Machine Learning Based Prediction Methods Research Articles

Predicting Increase in Demand for Public Buses in University Students Daily Life Needs: Case Study Based on a City in Japan

Accessibility and economic sustainability of public bus services (PBS) have been in a continuous decline in Japan’s countryside. Rural cities also suffer from population transformation toward industrial centers experiencing rapid economic growth. In the present study, we reviewed the current demand status of PBS in Kitami, a rural city in Japan that hosts a national university. The investigation was performed by examining students’ daily lives using a survey to collect data representing a portion of the population. The objective was to predict the change in demand rate for PBS concerning the necessities of everyday life from the perspective of university students as potential users of PBS. Intuitively, decision-makers at every level display a distinct prejudice toward alternatives that intend to change the long-lasting status quo, hence in the question sequence, a two-step verification probe was used to reveal a person’s actual perceived opinion. Accordingly, the respondents’ initial demand rate for PBS was around 60%; however, this score increased to 71% in the secondary confirmation. Afterward, using machine learning-based prediction methods, we could predict this demand at over 90% of F-measure, with the most reliable and stable prediction method reaching 80% by other daily life indicators’ weight. Finally, we supplied thorough evidence for our approach’s usability by collecting and processing the data’s right set regarding this study’s objective. This method’s highlighted outcomes would help to reduce the local governments’ and relevant initiatives’ adaptability time to demands and improve decision-making flexibility.

Predicting subcellular location of protein with evolution information and sequence-based deep learning

BackgroundProtein subcellular localization prediction plays an important role in biology research. Since traditional methods are laborious and time-consuming, many machine learning-based prediction methods have been proposed. However, most of the proposed methods ignore the evolution information of proteins. In order to improve the prediction accuracy, we present a deep learning-based method to predict protein subcellular locations.ResultsOur method utilizes not only amino acid compositions sequence but also evolution matrices of proteins. Our method uses a bidirectional long short-term memory network that processes the entire protein sequence and a convolutional neural network that extracts features from protein sequences. The position specific scoring matrix is used as a supplement to protein sequences. Our method was trained and tested on two benchmark datasets. The experiment results show that our method yields accurate results on the two datasets with an average precision of 0.7901, ranking loss of 0.0758 and coverage of 1.2848.ConclusionThe experiment results show that our method outperforms five methods currently available. According to those experiments, we can see that our method is an acceptable alternative to predict protein subcellular location.

Current status and future perspectives of computational studies on human-virus protein-protein interactions.

The protein-protein interactions (PPIs) between human and viruses mediate viral infection and host immunity processes. Therefore, the study of human-virus PPIs can help us understand the principles of human-virus relationships and can thus guide the development of highly effective drugs to break the transmission of viral infectious diseases. Recent years have witnessed the rapid accumulation of experimentally identified human-virus PPI data, which provides an unprecedented opportunity for bioinformatics studies revolving around human-virus PPIs. In this article, we provide a comprehensive overview of computational studies on human-virus PPIs, especially focusing on the method development for human-virus PPI predictions. We briefly introduce the experimental detection methods and existing database resources of human-virus PPIs, and then discuss the research progress in the development of computational prediction methods. In particular, we elaborate the machine learning-based prediction methods and highlight the need to embrace state-of-the-art deep-learning algorithms and new feature engineering techniques (e.g. the protein embedding technique derived from natural language processing). To further advance the understanding in this research topic, we also outline the practical applications of the human-virus interactome in fundamental biological discovery and new antiviral therapy development.

