Dropout Ratio Research Articles

Wheat Rust Disease Detection Using Convolutional Neural Network

Wheat is a vital crop globally, playing a crucial role in ensuring food security. Any damage to wheat crops, particularly from diseases like wheat rust, can exacerbate the global food crisis. Wheat rust, along with other crop diseases, poses a serious threat to agricultural sustainability and food supply. Technological approaches to detect crop health can significantly enhance disease prevention compared to traditional manual methods. This study focuses on detecting wheat rust diseases, specifically wheat leaf rust, stem rust, and yellow rust, all of which vary in their impact on crops. By employing image analysis of wheat plants, the research aims to accurately distinguish between healthy crops and those affected by rust diseases. The experiments consider multiple variables, such as learning rate, dropout, and train-test split ratio, reflecting a comprehensive research approach. The model achieved an impressive 99.64% accuracy in detecting wheat rust, highlighting its potential for early disease detection and prevention.

DETERMINING STUDENT'S ONLINE ACADEMIC PERFORMANCE USING MACHINE LEARNING TECHNIQUES

Predicting student's academic performance during online learning has been considered a major task during the pandemic period. During the online mode of learning, academic activities have been affected in such a way that the management of educational institutions has planned to design support systems for predicting the student's performance to reduce the dropout ratio of the students and bring improvement in academic activities. During COVID-19, the main challenge is maintaining student's grades by predicting their academic performance using different techniques such as Education Data Mining and Learning Analytics. Different features have been identified related to the teaching mechanisms in online learning, which have a great impact on the improvement of academic performance. A high-quality dataset helps us to generate productive results, which in turn helps us to make effective decisions for promoting high-quality education. In this research, five prediction models for predicting academic performance have been proposed by collecting an imbalanced dataset of 350 students from the same computer science domain. After applying pre-processing techniques for cleaning the data, machine learning models have been applied, including K-Nearest Neighbor Classifier, Decision Tree, Random Forest, Support Vector Classifier, and Gaussian Naive Bayes. Results have been predicted for an imbalanced and balanced dataset after feature selection. Support Vector classifier has produced the best results in a balanced dataset with selected features by giving an accuracy of 96.89%.

Deep Learning Algorithms for Addressing Overfitting and Biological Realism in Tree Taper and Volume Predictions

This study addresses the challenges of overfitting and maintaining biological realism in Deep Learning Algorithms (DLAs), for predicting individual tree taper using stem diameters outside bark (DOB) and total tree volume (TTV). To this end, DLAs were trained using two different approaches: a “hyperparameter-optimized DLA,” which customizes specific hyperparameters such as learning rate and momentum rate, and a “regularization-optimized DLA,” which incorporates optimization techniques like early stopping with Root Mean Square Error (RMSE), L1 and L2 regularization, and dropout. Although obtaining the deterioration in predictive capabilities statistics from the taring dataset to the validation dataset by standard DLA with adaptive learning processes without customizing the hyperparameters and regularization parameters, the hyperparameter-optimized DLA with a momentum of 0.8, and a 7 # hidden layer for the TTV and regularization-optimized DLA with a dropout ratio of 0.000001, a 3 # hidden layer for the DOB demonstrated comparable predictive capabilities statistics across both training and validation datasets with generating biologically plausible predictions. Our results support that these hyperparameter-optimized and regularization-optimized DLAs, by improving the "black-box" nature of artificial intelligence, offer significant potential for enhanced interpretability and performance by improving the problem of overfitting and the violations biological realism in forest biometrics applications.

A Multitask Learning-Based Vision Transformer for Plant Disease Localization and Classification

