A Machine Learning Based Funding Project Evaluation Decision Prediction

Traditional linear statistical methods cannot provide effective prediction results due to the complexity of human mind.In this paper,we apply machine learning to the field of funding allocation decision making,and try to explore whether personal characteristics of evaluators help predict the outcome of the evaluation decision?and how to improve the accuracy rate of machine learning methods on the imbalanced dataset of grant funding?Since funding data is characterized by imbalanced data distribution,we propose a slacked weighted entropy decision tree(SWE-DT).We assign weight to each class with the help of slacked factor.The experimental results show that the SWE decision tree performs well with sensitivity of 0.87,specificity of 0.85 and average accuracy of 0.75.It also provides a satisfied classification accuracy with Area Under Curve(AUC)=0.87.This implies that the proposed method accurately classified minority class instances and suitable to imbalanced datasets.By adding evaluator factors into the model,sensitivity is improved by over 9%,specificity improved by nearly 8%and the average accuracy also increased by 7%.It proves the feasibility of using evaluators’characteristics as predictors.And by innovatively using machine learning method to predict evaluation decisions based on the personal characteristics of evaluators,it enriches the literature in the field of decision making and machine learning field.

Applying Feature-Weighted Gradient Decent K-Nearest Neighbor to Select Promising Projects for Scientific Funding

Due to its outstanding ability in processing large quantity and high-dimensional data,machine learning models have been used in many cases,such as pattern recognition,classification,spam filtering,data mining and forecasting.As an outstanding machine learning algorithm,K-Nearest Neighbor(KNN)has been widely used in different situations,yet in selecting qualified applicants for winning a funding is almost new.The major problem lies in how to accurately determine the importance of attributes.In this paper,we propose a Feature-weighted Gradient Decent K-Nearest Neighbor(FGDKNN)method to classify funding applicants in to two types:approved ones or not approved ones.The FGDKNN is based on a gradient decent learning algorithm to update weight.It updates the weight of labels by minimizing error ratio iteratively,so that the importance of attributes can be described better.We investigate the performance of FGDKNN with Beijing Innofund.The results show that FGDKNN performs about 23%,20%,18%,15%better than KNN,SVM,DT and ANN,respectively.Moreover,the FGDKNN has fast convergence time under different training scales,and has good performance under different settings.

Three-Layer Structured SnO_(2)@C@TiO_(2)Hollow Spheres for High-Performance Sodium Storage

The unsatisfactory conductivity and large volume variation severely handicap the application of SnO_(2)in sodium-ion batteries(SIBs).Herein,we design unique three-layer structured SnO_(2)@C@TiO_(2)hollow spheres to tackle the above-mentioned issues.The hollow cavity affords empty space to accommodate the volume variation of SnO_(2),while the C and TiO_(2)protecting shells strengthen the structural integrity and enhances the electrical conductivity.As a result,the three-layer structured SnO_(2)@C@TiO_(2)hollow spheres demonstrate enhanced Na storage performances.The SnO_(2)@C@TiO_(2)manifests a reversible capacity two times to that of pristine SnO_(2)hollow spheres.In addition,Ex situ XRD reveals highly reversible alloying and conversion reactions in SnO_(2)@C@TiO_(2)hollow spheres.This study suggests the introduction of a hollow cavity and robust protecting shells is a promising strategy for constructing SIB anode materials.

Recent advances in TiO_2 nanoarrays/graphene for water treatment and energy conversion/storage

Although TiO2-based nanostructures with unique chemical and physical properties exhibit great promise in water treatment and energy conversion/storage,there still exist some limitations.In order to further improve the photochemical properties,one-dimension TiO2 nanoarrays on the substrate are primarily combined with graphene by various preparation technologies.The composite coating has exhibited extraordinary photocatalytic abilities in the degradation of organic pollutants into less toxic compounds,antimicrobial activity and adsorption capacity in water treatment.Especially,it is easy to recycle after photocatalytic reaction.Additionally,TiO2 nanoarrays/graphene on the substrate(especially flexible substrate)could provide potential opportunities for flexible-device fabrication with excellent photovoltaic conversion efficiency and electrochemical performance in energy conversion/storage devices.As far as we know,the relevant reviews have rarely been reported.Here,we present a comprehensive review on the preparation of TiO2 nanoarrays or TiO2 nanoarrays/graphene,and their application and mechanism in water treatment and energy conversion/storage.