Average Weighted Objective Distance-Based Method for Type 2 Diabetes Prediction

Early detection of Type 2 diabetes is necessary for its prevention. The prediction models for detection systems normally employ common factors that may not properly fit all persons having different health conditions. Therefore, this study proposes a method for type 2 diabetes prediction with factors representing personal health conditions. More specifically, this study proposes a novel prediction method named Average Weighted Objective Distance (AWOD) based on the assumption that the individual has diverse health conditions resulting from different individual factors, a requirement for an effective prediction model. AWOD is a modification of Weighted Objective Distance (WOD) by applying information gain to reveal significant and insignificant individual factors having different priorities, which are represented by different weights. For AWOD, the data set is divided into a training set used to determine all relevant thresholds and constant values required for AWOD calculation and the testing set. In particular, AWOD is designed for binary classification problems with a relatively small dataset. To validate the proposed method, two datasets from open sources, Pima Indians Diabetes (Dataset 1) and Mendeley Data for Diabetes (Dataset 2) each containing 392 records, were studied. The prediction performance for both datasets is compared with the machine learning-based prediction methods, including K-Nearest Neighbors, Support Vector Machines, Random Forest, and Deep Learning. The comparison results showed that the proposed method provided 93.22% and 98.95% accuracy for Dataset 1 and Dataset 2, respectively, which are higher than those provided by other machine learning-based methods.

Comparison of Single and Multitask Learning for Predicting Cognitive Decline Based on MRI Data

The Alzheimer’s Disease Assessment Scale-Cognitive subscale (ADAS-Cog) is a neuropsychological tool that has been designed to assess the severity of cognitive symptoms of dementia. Personalized prediction of the changes in ADAS-Cog scores could help in timing therapeutic interventions in dementia and at-risk populations. In the present work, we compared single and multitask learning approaches to predict the changes in ADAS-Cog scores based on T1-weighted anatomical magnetic resonance imaging (MRI). In contrast to most machine learning-based prediction methods ADAS-Cog changes, we stratified the subjects based on their baseline diagnoses and evaluated the prediction performances in each group. Our experiments indicated a positive relationship between the predicted and observed ADAS-Cog score changes in each diagnostic group, suggesting that T1-weighted MRI has a predictive value for evaluating cognitive decline in the entire AD continuum. We further studied whether correction of the differences in the magnetic field strength of MRI would improve the ADAS-Cog score prediction. The partial least square-based domain adaptation slightly improved the prediction performance, but the improvement was marginal. In summary, this study demonstrated that ADAS-Cog change could be, to some extent, predicted based on anatomical MRI. Based on this study, the recommended method for learning the predictive models is a single-task regularized linear regression due to its simplicity and good performance. It appears important to combine the training data across all subject groups for the most effective predictive models.

A machine learning-based method for prediction of macrocyclization patterns of polyketides and non-ribosomal peptides.

Even though genome mining tools have successfully identified large numbers of non-ribosomal peptide synthetase (NRPS) and polyketide synthase (PKS) biosynthetic gene clusters (BGCs) in bacterial genomes, currently no tool can predict the chemical structure of the secondary metabolites biosynthesized by these BGCs. Lack of algorithms for predicting complex macrocyclization patterns of linear PK/NRP biosynthetic intermediates has been the major bottleneck in deciphering the final bioactive chemical structures of PKs/NRPs by genome mining. Using a large dataset of known chemical structures of macrocyclized PKs/NRPs, we have developed a machine learning (ML) algorithm for distinguishing the correct macrocyclization pattern of PKs/NRPs from the library of all theoretically possible cyclization patterns. Benchmarking of this ML classifier on completely independent datasets has revealed ROC-AUC and PR-AUC values of 0.82 and 0.81, respectively. This cyclization prediction algorithm has been used to develop SBSPKSv3, a genome mining tool for completely automated prediction of macrocyclized structures of NRPs/PKs. SBSPKSv3 has been extensively benchmarked on a dataset of over 100 BGCs with known PKs/NRPs products. The macrocyclization prediction pipeline and all the datasets used in this study are freely available at http://www.nii.ac.in/sbspks3.html. Supplementary data are available at Bioinformatics online.

Summary and outlook of 4D track prediction methods

Four-dimensional track prediction is the precise control of the time dimension of three-dimensional space at each stage of the flight. Accurate prediction of the aircraft trajectory is a prerequisite for the automation of air traffic control. This article reviews 4D track prediction technology, that is, particle motion-based prediction method, hybrid estimation-based prediction method and machine learning-based prediction method. At the end, combined with aircraft track data, the method of data mining is used to extract the flight profile and describe the applicable scope of each method. The contents of this paper can be used for reference in the research direction of 4D track prediction technology.

