with or without methylation, did not reveal a role in HGSOC gene expression. However, we observed significant association between regional methylation and expression of 5 genes ( WDPCP, KRT6C, BRCA2, EFCAB13, and ZNF283). CpGs retained in ENET model for BRCA2 and ZNF283 appeared enriched in several regulatory elements, suggesting that regularized regression may provide a novel utility for integrative genomic analysis.
31
Sridhara, Shankarappa, Nandini Ramesh, Pradeep Gopakkali, et al. "Weather-Based Neural Network, Stepwise Linear and Sparse Regression Approach for Rabi Sorghum Yield Forecasting of Karnataka, India." Agronomy 10, no. 11 (2020): 1645. http://dx.doi.org/10.3390/agronomy10111645.
Full textAbstract:
Sorghum is an important dual-purpose crop of India grown for food and fodder. Prevailing weather conditions during the crop growth period determine the yield of sorghum. Hence, the crop yield forecasting models based on weather parameters will be an appropriate option for policymakers and researchers to develop sustainable cropping strategies. In the present study, six multivariate weather-based models viz., least absolute shrinkage and selection operator (LASSO), elastic net (ENET), principal component analysis (PCA) in combination with stepwise multiple linear regression (SMLR), artificial neural network (ANN) alone and in combination with PCA and ridge regression model are examined by fixing 90% of the data for calibration and remaining dataset for validation to forecast rabi sorghum yield for different districts of Karnataka. The R2 and root mean square error (RMSE) during calibration ranged between 0.42 to 0.98 and 30.48 to 304.17 kg ha−1, respectively, without actual evapotranspiration (AET) whereas, these evaluation parameters varied from 0.38 to 0.99 and 19.84 to 308.79 kg ha−1, respectively with AET inclusion. During validation, the RMSE and nRMSE (normalized root mean square error) varied between 88.99 to 1265.03 kg ha−1 and 4.49 to 96.84%, respectively without AET and including AET as one of the weather variable RMSE and nRMSE were 63.48 to 1172.01 kg ha−1 and 4.16 to 92.56%, respectively. The performance of six multivariate models revealed that LASSO was the best model followed by ENET compared to PCA_SMLR, ANN, PCA_ANN and ridge regression models because of reduced overfitting through penalisation of regression coefficient. Thus, it can be concluded that LASSO and ENET weather-based models can be effectively utilized for the district level forecast of sorghum yield.
32
Ma, Ling, Xiaomao Hou, and Zhi Gong. "Image Segmentation Technology Based on Attention Mechanism and ENet." Computational Intelligence and Neuroscience 2022 (August 4, 2022): 1–8. http://dx.doi.org/10.1155/2022/9873777.
Full textAbstract:
With the development of today’s society, medical technology is becoming more and more important in people’s daily diagnosis and treatment and the number of computed tomography (CT) images and MRI images is also increasing. It is difficult to meet today’s needs for segmentation and recognition of medical images by manpower alone. Therefore, the use of computer technology for automatic segmentation has received extensive attention from researchers. We design a tooth CT image segmentation method combining attention mechanism and ENet. First, dilated convolution is used with the spatial information path, with a small downsampling factor to preserve the resolution of the image. Second, an attention mechanism is added to the segmentation network based on CT image features to improve the accuracy of segmentation. Then, the designed feature fusion module obtains the segmentation result of the tooth CT image. It was verified on tooth CT image dataset published by West China Hospital, and the average intersection ratio and accuracy were used as the metric. The results show that, on the dataset of West China Hospital, Mean Intersection over Union (MIOU) and accuracy are 83.47% and 95.28%, respectively, which are 3.3% and 8.09% higher than the traditional model. Compared with the multiple watershed algorithm, the Chan–Vese segmentation algorithm, and the graph cut segmentation algorithm, our algorithm increases the calculation time by 56.52%, 91.52%, and 62.96%, respectively. It can be seen that our algorithm has obvious advantages in MIOU, accuracy, and calculation time.
33
Sanders, J. R. "A Perspective on the Merger of ENet and ERS." American Journal of Evaluation 6, no. 1 (1985): 16–19. http://dx.doi.org/10.1177/109821408500600105.
