Proposed Prediction System Research Articles

Dynamic-group-aware networks for multi-agent trajectory prediction with relational reasoning

Demystifying the interactions among multiple agents from their past trajectories is fundamental to precise and interpretable trajectory prediction. However, previous works mainly consider static, pairwise interactions with limited relational reasoning. To more comprehensively model interactions and reason relations, we propose DynGroupNet, a dynamic-group-aware network, which (i) models time-varying interactions in highly dynamic scenes; (ii) captures both pairwise and group-wise interactions; and (iii) reasons both interaction strength and category without direct supervision. Based on DynGroupNet, we further design a prediction system to forecast socially plausible trajectories with dynamic relational reasoning. The proposed prediction system leverages the Gaussian mixture model, multiple sampling and prediction refinement to promote prediction diversity for multiple future possibilities capturing, training stability for efficient model learning and trajectory smoothness for more realistic predictions, respectively. The proposed complex interaction modeling of DynGroupNet, future diversity capturing, efficient model training and trajectory smoothing of prediction system together to promote more accurate and plausible future predictions. Extensive experiments show that: (1) DynGroupNet can capture time-varying group behaviors, infer time-varying interaction category and interaction strength during prediction; (2) DynGroupNet significantly outperforms the state-of-the-art trajectory prediction methods by 28.0%, 34.9%, 13.0% in FDE on the NBA, NFL and SDD datasets.

From Prediction to Prevention: Leveraging Deep Learning in Traffic Accident Prediction Systems

We propose a novel system leveraging deep learning-based methods to predict urban traffic accidents and estimate their severity. The major challenge is the data imbalance problem in traffic accident prediction. The problem is caused by numerous zero values in the dataset due to the rarity of traffic accidents. To address the issue, we propose a grid-clustered feature map with the ideas of grids and cells. To predict the occurrence of accidents in the grid, we introduce an accident detector that combines the power of a Convolutional Neural Network (CNN) with a Deep Neural Network (DNN). Then, hierarchical DNNs are supposed to be an accident risk classifier to estimate the risk of each cell in the accident-occurrence grid. The proposed system can effectively reduce instances with no traffic accidents. Furthermore, we introduce the concept of the Accident Risk Index (ARI) to better represent the severity of risk at each cell. Also, we consider all the explanatory variables, such as dangerous driving behaviors, traffic mobility, and safety facility information, that can be related to traffic accidents. To improve the prediction accuracy, we further take into consideration all the explanatory variables, such as dangerous driving behaviors, traffic mobility, and safety facility information, that can be related to traffic accidents. In the experiment, we highlight the benefits of our method for urban traffic accident management by significantly improving model performance compared to the baselines. The feasibility and applicability of the proposed system are validated in the data of Daejeon City, Republic of Korea. The proposed prediction system can dynamically advise and recommend commuters, traffic management systems, and city planners on alternatives, optimizations, and interventions.

Regret theory-based multivariate fusion prediction system and its application to interest rate estimation in multi-scale information systems

Estimating interest rates is a typical multivariate prediction problem that has garnered considerable attention in the finance industry. However, the rising complexity of the prediction environment has presented significant obstacles to the methodology and application of traditional single-scale rational prediction models. Considering this challenge, the paper presents a new multivariate fusion prediction system that aims to tackle the following issues: (1) How to mine prediction information from multi-scale information systems (MSISs)? (2) How to describe the irrational behavior of decision-makers (DMs) in prediction processes? (3) How to improve the prediction performance and generalization capability of the models? Specifically, the score function of each feature under MSISs is primarily established by applying scale rules, regret theory (RT), and dominance relations to thoroughly explore prediction information across varying scales. Second, an adaptive S3WD model is developed for feature selection, which leverages the feature score distribution and the sequential three-way decision (S3WD) concept to avoid the problem of dimensional disasters, thereby improving the accuracy of selected features and reducing the learning cost. Furthermore, to enhance the effectiveness and rationality of the kernel extreme learning machine (KELM), an improved version known as IKELM is developed, which combines the regret-based comprehensive score of each sample. Finally, a multivariate fusion prediction system is constructed and abbreviated as an S3WD-IKELM-PSO system, where the particle swarm optimization (PSO) algorithm is employed to determine optimal parameters. It is worth noting that actual interest rate estimation datasets are utilized to verify the feasibility and validity of the proposed prediction system. According to the experimental results, the S3WD-IKELM-PSO system exhibits superior prediction performance and generalization ability compared to existing machine learning models.

