Combinations Of Input Features Research Articles

An adaptive feature selection schema using improved technical indicators for predicting stock price movements

Accurate stock market forecasts can bring high returns for investors. There have been a growing number of studies employing machine learning technology to perform stock prediction tasks with the development of machine learning and artificial intelligence technologies. However, accurately predicting stock price trends still is an elusive goal, not only because the stock market is affected by policies, market environment, market sentiment, etc., but also because stock price data is inherently complex, noisy, and nonlinear. Many technical indicators have been used as input features to stock prediction models, but the quality of technical indicators has always been a neglected issue, thus the application of feature engineering in stock prediction tasks needs to be further expanded. Using 18 technical indicators as the original features, this paper presents improved technical indicators based on wavelet denoising and a novel two-stage adaptive feature selection method. Finally, the random forest model is used as the stock prediction model. Experiments show that in contrast to the original technical indicators, the improved technical indicators significantly enhance the performance of the model (e.g., F1 scores increased by 34.48% on the SSE Composite Index (SSEC) data set, 41.56% on the Hang Seng Index (HSI) data set, 34.48% on the Dow Jones Industrial Average (DJI) data set, 32.75% on the Standard & Poor's 500 Index (S&P 500) data set). The experimental results verify the importance of the quality of technical indicators in the task of stock prediction. Meanwhile, the results also demonstrate the effectiveness of the feature selection method, which can achieve higher prediction accuracy with fewer features. In addition, we established multiple data sets according to the size-varied time windows to study the influence of the size-varied time windows. The results show that properly increasing the size of the time window can exert a positive impact on the model. Finally, by utilizing our two-stage adaptive feature selection method, we remove redundant features, and achieve excellent results on data sets from four different stock markets (e.g., F1 scores reached 0.754 on the SSEC data set, 0.794 on the HSI data set, 0.789 on the DJI data set, 0.821 on the S&P 500 data set). Overall, this study experimentally verifies that improving feature quality can positively impact model performance, and that choosing an appropriate combination of input features can not only improve model performance, but reduces the negative impact of the curse of dimensionality as well.

A machine learning-based method for prediction of ship performance in ice: Part I. ice resistance

This article focuses on design of an Artificial Neural Network (ANN) model to estimate ship resistance in ice-covered water by using suitable ship and ice parameters. In order to develop a reliable model, as much ice resistance test data as from the ship sea trials and model test measurements are collected to train the neural network. Different features (ship design parameters and ice mechanic properties) are explored to find a suitable combination of input features. Several algorithms are tested and compared to select a good model for resistance prediction. It turns out that seven features and the Radial Basis Function - Particle Swarm Optimization algorithm (RBF-PSO) can provide a reasonable generalization model. This study shows that the ice resistance predicted by the ANN correlates well with the measured data. The model developed herein can be used as an ice resistance prediction tool with high accuracy compared to the conventional semi-empirical formulae used in polar ship design.

Diagnosis for multiple faults of chiller using ELM-KNN model enhanced by multi-label learning and specific feature combinations

Existing fault detection and diagnosis methods for chillers are usually very effective on single faults diagnosis, but perform poorly while diagnosing multiple faults, and these fault diagnosis models depend on the range of training data. Such models tend to fail when the system encounters a fault that was not included in training data. This paper presents a novel multiple faults diagnosis method for chiller based on multi-label learning and specific feature combinations enhanced ELM-KNN. Firstly, Extreme Learning Machine (ELM) is used for mapping of features to improve the accuracy of K-Nearest Neighbor (KNN) algorithm for multiple faults. Then, through multi-label learning, a model is established for each single fault, and by merging these models a final multiple faults diagnosis model is formed. Finally, by examining the input features, the specific combinations of input features for each single fault are determined and applied to the actual chiller. Experimental results show that the model proposed in this paper has the highest accuracy among the compared methods. The model proposed has achieved better diagnosis performance for the multiple faults in the absence of several multiple faults training data. The specific feature combinations are beneficial to improve the diagnosis performance of the model. The model can have excellent diagnostic performance for both normal operation and multiple faults by only using a small amount of single fault data in training. In addition, the model proposed can also complete the diagnosis of single faults in the absence of some single faults training data.

Separability of Input Features and the Resulting Accuracy in Classifying Target Poses for Active Transhumeral Prosthetic Interfaces.

