Correlation-based Approach Research Articles

An Effective Recommendation System to Forecast the Best Educational Program Using Machine Learning Classification Algorithms

After passing the 10th class, every student is eager to know which educational program will be the best for their higher education to match their career goal. Sometimes, they are very much confused to decide the best path for their higher education, and they need help to determine the best suitable academic program to develop their careers and achieve their goal. So, we introduce an effective recommendation system to forecast each student's best educational program for their career development. This proposed research is accomplished by utilizing machine learning (ML) approaches to forecast every student's best academic path based on their past academic performances and recommend them the best suitable academic program for their higher studies. Class 10th standard passing student data are supplied to this automated system, and a correlation-based feature selection approach is applied to extract the relevant features for each academic program. This study utilizes multiple ML algorithms to provide the best results and forecast each student's academic performance and select the best model based on their performance for each educational program. Hence, the best-selected model and related features are involved in the recommendation process to provide the best suitable academic path for achieving every student's career goals.

A General Framework to Compare Announcement Accuracy: Static vs. LES-Based Announcement

Service providers often share delay information, in the form of delay announcements, with their customers. In practice, simple delay announcements, such as average waiting times or a weighted average of previously delayed customers, are often used. Our goal in this paper is to gain insight into when such announcements perform well. Specifically, we compare the accuracies of two announcements: (i) a static announcement that does not exploit real-time information about the state of the system and (ii) a dynamic announcement, specifically the last-to-enter-service (LES) announcement, which equals the delay of the last customer to have entered service at the time of the announcement. We propose a novel correlation-based approach that is theoretically appealing because it allows for a comparison of the accuracies of announcements across different queueing models, including multiclass models with a priority service discipline. It is also practically useful because estimating correlations is much easier than fitting an entire queueing model. Using a combination of queueing-theoretic analysis, real-life data analysis, and simulation, we analyze the performance of static and dynamic announcements and derive an appropriate weighted average of the two which we demonstrate has a superior performance using both simulation and data from a call center. This paper was accepted by Vishal Gaur, operations management.

Physicochemical Insights into the Role of Drug Functionality in Fibrillation Inhibition of Bovine Serum Albumin.

To revert amyloid fibrils to their native state is a challenge in finding a solution to prevent neurodegenerative diseases. We have adopted a structure-property-energetics correlation-based approach with drugs (5-fluorouracil and hydroxyurea) having multiple hydrogen-bond donors and acceptors as inhibitors targeting different stages of bovine serum albumin fibrillation. We present here a quantitative comprehensive biophysical approach for identifying functionalities in molecules, which offers this feature in terms of polarity and hydrogen bonding. Our objective of identifying the functionality on a drug molecule that establishes effective intermolecular hydrogen bonding with β-strands of protein fibrils was achieved by combined calorimetric, spectroscopic, volumetric, and microscopic correlations. Relationships have been established among thermodynamic signatures, F19-NMR chemical shifts, hydrodynamic diameters, and thermal expansion coefficients to demonstrate that the open-chain molecule is a better inhibitor of fibrillation, but its efficiency decreases with the formation of amorphous aggregates, as compared to the molecule having a uracil ring. The results have provided quantitative insights into the role of polarity and hydrogen bonding in prevention of the fibrillation process. The approach adopted here highlights the physical chemistry underlying such biologically important processes and hence has significance in deriving guidelines for rational drug design.

Discovery of novel quaternary bulk metallic glasses using a developed correlation-based neural network approach

The immense space of composition-processing parameters leads to numerous trial-and-error experimental works for engineering of novel bulk metallic glasses (BMGs). To tackle this challenging problem, it is required to consider specific guidelines which are able to restrict the productive alloying compositions. In this work, a correlation-based neural network (CBNN) approach was developed, based on a dataset of 7950 alloying compositions, to design potential new MGs through prediction of casting ability, reduced glass transition (Trg) and critical thickness (Dmax). This approach involves individual and mutual characteristics of contributory factors to improve the prediction accuracy. To validate our model, we selected the ZrCoAl alloying system and investigated the microalloying effects on the glass forming possibility (GFP). According to the results, the microalloying process effects strongly depended on the inherent features of added element. Moreover, the CBNN model predicted a quaternary system, i.e. ZrCoAlNi, in which the high GFP area was extended through a wide range of chemical compositions. Finally, it is concluded that the established framework offers a roadmap for potential applications in the development of new quaternary MG alloys.

