Showing papers by "Universiti Teknologi Petronas published in 2015"

A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings

Abstract: Electrical load forecasting plays a vital role in order to achieve the concept of next generation power system such as smart grid, efficient energy management and better power system planning. As a result, high forecast accuracy is required for multiple time horizons that are associated with regulation, dispatching, scheduling and unit commitment of power grid. Artificial Intelligence (AI) based techniques are being developed and deployed worldwide in on Varity of applications, because of its superior capability to handle the complex input and output relationship. This paper provides the comprehensive and systematic literature review of Artificial Intelligence based short term load forecasting techniques. The major objective of this study is to review, identify, evaluate and analyze the performance of Artificial Intelligence (AI) based load forecast models and research gaps. The accuracy of ANN based forecast model is found to be dependent on number of parameters such as forecast model architecture, input combination, activation functions and training algorithm of the network and other exogenous variables affecting on forecast model inputs. Published literature presented in this paper show the potential of AI techniques for effective load forecasting in order to achieve the concept of smart grid and buildings.

Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques.

Abstract: This paper describes a discrete wavelet transform-based feature extraction scheme for the classification of EEG signals. In this scheme, the discrete wavelet transform is applied on EEG signals and the relative wavelet energy is calculated in terms of detailed coefficients and the approximation coefficients of the last decomposition level. The extracted relative wavelet energy features are passed to classifiers for the classification purpose. The EEG dataset employed for the validation of the proposed method consisted of two classes: (1) the EEG signals recorded during the complex cognitive task--Raven's advance progressive metric test and (2) the EEG signals recorded in rest condition--eyes open. The performance of four different classifiers was evaluated with four performance measures, i.e., accuracy, sensitivity, specificity and precision values. The accuracy was achieved above 98 % by the support vector machine, multi-layer perceptron and the K-nearest neighbor classifiers with approximation (A4) and detailed coefficients (D4), which represent the frequency range of 0.53-3.06 and 3.06-6.12 Hz, respectively. The findings of this study demonstrated that the proposed feature extraction approach has the potential to classify the EEG signals recorded during a complex cognitive task by achieving a high accuracy rate.

Reduced graphene oxide-polyaniline composites—synthesis, characterization and optimization for thermoelectric applications

Abstract: Reduced graphene oxide (rGO) can improve the thermoelectric properties of polyaniline (PANI) by varying its concentration in composites of rGO nanosheets and PANI. The figure of merit (ZT) of rGO–PANI composites is increased with an increasing percentage of rGO (up to 50%), which is 7.5 times higher as compared to pure PANI. High resolution transmission electron microscopy (HRTEM), field emission scanning electron microscopy (FESEM) and X-ray diffraction (XRD) analyses show a uniform growth of PANI over the surface of rGO as a template, leading to a more ordered structure with high crystallinity during polymerization. Compared to pure PANI, both the electrical conductivity and thermoelectric power of the rGO–PANI composite is higher due to the increased carrier mobility as confirmed by a Hall effect measurement. Fourier transform infrared spectroscopy (FTIR), ultra-violet visible range spectroscopy (UV-Vis) and Raman spectroscopy analyses reveal that strong π–π interactions assisted the uniform distribution of PANI on the rGO nanosheets. Other strong interactions include electrostatic forces and hydrogen bonding between rGO and PANI, which provide a route for constructing highly ordered chain structures with improved thermoelectric performance of PANI. There is no significant change in the thermal conductivity of the rGO–PANI composite as compared to pure PANI, which improves the thermoelectric performance of composite.

Performance and emission of diesel engine fuelled by waste cooking oil methyl ester derived from palm olein using hydrodynamic cavitation

