Shortage Of Datasets Research Articles

Developing Multi-Label Breast Cancer Screening using Efficientnetb3 Feature Extractor

Breast cancer is the first new case occurring and the fifth death-causing cancer disease in 2020, which collapses the families as women are the pillar of the family members. 3D image acquisition technology increases treatment methods and decreases the rate of breast cancer death. Furthermore, single-label breast cancer classifications are deployed to solve the problem. However, it cannot convey more information about mammogram images. In the area where the shortage of datasets is there as in the medical image, data augmentation and transfer learning are the best solution. A Multi-Label Breast Cancer Screening is a deep learning model using a transfer learning model that gives information on finding, density, and pathology of patients' breast mammograms to the radiologists, aiming for life-saving and supporting the family. The existing model shows low accuracy on feature extraction and more layers with a very large number of nodes in a layer in the classification part. In this study, the best feature extractor for this particular work is investigated and identified as efficientnetb3, and ONN is used for the classification part. The proposed model outperforms the previous work in all evaluation metrics with a 13.25% f1_score, 53% hamming loss, 36.7% coverage error, and 12.5 an exact match. And , the number of parameters were decreased from 134M to 20M which was resulted from the optimizing of classification part of the model. The developed model with ONN in the classification part has made the best improvement over the existing model in terms of evaluation metrics and network performances.

Complex "zero-shot" super-resolution reconstruction algorithm for THz imaging.

To deal with a terahertz (THz) super-resolution (SR) algorithm based on a convolutional neural network (CNN) without standard training datasets, a complex "zero-shot" SR (CZSSR) reconstruction algorithm is proposed according to the internal image statistics with a five-layer complex CNN model. Instead of relying on pre-training, the proposed method is of sound self-adaptability. Compared with real ZSSR, the peak SNR of CZSSR rose by about 0.94 dB, MSE decreased by 0.042, and SSIM increased by about 40% for the SR result of the measured data. The results show that the CZSSR method can solve the low-resolution problem of a THz imaging system and the shortage of datasets in THz SR based on CNN. Therefore, this research is of great significance for application in the fields of medical imaging and non-destructive detection.

Forging An Optimized Bayesian Network Model With Selected Parameters For Detection of The Coronavirus In Delta State of Nigeria

Machine learning algorithm have become veritable tools for effective decision support towards the construction of systems that assist experts (individuals) in their field of exploits and endeavor with regards to problematic tasks.. They are best suited for tasks where data is explored and exploited; and cases where the dataset contains noise, partial truth, ambiguities and in cases where there is shortage of datasets. For this study, we employ the Bayesian network to construct a model trained towards a target system that can help predict best parameters used for classification of the novel coronavirus (covid-19). Data was collected from Federal Medical Center Epidemiology laboratory (a centralized databank for all cases of the covid-19 in Delta State). Data was split into training and investigation (test) dataset for the target system. Results show high predictive capability.

Text Detection in Trademark Images under Semi-Supervision

The texts in trademark image usually contain characters, text lines and other different parts. Therefore, compared with the detectors that can detect text lines directly, the detector that can detect characters is more suitable for the detection of texts in trademark images However, training character detectors needs a huge number of characters with position annotation, the con-struction process of this type of dataset will take a lot of time. In order to overcome the limitations of the detectors trained by datasets with word-level annotations and the shortage of datasets with character-level annotations, we propose a text detect method that can detect the single character in trademark images. Our proposed model is pretrained by the synthetic image dataset with character level annotation, then the pretrained model is used to detect the unannotated trademark images dataset to find more annotations for retrain the pretrained model. We also construct a trademark text dataset, which includes 4500 images. Experimental results on our dataset demonstrate our method can achieve the state-of-the-art performance compared to other methods. The results show our detector can detect complicated texts in trademark images.

Forecasting energy consumption using ensemble ARIMA–ANFIS hybrid algorithm

Energy consumption is on the rise in developing economies. In order to improve present and future energy supplies, forecasting energy demands is essential. However, lack of accurate and comprehensive data set to predict the future demand is one of big problems in these countries. Therefore, using ensemble hybrid forecasting models that can deal with shortage of data set could be a suitable solution. In this paper, the annual energy consumption in Iran is forecasted using 3 patterns of ARIMA–ANFIS model. In the first pattern, ARIMA (Auto Regressive Integrated Moving Average) model is implemented on 4 input features, where its nonlinear residuals are forecasted by 6 different ANFIS (Adaptive Neuro Fuzzy Inference System) structures including grid partitioning, sub clustering, and fuzzy c means clustering (each with 2 training algorithms). In the second pattern, the forecasting of ARIMA in addition to 4 input features is assumed as input variables for ANFIS prediction. Therefore, four mentioned inputs beside ARIMA’s output are used in energy prediction with 6 different ANFIS structures. In the third pattern, due to dealing with data insufficiency, the second pattern is applied with AdaBoost (Adaptive Boosting) data diversification model and a novel ensemble methodology is presented.The results indicate that proposed hybrid patterns improve the accuracy of single ARIMA and ANFIS models in forecasting energy consumption, though third pattern, used diversification model, acts better than others and model’s MSE criterion was decreased to 0.026% from 0.058% of second hybrid pattern. Finally, a comprehensive comparison between other hybrid prediction models is done.