New approach for near-infrared wavelength selection using a combination of MIC and firefly evolution.

Full-length spectral data analysis has a big problem that the variables are highly in collinearity and correlation. Spectral wavelength selection is a continuing hot topic in quantitative or qualitative analysis. In this paper, we propose a new approach for near-infrared (NIR) wavelength selection. The novel strategy mainly refers to the modification of maximum information coefficient (MIC) method and an improvement of firefly evolutionary algorithm. We introduce the orthogonal decomposition to modify the MIC method, so as to search the informative signals conceived in projection vectors. We also raise the common firefly algorithm (FA) as in the discretized mode, and design a novel adaptive mapping function to improve its intelligent computing effect. In experiment, the modified MIC (MICm) method and the adaptive discrete FA algorithm (DFAadp) are joint together for combined optimization of the NIR calibration model. The proposed combined modeling strategy is applied for quantitative analysis of the fishmeal samples, in the concern to select their informative variables/wavelengths. Experimental results indicate that the combination of MICm and DFAadp perform better than traditional MIC method and common DFA. We conclude that the proposed combined optimization strategy is beneficial for wavelength selection in NIR spectral analysis. It is anticipated to be validated for further applications in a wide range.

Empirical study of college students' extracurricular reading preference by functional data analysis of the library book borrowing behavior.

Library data contains many students' reading records that reflect their general knowledge acquisition. The purpose of this study is to deeply mine the library book-borrowing data, with concerns on different book catalogues and properties to predict the students' extracurricular interests. An intelligent computing framework is proposed by the fusion of a neural network architecture and a partial differential equations (PDE) function module. In model designs, the architecture is constructed as an adaptive learning backpropagation neural network (BPNN), with automatic tuning of its hyperparameters. The PDE module is embedded into the network structure to enhance the loss functions of each neural perceptron. For model evaluation, a novel comprehensive index is designed using the calculus of information entropy. Empirical experiments are conducted on a diverse and multimodal time-series dataset of library book borrowing records to demonstrate the effectiveness of the proposed methodology. Results validate that the proposed framework is capable of revealing the students' extracurricular reading interests by processing related book borrowing records, and expected to be applied to "big data" analysis for a wide range of various libraries.

Analysis of college students' canteen consumption by broad learning clustering: A case study in Guangdong Province, China.

Investigation on college students' consumption ability help classify them as from rich or relative poor family, thus to distinguish the students who are in urgent need for government's economic support. As canteen consumption is the main part of the expenses of the college students, we proposed the adjusted K-means clustering methods for discrimination of the college students at different economic levels. To improve the discrimination accuracy, a broad learning network architecture was built up for extracting informative features from the students' canteen consumption records. A fuzzy transformed technique was combined in the network architecture to extend the candidate range for identifying implicit informative variables from the single type of consumption data. Then, the broad learning network model is fully trained. We specially designed to train the network parameters in an iterative tuning mode, in order to find the precise properties that reflect the consumption characteristics. The selected feature variables are further delivered to establish the adjusted K-means clustering model. For the case study, the framework of combining the broad learning network with the adjusted K-means method was applied for the discrimination of the canteen consumption data of the college students in Guangdong province, China. Results show that the most optimal broad learning architecture is structured with 14 hidden nodes, the model training and testing results are appreciating. The results indicated that the framework was feasible to classify the students into different economic levels by analyzing their canteen consumption data, so that we are able to distinguish the students who are in need for financial aid.

Fusion Evaluation of College Cultivation by Adaptive Multivariate Neural Network Model.

The quality of graduates is the key factor in evaluating the cultivation effect of colleges and universities. Quantification of whether the graduates qualify for their working post in companies and industries provides conduction for further college cultivation reform enhancement. In this work, we proposed an adaptive multivariate neural network architecture for fusion evaluation of college student cultivation. Specifically, we designed a questionnaire to collect data on the current working status of 1231 graduates and recorded 32 in-school training items categorized into four different modules. For quantitative evaluation, 10 indices of career-require competence were set to describe the graduates' job abilities. The fused contribution of the in-school training items to the career-required competence was predicted by the multivariate network model with the linking weights adaptively trained. A comprehensive contribution matrix was generated by discrete PCA multivariate transforming to provide a digital reference for the network training. A 7-level scoring system was designed for quantifying the contribution matrix. For model optimization, the network structure was tuned by testing a different number of hidden nodes. The model was trained and optimized to reveal the direct correlation between college cultivation and job-required abilities. Experimental results indicated that the methodology we proposed is feasible to evaluate the cultivation mode in colleges and universities, theoretically and technically providing positive directions for colleges and universities to make their cultivation reforming, as to enhance the quality of their graduates.