Full text
34
Li, Qingyu, and Zhenjiang Miao. "Light Corner Based Object Detector with Stacked-ENet Backbones." Journal of Physics: Conference Series 1229 (May 2019): 012040. http://dx.doi.org/10.1088/1742-6596/1229/1/012040.
Full text
35
Bai, Wei. "An ENet Semantic Segmentation Method Combined with Attention Mechanism." Computational Intelligence and Neuroscience 2023 (February 22, 2023): 1–9. http://dx.doi.org/10.1155/2023/6965259.
Full textAbstract:
Image semantic segmentation is one of the core tasks for computer vision. It is widely used in fields such as unmanned driving, medical image processing, geographic information systems, and intelligent robots. Aiming at the problem that the existing semantic segmentation algorithm ignores the different channel and location features of the feature map and the simple method when the feature map is fused, this paper designs a semantic segmentation algorithm that combines the attention mechanism. First, dilated convolution is used, and a smaller downsampling factor is used to maintain the resolution of the image and to obtain its detailed information. Secondly, the attention mechanism module is introduced to assign weights to different parts of the feature map, which reduces the accuracy loss. The design feature fusion module assigns weights to the feature maps of different receptive fields obtained by the two paths and merges them together to obtain the final segmentation result. Finally, through experiments, it was verified on the Camvid, Cityscapes, and PASCAL VOC2012 data sets. Mean intersection over union (MIoU) and mean pixel accuracy (MPA) are used as metrics. The method in this paper can make up for the loss of accuracy caused by downsampling while ensuring the receptive field and improving the resolution, which can better guide the model learning. And the proposed feature fusion module can better integrate the features of different receptive fields. Therefore, the proposed method can significantly improve the segmentation performance compared to the traditional method.
36
إسماعيل, بان صباح. "استخدام الويب كاميرا نوع Enet ككاشف لشدة ضوء مصباح الفلورسنت". Journal of Al-Nahrain University Science 12, № 3 (2009): 16–25. http://dx.doi.org/10.22401/jnus.12.3.28.
Full text
37
Intelligence and Neuroscience, Computational. "Retracted: Image Segmentation Technology Based on Attention Mechanism and ENet." Computational Intelligence and Neuroscience 2023 (August 9, 2023): 1. http://dx.doi.org/10.1155/2023/9802601.
Full text
38
Nasiri, Vahid, Ali Asghar Darvishsefat, Hossein Arefi, Verena C. Griess, Seyed Mohammad Moein Sadeghi, and Stelian Alexandru Borz. "Modeling Forest Canopy Cover: A Synergistic Use of Sentinel-2, Aerial Photogrammetry Data, and Machine Learning." Remote Sensing 14, no. 6 (2022): 1453. http://dx.doi.org/10.3390/rs14061453.
Full textAbstract:
Forest canopy cover (FCC) is an important ecological parameter of forest ecosystems, and is correlated with forest characteristics, including plant growth, regeneration, biodiversity, light regimes, and hydrological properties. Here, we present an approach of combining Sentinel-2 data, high-resolution aerial images, and machine learning (ML) algorithms to model FCC in the Hyrcanian mixed temperate forest, Northern Iran. Sentinel-2 multispectral bands and vegetation indices were used as variables for modeling and mapping FCC based on UAV ground truth to a wider spatial extent. Random forest (RF), support-vector machine (SVM), elastic net (ENET), and extreme gradient boosting (XGBoost) were the ML algorithms used to learn and generalize on the remotely sensed variables. Evaluation of variable importance indicated that vegetation indices including NDVI, NDVI-A, NDRE, and NDI45 were the dominant predictors in most of the models. Model accuracy estimation results showed that among the tested models, RF (R2 = 0.67, RMSE = 18.87%, MAE = 15.35%) and ENET (R2 = 0.63, RMSE = 20.04%, MAE = 16.44%) showed the best and the worst performance, respectively. In conclusion, it was possible to prove the suitability of integrating UAV-obtained RGB images, Sentinel-2 data, and ML models for the estimation of FCC, intended for precise and fast mapping at landscape-level scale.