Transcriptome network of the papillary thyroid carcinoma radiation marker CLIP2

BackgroundWe present a functional gene association network of the CLIP2 gene, generated by de-novo reconstruction from transcriptomic microarray data. CLIP2 was previously identified as a potential marker for radiation induced papillary thyroid carcinoma (PTC) of young patients in the aftermath of the Chernobyl reactor accident. Considering the rising thyroid cancer incidence rates in western societies, potentially related to medical radiation exposure, the functional characterization of CLIP2 is of relevance and contributes to the knowledge about radiation-induced thyroid malignancies.MethodsWe generated a transcriptomic mRNA expression data set from a CLIP2-perturbed thyroid cancer cell line (TPC-1) with induced CLIP2 mRNA overexpression and siRNA knockdown, respectively, followed by gene-association network reconstruction using the partial correlation-based approach GeneNet. Furthermore, we investigated different approaches for prioritizing differentially expressed genes for network reconstruction and compared the resulting networks with existing functional interaction networks from the Reactome, Biogrid and STRING databases. The derived CLIP2 interaction partners were validated on transcript and protein level.ResultsThe best reconstructed network with regard to selection parameters contained a set of 20 genes in the 1st neighborhood of CLIP2 and suggests involvement of CLIP2 in the biological processes DNA repair/maintenance, chromosomal instability, promotion of proliferation and metastasis. Peptidylprolyl Isomerase Like 3 (PPIL3), previously identified as a potential direct interaction partner of CLIP2, was confirmed in this study by co-expression at the transcript and protein level.ConclusionIn our study we present an optimized preselection approach for genes subjected to gene-association network reconstruction, which was applied to CLIP2 perturbation transcriptome data of a thyroid cancer cell culture model. Our data support the potential carcinogenic role of CLIP2 overexpression in radiation-induced PTC and further suggest potential interaction partners of the gene.

Clustifyr: an R package for automated single-cell RNA sequencing cluster classification

Assignment of cell types from single-cell RNA sequencing (scRNA-seq) data remains a time-consuming and error-prone process. Current packages for identity assignment use limited types of reference data and often have rigid data structure requirements. We developed the clustifyr R package to leverage several external data types, including gene expression profiles to assign likely cell types using data from scRNA-seq, bulk RNA-seq, microarray expression data, or signature gene lists. We benchmark various parameters of a correlation-based approach and implement gene list enrichment methods. clustifyr is a lightweight and effective cell-type assignment tool developed for compatibility with various scRNA-seq analysis workflows. clustifyr is publicly available at https://github.com/rnabioco/clustifyr.

Post-Silicon Heat-Source Identification and Machine-Learning-Based Thermal Modeling Using Infrared Thermal Imaging

In this article, we present a novel post-silicon approach to locating the dominant heat sources on commercial multicore processors using heatmaps measured via an infrared (IR) thermal imaging setup. To locate the heat sources, 2-D spatial Laplacian transformation is performed on the heatmaps followed by K-means clustering to find the dominant power/heat-source clusters. This is an exclusively post-silicon approach that does not require any knowledge of the underlying design of the commercial chips other than the information that is publicly available. Since the identified clusters are the thermally vulnerable areas on the die, we then propose a machine-learning-based framework to deriving a thermal model capable of estimating their temperatures during online use. Our approach involves collecting transient temperature data of the aforementioned heat sources and synchronized high-level performance metrics from the chip, and training a long-short-term-memory (LSTM) neural network (NN) that uses the performance metrics as inputs to estimate the temperatures of the identified heat sources in real time. Since the model is meant for real-time use, we explore methods of reducing the performance overhead and inference time of the model. This includes a novel power correlation-based approach to identifying the thermally irrelevant performance metrics and eliminating them in order to reduce the input dimensionality of the model, and an analysis on network sizing to determine the ideal NN configuration for the problem at hand. The model is trained and tested exclusively using measured thermal data from commercial multicore processors. The experimental results from two Intel multicore processors (i5-3337U and i7-8650U) show that the proposed approach achieves very high accuracy (root-mean-square error: 0.55 °C-0.93 °C) in estimating the temperatures of all the identified heat sources on the chip.