Surface roughness classification of electro discharge machined surfaces with deep ensemble learning

In this study, a CNN-based image processing technique was utilized for an EDM-machined tactile plate (VDI 3400) with 16 distinct surface roughness features. The images (1600 × 1200 px) were captured with an optical microscope at different magnifications (50×, 100×, and 200×). The dataset was augmented with various image processing techniques and then split into training, validation, and testing sets. The proposed prediction system is trained on the state-of-the-art ResNet18, EfficientNetB2, and EfficientNetv2s CNN models. Additionally, deep Ensemble Learning (EL) approaches, consisting Majority Voting (MV) and Average Voting (AV), were conducted. The accuracy scores of the deep EL model were verified using independent test data and provided superior performance at 50× (99.42%). However, the accuracy obtained at other magnifications were not very high at 100× (98.05%) and 200X (87.37%) optical zoom. The findings of this study show that EL techniques show great potential for stable and efficient determination of surface roughness characteristics.

Prediction of wart treatment response using a hybrid GA-ensemble learning approach

Warts are a common type of skin disease that is caused mainly by human papillomavirus (HPV). Several approaches are used to treat warts, which include the popular cryotherapy and immunotherapy methods. Various machine learning-based approaches have been introduced to help physicians select a proper treatment method for each patient. The main drawback of those approaches is the limitation of samples used for each of those models (90 samples for cryotherapy model and 90 samples for immunotherapy model). This study develops a reliable wart treatment prediction system using a hybrid genetic algorithm (GA)-ensemble learning approach with a larger dataset. The immunotherapy and cryotherapy datasets used in previous studies are separately balanced and then combined into one wart dataset, and the treatment method is modeled as one of the input features. GA is combined with learning algorithms, namely backpropagation neural networks (BPNN), support vector machine (SVM), classification and regression tree (CART), and K-nearest neighbors (KNN), to determine the optimal features for the prediction model. The four base classifiers, GA-BPNN, GA-SVM, GA-CART, and GA-KNN, are ensembled using bagging, boosting, and stacking techniques. The results show that ensemble models yield better classification results on the combined balanced wart dataset than individual classifiers. In particular, the stacking model with GA-SVM, GA-CART, and GA-KNN as layer-1 classifiers performs the best (accuracies of 100 % and 98.3 % on 10-fold cross validation and testing samples, respectively). Furthermore, the stacking model outperforms the model introduced in the literature on the same combined dataset with 180 samples (97.2 % average accuracy of 10-fold cross validation compared to 89.3 %). The proposed prediction system can assist physicians to reliably select appropriate treatment methods for patients who have warts with high accuracy, which in turn will have a positive impact on clinical resources.

