Machine Learning and Synthetic Minority Oversampling Techniques for Imbalanced Data: Improving Machine Failure Prediction

Prediction of machine failure is challenging as the dataset is often imbalanced with a low failure rate. The common approach to handle classification involving imbalanced data is to balance the data using a sampling approach such as random undersampling, random oversampling, or Synthetic Minority Oversampling Technique (SMOTE) algorithms. This paper compared the classification performance of three popular classifiers (Logistic Regression, Gaussian Naïve Bayes, and Support Vector Machine) in predicting machine failure in the Oil and Gas industry. The original machine failure dataset consists of 20,473 hourly data and is imbalanced with 19945 (97%) ‘non-failure’ and 528 (3%) ‘failure data’. The three independent variables to predict machine failure were pressure indicator, flow indicator, and level indicator. The accuracy of the classifiers is very high and close to 100%, but the sensitivity of all classifiers using the original dataset was close to zero. The performance of the three classifiers was then evaluated for data with different imbalance rates (10% to 50%) generated from the original data using SMOTE, SMOTE-Support Vector Machine (SMOTE-SVM) and SMOTE-Edited Nearest Neighbour (SMOTE-ENN). The classifiers were evaluated based on improvement in sensitivity and F-measure. Results showed that the sensitivity of all classifiers increases as the imbalance rate increases. SVM with radial basis function (RBF) kernel has the highest sensitivity when data is balanced (50:50) using SMOTE (Sensitivity_test =0.5686, F_test= 0.6927) compared to Naïve Bayes (Sensitivity_test =0.4033, F_test= 0.6218) and Logistic Regression (Sensitivity_test =0.4194, F_test= 0.621). Overall, the Gaussian Naïve Bayes model consistently improves sensitivity and F-measure as the imbalance ratio increases, but the sensitivity is below 50%. The classifiers performed better when data was balanced using SMOTE-SVM compared to SMOTE and SMOTE-ENN.     

Measurement of Percentage Depth Dose and Half Value Layer of the <Emphasis Type="Italic">Rhizophora</Emphasis> spp. Particleboard Bonded by <Emphasis Type="Italic">Eremurus</Emphasis> spp. to 60, 80 and 100 kVp Diagnostic X-rays

Some researchers formerly provided the mechanical, physical, and attenuation properties of the fabricated Eremurus–Rhizophora spp. particleboard phantom. In this study, the percentage depth dose (PDD) and the half value layer (HVL) of fabricated Eremurus–Rhizophora spp. particleboard phantom were determined and compared with those of Perspex and water phantoms, with the same standard phantom size (30 cm?×?30 cm?×?30 cm) in the diagnostic energy range using TLD 100H. In addition, the energy range of X-ray was in diagnostic range of energy. The results indicated that the PDD and HVL of the fabricated Eremurus–Rhizophora spp. particleboard phantom were close to those of the Perspex phantom. Likewise, the PDD and HVL of the fabricated Eremurus–Rhizophora spp. particleboard phantom were found in good agreement with those of water phantom. According to the results of this study, the fabricated Eremurus–Rhizophora spp. particleboard phantom can be used as medical phantoms.     

Enhancement of thermal and electrical conductivities of cyanoacrylate by addition of carbon based nanofillers

Nanocomposites with addition of graphite nanoparticles, multi-walled carbon nanotubes (MWCNTs), and graphene in cyanoacrylate from 0.1 to 0.5 or 0.6 vol% were fabricated. The influences of morphology towards thermal and electrical conductivities of cyanoacrylate nanocomposites were studied. Microstructure based on field emission scanning electron microscopy and transmission electron microscopy images indicated that nanofillers have unique morphologies which affect the thermal and electrical conductivities of nanocomposites. The maximum thermal conductivity values were measured at 0.3195 and 0.3500 W/mK for 0.4 vol% of MWCNTs/cyanoacrylate and 0.5 vol% of graphene/cyanoacrylate nanocomposite, respectively. These values were improved as high as 204 and 233% as compared with the thermal conductivity of neat cyanoacrylate. Nanocomposites with 0.2 vol% MWCNTs/cyanoacrylate fulfilled the requirement for ESD protection material with surface resistivity of 6.52?×?10⁶ Ω/sq and volume resistivity of 6.97?×?10⁹ Ω m. On the other hand, 0.5 vol% MWCNTs/cyanoacrylate nanocomposite can be used as electrical conductive adhesive. Compared with graphene and graphite nanofillers, MWCNTs is the best filler to be used in cyanoacrylate for improvement in thermal and electrical conductivity enhancement at low filler loading.     