Plant disease detection is a critical task in agriculture, essential for ensuring crop health and productivity. Traditional methods in this context are often labor-intensive and prone to errors, highlighting the need for automated solutions. While computer vision-based solutions have been successfully deployed in recent years for plant disease identification and localization tasks, these often operate independently, leading to suboptimal performance. It is essential to develop an integrated solution combining these two tasks for improved efficiency and accuracy. This research proposes the innovative Plant Disease Localization and Classification model based on Vision Transformer (PDLC-ViT), which integrates co-scale, co-attention, and cross-attention mechanisms and a ViT, within a Multi-Task Learning (MTL) framework. The model was trained and evaluated on the Plant Village dataset. Key hyperparameters, including learning rate, batch size, dropout ratio, and regularization factor, were optimized through a thorough grid search. Early stopping based on validation loss was employed to prevent overfitting. The PDLC-ViT model demonstrated significant improvements in plant disease localization and classification tasks. The integration of co-scale, co-attention, and cross-attention mechanisms allowed the model to capture multi-scale dependencies and enhance feature learning, leading to superior performance compared to existing models. The PDLC-ViT model evaluated on two public datasets achieved an accuracy of 99.97%, a Mean Average Precision (MAP) of 99.18%, and a Mean Average Recall (MAR) of 99.11%. These results underscore the model's exceptional precision and recall, highlighting its robustness and reliability in detecting and classifying plant diseases. The PDLC-ViT model sets a new benchmark in plant disease detection, offering a reliable and advanced tool for agricultural applications. Its ability to integrate localization and classification tasks within an MTL framework promotes timely and accurate disease management, contributing to sustainable agriculture and food security.

Educational Marginalization in Rural Pakistan: Sociocultural Economic Determinants for Policy Implications

In the socioeconomic context of the Koh-e-Suleman Tamun Qaisrani region of District Dera Ghazi Khan, the research examined the critical issue of early school departure and its multifaceted implications for the community and broader economic progress. Addressing a core aspect of human capital formation and societal development, the study scrutinized the impact of educational discontinuation on a country's overall advancement, emphasizing the linkage between early school dropout and a low literacy rate with manifold concomitant social challenges. Using a methodological approach encompassing convenient sampling techniques, data was elicited from 250 respondents via questionnaires. The research's analytical focus unearthed a clear correlation between parental income and literacy levels with students' dropout ratios and early school leaving tendencies. Key determinants were identified, including familial socioeconomic background, peer relationships, cultural phenomena such as early marriages, and logistical barriers like school distance. The findings divulged that lower parental income and literacy contribute to higher dropout rates and augmented probabilities of premature educational withdrawal. The study thus expounded a sociological critique of these systemic failures, accentuating the state's onus to ameliorate these issues. Recommendations were proffered, accenting the government's obligation to furnish elementary school amenities and institute financial aid measures for economically disadvantaged students, thereby cultivating an environment conducive to the amelioration of this profound social malaise.

BiLSTM-Based Joint Torque Prediction From Mechanomyogram During Isometric Contractions: A Proof of Concept Study.

Quantifying muscle strength is an important measure in clinical settings; however, there is a lack of practical tools that can be deployed for routine assessment. The purpose of this study is to propose a deep learning model for ankle plantar flexion torque prediction from time-series mechanomyogram (MMG) signals recorded during isometric contractions (i.e., a similar form to manual muscle testing procedure in clinical practice) and to evaluate its performance. Four different deep learning models in terms of model architecture (based on a stacked bidirectional long short-term memory and dense layers) were designed with different combinations of the number of units (from 32 to 512) and dropout ratio (from 0.0 to 0.8), and then evaluated for prediction performance by conducting the leave-one-subject-out cross-validation method from the 10-subject dataset. As a result, the models explained more variance in the untrained test dataset as the error metrics (e.g., root-mean-square error) decreased and as the slope of the relationship between the measured and predicted joint torques became closer to 1.0. Although the slope estimates appear to be sensitive to an individual dataset, >70% of the variance in nine out of 10 datasets was explained by the optimal model. These results demonstrated the feasibility of the proposed model as a potential tool to quantify average joint torque during a sustained isometric contraction.

Feasibility Study of Taking Back Control Together, an Intervention to Support Parents of Children with Cancer.

Parents of children with cancer can experience increased emotional distress. This study aimed to assess the feasibility (i.e., reach, treatment fidelity, and social validity) of Taking Back Control Together (TBCT). We assessed reach with the enrollment and dropout ratios. We assessed treatment fidelity using items from existing programs, controlling for the reliability of the items. For social validity, we used an adapted version of the Treatment Evaluation Inventory and compared means with theoretical cut-points. 42 participants enrolled in the intervention. The enrollment and dropout ratios were 39% and 38%, respectively. Treatment fidelity was 77.3-84.3% (95%CI 75.3-86%). Acceptability (M = 90%), satisfaction (M = 87%), and relevance (M = 82%) were significantly positive. This study suggests that certain elements of TBCT need to be reassessed before the intervention is pilot tested. Although reach was likely impacted by the COVID-19 pandemic, it could be improved with some modifications to the intervention.