A correlation-based model order reduction approach for a diesel engine NOx and brake mean effective pressure dynamic model using machine learning

A correlation-based model order reduction algorithm is developed using support vector machine to model [Formula: see text] emission and break mean effective pressure of a medium-duty diesel engine. The support vector machine–based model order reduction algorithm is used to reduce the number of features of a 34-feature full-order model by evaluating the regression performance of the support vector machine–based model. Then, the support vector machine–based model order reduction algorithm is used to reduce the number of features of the full-order model. Two models for [Formula: see text] emission and break mean effective pressure are developed via model order reduction, one complex model with high accuracy, called high-order model, and the other with an acceptable accuracy and a simple structure, called low-order model. The high-order model has 29 features for [Formula: see text] and 20 features for break mean effective pressure, while the low-order model has nine features for [Formula: see text] and six features for break mean effective pressure. Then, the steady-state low-order model and high-order model are implemented in a nonlinear control-oriented model. To verify the accuracy of nonlinear control-oriented model, a fast response electrochemical [Formula: see text] sensor is used to experimentally study the engine transient [Formula: see text] emissions. The high-order model and low-order model support vector machine models of [Formula: see text] and break mean effective pressure are compared to a conventional artificial neural network with one hidden layer. The results illustrate that the developed support vector machine model has shorter training times (5–14 times faster) and higher accuracy especially for test data compared to the artificial neural network model. A control-oriented model is then developed to predict the dynamic behavior of the system. Finally, the performance of the low-order model and high-order model is evaluated for different rising and falling input transients at four different engine speeds. The transient test results validate the high accuracy of the high-order model and the acceptable accuracy of low-order model for both [Formula: see text] and break mean effective pressure. The high-order model is proposed as an accurate virtual plant while the low-order model is suitable for model-based controller design.

Clustifyr: an R package for automated single-cell RNA sequencing cluster classification

Assignment of cell types from single-cell RNA sequencing (scRNA-seq) data remains a time-consuming and error-prone process. Current packages for identity assignment use limited types of reference data and often have rigid data structure requirements. We developed the clustifyr R package to leverage several external data types, including gene expression profiles to assign likely cell types using data from scRNA-seq, bulk RNA-seq, microarray expression data, or signature gene lists. We benchmark various parameters of a correlation-based approach and implement gene list enrichment methods. clustifyr is a lightweight and effective cell-type assignment tool developed for compatibility with various scRNA-seq analysis workflows. clustifyr is publicly available at https://github.com/rnabioco/clustifyr

Determination of the Forming-Limit Diagram from Deformations within Necking Instability: A Digital Image Correlation-Based Approach

It is now possible using digital-image correlation techniques to precisely measure deformation within a developing necking instability, during forming-limit experiments. However, the current standards for measuring limit strains rely only on data outside of the instability. We propose exactly the opposite, to use just those deformations from the material where the instability will develop. Marciniak and Kuczynski experiments were performed on a drawing-quality steel and the entire deformation history recorded with a high-resolution photographic camera. The strain fields from these image were analyzed with the digital-image correlation program NCORR, concentrating on where the necking instability would form. The Merklein et al. (CIRP Ann Manuf Technol 59:295-298, 2010) and Hotz et al. (Key Eng Mater 549:397-404, 2013) temporal analyses were modified through an original smoothing technique to uniquely identify, through a correspondence of results, when the deformation acceleration rate begins to rapidly increase within the developing instability. This defines a limit strain. These results were compared to the standard Bragard-type determination specified in the norm International Standard ISO 12004-2:2008 (Metallic materials—sheet and strip: determination of forming-limit curves. Part 2—determination of forming-limit curves in the laboratory, International Organization for Standardization, Geneva, 2008). We found a close agreement in balanced-biaxial tension between our proposed technique and the standard Bragard-type analysis. However, in plane-strain and uniaxial deformation the standard analysis appeared to be excessively conservative, by as much as 40% for our steel.

Dual-plane stereo-astigmatism: a novel method to determine the full velocity gradient tensor in planar domain

A novel approach, which utilizes astigmatism-based depth codification and discrete dual-plane illumination, is developed to provide information on the full velocity-gradient tensor in pair of planar domains by means of stereoscopic particle image velocimetry (stereo-PIV). The technique is accordingly referred to as dual-plane stereo-astigmatism (DPSA). In contrast to conventional stereo-PIV, DPSA provides the determination of the desired out-of-plane gradient. The principle of the DPSA approach relies on the joint recording of two, consecutive, planar measurement domains and the subsequent allocation of particles based on their particle image shapes. For the identification of particles, a correlation-based particle identification approach (CPI), which addresses non-overlapping particles, is introduced. With regard to dense particle fields, a method for the iterative particle reconstruction (IPR) is adapted for DPSA. For displacement analysis, a modified PIV evaluation strategy is introduced, which utilizes derived information of particle locations. The DPSA approach is tested experimentally and synthetically by applying it to spray-induced flow measurement and synthetic images generated from DNS data of a turbulent boundary flow. Separate planar velocity fields are obtained by means of PIV and PTV evaluation. A performance analysis is carried out to assess the influence of noise, particle density and particle image size on the procedure of particle identification and allocation. The CPI technique provides adequate results for low to medium particle densities and further features a high robustness regarding particle identification with respect to background noise, optical aberrations and non-uniform particle images. The adapted IPR method, on the other hand, shows viable results for particle densities of up to 0.1 ppp.