Automatic COVID-19 prediction using explainable machine learning techniques

The coronavirus is considered this century's most disruptive catastrophe and global concern. This disease has prompted extreme social, psychological and economic impacts affecting millions of people around the globe. COVID-19 is transmitted from one infected person's body to another through respiratory droplets. This virus proliferates when people breathe in air-contaminated space with droplets and microscopic airborne particles. This research aims to analyze automatic COVID-19 detection using machine learning techniques to build an intelligent web application. The dataset has been preprocessed by dropping null values, feature engineering, and synthetic oversampling (SMOTE) techniques. Next, we trained and evaluated different classifiers, i.e., logistic regression, random forest, decision tree, k-nearest neighbor, support vector machine (SVM), ensemble models (adaptive boosting and extreme gradient boosting) and deep learning (artificial neural network, convolutional neural network and long short-term memory) techniques. Explainable AI with the LIME framework has been applied to interpret the prediction results. The hybrid CNN-LSTM algorithm with the SMOTE approach performed better than the other models on the employed open-source dataset obtained from the Israeli Ministry of Health website, with 96.34% accuracy and a 0.98 F1 score. Finally, this model was chosen to deploy the proposed prediction system to a website, where users may acquire an instantaneous COVID-19 prognosis based on their symptoms.

How well do investor sentiment and ensemble learning predict Bitcoin prices?

Investor sentiment is widely recognized as the major determinant of cryptocurrency prices. Although earlier research has revealed the influence of investor sentiment on cryptocurrency prices, it has not yet generated cohesive empirical findings on an important question: How effective is investor sentiment in predicting cryptocurrency prices? To address this gap, we propose a novel prediction model based on the Bitcoin Misery Index, using trading data for cryptocurrency rather than judgments from individuals who are not Bitcoin investors, as well as bagged support vector regression (BSVR), to forecast Bitcoin prices. The empirical analysis is performed for the period between March 2018 and May 2022. The results of this study suggest that the addition of the sentiment index enhances the predictive performance of BSVR significantly. Moreover, the proposed prediction system, enhanced with an automatic feature selection component, outperforms state-of-the-art methods for predicting cryptocurrency for the next 30 days.

Multivariate selection-combination short-term wind speed forecasting system based on convolution-recurrent network and multi-objective chameleon swarm algorithm

Wind energy, as a typical environmentally friendly source of energy for power generation, has the advantages of being renewable and emitting no greenhouse gases. Moreover, in wind power generation, accurate wind speed prediction is vital. However, most existing forecasting models use only univariate time series forecasting models, ignoring the effect of other variables on wind speed and the improvement of the model using optimization algorithms, resulting in lower accuracy and stability. Aiming to fill this gap, we develop a complete multivariate selection-combination short-term wind speed forecasting system, which is composed of two advanced feature-selection methods; six single forecasting models based on convolutional and recurrent neural networks and a multi-objective chameleon swarm optimization algorithm. We prove theoretically that the proposed multi-objective chameleon swarm optimization algorithm has Pareto optimal solutions and performs best in some test functions by comparing it with other multi-objective swarm optimization algorithms. For wind speed prediction in summer, our proposed prediction system achieves a mean absolute percentage error of 1.937%, 2.110% and 2.584% in one-, two- and three-step forecasting, respectively, which is higher than single and other combined models.

Physical human locomotion prediction using manifold regularization.

Human locomotion is an imperative topic to be conversed among researchers. Predicting the human motion using multiple techniques and algorithms has always been a motivating subject matter. For this, different methods have shown the ability of recognizing simple motion patterns. However, predicting the dynamics for complex locomotion patterns is still immature. Therefore, this article proposes unique methods including the calibration-based filter algorithm and kinematic-static patterns identification for predicting those complex activities from fused signals. Different types of signals are extracted from benchmarked datasets and pre-processed using a novel calibration-based filter for inertial signals along with a Bessel filter for physiological signals. Next, sliding overlapped windows are utilized to get motion patterns defined over time. Then, polynomial probability distribution is suggested to decide the motion patterns natures. For features extraction based kinematic-static patterns, time and probability domain features are extracted over physical action dataset (PAD) and growing old together validation (GOTOV) dataset. Further, the features are optimized using quadratic discriminant analysis and orthogonal fuzzy neighborhood discriminant analysis techniques. Manifold regularization algorithms have also been applied to assess the performance of proposed prediction system. For the physical action dataset, we achieved an accuracy rate of 82.50% for patterned signals. While, the GOTOV dataset, we achieved an accuracy rate of 81.90%. As a result, the proposed system outdid when compared to the other state-of-the-art models in literature.