In active prostheses, it is desired to achieve target poses for a given family of tasks, for example, in the task of forward reaching using a transhumeral prosthesis with coordinated joint movements. To do so, it is necessary to distinguish these target poses accurately using the input features (e.g. kinematic and sEMG) obtained from the human users. However, the input features have conventionally been selected through human observations and influenced heavily by the availability of sensors in this context, which may not always yield the most relevant information to differentiate the target poses in the given task. In order to better select from a pool of available input features, those most appropriate for a given set of target poses, a measure that correlates well with the resulting classification accuracy is required so that it can inform the interface design process. In this paper, a scatter-matrix based class separability measure is adopted to quantitatively evaluate the separability of the target poses from their corresponding input features. A human experiment was performed on ten able-bodied subjects. Subjects were asked to perform forward-reaching movements with their arms on nine target poses in a virtual reality (VR) platform and the corresponding kinematic information of their arm movement and muscle activities were recorded. The accuracy of the prosthetic interface in determining the intended target poses of the human user during forward reaching is evaluated for different combinations of input features, selected from the kinematic and sEMG sensors worn by the users. The results demonstrate that employing input features that yield a high separability measure between target poses results in a high accuracy in identifying the intended target poses in the execution of the task.

Mowing event detection in permanent grasslands: Systematic evaluation of input features from Sentinel-1, Sentinel-2, and Landsat 8 time series

The intensity of land use and management in permanent grasslands affects both biodiversity and important ecosystem services. Comprehensive knowledge about these intensities is a crucial factor for sustainable decision-making in landscape policy. For meadows, the management intensity can be described by proxies such as the mowing frequency, usually, a higher number of cuts indicate higher intensities. Dense time series of medium resolution (10–30 m) remote sensing data are suitable for the detection of mowing events. However, existing studies revealed a general lack of consensus about the most appropriate input data set for a consistent and reliable mowing detection.We systematically evaluated the synergistic use of acquisitions from Sentinel-1, Sentinel-2, and Landsat 8 to detect the occurrence, frequency, and date of mowing events as an indicator of grassland management intensity. Dense time series of NDVI (Sentinel-2 and Landsat 8), γ0 backscatter, backscatter cross-ratio, backscatter second-order texture metrics as well as 6-day interferometric coherence (Sentinel-1) were used as input features. All possible combinations of input features were tested to train a one-dimensional convolutional neural network, which enables enhanced exploitation of the temporal domain of the data. The evaluation was conducted on 64 meadows for an overall of 257 mowing events from 2017 to 2019 in Germany.Our results revealed that the combination of input features improves the detection performance. The highest overall accuracy was reached by a combination of NDVI, backscatter cross-ratio, and interferometric coherence with an F1-Score of 0.84. The mowing frequency was predicted with a mean absolute error of 0.38 events per year, while the date of the events was missed by 3.79 days on average. NDVI time series alone mostly underperformed in comparison to optical/SAR combinations but clearly outperformed input-sets that were solely based on SAR features. The proposed model performed well for meadows with low to medium management intensities but further testing is recommended for highly intensive managed parcels.The results clearly demonstrate the additional value of fusing time series of the three present Earth observation systems that deliver a freely available global coverage of the land surface at medium resolution.

Predicting traffic demand during hurricane evacuation using Real-time data from transportation systems and social media

In recent times, hurricanes Matthew, Harvey, and Irma have disrupted the lives of millions of people across multiple states in the United States. Under hurricane evacuation, efficient traffic operations can maximize the use of transportation infrastructure, reducing evacuation time and stress due to massive congestion. Evacuation traffic prediction is critical to plan for effective traffic management strategies. However, due to the complex and dynamic nature of evacuation participation, predicting evacuation traffic demand long ahead of the actual evacuation is a very challenging task. Real-time information from various sources can significantly help us reliably predict evacuation demand. In this study, we use traffic sensor and Twitter data during hurricanes Matthew and Irma to predict traffic demand during evacuation for a longer forecasting horizon (greater than 1 h). We present a machine learning approach using Long-Short Term Memory Neural Networks (LSTM-NN), trained over real-world traffic data during hurricane evacuation (hurricanes Irma and Matthew) using different combinations of input features and forecast horizons. We compare our prediction results against a baseline prediction and existing machine learning models. Results show that the proposed model can predict traffic demand during evacuation well up to 24 h ahead. The proposed LSTM-NN model can significantly benefit future evacuation traffic management.