Machine learning in predicting graft failure following kidney transplantation: A systematic review of published predictive models

IntroductionMachine learning has been increasingly used to develop predictive models to diagnose different disease conditions. The heterogeneity of the kidney transplant population makes predicting graft outcomes extremely challenging. Several kidney graft outcome prediction models have been developed using machine learning, and are available in the literature. However, a systematic review of machine learning based prediction methods applied to kidney transplant has not been done to date. The main aim of our study was to perform an in-depth systematic analysis of different machine learning methods used to predict graft outcomes among kidney transplant patients, and assess their usefulness as an aid to decision-making. MethodsA systemic review of machine learning methods used to predict graft outcomes among kidney transplant patients was carried out using a search of the Medline, the Cumulative Index to Nursing and Allied Health Literature, EMBASE, PsycINFO and Cochrane databases. ResultsA total of 295 articles were identified and extracted. Of these, 18 met the inclusion criteria. Most of the studies were published in the United States after 2010. The population size used to develop the models varied from 80 to 92,844, and the number of features in the models ranged from 6 to 71. The most common machine learning methods used were artificial neural networks, decision trees and Bayesian belief networks. Most of the machine learning based predictive models predicted graft failure with high sensitivity and specificity. Only one machine learning based prediction model had modelled time-to-event (survival) information. Seven studies compared the predictive performance of machine learning models with traditional regression methods and the performance of machine learning methods was found to be mixed, when compared with traditional regression methods. ConclusionThere was a wide variation in the size of the study population and the input variables used. However, the prediction accuracy provided mixed results when machine learning and traditional predictive methods are compared. Based on reported gains in predictive performance, machine learning has the potential to improve kidney transplant outcome prediction and aid medical decision making

Analysing machine learning techniques for predicting the hole-filling in pin-in-paste technology

Pin-in-paste technology is an advanced and constantly developing assembly method, where both the surface mounted and through-hole components are joined commonly with the same reflow soldering step. In the paper, detailed evaluation of machine learning based prediction methods was performed, including artificial neural networks (ANN), adaptive neuro fuzzy inference systems (AFNIS) and gradient boosted decision trees to optimize the process parameters of pin-in-paste. The methods were presented for predicting the hole-filling of solder paste during stencil printing and to enable an evaluation of the aforementioned methods for the specific problem. Experiments were performed to obtain the required input data (hole-filling against the process parameters) for the training of the prediction tools. A testboard with plated through-holes of different diameters (0.8, 1, 1.1, 1.4 mm) was applied. Type 4 lead-free solder paste (particle size 20–38 µm) was deposited with stencil printing into the through-holes with different printing speeds (between 20 mm/s and 70 mm/s). The extent of hole-filling was investigated with X-ray analysis. The optimal structure for the prediction method was determined for every approach by varying the size and configuration iteration-wise. Optimal number of hidden neurons was 34 for the full data set and 18 for the smaller – incomplete- test cases. The optimal structure for the ANFIS consists of 8 and 6 membership functions respectively. Triangular and Gaussian membership function types and 7 different training methods were assessed. The ANN, which was trained with Bayesien Regularization (prediction error <15%) was found to be the recommended one for the PIP technology. A sensitivity analysis was carried out serving as a basis for managerial implications, which were also described in the paper. The obtained results aid in improving the quality and reliability of products assembled with pin-in-paste technology, also enable the more precise control in the wake of Industry 4.0 recommendations.

Conservation region finding for influenza A viruses by machine learning methods of N-linked glycosylation sites and B-cell epitopes

Influenza type A, a serious infectious disease of the human respiratory tract, poses an enormous threat to human health worldwide. It leads to high mortality rates in poultry, pigs, and humans. The primary target identity regions for the human immune system are hemagglutinin (HA) and neuraminidase (NA), two surface proteins of the influenza A virus. Research and development of vaccines is highly complex because the influenza A virus evolves rapidly. This study focused on three genetic features of viral surface proteins: ribonucleic acid (RNA) sequence conservation, linear B-cell epitopes, and N-linked glycosylation. On the basis of these three properties, we analyzed 12,832 HA and 9487 NA protein sequences, which we retrieved from the influenza virus database. We classified the viral surface protein sequences into the 18 HA and 11 NA subtypes that have been identified thus far. Using available analytic tools, we searched for the representative strain of each virus subtype. Furthermore, using machine learning methods, we looked for conservation regions with sequences showing linear B-cell epitopes and N-linked glycosylation. Compared to the prediction of the Immune Epitope Database (IEDB) antibody neutralization response (i.e., screening of antibody sequence regions), in this study, the virus sequence coverage was large and accurate and contained N-linked glycosylation sites. The results of this study proved that we can use the machine learning-based prediction method to solve the problem of vaccine invalidation that occurred during the rapid evolution of the influenza A virus and also as a prevaccine assessment. In addition, the screening fragments can be used as a universal influenza vaccine design reference in the future.

