Comparison study between conventional machine learning and distributed multi-task learning models

2020 ◽  
Author(s):  
Salam Hamdan ◽  
Sufyan Almajali ◽  
Moussa Ayyash
Keyword(s):  
Machine Learning ◽  
Comparison Study ◽  
Learning Models ◽  
Task Learning ◽  
Conventional Machine

scholarly journals Automated Retraining of Machine Learning Models

2019 ◽  
Vol 8 (12) ◽  
pp. 445-452
Keyword(s):  
Machine Learning ◽  
Input Data ◽  
Research Work ◽  
Learning Models ◽  
Machine Learning Methods ◽  
Machine Learning Model ◽  
Crucial Component ◽  
Conventional Machine ◽  
Over Time ◽  
Machine Learning Models

Data is the most crucial component of a successful ML system. Once a machine learning model is developed, it gets obsolete over time due to presence of new input data being generated every second. In order to keep our predictions accurate we need to find a way to keep our models up to date. Our research work involves finding a mechanism which can retrain the model with new data automatically. This research also involves exploring the possibilities of automating machine learning processes. We started this project by training and testing our model using conventional machine learning methods. The outcome was then compared with the outcome of those experiments conducted using the AutoML methods like TPOT. This helped us in finding an efficient technique to retrain our models. These techniques can be used in areas where people do not deal with the actual working of a ML model but only require the outputs of ML processes

scholarly journals Traffic congestion prediction based on GPS trajectory data

2019 ◽  
Vol 15 (5) ◽  
pp. 155014771984744 ◽  
Author(s):  
Shuming Sun ◽  
Juan Chen ◽  
Jian Sun
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Traffic Congestion ◽  
Learning Models ◽  
Trajectory Data ◽  
Congestion Prediction ◽  
Gps Trajectory Data ◽  
Conventional Machine ◽  
Gps Trajectory ◽  
Machine Learning Models

Since speed sensors are not as widely used as GPS devices, the traffic congestion level is predicted based on processed GPS trajectory data in this article. Hidden Markov model is used to match GPS trajectory data to road network and the average speed of road sections can be estimated by adjacent GPS trajectory data. Four deep learning models including convolutional neural network, recurrent neural network, long short-term memory, and gated recurrent unit and three conventional machine learning models including autoregressive integrated moving average model, support vector regression, and ridge regression are used to perform congestion level prediction. According to the experimental results, deep learning models obtain higher accuracy in traffic congestion prediction compared with conventional machine learning models.

scholarly journals Automating Visual Blockage Classification of Culverts with Deep Learning

2021 ◽  
Vol 11 (16) ◽  
pp. 7561
Author(s):  
Umair Iqbal ◽  
Johan Barthelemy ◽  
Wanqing Li ◽  
Pascal Perez
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
False Negative ◽  
Hydraulic Modeling ◽  
Machine Learning Algorithms ◽  
Visual Features ◽  
Learning Approaches ◽  
Learning Models ◽  
Conventional Machine

Blockage of culverts by transported debris materials is reported as the salient contributor in originating urban flash floods. Conventional hydraulic modeling approaches had no success in addressing the problem primarily because of the unavailability of peak floods hydraulic data and the highly non-linear behavior of debris at the culvert. This article explores a new dimension to investigate the issue by proposing the use of intelligent video analytics (IVA) algorithms for extracting blockage related information. The presented research aims to automate the process of manual visual blockage classification of culverts from a maintenance perspective by remotely applying deep learning models. The potential of using existing convolutional neural network (CNN) algorithms (i.e., DarkNet53, DenseNet121, InceptionResNetV2, InceptionV3, MobileNet, ResNet50, VGG16, EfficientNetB3, NASNet) is investigated over a dataset from three different sources (i.e., images of culvert openings and blockage (ICOB), visual hydrology-lab dataset (VHD), synthetic images of culverts (SIC)) to predict the blockage in a given image. Models were evaluated based on their performance on the test dataset (i.e., accuracy, loss, precision, recall, F1 score, Jaccard Index, region of convergence (ROC) curve), floating point operations per second (FLOPs) and response times to process a single test instance. Furthermore, the performance of deep learning models was benchmarked against conventional machine learning algorithms (i.e., SVM, RF, xgboost). In addition, the idea of classifying deep visual features extracted by CNN models (i.e., ResNet50, MobileNet) using conventional machine learning approaches was also implemented in this article. From the results, NASNet was reported most efficient in classifying the blockage images with the 5-fold accuracy of 85%; however, MobileNet was recommended for the hardware implementation because of its improved response time with 5-fold accuracy comparable to NASNet (i.e., 78%). Comparable performance to standard CNN models was achieved for the case where deep visual features were classified using conventional machine learning approaches. False negative (FN) instances, false positive (FP) instances and CNN layers activation suggested that background noise and oversimplified labelling criteria were two contributing factors in the degraded performance of existing CNN algorithms. A framework for partial automation of the visual blockage classification process was proposed, given that none of the existing models was able to achieve high enough accuracy to completely automate the manual process. In addition, a detection-classification pipeline with higher blockage classification accuracy (i.e., 94%) has been proposed as a potential future direction for practical implementation.