PLACE Dropout: A Progressive Layer-wise and Channel-wise Dropout for Domain Generalization

Domain generalization (DG) aims to learn a generic model from multiple observed source domains that generalizes well to arbitrary unseen target domains without further training. The major challenge in DG is that the model inevitably faces a severe overfitting issue due to the domain gap between source and target domains. To mitigate this problem, some dropout-based methods have been proposed to resist overfitting by discarding part of the representation of the intermediate layers. However, we observe that most of these methods only conduct the dropout operation in some specific layers, leading to an insufficient regularization effect on the model. We argue that applying dropout at multiple layers can produce stronger regularization effects, which could alleviate the overfitting problem on source domains more adequately than previous layer-specific dropout methods. In this article, we develop a novel layer-wise and channel-wise dropout for DG, which randomly selects one layer and then randomly selects its channels to conduct dropout. Particularly, the proposed method can generate a variety of data variants to better deal with the overfitting issue. We also provide theoretical analysis for our dropout method and prove that it can effectively reduce the generalization error bound. Besides, we leverage the progressive scheme to increase the dropout ratio with the training progress, which can gradually boost the difficulty of training the model to enhance its robustness. Extensive experiments on three standard benchmark datasets have demonstrated that our method outperforms several state-of-the-art DG methods. Our code is available at https://github.com/lingeringlight/PLACEdropout .

A relay velocity model infers cell-dependent RNA velocity

RNA velocity provides an approach for inferring cellular state transitions from single-cell RNA sequencing (scRNA-seq) data. Conventional RNA velocity models infer universal kinetics from all cells in an scRNA-seq experiment, resulting in unpredictable performance in experiments with multi-stage and/or multi-lineage transition of cell states where the assumption of the same kinetic rates for all cells no longer holds. Here we present cellDancer, a scalable deep neural network that locally infers velocity for each cell from its neighbors and then relays a series of local velocities to provide single-cell resolution inference of velocity kinetics. In the simulation benchmark, cellDancer shows robust performance in multiple kinetic regimes, high dropout ratio datasets and sparse datasets. We show that cellDancer overcomes the limitations of existing RNA velocity models in modeling erythroid maturation and hippocampus development. Moreover, cellDancer provides cell-specific predictions of transcription, splicing and degradation rates, which we identify as potential indicators of cell fate in the mouse pancreas.

Automatic segmentation and quantified analysis of meibomian glands from infrared images.

An algorithm for automated segmentation of meibomian glands from infrared images obtained using a novel prototype infrared hand-held imager has been proposed in this study. Meibomian gland dysfunction (MGD) is quantified in terms of five clinically relevant metrics. A comparison of these metrics in patients with MGD has been presented against a sample of the normative healthy population. This is a prospective cross-sectional observational study. Patients presenting to the clinics were enrolled after written informed consent. The everted eyelids of 200 eyes of patients (of which 100 were healthy and 100 were diagnosed with MGD) were imaged using a prototype hand-held camera. The proposed algorithm was used to process the images using enhancement techniques and the glands were automatically segmented. A comparison of glands of normal eyes versus MGD-affected eyes is performed using five metrics presented in this study: (i) drop-out, (ii) length, (iii) width, (iv) the number of glands, and (v) the number of tortuous glands. The 95% confidence interval for the metrics did not show any overlap between the two groups. In MGD patients, the drop-out ratio was higher than normal. The length and number of glands were significantly lesser than normal. A number of tortuous glands were more in the MGD group. The metrics for MGD versus healthy and cut-off ranges were computed in the results. The prototype infrared hand-held meibographer and the proposed automatic algorithm for gland segmentation and quantification are effective aids in MGD diagnosis. We present a set of five metrics, which are clinically relevant for guiding clinicians in the diagnosis of MGD.

Exploring the Factors Affecting Students Drop-out: A Case Study of Public Secondary Schools in Pakistan

The purpose of this study was to explore the factors affecting the dropout rate in public secondary schools. The research design for this study was a case study design. The tool of the study was a semi-structured interview schedule. The population of the study was all the students of public secondary school. The convenient sampling technique was used to select the sample. The sample of the study was 80 students of secondary school in Tehsil Hafizabad district Gujranwala. The results of the study were that social culture and economic constraints were the main factors of the dropout ratio. This study will be helpful for parents, teachers and high-ups to know about the factors of the dropout ratio in the secondary school of Punjab (Pakistan).