39
Aschauer, Johannes, and Christoph Marty. "Evaluating methods for reconstructing large gaps in historic snow depth time series." Geoscientific Instrumentation, Methods and Data Systems 10, no. 2 (2021): 297–312. http://dx.doi.org/10.5194/gi-10-297-2021.
Full textAbstract:
Abstract. Historic measurements are often temporally incomplete and may contain longer periods of missing data, whereas climatological analyses require continuous measurement records. This is also valid for historic manual snow depth (HS) measurement time series, for which even whole winters can be missing in a station record, and suitable methods have to be found to reconstruct the missing data. Daily in situ HS data from 126 nivo-meteorological stations in Switzerland in an altitudinal range of 230 to 2536 m above sea level are used to compare six different methods for reconstructing long gaps in manual HS time series by performing a “leave-one-winter-out” cross-validation in 21 winters at 33 evaluation stations. Synthetic gaps of one winter length are filled with bias-corrected data from the best-correlated neighboring station (BSC), inverse distance-weighted (IDW) spatial interpolation, a weighted normal ratio (WNR) method, elastic net (ENET) regression, random forest (RF) regression and a temperature index snow model (SM). Methods that use neighboring station data are tested in two station networks with different density. The ENET, RF, SM and WNR methods are able to reconstruct missing data with a coefficient of determination (r2) above 0.8 regardless of the two station networks used. The median root mean square error (RMSE) in the filled winters is below 5 cm for all methods. The two annual climate indicators, average snow depth in a winter (HSavg) and maximum snow depth in a winter (HSmax), can be reproduced by ENET, RF, SM and WNR well, with r2 above 0.85 in both station networks. For the inter-station approaches, scores for the number of snow days with HS>1 cm (dHS1) are clearly weaker and, except for BCS, positively biased with RMSE of 18–33 d. SM reveals the best performance with r2 of 0.93 and RMSE of 15 d for dHS1. Snow depth seems to be a relatively good-natured parameter when it comes to gap filling of HS data with neighboring stations in a climatological use case. However, when station networks get sparse and if the focus is set on dHS1, temperature index snow models can serve as a suitable alternative to classic inter-station gap filling approaches.
40
Pintér, Róbert. "A gamer bennük van – Az eNET Internetkutató, az Esportmilla és az Esport1 közös magyar videojátékos és e-sport kutatásának főbb eredményei." Információs Társadalom 18, no. 1 (2018): 107. http://dx.doi.org/10.22503/inftars.xviii.2018.1.7.
Full textAbstract:
A tanulmány az eNET, Esportmilla és Esport1 videojáték és e-sport kutatásának főbb kutatási eredményeit mutatja be. A két kutatás számos témát felölelt, ezek közül a tanulmány először a videojáték kutatás eredményeit ismertetve kitér arra, hogy mennyien játszanak videojátékkal idehaza és ehhez mik a főbb motivációik. Foglalkozik annak vizsgálatával, hogy a nem játszók körében mennyire elterjedtek a videojátékosokkal kapcsolatos negatív sztereotípiák, illetve milyen a szülők viszonya a témához. Ezt követően bemutatja, hogy min és mit játszanak a játékosok, illetve mekkora az e-sport játékkal játszók hazai bázisa. A tanulmány ismerteti az e-sport kutatás eredményeit is, így, hogy mik a főbb játékplatformok, hány órát tesz ki a játékkal töltött idő és az általában vett „screen time”, mi mondható az egyéni fejlődésről és streamek követéséről, valamint, hogy hagyományos értelemben sportolnak-e egyáltalán a gamerek? A tanulmány kísérletet tesz a videojátékokhoz köthető piac magyarországi méretének becslésére is. Végül a befejezésben azt vizsgálja, hogy vajon széleskörű társadalmi elfogadottság előtt áll-e idehaza a videojáték és az e-sport?