Short-Term Wind Power Forecasting Using Mixed Input Feature-Based Cascade-connected Artificial Neural Networks

Accurate short-term wind power forecasting is crucial for the efficient operation of power systems with high wind power penetration. Many forecasting approaches have been developed in the past to forecast short-term wind power. Artificial neural network-based approaches (ANNs) have become one of the most effective and popular short-term wind speed and wind power forecasting approaches in recent years. However, most researchers have used only historical data from a specific station to train the ANNs without considering meteorological variables from many neighboring stations on the forecasting performance. Using additional meteorological variables from neighboring stations can contribute valuable surrounding information to the forecasting model of the target station and improve ANNs performance. In this paper, a mixed input features-based cascade-connected artificial neural network (MIF-CANN) is used to train input features from many neighboring stations without encountering overfitting issues caused by many input features. Multiple ANNs train different combinations of input features in the first layer of the MIF-CANN model to produce preliminary results, then cascading into the second phase of the MIF-CANN model as inputs. The performance of the proposed MIF-CANN model is compared with the ANNs-based spatial correlation models. Simulation results show that the proposed MIF-CANN has better performance than the ANNs-based spatial correlation models.

Optimal Design of a U-Shaped Oscillating Water Column Device Using an Artificial Neural Network Model

A U-shaped oscillating water column (U-OWC) device has been investigated to enhance power extraction by placing the bottom-mounted vertical barrier in front of a conventional OWC. Then, the optimal design of a U-OWC device has been attempted by using an artificial neural network (ANN) model. First, the analytical model is developed by a matched eigenfunction expansion method (MEEM) based on linear potential theory. Using the developed analytical model, the input and output features for training an ANN model are identified, and then the database containing input and output features is established by a Latin hypercube sampling (LHS) method. With 200 samples, an ANN model is trained with the training data (70%) and validated with the remaining test data (30%). The predictions on output features are made for 4000 random combinations of input features for given significant wave heights and energy periods in irregular waves. From these predictions, the optimal geometric values of a U-OWC are determined by considering both the conversion efficiency and wave force on the barrier. It is found that a well-trained ANN model shows good prediction accuracy and provides the optimal geometric values of a U-OWC suitable for wave conditions at the installation site.

A Wave Prediction Framework Based on Machine Learning and the Third Generation Wave Model

Abstract To predict the evolution of wave spectrum in the real ocean, a machine learning framework is developed by training a long short-term memory (LSTM) neural network on a physics-based third-generation wave model (Simulating WAve Nearshore (SWAN)). Considering the realistic ocean waves are usually mixtures of windsea and swells, the wave spectrum is partitioned using a watershed algorithm, such that the windsea and swells are analyzed and predicted separately. Four parameters are selected to capture the wave spectrum of each system, including the significant wave height Hs, peaked wave period Tp, mean propagation direction θm, and directional spreading width σθ. The results demonstrate that the LSTM neural network can achieve accurate prediction of wave condition, the mean absolute error percentage (MAEPs) of 1-h prediction is less than 5.9%, 3.3%, 3.5%, and 3.3% for Hs, Tp, θm, and σθ, respectively, and accurate prediction of wave spectra is achieved. Even for the 10-h prediction, satisfactory results are obtained, e.g., the MAEP of Hs is less than 15.5%. The effects of output size (i.e., prediction duration), input data size (i.e., number of delays), as well as different combinations of input features on predictions of wave conditions are examined.

Machine learning for accelerating 2D flood models: Potential and challenges

AbstractTwo‐dimensional hydrodynamic models numerically solve full Shallow Water Equations (SWEs). Despite their high accuracy, these models have long simulation run times and therefore are of limited use for exploratory or real‐time flood predictions. We investigated the possibility of improving flood modelling speed using Machine Learning (ML). We propose a new method that replaces the computationally expensive parts of the hydrodynamic models with simple and efficient data‐driven approximations. Our hypothesis is that by integrating ML with physics‐based numerical methods, we can achieve improved generalization performance: that is, the trained model for one case study can be used in other studies without the need for new training. We tested two ML approaches: for the first, we integrated curve fitting, and, for the second, artificial neural networks (ANN) with a finite volume scheme to solve the local inertial approximation of the SWEs. The data‐driven models approximated the Momentum Equation, which explicitly solved the time derivative of flow rates. Water depths were then updated by applying a water balance equation. We also tested two different training datasets: the simulated dataset, generated from the results of hydrodynamic model, and the random dataset, generated by directly solving the momentum equation on randomly sampled input data. Various combinations of input features, for example, water slope and depth, were explored. The proposed models were trained in a small hypothetical case and tested in a different hypothetical and in two real case studies. Results showed that the curve‐fitting method can be implemented successfully, given sufficient training and input data. The ANN model trained with a random dataset was substantially more accurate than that of the model trained with the simulated dataset. However, it was not successful in the real case studies. The curve‐fitting method resulted in better generalization performance and increased the simulation speed of the local inertial model by 23%. Future research should test the performance of ML in terms of an increase in stable time step size and approximation of the full SWEs.