Fractal structure in the S&P500: A correlation-based threshold network approach

• A correlation-based threshold network to examine the network fractality is proposed. • A self-similarity aspects of the S&P500 network is revealed. • A strong effective repulsion phenomenon is detected. • Different growth patterns are observed for various cases of S&P500 network. • Proposed measures improve the prediction performance for long-term future. This research aims to analyze the S&P500 network, one of the representatives of the global financial market, based on its network fractality. The research is conducted in the following steps. At first, we propose the concept of a correlation-based threshold network based on minimum spanning tree. Secondly, we investigate the fractal dimension of threshold networks and propose suitable fractal dimension measures. Lastly, we analyze the S&P500 network based on the proposed measures and utilize them in the market prediction. Based on the results, we discover the self-similarity characteristic of the S&P500 network, where a strong effective repulsion phenomenon is detected. Furthermore, we observe the different growth patterns of S&P500 network for different combinations of fractal conditions defined by the proposed measures. Then, we utilize the measures in the prediction of the cumulative log-return of S&P500 index via a simple artificial neural network and detect the improvement of prediction performance in the long-term development of the market.

The Use of Ensemble Models for Multiple Class and Binary Class Classification for Improving Intrusion Detection Systems.

The pursuit to spot abnormal behaviors in and out of a network system is what led to a system known as intrusion detection systems for soft computing besides many researchers have applied machine learning around this area. Obviously, a single classifier alone in the classifications seems impossible to control network intruders. This limitation is what led us to perform dimensionality reduction by means of correlation-based feature selection approach (CFS approach) in addition to a refined ensemble model. The paper aims to improve the Intrusion Detection System (IDS) by proposing a CFS + Ensemble Classifiers (Bagging and Adaboost) which has high accuracy, high packet detection rate, and low false alarm rate. Machine Learning Ensemble Models with base classifiers (J48, Random Forest, and Reptree) were built. Binary classification, as well as Multiclass classification for KDD99 and NSLKDD datasets, was done while all the attacks were named as an anomaly and normal traffic. Class labels consisted of five major attacks, namely Denial of Service (DoS), Probe, User-to-Root (U2R), Root to Local attacks (R2L), and Normal class attacks. Results from the experiment showed that our proposed model produces 0 false alarm rate (FAR) and 99.90% detection rate (DR) for the KDD99 dataset, and 0.5% FAR and 98.60% DR for NSLKDD dataset when working with 6 and 13 selected features.

At What Cost Can Renewable Hydrogen Offset Fossil Fuel Use in Ireland’s Gas Network?

The results of a techno-economic model of distributed wind-hydrogen systems (WHS) located at each existing wind farm on the island of Ireland are presented in this paper. Hydrogen is produced by water electrolysis from wind energy and backed up by grid electricity, compressed before temporarily stored, then transported to the nearest injection location on the natural gas network. The model employs a novel correlation-based approach to select an optimum electrolyser capacity that generates a minimum levelised cost of hydrogen production (LCOH) for each WHS. Three scenarios of electrolyser operation are studied: (1) curtailed wind, (2) available wind, and (3) full capacity operations. Additionally, two sets of input parameters are used: (1) current and (2) future techno-economic parameters. Additionally, two electricity prices are considered: (1) low and (2) high prices. A closest facility algorithm in a geographic information system (GIS) package identifies the shortest routes from each WHS to its nearest injection point. By using current parameters, results show that small wind farms are not suitable to run electrolysers under available wind operation. They must be run at full capacity to achieve sufficiently low LCOH. At full capacity, the future average LCOH is 6–8 €/kg with total hydrogen production capacity of 49 kilotonnes per year, or equivalent to nearly 3% of Irish natural gas consumption. This potential will increase significantly due to the projected expansion of installed wind capacity in Ireland from 5 GW in 2020 to 10 GW in 2030.

Clustifyr: an R package for automated single-cell RNA sequencing cluster classification.

Assignment of cell types from single-cell RNA sequencing (scRNA-seq) data remains a time-consuming and error-prone process. Current packages for identity assignment use limited types of reference data and often have rigid data structure requirements. We developed the clustifyr R package to leverage several external data types, including gene expression profiles to assign likely cell types using data from scRNA-seq, bulk RNA-seq, microarray expression data, or signature gene lists. We benchmark various parameters of a correlation-based approach and implement gene list enrichment methods. clustifyr is a lightweight and effective cell-type assignment tool developed for compatibility with various scRNA-seq analysis workflows. clustifyr is publicly available at https://github.com/rnabioco/clustifyr.