One-step synthesis of conductive graphene/polyaniline nanocomposites using sodium dodecylbenzenesulfonate: preparation and properties

The preparation of conducting graphene/polyaniline–sodium dodecylbenzenesulfonate (PANI–SDBS) nanocomposites using synthesised graphene as the starting material is successfully conducted in the present study. The effect of the anionic surfactant SDBS on the properties of the graphene/PANI–SDBS nanocomposites is studied. The structure and morphology of the synthesised nanocomposites are characterised by field emission scanning electron microscopy (FESEM), transmission electron microscopy (TEM), Fourier transform infrared (FTIR) spectroscopy, ultraviolet–visible (UV–vis) spectrophotometry, X-ray diffraction and atomic force microscopy (AFM). The electrical conductivity properties of the resulting nanocomposites are determined using a resistance meter measurement system. The FESEM and TEM images reveal that the addition of SDBS surfactant to the PANI transforms the nanofibers of the PANI to a nanosphere morphology of PANI–SDBS. FTIR and UV–vis studies reveal that the conductive graphene/PANI–SDBS nanocomposites are successfully synthesised. AFM characterisation shows that the addition of graphene reduces the root mean square roughness of the surface of the PANI. The electrical conductivity and thermal stability of the PANI are improved after the introduction of SDBS. The nanocomposites containing a 5 wt% graphene loading exhibit the highest electrical conductivity of 2.94?×?10^?2 S/cm, which is much higher than that of PANI (9.09?×?10^?6 S/cm).     

Water quality prediction model utilizing integrated wavelet-ANFIS model with cross-validation

This paper discusses the accuracy performance of training, validation and prediction of monthly water quality parameters utilizing Adaptive Neuro-Fuzzy Inference System (ANFIS). This model was used to analyse the historical data that were generated through continuous monitoring stations of water quality parameters (i.e. the dependent variable) of Johor River in order to imitate their secondary attribute (i.e. the independent variable). Nevertheless, the data arising from the monitoring stations and experiment might be polluted by noise signals owing to systematic and random errors. This noisy data often made the predicted task relatively difficult. Thus, in order to compensate for this augmented noise, the primary objective of this study was to develop a technique that could enhance the accuracy of water quality prediction (WQP). Therefore, this study proposed an augmented wavelet de-noising technique with Neuro-Fuzzy Inference System (WDT-ANFIS) based on the data fusion module for WQP. The efficiency of the modules was examined to predict critical parameters that were affected by the urbanization surrounding the river. The parameters were investigated in terms of the following: the electrical conductivity (COND), the total dissolved solids (TDSs) and turbidity (TURB). The results showed that the optimum level of accuracy was achieved by making the length of cross-validation equal one-fifth of the data records. Moreover, the WDT-ANFIS module outperformed the ANFIS module with significant improvement in predicting accuracy. This result indicated that the proposed approach was basically an attractive alternative, offering a relatively fast algorithm with good theoretical properties to de-noise and predict the water quality parameters. This new technique would be valuable to assist decision-makers in reporting the status of water quality, as well as investigating spatial and temporal changes.     