 
 ---
 
 The Gamer Inside Them: the Main Results of Hungarian Esport and Videogames Research by eNET, Esportmilla and Esport1
 
 The study presents the main research results of eNET, Esportmilla and Esport1 video games and esports research. The two research projects covered a few themes, this article first shows the results of the video games research, which demonstrates how much gamers play video games in Hungary and what their main motivations are. It deals with examining how widespread the negative stereotypes are associated with video game players among non-gamers and how parents relate to the topic. It then shows what and how gamers play and how many esports gamers there are. The study also describes the results of esports research, including the main gaming platforms, how much the playing time is and how much the usual "screen time" is, what can be said about individual development and watching of streaming, and whether or not gamers pursue traditional sports. The study also attempts to estimate the size of the video games market in Hungary. Finally, it examines whether video games and esports are about to be widely accepted in Hungary?
 
 Keywords: videogames, esport, research, Hungary
41
Molla, Md Maeen, Md Sifat Hossain, Md Ayub Ali, Md Raqibul Islam, Mst Papia Sultana, and Dulal Chandra Roy. "Exploring the achievements and forecasting of SDG 3 using machine learning algorithms: Bangladesh perspective." PLOS ONE 20, no. 3 (2025): e0314466. https://doi.org/10.1371/journal.pone.0314466.
Full textAbstract:
Background Sustainable Development Goal 3 (SDG 3), focusing on ensuring healthy lives and well-being for all, holds global significance and is particularly vital for Bangladesh. Neonatal Mortality Rate (NMR), Under-5 Mortality Rate (U5MR), Maternal Mortality Ratio (MMR) and Death Rate Due to Road Traffic Injuries (RTI) are considered responsible indicators of SDG 3 progress in Bangladesh. The objective of the study is to forecast these indicators of Bangladesh up to 2030 and compare these forecasts with predetermined 2030 targets. The data is obtained from the World Bank’s (WB) website. Method For forecasting, time series models were employed, specifically Autoregressive Integrated Moving Average- ARIMA (0,2,1) with Akaike Information Criterion (AIC) 94.6 for NMR and ARIMA (2,1,2) with AIC 423.2 for U5MR, selected based on their lowest AIC values. Additionally, Machine Learning (ML) models, including Bidirectional Recurrent Neural Networks (BRNN) and Elastic Neural Networks (ENET), were employed for all the indicators. Results ENET demonstrates superior performance compared to both BRNN and ARIMA in the context of NMR, achieving a Root Mean Absolute Error (RMAE) of 0.603446 and a Root Mean Square Error (RMSE) of 0.451162. Furthermore, when considering U5MR, MMR, and Death Rate Due to RTI, ENET consistently exhibits lower error metrics compared to the alternative models. Following the time series and ML analyses, a consistent trend emerges in the forecasted values for NMR and U5MR, which consistently fall below their respective 2030 targets. This promising finding suggests that Bangladesh is making significant progress toward meeting its 2030 targets for NMR and U5MR. However, in the cases of MMR and Death Rate Due to RTI, the forecasted values exceeded 2030 targets. This indicates that Bangladesh faces challenges in meeting the 2030 targets for MMR and Death Rate Due to RTI. Conclusion The analyses underscore the importance of SDG 3 in Bangladesh and its progress towards ensuring healthy lives and well-being for all. While there is optimism regarding NMR and U5MR, more focused efforts may be needed to address the challenges posed by MMR and Death Rate Due to RTI to align with the 2030 targets. This study contributes valuable insights into Bangladesh’s journey toward sustainable development in the realm of health and well-being.
42
Moayedi, Hossein, Dieu Tien Bui, Anastasios Dounis, Zongjie Lyu, and Loke Kok Foong. "Predicting Heating Load in Energy-Efficient Buildings Through Machine Learning Techniques." Applied Sciences 9, no. 20 (2019): 4338. http://dx.doi.org/10.3390/app9204338.