Deep Learning Neural Network Prediction System Enhanced with Best Window Size in Sliding Window Algorithm for Predicting Domestic Power Consumption in a Residential Building.

Buildings are considered to be one of the world's largest consumers of energy. The productive utilization of energy will spare the accessible energy assets for the following ages. In this paper, we analyze and predict the domestic electric power consumption of a single residential building, implementing deep learning approach (LSTM and CNN). In these models, a novel feature is proposed, the “best N window size” that will focus on identifying the reliable time period in the past data, which yields an optimal prediction model for domestic energy consumption known as deep learning recurrent neural network prediction system with improved sliding window algorithm. The proposed prediction system is tuned to achieve high accuracy based on various hyperparameters. This work performs a comparative study of different variations of the deep learning model and records the best Root Mean Square Error value compared to other learning models for the benchmark energy consumption dataset.

Stress prediction using micro-EMA and machine learning during COVID-19 social isolation.

Accurately predicting users’ perceived stress is beneficial to aid early intervention and prevent both mental illness and physical disease during the COVID-19 pandemic. However, the existing perceived stress predicting system needs to collect a large amount of previous data for training but has a limited prediction range (i.e., next 1–2 days). Therefore, we propose a perceived stress prediction system based on the history data of micro-EMA for identifying risks 7 days earlier. Specifically, we first select and deliver an optimal set of micro-EMA questions to users every Monday, Wednesday, and Friday for reducing the burden. Then, we extract time-series features from the past micro-EMA responses and apply an Elastic net regularization model to discard redundant features. After that, selected features are fed to an ensemble prediction model for forecasting fine-grained perceived stress in the next 7 days. Experiment results show that our proposed prediction system can achieve around 4.26 (10.65% of the scale) mean absolute error for predicting the next 7 day’s PSS scores, and higher than 81% accuracy for predicting the next 7 day’s stress labels.

A machine learning approach to predict the activity of smart home inhabitant

A smart home inhabitant performs a unique pattern or sequence of tasks repeatedly. Thus, a machine learning approach will be required to build an intelligent network of home appliances, and the algorithm should respond quickly to execute the decision. This study proposes a decision tree-based machine learning approach for predicting the activities using different appliances such as state, locations and time. A noise filter is employed to remove unwanted data and generate task sequences, and dual state properties of a home appliance are utilized to extract episodes from the sequence. An incremental decision tree approach was taken to reduce execution time. The algorithm was tested using a well-known smart home dataset from MavLab. The experimental results showed that the algorithm successfully extracted 689 predictions and their location at 90% accuracy, and the total execution time was 94 s, which is less than that of existing methods. A hardware prototype was designed using Raspberry Pi 2 B to validate the proposed prediction system. The general-purpose input-output (GPIO) interfaces of Raspberry Pi 2 B were used to communicate with the prototype testbed and showed that the algorithm successfully predicted the next activities.

Cloud‐based onboard prediction and diagnosis of diabetic retinopathy

SummaryDiabetic retinopathy remains the most daunting microvascular complication of diabetic disease. Major risk factors of diabetic retinopathy include long‐term diabetics, improper blood glucose level, and dyslipidemia. In order to investigate the presence of diabetic retinopathy‐related features and to deal with the diagnosis of various diabetic severity stages, there is a need for a cloud‐based automated screening system. So, the development of novel biomarkers should take the advantage of objective measurement and evaluation indicating the biological and pathogenic processes to all the therapeutic interventions. Current state‐of‐the‐art research studies lack accommodating large sample size, cross‐validation among the diverse populations, time, and cost‐effective diagnosis techniques. To overcome these challenges, a cloud‐based diabetic retinopathy prediction system is proposed using the recurrent convolution neural network classifier model. The proposed prediction system can provide risk stratification, optimized resource allocation, a severe form of disease prediction, risk control, and preventive interventions during the screening and diagnosis process. It also provides prognostic information to patients stating various cost‐effective predictive responses according to treatment modalities. Moreover, the proposed system clinical decision‐making will outperform the existing classifiers in terms of prediction accuracy, sensitivity, specificity, precision, recall, and F1‐score.