Abstract: The depleting of fossil fuel reserves and increasing environmental concerns have continued to stimulate research into biodiesel as a greener fuel alternative produced from renewable resources. In this study, the performance and emission characteristics of biodiesel blends of 10, 30 and 50 % from waste cooking oil based on hydrodynamic cavitation were compared to diesel fuel, and found to be acceptable according to the EN 14214 and ASTM D 6751 standards. The tests have been performed using an in-line vertical six-cylinder diesel engine at different engine speeds, ranging from 1000 to 2000 rpm under full throttle load. During engine performance tests, biodiesel blends showed higher brake specific fuel consumption (2.1–9.0 %) and exhaust gas temperature (1.0–6.8 %), while lower brake power (1.6–6.7 %), torque (0.6–5.2 %) and brake thermal efficiency (1.9–8.4 %) than diesel fuel. Engine emissions showed higher carbon dioxide (8.7–38.5 %) and nitrogen oxide (4.7–19.0 %) releases, but surprisingly decreased amount of carbon monoxide (3.3–26.3 %) for biodiesel blends compared to diesel fuel. Although higher carbon dioxide amounts were emitted, the use of biodiesel greatly reduced the life cycle circulation of carbon dioxide. Waste cooking methyl ester produced by using hydrodynamic cavitation seems to be relatively easy to scale up to higher production values, is energy efficient, time saving and eco-friendly, which results in biodiesel being a viable fuel for industrial production. The waste cooking oil-based biodiesel can also be used without any engine modifications.

Investigation of window size in classification of EEG-emotion signal with wavelet entropy and support vector machine

Abstract: When dealing with patients with psychological or emotional symptoms, medical practitioners are often faced with the problem of objectively recognizing their patients' emotional state. In this paper, we approach this problem using a computer program that automatically extracts emotions from EEG signals. We extend the finding of Koelstra et. al [IEEE trans. affective comput., vol. 3, no. 1, pp. 18–31, 2012] using the same dataset (i.e. the DEAP: dataset for emotion analysis using electroencephalogram, physiological and video signals), where we observed that the accuracy can be further improved using wavelet features extracted from shorter time segments. More precisely, we achieved accuracy of 65% for both valence and arousal using the wavelet entropy of 3 to 12 seconds signal segments. This improvement in accuracy entails an important discovery that information on emotions contained in the EEG signal may be better described in term of wavelets and in shorter time segments.

A survey of approaches for verifying model transformations

Abstract: As with other software development artifacts, model transformations are not bug-free and so must be systematically verified. Their nature, however, means that transformations require specialist verification techniques. This paper brings together current research on model transformation verification by classifying existing approaches along two dimensions. Firstly, we present a coarse-grained classification based on the technical details of the approach (e.g., testing, theorem proving, model checking). Secondly, we present a finer-grained classification which categorizes approaches according to criteria such as level of formality, transformation language, properties verified. The purpose of the survey is to bring together research in model transformation verification to act as a resource for the community. Furthermore, based on the survey, we identify a number of trends in current and past research on model transformation verification.

Effective removal of methylene blue from water using phosphoric acid based geopolymers: synthesis, characterizations and adsorption studies

Abstract: Phosphoric acid based geopolymers (PAGPs) are a class of geopolymers that are produced by phosphoric acid activation of metakaolin. In this work, two different PAGPs have been synthesized using phosphoric acid to alumina molar ratios of 1 : 1 and 1.2 : 1. The surface profile, chemical composition, micromorphology, and texture properties of the geopolymers were instrumentally determined. Both geopolymers have shown a mesoporous profile with the avg. pore size of 8.6 and 19.4 nm by GP-1M (P : Al = 1 : 1) and GP-2M (P : Al = 1.2 : 1), respectively. Thermogravimetric analysis revealed that these geopolymers were thermally stable up to 800 °C, although the formation of quartz, cristobalite and tridymite was observed in XRD analysis of the samples treated at 800 °C for two hours. The synthesized geopolymers were utilized for the adsorption of methylene blue (MB) by investigating the effect of the amount of adsorbent, pH of the solution and shaking period. The batch kinetics study fitted best into the pseudo second order (PSO) reaction kinetic model. In isotherm modelling studies, the Langmuir isotherm model was best fitted and was used to describe the mechanism of the adsorption. Experimental adsorption capacities (qe) of 2.84 and 3.01 mg g−1 were recorded for GP-1M and GP-2M, respectively. Used adsorbents were successfully regenerated by furnace treatment at 400 °C for two hours, and the regenerated adsorbents presented enhanced adsorption capacities in the range of 4.9–5.07 mg g−1 for five repeat cycles, elucidating that the material is suitable for multiple time use.