Full textAbstract:
The heating load calculation is the first step of the iterative heating, ventilation, and air conditioning (HVAC) design procedure. In this study, we employed six machine learning techniques, namely multi-layer perceptron regressor (MLPr), lazy locally weighted learning (LLWL), alternating model tree (AMT), random forest (RF), ElasticNet (ENet), and radial basis function regression (RBFr) for the problem of designing energy-efficient buildings. After that, these approaches were used to specify a relationship among the parameters of input and output in terms of the energy performance of buildings. The calculated outcomes for datasets from each of the above-mentioned models were analyzed based on various known statistical indexes like root relative squared error (RRSE), root mean squared error (RMSE), mean absolute error (MAE), correlation coefficient (R2), and relative absolute error (RAE). It was found that between the discussed machine learning-based solutions of MLPr, LLWL, AMT, RF, ENet, and RBFr, the RF was nominated as the most appropriate predictive network. The RF network outcomes determined the R2, MAE, RMSE, RAE, and RRSE for the training dataset to be 0.9997, 0.19, 0.2399, 2.078, and 2.3795, respectively. The RF network outcomes determined the R2, MAE, RMSE, RAE, and RRSE for the testing dataset to be 0.9989, 0.3385, 0.4649, 3.6813, and 4.5995, respectively. These results show the superiority of the presented RF model in estimation of early heating load in energy-efficient buildings.
43
Wang, Yiqin. "Remote Sensing Image Semantic Segmentation Algorithm Based on Improved ENet Network." Scientific Programming 2021 (October 4, 2021): 1–10. http://dx.doi.org/10.1155/2021/5078731.
Full textAbstract:
A remote sensing image semantic segmentation algorithm based on improved ENet network is proposed to improve the accuracy of segmentation. First, dilated convolution and decomposition convolution are introduced in the coding stage. They are used in conjunction with ordinary convolution to increase the receptive field of the model. Each convolution output contains a larger range of image information. Second, in the decoding stage, the image information of different scales is obtained through the upsampling operation and then through the compression, excitation, and reweighting operations of the Squeeze and Excitation (SE) module. The weight of each feature channel is recalibrated to improve the accuracy of the network. Finally, the Softmax activation function and the Argmax function are used to obtain the final segmentation result. Experiments show that our algorithm can significantly improve the accuracy of remote sensing image semantic segmentation.
44
Agaba, Sara, Chiara Ferré, Marco Musetti, and Roberto Comolli. "Mapping Soil Organic Carbon Stock and Uncertainties in an Alpine Valley (Northern Italy) Using Machine Learning Models." Land 13, no. 1 (2024): 78. http://dx.doi.org/10.3390/land13010078.
Full textAbstract:
In this study, we conducted a comprehensive analysis of the spatial distribution of soil organic carbon stock (SOC stock) and the associated uncertainties in two soil layers (0–10 cm and 0–30 cm; SOC stock 10 and SOC stock 30, respectively), in Valchiavenna, an alpine valley located in northern Italy (450 km2). We employed the digital soil mapping (DSM) approach within different machine learning models, including multivariate adaptive regression splines (MARS), random forest (RF), support vector regression (SVR), and elastic net (ENET). Our dataset comprised soil data from 110 profiles, with SOC stock calculations for all sampling points based on bulk density (BD), whether measured or estimated, considering the presence of rock fragments. As environmental covariates for our research, we utilized environmental variables, in particular, geomorphometric parameters derived from a digital elevation model (with a 20 m pixel resolution), land cover data, and climatic maps. To evaluate the effectiveness of our models, we evaluated their capacity to predict SOC stock 10 and SOC stock 30 using the coefficient of determination (R2). The results for the SOC stock 10 were as follows: MARS 0.39, ENET 0.41, RF 0.69, and SVR 0.50. For the SOC stock 30, the corresponding R2 values were: MARS 0.45, ENET 0.48, RF 0.65, and SVR 0.62. Additionally, we calculated the root-mean-squared error (RMSE), mean absolute error (MAE), the bias, and Lin’s concordance correlation coefficient (LCCC) for further assessment. To map the spatial distribution of SOC stock and address uncertainties in both soil layers, we chose the RF model, due to its better performance, as indicated by the highest R2 and the lowest RMSE and MAE. The resulting SOC stock maps using the RF model demonstrated an accuracy of RMSE = 1.35 kg m−2 for the SOC stock 10 and RMSE = 3.36 kg m−2 for the SOC stock 30. To further evaluate and illustrate the precision of our soil maps, we conducted an uncertainty assessment and mapping by analyzing the standard deviation (SD) from 50 iterations of the best-performing RF model. This analysis effectively highlighted the high accuracy achieved in our soil maps. The maps of uncertainty demonstrated that the RF model better predicts the SOC stock 10 compared to the SOC stock 30. Predicting the correct ranges of SOC stocks was identified as the main limitation of the methodology.