PSEUDO-MULTIVARIATE LSTM NEURAL NETWORK APPROACH FOR PURCHASE DAY PREDICTION IN B2B

This research focuses on trying to predict the moment of the next purchase for a customer in vendor-customer B2B scenario using an LSTM neural network and comparing prediction results from different input features. In a previous research we performed predictions for a specific customer product pair and used previous purchases for that pair as input data, but the number of such previous purchases was often very limited which resulted in low accuracy of predictions. By aggregating purchase data for all products a customer purchased, we were able to get more precise predictions of the next purchase. Additionally, expanding our input feature set yielded even better results. We performed an evaluation of LSTM networks trained with the most successful combination of input features for a six month period. Each of the networks was trained with purchase data up to the starting point of the selected period and the predictions were performed, after which additional input for the following seven days was added to the network. This process was then repeated for the entire six month period and a slight downward trend can be noticed for error metrics, leading to the conclusion that the network would perform even better over time with the addition of future purchases.

Prediction of Chronic Periodontitis Severity Using Machine Learning Models Based On Salivary Bacterial Copy Number.

Periodontitis is a widespread chronic inflammatory disease caused by interactions between periodontal bacteria and homeostasis in the host. We aimed to investigate the performance and reliability of machine learning models in predicting the severity of chronic periodontitis. Mouthwash samples from 692 subjects (144 healthy controls and 548 generalized chronic periodontitis patients) were collected, the genomic DNA was isolated, and the copy numbers of nine pathogens were measured using multiplex qPCR. The nine pathogens are as follows: Porphyromonas gingivalis (Pg), Tannerella forsythia (Tf), Treponema denticola (Td), Prevotella intermedia (Pi), Fusobacterium nucleatum (Fn), Campylobacter rectus (Cr), Aggregatibacter actinomycetemcomitans (Aa), Peptostreptococcus anaerobius (Pa), and Eikenella corrodens (Ec). By adding the species one by one in order of high accuracy to find the optimal combination of input features, we developed an algorithm that predicts the severity of periodontitis using four machine learning techniques. The accuracy was the highest when the models classified “healthy” and “moderate or severe” periodontitis (H vs. M-S, average accuracy of four models: 0.93, AUC = 0.96, sensitivity of 0.96, specificity of 0.81, and diagnostic odds ratio = 112.75). One or two red complex pathogens were used in three models to distinguish slight chronic periodontitis patients from healthy controls (average accuracy of 0.78, AUC = 0.82, sensitivity of 0.71, and specificity of 0.84, diagnostic odds ratio = 12.85). Although the overall accuracy was slightly reduced, the models showed reliability in predicting the severity of chronic periodontitis from 45 newly obtained samples. Our results suggest that a well-designed combination of salivary bacteria can be used as a biomarker for classifying between a periodontally healthy group and a chronic periodontitis group.

Discriminating crops/weeds in an upland rice field from UAV images with the SLIC-RF algorithm

ABSTRACT In this study, we propose a method for discriminating crops/weeds in upland rice fields using a commercial unmanned aerial vehicles (UAVs) and red-green-blue (RGB) cameras with the simple linear iterative clustering (SLIC) algorithm and random forest (RF) classifier. In the SLIC-RF algorithm, we evaluated different combinations of input features: three color spaces (RGB, hue-saturation-brightness [HSV], CIE-L*a*b), canopy height model (CHM), spatial texture (Texture) and four vegetation indices (VIs) (excess green [ExG], excess red [ExR], green-red vegetation index [GRVI] and color index of vegetation extraction [CIVE]). Among the color spaces, the HSV-based SLIC-RF model showed the best performance with the highest out-of-bag (OOB) accuracy (0.904). The classification accuracy was improved by the combination of HSV with CHM, Texture, ExG, or CIVE. The highest OOB accuracy (0.915) was obtained from the HSV+Texture combination. The greatest errors from the confusion matrix occurred in the classification between crops and weeds, while soil could be classified with a very high accuracy. These results suggest that with the SLIC-RF algorithm developed in this study, rice and weeds can be discriminated by consumer-grade UAV images with acceptable accuracy to meet the needs of site-specific weed management (SSWM) even in the early growth stages of small rice plants..