M6AMRFS: Robust Prediction of N6-Methyladenosine Sites With Sequence-Based Features in Multiple Species.

As one of the well-studied RNA methylation modifications, N6-methyladenosine (m6A) plays important roles in various biological progresses, such as RNA splicing and degradation, etc. Identification of m6A sites is fundamentally important for better understanding of their functional mechanisms. Recently, machine learning based prediction methods have emerged as an effective approach for fast and accurate identification of m6A sites. In this paper, we proposed “M6AMRFS”, a new machine learning based predictor for the identification of m6A sites. In this predictor, we exploited a new feature representation algorithm to encode RNA sequences with two feature descriptors (dinucleotide binary encoding and Local position-specific dinucleotide frequency), and used the F-score algorithm combined with SFS (Sequential Forward Search) to enhance the feature representation ability. To predict m6A sites, we employed the eXtreme Gradient Boosting (XGBoost) algorithm to build a predictive model. Benchmarking results showed that the proposed predictor is competitive with the state-of-the art predictors. Importantly, robust predictions for multiple species by our predictor demonstrate that our predictive models have strong generalization ability. To the best of our knowledge, M6AMRFS is the first tool that can be used for the identification of m6A sites in multiple species. To facilitate the use of our predictor, we have established a user-friendly webserver with the implementation of M6AMRFS, which is currently available in http://server.malab.cn/M6AMRFS/. We anticipate that it will be a useful tool for the relevant research of m6A sites.

The role of pertinently diversified and balanced training as well as testing data sets in achieving the true performance of classifiers in predicting the antifreeze proteins

Antifreeze proteins (AFPs) are those proteins, which inhibit the ice nucleation process and thereby enabling certain organisms to survive under sub-zero temperature habitats. AFPs are supposed to be evolved from different types of protein families to perform the unique function of antifreeze activity and turn out to be the classical example of convergent evolution. The common sequence similarity search methods have failed to predict putative AFPs due to poor sequence and structural similarity that exists among the different sub-types of AFP. The machine learning techniques are the viable alternative approaches to predict putative AFPs. In this paper, we have discussed about the criteria (like apposite feature selection, balanced data sets and complete learning) that are needed to be taken into account for successful application of machine learning methods and implemented these criteria by using a clustering procedure in order to achieve the true performance of the learning algorithms. Diversified and representative training and testing data sets are very crucial for perfect learning as well as true testing of machine learning based prediction methods for two reasons: first is that a training dataset that lacks definable subset of input patterns makes prediction of patterns belonging to this subset either difficult or unfeasible (thus resulting in incomplete learning) and secondly a testing data set that lacks definable subset of input patterns does not tell about whether this subset of patterns can be correctly predicted by the classifier or not (thus resulting in incomplete testing). Moreover, balanced training and testing data sets are equally important for achieving the true (robust) performance of classifiers because a well-balanced training set eliminates bias of the classifier toward particular class/sub-class due to over-representation or under-representation of input patterns belonging to those classes/sub-classes. We have used K-means clustering algorithm for creating the diversified and balanced training as well as testing data sets, to overcome the shortcoming of random splitting, which cannot guarantee representative training and testing sets. The current clustering based optimal splitting criteria proved to be better than random splitting for creating training and testing set in terms of superior generalization and robust evaluation.

Machine Learning Based Power Grid Outage Prediction in Response to Extreme Events

A machine learning based prediction method is proposed in this paper to determine the potential outage of power grid components in response to an imminent hurricane. The decision boundary, which partitions the components’ states into two sets of damaged and operational, is obtained via logistic regression by using a second-order function and proper parameter fitting. Two metrics are examined to validate the performance of the obtained decision boundary in efficiently predicting component outages.

