Cervical cancer is one of the leading causes of premature mortality among women worldwide and more than 85% of these deaths are in developing countries. There are several risk factors associated with cervical cancer. In this paper, we developed a predictive model for predicting the outcome of patients with cervical cancer, given risk patterns from individual medical records and preliminary screening. This work presents a decision tree (DT) classification algorithm to analyze the risk factors of cervical cancer. Recursive feature elimination (RFE) and least absolute shrinkage and selection operator (LASSO) feature selection techniques were fully explored to determine the most important attributes for cervical cancer prediction. The dataset employed here contains missing values and is highly imbalanced. Therefore, a combination of under and oversampling techniques called SMOTETomek was employed. A comparative analysis of the proposed model has been performed to show the effectiveness of feature selection and class imbalance based on the classifier’s accuracy, sensitivity, and specificity. The DT with the selected features from RFE and SMOTETomek has better results with an accuracy of 98.72% and sensitivity of 100%. DT classifier is shown to have better performance in handling classification problems when the features are reduced, and the problem of high class imbalance is addressed.
Deep learning models are applied in precision agriculture for site-specific weed management by identifying weeds in farmlands. Unfortunately, because deep learning models are usually large, they are rarely adopted in resource-constrained devices (like edge devices) used in precision agriculture. In this study, we propose a lightweight deep learning model for detecting weeds in corn and soybean plants. We used transfer learning to train an InceptionnetV3 model for the task. The dataset used consists of a total of 13,177 samples of corn, soybean, and weeds. The InceptionV3 model, whose size is 183.34 MB, achieved a classification accuracy of 97%. We then applied the quantization technique to reduce the size of the model. The quantized model was reduced to a size of 23.38 MB, achieving an accuracy of 87%. The results show that quantization can reduce the size of a deep learning model while maintaining a reasonable amount of performance.
In this paper, we present the concept of context and the three-contextualization paradigms for incorporating contextual information in the recommendation process. We provide a comprehensive overview on the several novel approaches of contextual pre-filtering, contextual post-filtering and contextual modelling approaches. We then present state-of-the-art comparison across these three paradigms and raised some key concerns that are not fully addressed in the literature. This will help academicians and practitioners in comparing these three approaches to choose the best option according to their market strategy.
Metabolic syndrome (MetS), known to substantially lower the quality of life is associated with the increased incidence of non-communicable diseases (NCDs) such as type II diabetes mellitus, cardiovascular diseases and cancer. Evidence suggests that MetS accounts for the highest global mortality rate. For the early and accurate diagnosis of MetS, various statistical and ML techniques have been developed to support its clinical diagnosis. We performed a systematic review to investigate the various statistical and machine learning techniques (ML) that have been used to support the clinical diagnoses of MetS from the earliest studies to January 2020. Published literature relating to statistical and ML techniques for the diagnosis of MetS were identified by searching five major scientific databases: PubMed, Science Direct, IEEE Xplore, ACM digital library, and SpringerLink. Fifty-three primary studies that met the inclusion criteria were obtained after screening titles, abstracts and full text. Three main types of techniques were identified: statistical (n = 10), ML (n = 40), and risk quantification (n = 3). Standardized Z-score is the only statistical technique identified while the ML techniques include principal component analysis, confirmatory factory analysis, artificial neural networks, multiple logistics regression, decision trees, support vector machines, random forests, and Bayesian networks. The areal similarity degree risk quantification, framingham risk score and simScore were the three risk quantification techniques identified. Evidence suggests that evaluated ML techniques, with accuracy ranging from 75.5% to 98.9%, can more accurately diagnose MetS than both statistical and risk quantification techniques. The standardised Z-score is the most frequent statistical technique identified. However, highlighted proof based on performance measures indicate that the decision tree and artificial neural network ML techniques have the highest predictive performance for the prediction of MetS. Evidence suggests that more accurate diagnosis of MetS is required to evaluate the predictive performance of the statistical and ML techniques.
Metabolic syndrome which precedes the increased incidence of cardiovascular, disease and Type 2 diabetes and other noncommunicable diseases is defined as a group of metabolic dysfunction including glucose intolerance, central obesity, hypertriglyceridemia, dyslipidemia, and hypertension. This study aims to employ areal similarity degree risk quantification and MediBoost methods; to predict the risk of metabolic syndrome. This research is a practical one in which data from 11,237 participants of the CLUSTer Cohort Study in Malaysia has been utilized. Metabolic syndrome risk factors used are: fasting blood glucose, waist circumference, triglycerides, HDL-cholesterol, systolic and diastolic blood pressure. The data set was stratified by gender and age groups into young, middle-age and old. Data was labeled based on JIS criteria. The MediBoost algorithm outperformed the ASD risk quantification in all the performance metrics for all the subgroups of the CLUSTer dataset. For example, in the young male subgroup the accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and area under the receiver operating curve (AUC) are 87.64 (g7.g6), 46.54 (100), g8.g6 (97.46), g2.5 (go.63), 87.04 (100), 72.75 (g6.03) for ASD(MediBoost) respectively. In a two-way sign-to-sign test, the performance metrics of MediBoost is significantly more efficient than ASD. The MediBoost algorithm also generates a simple interpretable decision tree which can be used to aid both individuals and medical practitioners in the timely and accurate diagnosis of the risk of metabolic syndrome.