A COMPARISON OF EIDETIC IMAGE THERAPY WITH COGNITIVE BEHAVIOR THERAPY FOR TREATING DEPRESSIVE AND ANXIETY DISORDERS IN ADULTS: A RANDOMIZED CONTROLLED TRIAL

Background & Objectives: Depression and anxiety are common mental health disorders around the world. This study aims to examine efficacy of eidetic image therapy in comparison to cognitive behavior therapy for treating depressive and anxiety disorders, and to compare the patients' dropout ratio in these therapies.
 Methods: This was a randomized controlled trial conducted from January through June 2021 in psychiatry department of Sir Ganga Ram hospital Lahore. Using DSM-5 diagnostic criteria, 60 adult patients with depressive and anxiety disorders were recruited and were randomly and equally assigned to experimental (eidetic image therapy) and control (cognitive behavior therapy) groups. These participants received respective therapies and followed. Beck Depression Inventory and Beck Anxiety Inventory were used at baseline and after conducting five therapy sessions. Paired t-test was used to compare the mean difference and p-value of <0.05 was considered statistically significant.
 Results: Descriptive analysis demonstrated a major difference in dropout numbers of eidetic image therapy (9; 30 %) and cognitive behavior therapy (25; 83 %). The efficacy of both interventions was statistically incomparable due to this excessive number of dropouts in control group. However, eidetic image therapy showed a significant difference (p<0.001) in pre and post therapy ratings; each patient exhibited a marked decline in depression/anxiety symptoms after taking 5 sessions.
 Conclusion: Eidetic imagery is a promising therapeutic utility for depressive and anxiety disorders. Cognitive behavior therapy is also an effective treatment methodology but this narrative is based on analysis of few cases.

Single-cell whole-genome sequencing, haplotype analysis in prenatal diagnosis of monogenic diseases.

Monogenic inherited diseases are common causes of congenital disabilities, leading to severe economic and mental burdens on affected families. In our previous study, we demonstrated the validity of cell-based noninvasive prenatal testing (cbNIPT) in prenatal diagnosis by single-cell targeted sequencing. The present research further explored the feasibility of single-cell whole-genome sequencing (WGS) and haplotype analysis of various monogenic diseases with cbNIPT. Four families were recruited: one with inherited deafness, one with hemophilia, one with large vestibular aqueduct syndrome (LVAS), and one with no disease. Circulating trophoblast cells (cTBs) were obtained from maternal blood and analyzed by single-cell 15X WGS. Haplotype analysis showed that CFC178 (deafness family), CFC616 (hemophilia family), and CFC111 (LVAS family) inherited haplotypes from paternal and/or maternal pathogenic loci. Amniotic fluid or fetal villi samples from the deafness and hemophilia families confirmed these results. WGS performed better than targeted sequencing in genome coverage, allele dropout (ADO), and false-positive (FP) ratios. Our findings suggest that cbNIPT by WGS and haplotype analysis have great potential for use in prenatally diagnosing various monogenic diseases.

Analysis of Enrollment Criteria in Secondary Schools Using Machine Learning and Data Mining Approach

Out-of-school children (OSC) surveys are conducted annually throughout Pakistan, and the results show that the literacy rate is increasing gradually, but not at the desired speed. Enrollment campaigns and targets system of enrollment given to the schools required a valuable model to analyze the enrollment criteria better. In existing studies, the research community mainly focused on performance evaluation, dropout ratio, and results, rather than student enrollment. There is a great need to develop a model for analyzing student enrollment in schools. In this proposed work, five years of enrollment data from 100 schools in the province of Punjab (Pakistan) have been taken. The significant features have been extracted from data and analyzed through machine learning algorithms (Multiple Linear Regression, Random Forest, and Decision Tree). These algorithms contribute to the future prediction of school enrollment and classify the school’s target level. Based on these results, a brief analysis of future registrations and target levels has been carried out. Furthermore, the proposed model also facilitates determining the solution of fewer enrollments in school and improving the literacy rate.

Implementation of a Hybrid Care Model for Telemedicine-based Cancer Pain Management at the Cancer Center of Naples, Italy: A Cohort Study.