Predicting of Job Failure in Compute Cloud Based on Online Extreme Learning Machine: A Comparative Study

Early prediction of job failures and specific disposal steps in advance could significantly improve the efficiency of resource utilization in large-scale data center. The existing machine learning-based prediction methods commonly adopt offline working pattern, which cannot be used for online prediction in practical operations, in which data arrive sequentially. To solve this problem, a new method based on online sequential extreme learning machine (OS-ELM) is proposed in this paper to predict online job termination status. With this method, real-time data are collected according to the sequence of job arriving, the job status could be predicted and the operation model is thus updated based on these data. The method with online incremental learning strategy has fast learning speed and good generalization. Comparative study using Google trace data shows that prediction accuracy of the proposed method is 93% with updating model in 0.01 s. Compared with some state-of-the-art methods, such, as support vector machine (SVM), ELM, and OS-SVM, the method developed in this paper has many advantages, such as less time-consuming in establishing and updating the model, higher prediction accuracy and precision, and better false negative performance.

Development of Antimicrobial Peptide Prediction Tool for Aquaculture Industries.

Microbial diseases in fish, plant, animal and human are rising constantly; thus, discovery of their antidote is imperative. The use of antibiotic in aquaculture further compounds the problem by development of resistance and consequent consumer health risk by bio-magnification. Antimicrobial peptides (AMPs) have been highly promising as natural alternative to chemical antibiotics. Though AMPs are molecules of innate immune defense of all advance eukaryotic organisms, fish being heavily dependent on their innate immune defense has been a good source of AMPs with much wider applicability. Machine learning-based prediction method using wet laboratory-validated fish AMP can accelerate the AMP discovery using available fish genomic and proteomic data. Earlier AMP prediction servers are based on multi-phyla/species data, and we report here the world's first AMP prediction server in fishes. It is freely accessible at http://webapp.cabgrid.res.in/fishamp/ . A total of 151 AMPs related to fish collected from various databases and published literature were taken for this study. For model development and prediction, N-terminus residues, C-terminus residues and full sequences were considered. Best models were with kernels polynomial-2, linear and radial basis function with accuracy of 97, 99 and 97%, respectively. We found that performance of support vector machine-based models is superior to artificial neural network. This in silico approach can drastically reduce the time and cost of AMP discovery. This accelerated discovery of lead AMP molecules having potential wider applications in diverse area like fish and human health as substitute of antibiotics, immunomodulator, antitumor, vaccine adjuvant and inactivator, and also for packaged food can be of much importance for industries.

Maximizing lipocalin prediction through balanced and diversified training set and decision fusion

Lipocalins are short in sequence length and perform several important biological functions. These proteins are having less than 20% sequence similarity among paralogs. Experimentally identifying them is an expensive and time consuming process. The computational methods based on the sequence similarity for allocating putative members to this family are also far elusive due to the low sequence similarity existing among the members of this family. Consequently, the machine learning methods become a viable alternative for their prediction by using the underlying sequence/structurally derived features as the input. Ideally, any machine learning based prediction method must be trained with all possible variations in the input feature vector (all the sub-class input patterns) to achieve perfect learning. A near perfect learning can be achieved by training the model with diverse types of input instances belonging to the different regions of the entire input space. Furthermore, the prediction performance can be improved through balancing the training set as the imbalanced data sets will tend to produce the prediction bias towards majority class and its sub-classes. This paper is aimed to achieve (i) the high generalization ability without any classification bias through the diversified and balanced training sets as well as (ii) enhanced the prediction accuracy by combining the results of individual classifiers with an appropriate fusion scheme. Instead of creating the training set randomly, we have first used the unsupervised Kmeans clustering algorithm to create diversified clusters of input patterns and created the diversified and balanced training set by selecting an equal number of patterns from each of these clusters. Finally, probability based classifier fusion scheme was applied on boosted random forest algorithm (which produced greater sensitivity) and K nearest neighbour algorithm (which produced greater specificity) to achieve the enhanced predictive performance than that of individual base classifiers. The performance of the learned models trained on Kmeans preprocessed training set is far better than the randomly generated training sets. The proposed method achieved a sensitivity of 90.6%, specificity of 91.4% and accuracy of 91.0% on the first test set and sensitivity of 92.9%, specificity of 96.2% and accuracy of 94.7% on the second blind test set. These results have established that diversifying training set improves the performance of predictive models through superior generalization ability and balancing the training set improves prediction accuracy. For smaller data sets, unsupervised Kmeans based sampling can be an effective technique to increase generalization than that of the usual random splitting method.