Recent Advances in Predicting ncRNA-Protein Interactions Based on Machine Learning

2021 ◽  
Vol 01 ◽  
Author(s):  
Jingjing Wang ◽  
Yanpeng Zhao ◽  
Xiaoqian Huang ◽  
Yi Shi ◽  
Jianjun Tan
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Protein Interactions ◽  
Predictive Performance ◽  
Research Approach ◽  
Learning Models ◽  
Recent Advances ◽  
Conventional Machine ◽  
Near Future ◽  
Better Than

: Non-coding RNAs (ncRNAs) play significant roles in various physiological and pathological processes via interacting with the proteins. The existing experimental methods used for predicting ncRNA-protein interactions are costly and time-consuming. Therefore, an increasing number of machine learning models have been developed to efficiently predict ncRNA-protein interactions (ncRPIs), including shallow machine learning and deep learning models, which have achieved dramatic achievement on the identification of ncRPIs. In this review, we provided an overview of the recent advances in various machine learning methods for predicting ncRPIs, mainly focusing on ncRNAs-protein interaction databases, classical datasets, ncRNA/protein sequence encoding methods, conventional machine learning-based models, deep learning-based models, and the two integration-based models. Furthermore, we compared the reported accuracy of these approaches and discussed the potential and limitations of deep learning applications in ncRPIs. It was found that the predictive performance of integrated deep learning is the best, and those deep learning-based methods do not always perform better than shallow machine learning-based methods. We discussed the potential of using deep learning and proposed a research approach on the basis of the existing research. We believe that the model based on integrated deep learning is able to achieve higher accuracy in the prediction if substantial experimental data were available in the near future.

scholarly journals Mood Detection from Physical and Neurophysical Data Using Deep Learning Models

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-15
Author(s):  
Zeynep Hilal Kilimci ◽  
Aykut Güven ◽  
Mitat Uysal ◽  
Selim Akyokus
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Behavioral Data ◽  
Support Vector ◽  
Learning Models ◽  
Physical Data ◽  
Conventional Machine

Nowadays, smart devices as a part of daily life collect data about their users with the help of sensors placed on them. Sensor data are usually physical data but mobile applications collect more than physical data like device usage habits and personal interests. Collected data are usually classified as personal, but they contain valuable information about their users when it is analyzed and interpreted. One of the main purposes of personal data analysis is to make predictions about users. Collected data can be divided into two major categories: physical and behavioral data. Behavioral data are also named as neurophysical data. Physical and neurophysical parameters are collected as a part of this study. Physical data contains measurements of the users like heartbeats, sleep quality, energy, movement/mobility parameters. Neurophysical data contain keystroke patterns like typing speed and typing errors. Users’ emotional/mood statuses are also investigated by asking daily questions. Six questions are asked to the users daily in order to determine the mood of them. These questions are emotion-attached questions, and depending on the answers, users’ emotional states are graded. Our aim is to show that there is a connection between users’ physical/neurophysical parameters and mood/emotional conditions. To prove our hypothesis, we collect and measure physical and neurophysical parameters of 15 users for 1 year. The novelty of this work to the literature is the usage of both combinations of physical and neurophysical parameters. Another novelty is that the emotion classification task is performed by both conventional machine learning algorithms and deep learning models. For this purpose, Feedforward Neural Network (FFNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) neural network are employed as deep learning methodologies. Multinomial Naïve Bayes (MNB), Support Vector Regression (SVR), Decision Tree (DT), Random Forest (RF), and Decision Integration Strategy (DIS) are evaluated as conventional machine learning algorithms. To the best of our knowledge, this is the very first attempt to analyze the neurophysical conditions of the users by evaluating deep learning models for mood analysis and enriching physical characteristics with neurophysical parameters. Experiment results demonstrate that the utilization of deep learning methodologies and the combination of both physical and neurophysical parameters enhances the classification success of the system to interpret the mood of the users. A wide range of comparative and extensive experiments shows that the proposed model exhibits noteworthy results compared to the state-of-art studies.