Telemedicine, the remote delivery of healthcare services, represents a great opportunity for cancer pain management. A care model of telemedicine that combines remote visits and hospital access could be an effective and safe strategy for pain management of cancer patients. A retrospective study was conducted using the dataset of the telemedicine program at the Istituto Nazionale Tumori of Naples, Italy for assessing the efficacy of a telehealth-based model of care. Demographic, clinical, and process variables were investigated. A total of 226 cases and 489 visits were included in the analysis. The mean age of patients was 63.4 years (SD=12.4 years), and no sex differences were observed. Approximately 55% of patients were ECOG-PS ≤2 and 87% suffered from metastatic disease. More than half of the patients were treated with high doses of opioids. Each patient had a mean of 2 remote visits and half of the patients had more than 1 telehealth consultation. The dropout ratio was 5.3%. Most visits (n=472) were conducted on patients in the Campania Region, Italy. The maximum covered distance from the Cancer Center and the patients' location was 555.22 Km. A significant difference in the overall number of visits (p=0.006) and the number of pro-capita remote visits (p=0.010) was found, in favor of the group of patients treated before the end of the Covid-19 emergency in Italy, compared to those treated after the pandemic. Despite various positive outcomes, the analysis highlights several weaknesses, such as the need to assist patients with advanced and non-advanced disease located outside the regional territory. Overall, the telehealth processes should be adapted to post-pandemic scenarios towards their implementation in routine clinical practice.

Artificial Intelligence in Internet of Things System for Predicting Water Quality in Aquaculture Fishponds

Aquaculture has long been a critical economic sector in Taiwan. Since a key factor in aquaculture production efficiency is water quality, an effective means of monitoring the dissolved oxygen content (DOC) of aquaculture water is essential. This study developed an internet of things system for monitoring DOC by collecting essential data related to water quality. Artificial intelligence technology was used to construct a water quality prediction model for use in a complete system for managing water quality. Since aquaculture water quality depends on a continuous interaction among multiple factors, and the current state is correlated with the previous state, a model with time series is required. Therefore, this study used recurrent neural networks (RNNs) with sequential characteristics. Commonly used RNNs such as long short-term memory model and gated recurrent unit (GRU) model have a memory function that appropriately retains previous results for use in processing current results. To construct a suitable RNN model, this study used Taguchi method to optimize hyperparameters (including hidden layer neuron count, iteration count, batch size, learning rate, and dropout ratio). Additionally, optimization performance was also compared between 5-layer and 7-layer network architectures. The experimental results revealed that the 7-layer GRU was more suitable for the application considered in this study. The values obtained in tests of prediction performance were mean absolute percentage error of 3.7134%, root mean square error of 0.0638, and R-value of 0.9984. Therefore, the water quality management system developed in this study can quickly provide practitioners with highly accurate data, which is essential for a timely response to water quality issues. This study was performed in collaboration with the Taiwan Industrial Technology Research Institute and a local fishery company. Practical application of the system by the fishery company confirmed that the monitoring system is effective in improving the survival rate of farmed fish by providing data needed to maintain DOC higher than the standard value.

Quality enhancement at higher education institutions by early identifying students at risk using data mining

Accurate prediction of students' academic performance is one of the challenges in maintaining quality standards in any Higher Education Institution (H.E.I.). To ensure the quality of teaching and learning, H.E.I.s often employ Self-Assessment Reports (S.A.R.s) in which identifying a student drop-out ratio is important. Hence, it is essential to identify at-risk students in a given academic program. This article aims to identify at-risk students early by proposing a data mining-based predictive framework to improve the student's learning experience and minimize the dropped-out ratio. The academic sub-attributes or indicators in each course that may affect the performance of students in higher education institutions used in this study to examine students' academic achievement and predict students' performance to distinguish at-risk students are the marks of assignments, mid-term, lab exams, semester marks, total, grade, grade point (G.P.), quality point (Q.P.), grade point average (G.P.A.), and credit hours data of multiple courses categorized according to three knowledge areas defined by Higher Education Commission (H.E.C), Pakistan using data mining predictive techniques. The results indicate that the proposed methods can achieve maximum accuracy in predicting and identifying at-risk students in different courses.