Software defect prediction based on correlation weighted class association rule mining

Software defect prediction based on supervised learning plays a crucial role in guiding software testing for resource allocation. In particular, it is worth noticing that using associative classification with high accuracy and comprehensibility can predict defects. But owing to the imbalance data distribution inherent, it is easy to generate a large number of non-defective class association rules, but the defective class association rules are easily ignored. Furthermore, classical associative classification algorithms mainly measure the interestingness of rules by the occurrence frequency, such as support and confidence, without considering the importance of features, resulting in combinations of the insignificant frequent itemset. This promotes the generation of weighted associative classification. However, the feature weighting based on domain knowledge is subjective and unsuitable for a high dimensional dataset. Hence, we present a novel software defect prediction model based on correlation weighted class association rule mining (CWCAR). It leverages a multi-weighted supports-based framework rather than the traditional support-confidence approach to handle class imbalance and utilizes the correlation-based heuristic approach to assign feature weight. Besides, we also optimize the ranking, pruning and prediction stages based on weighted support. Results show that CWCAR is significantly superior to state-of-the-art classifiers in terms of Balance, MCC, and Gmean.

A kernel principal component analysis-based approach for determining the spatial warning domain of dam safety

It is important to determine the warning value of structural behavior for evaluating the service safety, identifying the potential risk and preventing the failure of dam engineering. However, more attention was paid to determining the security warning value of a single observation point on deformation, seepage or stress. And the correlation between the adjacent points or among all points in one dam section is usually lack of consideration. In this paper, the monitoring data of multi-points are taken to determine the spatial warning domain of dam safety. The warning mode of abnormal structural behavior is changed from the single point into the linked multi-points. First, the kernel principal component analysis method is adopted to identify the inherent characteristics among observation points in a dam section. Second, considering the correlation among observation points, the implementation process is proposed to determine the spatial warning domain of dam safety. Finally, an actual concrete gravity dam is taken as an example. The proposed approach is used to determine the spatial warning domains of deformation and seepage. The results, which are obtained by the proposed approach, the traditional method and the qualitative analysis for monitoring data, are compared. It is indicated that the proposed multi-points correlation-based approach is feasible and superior to determine the spatial warning domain of dam safety.

Correlation-Based Cooperative Jamming to Enhance Secrecy With Receiver-Side Correlation

This paper investigates cooperative security for slow-fading channels, where the source sends confidential messages to the destination with the assistance of a cooperative jammer coexisting with multiple passive eavesdroppers. Assuming that accurate legitimate channel information and statistical illegitimate channel information are available with an independent transmitter side and a highly correlated receiver side, we propose a correlation-based cooperative jamming approach to reduce the secrecy loss due to receiver-side correlation. In particular, the correlation is considered to be a resource for acquiring more knowledge about illegitimate channels, based on which the statistical distribution of illegitimate channels is described more precisely. Then, the power of artificial noise in the null space of the legitimate channel from the jammer to the destination is placed more reasonably rather than as a simple uniform distribution. Additionally, a correlation-based beamformer is designed for transmitting the information-bearing signal. Finally, the achievable secrecy rate under a secrecy outage constraint is computed. The numerical results confirm that the proposed scheme achieves a performance improvement in terms of secrecy rate under a secrecy outage constraint when the receiver side is highly correlated.

The correlation-based redundancy multiple-filter approach for gene selection

The correlation-based redundancy multiple-filter approach for gene selection

StomachNet: Optimal Deep Learning Features Fusion for Stomach Abnormalities Classification

A fully automated design is proposed in this work employing optimal deep learning features for classifying gastrointestinal infections. Here, three prominent infections- ulcer, bleeding, polyp and a healthy class are considered as class labels. In the initial stage, the contrast is improved by fusing bi-directional histogram equalization with top-hat filtering output. The resultant fusion images are then passed to ResNet101 pre-trained model and trained once again using deep transfer learning. However, there are challenges involved in extracting deep learning features including impertinent information and redundancy. To mitigate this problem, we took advantage of two metaheuristic algorithms- Enhanced Crow Search and Differential Evolution. These algorithms are implemented in parallel to obtain optimal feature vectors. Following this, a maximum correlation-based fusion approach is applied to fuse optimal vectors from the previous step to obtain an enhanced vector. This final vector is given as input to Extreme Learning Machine (ELM) classifier for final classification. The proposed method is evaluated on a combined database. It accomplished an accuracy of 99.46%, which shows significant improvement over preceding techniques and other neural network architectures.