45
Wang, Zhu, Shuangge Ma, Michael Zappitelli, Chirag Parikh, Ching-Yun Wang, and Prasad Devarajan. "Penalized count data regression with application to hospital stay after pediatric cardiac surgery." Statistical Methods in Medical Research 25, no. 6 (2016): 2685–703. http://dx.doi.org/10.1177/0962280214530608.
Full textAbstract:
Pediatric cardiac surgery may lead to poor outcomes such as acute kidney injury (AKI) and prolonged hospital length of stay (LOS). Plasma and urine biomarkers may help with early identification and prediction of these adverse clinical outcomes. In a recent multi-center study, 311 children undergoing cardiac surgery were enrolled to evaluate multiple biomarkers for diagnosis and prognosis of AKI and other clinical outcomes. LOS is often analyzed as count data, thus Poisson regression and negative binomial (NB) regression are common choices for developing predictive models. With many correlated prognostic factors and biomarkers, variable selection is an important step. The present paper proposes new variable selection methods for Poisson and NB regression. We evaluated regularized regression through penalized likelihood function. We first extend the elastic net (Enet) Poisson to two penalized Poisson regression: Mnet, a combination of minimax concave and ridge penalties; and Snet, a combination of smoothly clipped absolute deviation (SCAD) and ridge penalties. Furthermore, we extend the above methods to the penalized NB regression. For the Enet, Mnet, and Snet penalties (EMSnet), we develop a unified algorithm to estimate the parameters and conduct variable selection simultaneously. Simulation studies show that the proposed methods have advantages with highly correlated predictors, against some of the competing methods. Applying the proposed methods to the aforementioned data, it is discovered that early postoperative urine biomarkers including NGAL, IL18, and KIM-1 independently predict LOS, after adjusting for risk and biomarker variables.
46
Li, Hui, Jinyi Li, Bowen Li, Zhengqian Miao, and Shengli Lu. "Design and Implementation of a Lightweight and Energy-Efficient Semantic Segmentation Accelerator for Embedded Platforms." Micromachines 16, no. 3 (2025): 258. https://doi.org/10.3390/mi16030258.
Full textAbstract:
With the rapid development of lightweight network models and efficient hardware deployment techniques, the demand for real-time semantic segmentation in areas such as autonomous driving and medical image processing has increased significantly. However, realizing efficient semantic segmentation on resource-constrained embedded platforms still faces many challenges. As a classical lightweight semantic segmentation network, ENet has attracted much attention due to its low computational complexity. In this study, we optimize the ENet semantic segmentation network to significantly reduce its computational complexity through structural simplification and 8-bit quantization and improve its hardware compatibility through the optimization of on-chip data storage and data transfer while maintaining 51.18% mIoU. The optimized network is successfully deployed on hardware accelerator and SoC systems based on Xilinx ZYNQ ZCU104 FPGA. In addition, we optimize the computational units of transposed convolution and dilated convolution and improve the on-chip data storage and data transfer design. The optimized system achieves a frame rate of 130.75 FPS, which meets the real-time processing requirements in areas such as autonomous driving and medical imaging. Meanwhile, the power consumption of the accelerator is 3.479 W, the throughput reaches 460.8 GOPS, and the energy efficiency reaches 132.2 GOPS/W. These results fully demonstrate the effectiveness of the optimization and deployment strategies in achieving a balance between computational efficiency and accuracy, which makes the system well suited for resource-constrained embedded platform applications.