scholarly journals Improving Current Glycated Hemoglobin Prediction in Adults: Consistency and Robustness of Machine Learning Algorithms with Electronic Health Records (Preprint)

2020 ◽  
Author(s):  
Zakhriya Alhassan ◽  
MATTHEW WATSON ◽  
David Budgen ◽  
Riyad Alshammari ◽  
Ali Alessan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Time Series Data ◽  
Learning Model ◽  
Series Data ◽  
Learning Models ◽  
Health Records ◽  
Conventional Machine ◽  
Deep Learning Model ◽  
Machine Learning Models

BACKGROUND Predicting the risk of glycated hemoglobin (HbA1c) elevation can help identify patients with the potential for developing serious chronic health problems such as diabetes and cardiovascular diseases. Early preventive interventions based upon advanced predictive models using electronic health records (EHR) data for such patients can ultimately help provide better health outcomes. OBJECTIVE Our study investigates the performance of predictive models to forecast HbA1c elevation levels by employing machine learning approaches using data from current and previous visits in the EHR systems for patients who had not been previously diagnosed with any type of diabetes. METHODS This study employed one statistical model and three commonly used conventional machine learning models, as well as a deep learning model, to predict patients’ current levels of HbA1c. For the deep learning model, we also integrated current visit data with historical (longitudinal) data from previous visits. Explainable machine learning methods were used to interrogate the models and have an understanding of the reasons behind the models' decisions. All models were trained and tested using a large and naturally balanced dataset from Saudi Arabia with 18,844 unique patient records. RESULTS The machine learning models achieved the best results for predicting current HbA1c elevation risk. The deep learning model outperformed the statistical and conventional machine learning models with respect to all reported measures when employing time-series data. The best performing model was the multi-layer perceptron (MLP) which achieved an accuracy of 74.52% when used with historical data. CONCLUSIONS This study shows that machine learning models can provide promising results for the task of predicting current HbA1c levels. For deep learning in particular, utilizing the patient's longitudinal time-series data improved the performance and affected the relative importance for the predictors used. The models showed robust results that were consistent with comparable studies.

scholarly journals Early Warning System for Online STEM Learning—A Slimmer Approach Using Recurrent Neural Networks

2021 ◽  
Vol 13 (22) ◽  
pp. 12461
Author(s):  
Chih-Chang Yu ◽  
Yufeng (Leon) Wu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
At Risk ◽  
At Risk Students ◽  
Training Data ◽  
Support Vector ◽  
Learning Models ◽  
Conventional Machine ◽  
Machine Learning Models

While the use of deep neural networks is popular for predicting students’ learning outcomes, convolutional neural network (CNN)-based methods are used more often. Such methods require numerous features, training data, or multiple models to achieve week-by-week predictions. However, many current learning management systems (LMSs) operated by colleges cannot provide adequate information. To make the system more feasible, this article proposes a recurrent neural network (RNN)-based framework to identify at-risk students who might fail the course using only a few common learning features. RNN-based methods can be more effective than CNN-based methods in identifying at-risk students due to their ability to memorize time-series features. The data used in this study were collected from an online course that teaches artificial intelligence (AI) at a university in northern Taiwan. Common features, such as the number of logins, number of posts and number of homework assignments submitted, are considered to train the model. This study compares the prediction results of the RNN model with the following conventional machine learning models: logistic regression, support vector machines, decision trees and random forests. This work also compares the performance of the RNN model with two neural network-based models: the multi-layer perceptron (MLP) and a CNN-based model. The experimental results demonstrate that the RNN model used in this study is better than conventional machine learning models and the MLP in terms of F-score, while achieving similar performance to the CNN-based model with fewer parameters. Our study shows that the designed RNN model can identify at-risk students once one-third of the semester has passed. Some future directions are also discussed.

Sign in / Sign up

Export Citation Format

Share Document