E-Learning Environment Based Intelligent Profiling System for Enhancing User Adaptation

Online learning systems have expanded significantly over the last couple of years. Massive Open Online Courses (MOOCs) have become a major trend on the internet. During the COVID-19 pandemic, the count of learner enrolment has increased in various MOOC platforms like Coursera, Udemy, Swayam, Udacity, FutureLearn, NPTEL, Khan Academy, EdX, SWAYAM, etc. These platforms offer multiple courses, and it is difficult for online learners to choose a suitable course as per their requirements. In order to improve this e-learning education environment and to reduce the drop-out ratio, online learners will need a system in which all the platform’s offered courses are compared and recommended, according to the needs of the learner. So, there is a need to create a learner’s profile to analyze so many platforms in order to fulfill the educational needs of the learners. To develop a profile of a learner or user, three input parameters are considered: personal details, educational details, and knowledge level. Along with these parameters, learners can also create their user profiles by uploading their CVs or LinkedIn. In this paper, the major innovation is to implement a user interface-based intelligent profiling system for enhancing user adaptation in which feedback will be received from a user and courses will be recommended according to user/learners’ preferences.

A socio-ecological approach to reduce the physical activity drop-out ratio in primary care-based patients with type 2 diabetes: the SENWI study protocol for a randomized control trial

BackgroundPhysical activity (PA) is a key behaviour for patients with type 2 diabetes (T2DM). However, healthcare professionals’ (HCP) recommendations (walking advice), which are short-term and individually focused, did not reduce the PA drop-out ratio in the long run. Using a socio-ecological model approach may contribute to reducing patient dropout and improving adherence to PA. The aim of this study is threefold: first, to evaluate the effectiveness of a theory-driven Nordic walking intervention using a socio-ecological approach with T2DM patients in Spain; second, to explore the feasibility on the PA adherence process in T2DM patients while participating in the SENWI programme; and third, to understand the HCPs’ opinion regarding its applicability within the Spanish healthcare system.MethodsA three-arm randomized control trial (n = 48 each group) will assess the efficacy of two primary care-based PA interventions (Nordic walking vs. Nordic walking plus socio-ecological approach; two sessions per week for twelve weeks) compared to a control group (usual HCPs’ walking advice on PA). Inclusion criteria will include physically inactive patients with T2DM, older than 40 years and without health contraindications to do PA. PA levels and drop-out ratio, quality of life and metabolic and health outcomes will be assessed at baseline, post-intervention and at 9- and 21-month follow-ups. The effect of the different interventions will be assessed by a two-factor analysis of variance: treatment group vs time. Also, a two-factor ANOVA test will be performed with linear mixed models for repeated measures.A qualitative analysis using focus groups will explore the reasons for the (in)effectiveness of the new PA interventions. Qualitative outcomes will be assessed at post-intervention using thematic analysis.DiscussionCompared with the general PA walking advice and Nordic walking prescriptions, integrating a socio-ecological approach into Spanish primary care visits could be an effective way to reduce the PA drop-out ratio and increase PA levels in patients with T2DM. Such interventions are necessary to understand the role that multiple socio-complex process in day-to-day PA behaviour has in patients with T2DM in the Spanish context.Trial registrationClinicalTrials.gov NCT05159089. Physical Activity Drop-out Ratio in Patients’ Living with Type 2 Diabetes. Prospectively registered on 15 December 2021.

Apply an optimized NN model to low-dimensional format speech recognition and exploring the performance with restricted factors

The SCD (speech control detection) have received a lot of attention in recent years. A framework established by employing DNN-LSTM (deep neural network-long-short term memory) model for speech and text recognition is implemented in the current article. The performance of the build framework is analyzed with many different merits which consider many features, such as (with and without) noise, track number of speeches (ST (single track) and DT (double track)), and dropout ratio of data training. On the other hand, the speech discriminator model is developed and implemented with the DNN-LSTM framework, and the data sets are collected by four different persons. The adopted model performance is evaluated using the four different datasets, and each with 400–5000 training times. There are three parameters considered as the dominators for the performance evaluation of the completed speech platform. The results from the experiment with DT channel case clearly show that it outperforms the case with ST channel. It can see that the accuracy of the DNN-LSTM model increases from 0.3339 to 0.9696 and the loss rate decreases from 1.09984 to 0.19298 after adjusting the dropout ratio during the training step. This shows that the dropout ratio also dominates the accuracy and loss rate. Eventually, the results indicate that the used model compared to other similar methods, Bi-LSTM (bi-directional LSTM), achieves a more efficient preserving a high accuracy level.