Hybrid Adaptive Neuro-Fuzzy Models for Water Quality Index Estimation

Soft computing models are known as an efficient tool for modelling temporal and spatial variation of surface water quality variables and particularly in rivers. These model’s performance relies on how effective their simulation processes are accomplished. Fuzzy logic approach is one of the authoritative intelligent model in solving complex problems that deal with uncertainty and vagueness data. River water quality nature is involved with high stochasticity and redundancy due to the its correlation with several hydrological and environmental aspects. Yet, the fuzzy logic theory can give robust solution for modelling river water quality problem. In addition, this approach likewise can be coordinated with an expert system framework for giving reliable and trustful information for decision makers in enhancing river system sustainability and factual strategies. In this research, different hybrid intelligence models based on adaptive neuro-fuzzy inference system (ANFIS) integrated with fuzzy c-means data clustering (FCM), grid partition (GP) and subtractive clustering (SC) models are used in modelling river water quality index (WQI). Monthly measurement records belong to Selangor River located in Malaysia were selected to build the predictive models. The modelling process was included several water quality terms counting physical, chemical and biological variables whereas WQI was the target variable. At the first stage of the research, statistical analysis for each water quality parameter was analyzed toward the WQI. Whereas in the second stage, the predictive models were established. The finding of the current research provides an authorized soft computing model to determine WQI that can be used instead of the conventional procedure that consumes time, cost, efforts and sometimes computation errors.     

An improved hybrid nanocomposites of rice husk derived graphene (GRHA)/Zeolitic imidazolate framework-8 for hydrogen adsorption

In this work, hybrid nanocomposites rice husk derived graphene (GRHA) and zeolitic imidazolate framework-8 (ZIF-8) were prepared for hydrogen adsorption. The main contribution of this study is the simplification of the synthesized GRHA/ZIF-8 hybrid nanocomposites. Besides that, the use of synthesized graphene from rice husk (RH) could help in overcoming environmental issue since disposal of RH is rather challenging. GRHA was obtained through calcining rice husk ash (RHA) at 900 °C for 2 h in a muffle furnace at atmospheric condition while the nanocomposite of GRHA/ZIF-8 was produced in free solvent condition using deionized water at room temperature for only 1 h. The N₂ adsorption-desorption indicated a type I isotherm. Interestingly, it was found that the BET specific surface area (BET_SSA) of GRHA/ZIF-8 showed enhancement up to 3 times higher as compared to pristine GRHA with the addition of 0.2 g of GRHA. From the experimental data, the adsorption of H₂ by nanocomposite GRHA/ZIF-8 obeyed the pseudo-second order kinetic model and intraparticle diffusion model with R² value up to 0.9890 and 0.8087 respectively at 12 bar. Moreover, the GRHA/ZIF-8 possessed highest hydrogen adsorption of 31.84 mmol/g at 12 bar. These impressive results are justified by the combination of ZIF-8's microporosity and GRHA's mesoporosity.     

Binary and ternary effects of ground dune sand and blast furnace slag on the compressive strength of mortar

The aim of this study is to promote the use of available natural dune sand from desert areas as a partial cement replacement. Binary and ternary combinations of ground dune sand (GDS), Portland cement (PC) and ground granulated blast furnace slag (GGBS) were investigated for their effects on the compressive strength of mortar cured under standard or autoclave curing conditions. The results showed that the compressive strength decreased significantly with increasing GDS and GGBS contents under standard curing. However, with autoclave curing, all of the binary and ternary mixtures yielded mortar with a compressive strength higher than that of the control sample. The autoclave-cured ternary combination of 30% GDS, 50% PC and 20% GGBS showed the highest compressive strength. It is possible to use a PC content as low as 10% since the mixture of 30% GDS, 10% PC and 60% GGBS displayed strength comparable to the control sample.     

Effects of filler shape and size on the properties of silver filled epoxy composite for electronic applications

Epoxy composites filled with nano- and micro-sized silver (Ag) particulate fillers were prepared and characterized based on flexural properties, coefficient of thermal expansion, dynamic mechanical analysis, electrical conductivity, and morphological properties. The influences of these two types of Ag fillers, especially in terms of their sizes and shapes, were investigated. Silver nanoparticles were nano-sized and spherical, while silver flakes were micron-sized and flaky. It was found that the flexural strength of the epoxy composite filled with silver flakes decreased, while the flexural strength of the epoxy composite filled with silver nanoparticles showed an optimum value at 4 vol.% before it subsequently dropped. Both silver composites showed improvement in flexural modulus with increasing filler loads. CTE value indicated significant decrements in filled samples compared to neat epoxy. Results on the electrical conductivity of both systems showed a transition from insulation to conduction at 6 vol.%.