Improvement of NIR prediction ability by dual model optimization in fusion of NSIA and SA methods.

Feature selection and sample partitioning are both important to establish a quantitative analytical model for near-infrared (NIR) spectroscopy. The classical interval partial least squares (iPLS) model for waveband selection can be improved in combination of the simulated annealing (SA) algorithm. The sample set partitioning based on a joint x-y distance (SPXY) method for sample partitioning is based on the distances of both the x- and y- dimensions; it is expected to be optimized using the non-dominant sorting strategies (NS) combined with the immune algorithm (IA). In this study, we investigated the dual model optimization mode for simultaneous selection of feature waveband and sample partitioning, and proposed a novel method defined as SA-iPLS & SPXY-NSIA. The method explores a population evolution process, and takes the candidate individual as the link for the fusion optimization of SA-iPLS and SPXY-NSIA. The method screens feature wavebands and observes a good partition of the modeling samples, to construct a combined optimization strategy for fusion optimization of the target waveband and suitable sets of sample partitioning. The performance of the SA-iPLS & SPXY-NSIA method was tested using a soil sample dataset. To prove model enhancement, the proposed method was compared to the two traditional methods of Kennard-Stone (KS) and SPXY in combination with SA-iPLS. Experimental results show that the fusion model established by SA-iPLS & SPXY-NSIA performed better than the KS-SA-iPLS and SPXY-SA-iPLS models. The best testing results of the fusion model is with RMSET, RPDT and RT observed as 0.0107, 1.7233 and 0.9097, respectively. The proposed method is prospectively able to effectively improve the predictive ability of the NIR analytical model.

A Dual-Network Modeling Architecture for Statistical Evaluation of College Graduates' Working Ability in Consistence with Their Job Position and Remuneration.

Optimal human resources allocation asks to employ a person to work in the position corresponding to his/her ability. Employment competence is the key feedback to the cultivation of college students' working ability. The data relationship needs to analyze between the in-school cultivation items and the working abilities required by the companies. Machine learning framework is introduced to study the companies' responses to the cultivation of college students. In this work, a dual-network architecture is built up for statistical modeling evaluation of college graduates' working ability in consistence with their job position and remuneration. A requirement network and a cultivation network are constructed for extracting features from the original working ability data required by companies and cultivated ever in school. The networks are fully trained by adaptively tuning the linking weights. The extracted features are fused together to estimate the working competence of each target sample/person. To evaluate the dual-network model, a modeling index system is designed, including proposing a total evaluation index calculus for the dual-network model, and a variable importance index from the original data. The samples are consequently ranked by the model predicted index and by the variable importance index, respectively. The ranking difference is used to evaluate the prediction efficiency of the dual-network model. Experimental results show that the dual network architecture is feasible to establish statistical models for the evaluation of college graduates' in-school cultivated working ability in consistence with the company's required working ability at their job position and their deserved remuneration.

A hybrid optimization method for sample partitioning in near-infrared analysis.

The division of calibration and validation is one of the essential procedures that affect the prediction result of the calibration model in quantitative analysis of near-infrared (NIR) spectroscopy. The conventional methods are Kennard-Stone (KS) and sample set partitioning based on joint x-y distances (SPXY). These algorithms use Euclidean distance to cover as many representative samples as possible. This paper proposes an Adaptive Hybrid Cuckoo-Tabu Search (AHCTS) algorithm for partitioning samples based on optimization. The algorithm combines the characteristics of cuckoo search (CS) and tabu search (TS) and fuses with an adaptive function. For comparison, using fishmeal samples as spectral analysis data, KS, SPXY, and AHCTS algorithms were used to divide the modeling samples to establish partial least squares regression (PLSR) models. The experimental results showed that the model established by the proposed algorithm performs better than KS and SPXY. It reveals that the AHCTS method may be an advantageous alternative for quantitative analysis of NIR spectroscopy.