Prediction of sulfur content in diesel fuel using fluorescence spectroscopy and a hybrid ant colony - Tabu Search algorithm with polynomial bases expansion

It is widely accepted that feature selection is an essential step in predictive modeling. There are several approaches to feature selection, from filter techniques to meta-heuristics wrapper methods. In this paper, we propose a compilation of tools to optimize the fitting of black-box linear models. The proposed AnTSbe algorithm combines Ant Colony Optimization and Tabu Search memory list for the selection of features and uses l1 and l2 regularization norms to fit the linear models. In addition, a polynomial combination of input features was introduced to further explore the information contained in the original data. As a case study, excitation-emission matrix fluorescence data were used as the primary measurements to predict total sulfur concentration in diesel fuel samples. The sample dataset was divided into S10 (less than 10 ​ppm of total sulfur), and S100 (mean sulfur content of 100 ​ppm) groups and local linear models were fit with AnTSbe. For the Diesel S100 local models, using only 5 out of the original 1467 fluorescence pairs, combined with bases expansion, we were able to satisfactorily predict total sulfur content in samples with MAPE of less than 4% and RMSE of 4.68 ​ppm, for the test subset. For the Diesel S10 local models, the use of 4 Ex/Em pairs was sufficient to predict sulfur content with MAPE 0.24%, and RMSE of 0.015 ​ppm, for the test subset. Our experimental results demonstrate that the proposed methodology was able to satisfactorily optimize the fitting of linear models to predict sulfur content in diesel fuel samples without need of chemical of physical pre-treatment, and was superior to classic PLS regression methods and also to our previous results with ant colony optimization studies in the same dataset. The proposed AnTSbe can be directly applied to data from other sources without need for adaptations.

Identifying relationships between imaging phenotypes and lung cancer-related mutation status: EGFR and KRAS

EGFR and KRAS are the most frequently mutated genes in lung cancer, being active research topics in targeted therapy. The biopsy is the traditional method to genetically characterise a tumour. However, it is a risky procedure, painful for the patient, and, occasionally, the tumour might be inaccessible. This work aims to study and debate the nature of the relationships between imaging phenotypes and lung cancer-related mutation status. Until now, the literature has failed to point to new research directions, mainly consisting of results-oriented works in a field where there is still not enough available data to train clinically viable models. We intend to open a discussion about critical points and to present new possibilities for future radiogenomics studies. We conducted high-dimensional data visualisation and developed classifiers, which allowed us to analyse the results for EGFR and KRAS biological markers according to different combinations of input features. We show that EGFR mutation status might be correlated to CT scans imaging phenotypes; however, the same does not seem to hold for KRAS mutation status. Also, the experiments suggest that the best way to approach this problem is by combining nodule-related features with features from other lung structures.

Improved Self-Organizing Map Clustering of Power Transformer Dissolved Gas Analysis Using Inputs Pre-Processing

Ability to organize data spatially while conserving the topological relation between data features makes the Self Organizing Map (SOM) a very useful tool for analysis and visualization of high dimensional data such as a power transformer's Dissolved Gas Analysis (DGA). Past SOM application required large historical data for its training and has limited fault detection sensitivity. In this paper, the effects of input features and data normalization are studied to enhance SOM's clustering. SOM is trained using DGA results extracted from actual faulted transformers. Combination of input features and data normalization methods are tested on SOM before the best SOM is identified. Validation is conducted using several datasets i.e. the IEC Technical Committee 10 database. Compared with past SOM applications, the proposed SOM required lesser training data, improved SOM's sensitivity in incipient fault detection and has good diagnosis accuracy. The proposed SOM is also compared with other AI-based DGA interpretation method i.e. Support Vector Machine (SVM) for benchmarking.