Heart Diseases Prediction System Using Classification and Genetic Algorithm

Cardiovascular diseases is the main cause of death all over the world and becomes severe health threat among higher age people. Early diagnosis of the disease can save lives and medical diagnosis plays key role. the practitioners are applying many advance treatments. The proposed works studies the risk of Cardiovascular diseases prediction based on machine learning and genetic algorithm. This work is an ensemble model of combining the efficacy of genetic algorithm along with decision tree classification. The features determined by the genetic algorithm are used for machine learning classification, which improves the efficacy of proposed prediction system. The dataset provided by UCI repository, named Cleveland dataset is used for the study. The dataset with 303 instances and 14 attributes with five class types are used for the study. The class values range from 0 - Normal to 4- Stoke. The experimental results shows that the Genetic Algorithm based feature selection and classification bring best results on multiple class disease threat prediction. The application is designed that patients can able to predict and discuss with practitioners through the designed web application.

Quantitative prediction for weld reinforcement in arc welding additive manufacturing based on molten pool image and deep residual network

In the process of arc welding additive manufacturing, real-time monitoring weld reinforcement of the deposited layer could provide additional information for the researcher to understand the layer by layer mechanics. In this paper, a molten pool vision sensor system is utilized to collect the welding pool image at the first 1 ms of the short circuit phase. A locating system is applied to detect the position of welding pool image on the deposited layer and a three-dimensional system is utilized to measure the actual weld reinforcement. A residual-based network is designed to quantitatively predict the weld reinforcement of the deposited layer. The prediction results indicate that the proposed prediction system has low prediction error (less than 0.05 mm) and strong generalizing performance in different inter-layer cool-down time, because the shape and temperature distribution of the molten pool are the main affecting factors in weld reinforcement quantitative prediction of arc welding additive manufacturing.

WITHDRAWN: Review on intelligent prediction transportation system for pedestrian crossing using machine learning

A Pedestrian path in road crossing is an essential infrastructure in the part of transportation, which help to serve in the of secure and saving lives of million people and possessions and helps flow in order of the traffic in roads. The main objective of the proposed prediction system is in the process to detect the pedestrian crossing by considering various behaviors of the pedestrians in different types of lanes. We proposed a technique in which the pre-processing of the captured frame and probabilistic branching of the frame are taken care by the Convolutional Neural Networks (CNN). When the pedestrian crossing is detected, the distance is calculated based on the ratio of the area of ROI between them and the frame area. Based on the calculated distance, the brake is controlled automatically to prevent the accidents in obstructed areas. The proposed technique is useful in road safety applications to reduce the unpredictability in determining the behaviour of the pedestrians while crossing the road. This technique mainly comprises of Convolutional Neural Networks (CNN) which can produce higher range of accuracy of 96.7% than in histogram-oriented gradients (HOG) and support vector machine (SVM) which produces accuracy of 78–80%.

Development of an In Silico Prediction Model for P-glycoprotein Efflux Potential in Brain Capillary Endothelial Cells toward the Prediction of Brain Penetration.

Developing in silico models to predict the brain penetration of drugs remains a challenge owing to the intricate involvement of multiple transport systems in the blood brain barrier, and the necessity to consider a combination of multiple pharmacokinetic parameters. P-glycoprotein (P-gp) is one of the most important transporters affecting the brain penetration of drugs. Here, we developed an in silico prediction model for P-gp efflux potential in brain capillary endothelial cells (BCEC). Using the representative values of P-gp net efflux ratio in BCEC, we proposed a novel prediction system for brain-to-plasma concentration ratio (Kp,brain) and unbound brain-to-plasma concentration ratio (Kp,uu,brain) of P-gp substrates. We validated the proposed prediction system using newly acquired experimental brain penetration data of 28 P-gp substrates. Our system improved the predictive accuracy of brain penetration of drugs using only chemical structure information compared with that of previous studies.