47
Mastourah Abdulsatar Ahmeedah, Abdelbaset A.Sh Abdalla, and Ahmed M. Mami. "On using the penalized regression estimators to solve the multicollinearity problem." World Journal of Advanced Research and Reviews 24, no. 1 (2024): 2654–64. http://dx.doi.org/10.30574/wjarr.2024.24.1.3265.
Full textAbstract:
The paper compares coefficient parameter estimation efficiency using penalized regression approaches. Five estimators are employed: Ridge Regression, LASSO regression, Elastic Net (ENET) Regression, Adaptive Lasso (ALASSO) regression, and Adaptive Elastic Net (AENET) regression methods. The study uses a multiple linear regression model to address multicollinearity issues. The comparison is based on average mean square errors (MSE) using simulated data with varying sizes, numbers of independent variables, and correlation coefficients. The results are expected to be useful and will be applied to real data to determine the best-performing estimator.
48
Mastourah, Abdulsatar Ahmeedah, A.Sh Abdalla Abdelbaset, and M. Mami Ahmed. "On using the penalized regression estimators to solve the multicollinearity problem." World Journal of Advanced Research and Reviews 24, no. 1 (2024): 2654–64. https://doi.org/10.5281/zenodo.15064625.
Full textAbstract:
The paper compares coefficient parameter estimation efficiency using penalized regression approaches. Five estimators are employed: Ridge Regression, LASSO regression, Elastic Net (ENET) Regression, Adaptive Lasso (ALASSO) regression, and Adaptive Elastic Net (AENET) regression methods. The study uses a multiple linear regression model to address multicollinearity issues. The comparison is based on average mean square errors (MSE) using simulated data with varying sizes, numbers of independent variables, and correlation coefficients. The results are expected to be useful and will be applied to real data to determine the best-performing estimator.
49
Deng, Qitian, Xu Li, Peizhou Ni, Honghai Li, and Zhiyong Zheng. "Enet-CRF-Lidar: Lidar and Camera Fusion for Multi-Scale Object Recognition." IEEE Access 7 (2019): 174335–44. http://dx.doi.org/10.1109/access.2019.2956492.
Full text
50
Alimadadi, Ahmad, Ishan Manandhar, Sachin Aryal, Patricia B. Munroe, Bina Joe, and Xi Cheng. "Machine learning-based classification and diagnosis of clinical cardiomyopathies." Physiological Genomics 52, no. 9 (2020): 391–400. http://dx.doi.org/10.1152/physiolgenomics.00063.2020.
Full textAbstract:
Dilated cardiomyopathy (DCM) and ischemic cardiomyopathy (ICM) are two common types of cardiomyopathies leading to heart failure. Accurate diagnostic classification of different types of cardiomyopathies is critical for precision medicine in clinical practice. In this study, we hypothesized that machine learning (ML) can be used as a novel diagnostic approach to analyze cardiac transcriptomic data for classifying clinical cardiomyopathies. RNA-Seq data of human left ventricle tissues were collected from 41 DCM patients, 47 ICM patients, and 49 nonfailure controls (NF) and tested using five ML algorithms: support vector machine with radial kernel (svmRadial), neural networks with principal component analysis (pcaNNet), decision tree (DT), elastic net (ENet), and random forest (RF). Initial ML classifications achieved ~93% accuracy (svmRadial) for NF vs. DCM, ~82% accuracy (RF) for NF vs. ICM, and ~80% accuracy (ENet and svmRadial) for DCM vs. ICM. Next, 50 highly contributing genes (HCGs) for classifying NF and DCM, 68 HCGs for classifying NF and ICM, and 59 HCGs for classifying DCM and ICM were selected for retraining ML models. Impressively, the retrained models achieved ~90% accuracy (RF) for NF vs. DCM, ~90% accuracy (pcaNNet) for NF vs. ICM, and ~85% accuracy (pcaNNet and RF) for DCM vs. ICM. Pathway analyses further confirmed the involvement of those selected HCGs in cardiac dysfunctions such as cardiomyopathies, cardiac hypertrophies, and fibrosis. Overall, our study demonstrates the promising potential of using artificial intelligence via ML modeling as a novel approach to achieve a greater level of precision in diagnosing different types of cardiomyopathies.