On explaining machine learning models by evolving crucial and compact features

Feature construction can substantially improve the accuracy of Machine Learning (ML) algorithms. Genetic Programming (GP) has been proven to be effective at this task by evolving non-linear combinations of input features. GP additionally has the potential to improve ML explainability since explicit expressions are evolved. Yet, in most GP works the complexity of evolved features is not explicitly bound or minimized though this is arguably key for explainability. In this article, we assess to what extent GP still performs favorably at feature construction when constructing features that are (1) Of small-enough number, to enable visualization of the behavior of the ML model; (2) Of small-enough size, to enable interpretability of the features themselves; (3) Of sufficient informative power, to retain or even improve the performance of the ML algorithm. We consider a simple feature construction scheme using three different GP algorithms, as well as random search, to evolve features for five ML algorithms, including support vector machines and random forest. Our results on 21 datasets pertaining to classification and regression problems show that constructing only two compact features can be sufficient to rival the use of the entire original feature set. We further find that a modern GP algorithm, GP-GOMEA, performs best overall. These results, combined with examples that we provide of readable constructed features and of 2D visualizations of ML behavior, lead us to positively conclude that GP-based feature construction still works well when explicitly searching for compact features, making it extremely helpful to explain ML models.

A nature-inspired biomarker for mental concentration using a single-channel EEG

We developed a system for measuring the attentional process during the performance of specific activities. The proposed biomarker device is able to estimate the mental concentration using a single-channel EEG. The system captures the EEG signal and several brain waves located in the left orbitofrontal brain region. Furthermore, we extended the input features of the system applying spectrum analysis. We applied two well-known evolutionary algorithms for selecting the best combination of input features: simulated annealing and geometric particle swarm optimization. Besides, we solved the binary classification problem (concentration vs. relaxation) using support vector machines and neural networks. Support vector machines are among the most common instruments for solving binary classification problems. On the other hand, we selected to study a family of neural networks named echo state networks, because the model is ideal for embedded systems and has shown good accuracy in real-world applications. The training and execution are fast, robust, and reliable. The developed system is autonomous, portable, reliable, non-invasive and has a low economic cost. Besides, it can be easily adjusted for each person and for each problem.

Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images

The Local Climate Zone (LCZ) scheme is a classification system providing a standardization framework to present the characteristics of urban forms and functions, especially for urban heat island (UHI) research. Landsat-based 100 m resolution LCZ maps have been classified by the World Urban Database and Portal Tool (WUDAPT) method using a random forest (RF) machine learning classifier. Some studies have proposed modified RF and convolutional neural network (CNN) approaches. This study aims to compare CNN with an RF classifier for LCZ mapping in great detail. We designed five schemes (three RF-based schemes (S1–S3) and two CNN-based ones (S4–S5)), which consist of various combinations of input features from bitemporal Landsat 8 data over four global mega cities: Rome, Hong Kong, Madrid, and Chicago. Among the five schemes, the CNN-based one with the incorporation of a larger neighborhood information showed the best classification performance. When compared to the WUDAPT workflow, the overall accuracies for entire land cover classes (OA) and for urban LCZ types (i.e., LCZ1-10; OAurb) increased by about 6–8% and 10–13%, respectively, for the four cities. The transferability of LCZ models for the four cities were evaluated, showing that CNN consistently resulted in higher accuracy (increased by about 7–18% and 18–29% for OA and OAurb, respectively) than RF. This study revealed that the CNN classifier classified particularly well for the specific LCZ classes in which buildings were mixed with trees or buildings or plants were sparsely distributed. The research findings can provide a basis for guidance of future LCZ classification using deep learning.

Down Syndrome Prediction Using a Cascaded Machine Learning Framework Designed for Imbalanced and Feature-correlated Data

Down syndrome (DS) caused by the presence of part or all of a third copy of chromosome 21 is the most common form of aneuploidy. The prenatal screening for DS is a key component of antenatal care and is recommended to be universally offered to women irrespective of age or background. The objective of this paper is to introduce a noninvasive and accurate diagnosis procedure for DS and to minimize social and financial cost of prenatal diagnosis. Recently, machine learning has received considerable attention in predictive analytics for medical problems. However, there is few its applications on DS prediction reported due to the difficulty of dealing with highly imbalanced and feature-correlated screening data. In this paper, we propose a cascaded machine learning framework designed for DS prediction based on three complementary stages: 1) pre-judgment with isolation forest technique, 2) model ensemble by voting strategy, and 3) final judgment using logistic regression approach. The experimental results show that the performance of this framework on maternal serum screening data set, when evaluated with different evaluation parameters, is superior to those of some machine learning methods. The best suggested combination of input features for DS screening is the group of alpha-fetoprotein, human chorionic gonadotropin, unconjugated estriol, and maternal age. In addition, our method has the potential to generate further accurate prediction for imbalanced and feature-correlated data, thereby providing a novel and effective approach for certain diseases analysis.