Hydrogen-bond acidity of ionic liquids: an extended scale

Abstract: One of the main drawbacks comprising an appropriate selection of ionic liquids (ILs) for a target application is related to the lack of an extended and well-established polarity scale for these neoteric fluids. Albeit considerable progress has been made on identifying chemical structures and factors that influence the polarity of ILs, there still exists a high inconsistency in the experimental values reported by different authors. Furthermore, due to the extremely large number of possible ILs that can be synthesized, the experimental characterization of their polarity is a major limitation when envisaging the choice of an IL with a desired polarity. Therefore, it is of crucial relevance to develop correlation schemes and a priori predictive methods able to forecast the polarity of new (or not yet synthesized) fluids. In this context, and aiming at broadening the experimental polarity scale available for ILs, the solvatochromic Kamlet–Taft parameters of a broad range of bis(trifluoromethylsulfonyl)imide-([NTf2]−)-based fluids were determined. The impact of the IL cation structure on the hydrogen-bond donating ability of the fluid was comprehensively addressed. Based on the large amount of novel experimental values obtained, we then evaluated COSMO-RS, COnductor-like Screening MOdel for Real Solvents, as an alternative tool to estimate the hydrogen-bond acidity of ILs. A three-parameter model based on the cation–anion interaction energies was found to adequately describe the experimental hydrogen-bond acidity or hydrogen-bond donating ability of ILs. The proposed three-parameter model is also shown to present a predictive capacity and to provide novel molecular-level insights into the chemical structure characteristics that influence the acidity of a given IL. It is shown that although the equimolar cation–anion hydrogen-bonding energies (EHB) play the major role, the electrostatic-misfit interactions (EMF) and van der Waals forces (EvdW) also contribute, admittedly in a lower extent, towards the hydrogen-bond acidity of ILs. The new extended scale provided for the hydrogen-bond acidity of ILs is of high value for the design of new ILs for task-specific applications.

Intensification of biodiesel synthesis from waste cooking oil (Palm Olein) in a Hydrodynamic Cavitation Reactor: Effect of operating parameters on methyl ester conversion

Abstract: This paper investigates a new route for intensification of methyl ester synthesis in Malaysia via alkali-catalysed transesterification of waste cooking oil derived from palm olein using a hydrodynamic cavitation reactor. The effects of the oil to methanol molar ratio (1:4–1:7), catalyst loading concentration (0.5–1.25 wt%) and reaction temperature (50–65 °C) have been investigated using an optimised plate with 21 holes of 1 mm diameter and an inlet pressure of 2 bar in a 50 L of hydrodynamic cavitation reactor assisted by a double diaphragm pump. Optimal conversion of 98.1% was achieved in 15 min in a hydrodynamic cavitation reactor with 1:6 molar ratio of oil to methanol, 1 wt% of catalyst and 60 °C of reaction temperature. It has been observed that a significant reduction in the optimum reaction time (about 6 fold) for transesterification from 90 min for mechanical stirring approach to 15 min for the hydrodynamic cavitation approach. Optimal yield efficiency of 12.50 × 10 −4 g/J was found using hydrodynamic cavitation and it was 8 fold higher than 1.5 × 10 −4 g/J when mechanical stirring was used.

A Review on Phytoremediation of Crude Oil Spills

Abstract: Changes in crude oil production and distribution have increased the incidence of oil spills throughout the world. Oil spills often cause destructive effects on aquatic and land ecosystems. The oil spill cleanup and recovery techniques are challenging and usually involve complex mechanical, chemical, and biological methods. Usually, mechanical removal of free oil is utilized as an effective strategy for cleanup in aquatic and terrestrial environments; however, they are expensive and need specialist personnel and equipment. The other commonly used method is the application of chemical materials such as dispersants, cleaners, demulsifiers, biosurfactants, and soil oxidizers. Nevertheless, these reagents can have potential harmful environmental impacts, which may limit their application. As an alternative, bioremediation can offer reduced environment risk; however, the limitations of microbial activity in the soil can make this option unsuitable. One area of bioremediation is phytoremediation, which offers potential for restoring large areas of contaminated ground. Plants are able to remove pollutants through processes such as biodegradation, phytovolatilization, accumulation, and metabolic transformation. This review presents the fate of crude oil spills in aquatic and land ecosystems and their environmental effects. Furthermore, the paper focuses on crude oil phytoremediation and its applications in polluted ecosystems.