Selecting the embryo with the highest implantation potential using developmental and morphometric scoring.

Embryo selection has been based on developmental and morphological characteristics. However, the presence of an important intra-and inter-observer variability in the microscopic evaluation of standard scoring system (SSS) has been reported. A golden standard for selection of embryos on day 3 is currently lacking. New technology using multilevel images combined with a computer-assisted scoring system (CASS) has the potential to overcome most of these disadvantages associated with the SSS. The aim of this study was to construct a multivariable prediction model, with data mining approaches, and compare the predictive performance of models in SSS and CASS. A total of 871 single embryo transfers between 2008 and 2013 were included. Embryos were evaluated with two scoring systems: SSS and CASS. Prediction models were developed using multivariable logistic regression (LR) and multivariate adaptive regression splines (MARSplines). The prediction models were externally validated with a test set of 109 single transfers between January and June 2014. Results showed that prediction of implantation was superior using CASS when compared with SSS. With CASS, two final prediction model were obtained using LR and MARSplines, which showed moderate discriminative capacity (c-statistic 0.64 and 0.69 respectively) on validation data. The findings of this study show that combination of computer-assisted scoring system and machine learning based prediction method is a promising approach for in the selection of embryo with the highest implantation potential.

Prediction of length-of-day using extreme learning machine

Traditional artificial neural networks (ANN) such as back-propagation neural networks (BPNN) provide good predictions of length-of-day (LOD). However, the determination of network topology is difficult and time consuming. Therefore, we propose a new type of neural network, extreme learning machine (ELM), to improve the efficiency of LOD predictions. Earth orientation parameters (EOP) C04 time-series provides daily values from International Earth Rotation and Reference Systems Service (IERS), which serves as our database. First, the known predictable effects that can be described by functional models—such as the effects of solid earth, ocean tides, or seasonal atmospheric variations—are removed a priori from the C04 time-series. Only the residuals after the subtraction of a priori model from the observed LOD data (i.e., the irregular and quasi-periodic variations) are employed for training and predictions. The predicted LOD is the sum of a prior extrapolation model and the ELM predictions of the residuals. Different input patterns are discussed and compared to optimize the network solution. The prediction results are analyzed and compared with those obtained by other machine learning-based prediction methods, including BPNN, generalization regression neural networks (GRNN), and adaptive network-based fuzzy inference systems (ANFIS). It is shown that while achieving similar prediction accuracy, the developed method uses much less training time than other methods. Furthermore, to conduct a direct comparison with the existing prediction techniques, the mean-absolute-error (MAE) from the proposed method is compared with that from the EOP prediction comparison campaign (EOP PCC). The results indicate that the accuracy of the proposed method is comparable with that of the former techniques. The implementation of the proposed method is simple.

Prediction models for long-term Internet prefix availability

The Border Gateway Protocol (BGP) maintains inter-domain routing information by announcing and withdrawing IP prefixes. These routing updates can cause prefixes to be unreachable for periods of time, reducing prefix availability observed from different vantage points on the Internet. The observed prefix availability values may not meet the standards promised by Service Level Agreements (SLAs).In this paper, we develop a framework for predicting long-term availability of prefixes, given short-duration prefix information from publicly available BGP routing databases like RouteViews, and prediction models constructed from information about other Internet prefixes. We compare three prediction models and find that machine learning-based prediction methods outperform a baseline model that predicts the future availability of a prefix to be the same as its past availability. Our results show that mean time to failure is the most important attribute for predicting availability. We also quantify how prefix availability is related to prefix length and update frequency. Our prediction models achieve 82% accuracy and 0.7 ranking quality when predicting for a future duration equal to the learning duration. We can also predict for a longer future duration, with graceful performance reduction. Our models allow ISPs to adjust BGP routing policies if predicted availability is low, and are generally useful for cloud computing systems, content distribution networks, P2P, and VoIP applications.