Prediction of surface roughness based on a hybrid feature selection method and long short-term memory network in grinding

Ground surface roughness is regarded as one of the most crucial indicators of machining quality and is hard to be predicted due to the random distribution of abrasive grits and sophisticated grinding mechanism. In order to estimate surface roughness accurately in grinding process and provide feasible monitoring scheme for practical manufacturing application, a novel prediction system of surface roughness is presented in this article, including the processing of grinding signals, selection of feature combination, and development of prediction model. Grinding force, vibration, and acoustic emission signals are collected during the grinding of C-250 maraging steel. Numerous features in time domain and frequency domain are extracted from original and decomposed signals. A hybrid feature selection approach is proposed to select features based on their relevance to surface roughness as well as hardware and time costs. A sequential deep learning framework, long short-term memory (LSTM) network, is employed to predict ground surface roughness. The results have shown that the LSTM model achieves excellent prediction performance with a feature combination of grinding force and acoustic emission. After considering the hardware and time costs, features in acceleration signal replace those in grinding force and acoustic emission signals with slight loss of prediction performance and significant reduction of costs, which proves the practicability and feasibility of proposed prediction system.

Tax Default Prediction Using Feature Transformation-Based Machine Learning

This study proposes to address the economic significance of unpaid taxes by using an automatic system for predicting a tax default. Too little attention has been paid to tax default prediction in the past. Moreover, existing approaches tend to apply conventional statistical methods rather than advanced data analytic approaches, including state-of-the-art machine learning methods. Therefore, existing studies cannot effectively detect tax default information in real-world financial data because they fail to take into account the appropriate data transformations and nonlinear relationships between early-warning financial indicators and tax default behavior. To overcome these problems, this study applies diverse feature transformation techniques and state-of-the-art machine learning approaches. The proposed prediction system is validated by using a dataset showing tax defaults and non-defaults at Finnish limited liability firms. Our findings provide evidence for a major role of feature transformation, such as logarithmic and square-root transformation, in improving the performance of tax default prediction. We also show that extreme gradient boosting and the systematically developed forest of multiple decision trees outperform other machine learning methods in terms of accuracy and other classification performance measures. We show that the equity ratio, liquidity ratio, and debt-to-sales ratio are the most important indicators of tax defaults for 1-year-ahead predictions. Therefore, this study highlights the essential role of well-designed tax default prediction systems, which require a combination of feature transformation and machine learning methods. The effective implementation of an automatic tax default prediction system has important implications for tax administration and can assist administrators in achieving feasible government expenditure allocations and revenue expansions.

A Smart Architecture for Diabetic Patient Monitoring Using Machine Learning Algorithms.

Continuous monitoring of diabetic patients improves their quality of life. The use of multiple technologies such as the Internet of Things (IoT), embedded systems, communication technologies, artificial intelligence, and smart devices can reduce the economic costs of the healthcare system. Different communication technologies have made it possible to provide personalized and remote health services. In order to respond to the needs of future intelligent e-health applications, we are called to develop intelligent healthcare systems and expand the number of applications connected to the network. Therefore, the 5G network should support intelligent healthcare applications, to meet some important requirements such as high bandwidth and high energy efficiency. This article presents an intelligent architecture for monitoring diabetic patients by using machine learning algorithms. The architecture elements included smart devices, sensors, and smartphones to collect measurements from the body. The intelligent system collected the data received from the patient, and performed data classification using machine learning in order to make a diagnosis. The proposed prediction system was evaluated by several machine learning algorithms, and the simulation results demonstrated that the sequential minimal optimization (SMO) algorithm gives superior classification accuracy, sensitivity, and precision compared to other algorithms.