An Energy Efficient Cross-Layer Network Operation Model for IEEE 802.15.4-Based Mobile Wireless Sensor Networks

Abstract: IEEE 802.15.4 mobile wireless sensor networks (MWSNs) have been investigated in literature. One major finding is that these networks suffer from control packet overhead and delivery ratio degradation. This increases the network's energy consumption. This paper introduces a cross-layer operation model that can improve the energy consumption and system throughput of IEEE 802.15.4 MWSNs. The proposed model integrates four layers in the network operation: 1) application (node location); 2) network (routing); 3) medium access control (MAC); and 4) physical layers. The location of the mobile nodes is embedded in the routing operation after the route discovery process. The location information is then utilized by the MAC layer transmission power control to adjust the transmission range of the node. This is used to minimize the power utilized by the network interface to reduce the energy consumption of the node(s). The model employs a mechanism to minimize the neighbor discovery broadcasts to the active routes only. Reducing control packet broadcasts between the nodes reduces the network's consumed energy. It also decreases the occupation period of the wireless channel. The model operation leads the network to consume less energy while maintaining the network packet delivery ratio. To the best of our knowledge, the presented operational model with its simplicity has never been introduced. Through simulation-based evaluations, the proposed model outperforms the conventional operation of IEEE 802.15.4-based network and the energy efficient and QoS aware multipath routing protocol in terms of energy consumption by roughly 10%, twice less control packet overhead, on-par end-to-end delays and comparative packet delivery ratios.

Biochar efficiency in pesticides sorption as a function of production variables—a review

Abstract: Biochar is a stabilized, carbon-rich by-product derived from pyrolysis of biomass. Recently, biochar has received extensive attentions because of its multi-functionality for agricultural and environmental applications. Biochar can contribute to sequestration of atmosphere carbon, improvement of soils quality, and mitigation of environmental contaminations. The capability of biochar for specific application is determined by its properties which are predominantly controlled by source material and pyrolysis route variables. The biochar sorption potential is a function of its surface area, pores volume, ash contents, and functional groups. The impacts of each production factors on these characteristics of biochar need to be well-understood to design efficient biochars for pesticides removal. The effects of biomass type on biochar sorptive properties are determined by relative amounts of its lingo-cellulosic compounds, minerals content, particles size, and structure. The highest treatment temperature is the most effective pyrolysis factor in the determination of biochar sorption behavior. The expansion of micro-porosity and surface area and also increase of biochar organic carbon content and hydrophobicity mostly happen by pyrolysis peak temperature rise. These changes make biochar suitable for immobilization of organic contaminants. Heating rate, gas pressure, and reaction retention time after the pyrolysis temperatures are sequentially important pyrolysis variables effective on biochar sorptive properties. This review compiles the available knowledge about the impacts of production variables on biochars sorptive properties and discusses the aging process as the main factor in post-pyrolysis alterations of biochars sorption capacity. The drawbacks of biochar application in the environment are summarized as well in the last section.

Application of CCD in RSM to obtain optimize treatment of POME using Fenton oxidation process

Abstract: Post treatment palm oil mill effluent (POME) is typically non-biodegradable and contains high organic and inorganic matter. This study aims to optimize the operating parameters of the Fenton process in removing recalcitrant organics from POME by using a central composite design (CCD), which is a response surface methodology (RSM) module in the Design-Expert ® software. Important parameters such as reaction time, H 2 O 2 and Fe 2+ ion concentrations, and pH were empirically determined and successfully optimized via RSM. Significant statistical quadratic polynomial for color and COD removal efficiency were obtained via regression analyses R 2 , (0.81 and 0.70) for color and COD, respectively. The highest results were 97.36% removal for color and 91.11% removal for COD at pH 3.5 and 30 min of reaction time. Numerical optimization based on desirable functions was employed; 92.1% of color and 85.1% of COD were removed efficiently at pH (3.0–5.0) with a final pH of 2.85 (after reaction settlement), 4.57 g/L H 2 O 2 and 1.88 g/L Fe 2+ ions concentration, respectively, and 30 min of reaction time at 120 rpm agitation rate. The result showed that the Fenton process, at an accurate level, may be used as an effective technology for the post treatment of POME before final discharge into a nearby water body.