Search results for: feature extraction

Authors: Andi Hasizah Mochtar, Meta Mahendradatta, Amran Laga, Metusalach Metusalach, Salengke Salengke, Mariati Bilang, Andi Amijoyo Mochtar, Reta Reta, Aminah Muhdar, Sri Suhartini

Abstract:

This study aims to determine the effect of alcohol type on the quality of iota carrageenan-based on extraction technology through the application of ohmic reactor. Results of this analysis will be used as a reference for selecting the proper type of alcohol used for carrageenan precipitated after extraction by technology based ohmic. The results of analysis performed included analysis of viscosity, gel strength, and yield of iota carrageenan. Viscosity is the highest obtained at precipitated by using isopropyl alcohol with an average of 291.5 Cp (at 160 rpm), then with methanol at an average of 282 Cp, then precipitated by using ethanol at an average of 206.5 Cp. Gel strength is the lowest obtained 67.74 on precipitated by using ethanol, then an average of 74.34 in precipitated that using methanol, and the highest average of 80.11 in precipitated that using isopropyl alcohol.

Keywords: extraction of carrageenan, gel strength, ohmic technology, precipitated, seaweed (Eucheuma spinosum), viscosity

Procedia PDF Downloads 198

Authors: Soyon Kim, Edward Kim

Abstract:

In order to retrieve information from the massive stream of songs in the music industry, music search by title, lyrics, artist, mood, and genre has become more important. Despite the subjectivity and controversy over the definition of music genres across different nations and cultures, automatic genre classification systems that facilitate the process of music categorization have been developed. Manual genre selection by music producers is being provided as statistical data for designing automatic genre classification systems. In this paper, an automatic music genre classification system utilizing non-negative matrix factorization (NMF) is proposed. Short-term characteristics of the music signal can be captured based on the timbre features such as mel-frequency cepstral coefficient (MFCC), decorrelated filter bank (DFB), octave-based spectral contrast (OSC), and octave band sum (OBS). Long-term time-varying characteristics of the music signal can be summarized with (1) the statistical features such as mean, variance, minimum, and maximum of the timbre features and (2) the modulation spectrum features such as spectral flatness measure, spectral crest measure, spectral peak, spectral valley, and spectral contrast of the timbre features. Not only these conventional basic long-term feature vectors, but also NMF based feature vectors are proposed to be used together for genre classification. In the training stage, NMF basis vectors were extracted for each genre class. The NMF features were calculated in the log spectral magnitude domain (NMF-LSM) as well as in the basic feature vector domain (NMF-BFV). For NMF-LSM, an entire full band spectrum was used. However, for NMF-BFV, only low band spectrum was used since high frequency modulation spectrum of the basic feature vectors did not contain important information for genre classification. In the test stage, using the set of pre-trained NMF basis vectors, the genre classification system extracted the NMF weighting values of each genre as the NMF feature vectors. A support vector machine (SVM) was used as a classifier. The GTZAN multi-genre music database was used for training and testing. It is composed of 10 genres and 100 songs for each genre. To increase the reliability of the experiments, 10-fold cross validation was used. For a given input song, an extracted NMF-LSM feature vector was composed of 10 weighting values that corresponded to the classification probabilities for 10 genres. An NMF-BFV feature vector also had a dimensionality of 10. Combined with the basic long-term features such as statistical features and modulation spectrum features, the NMF features provided the increased accuracy with a slight increase in feature dimensionality. The conventional basic features by themselves yielded 84.0% accuracy, but the basic features with NMF-LSM and NMF-BFV provided 85.1% and 84.2% accuracy, respectively. The basic features required dimensionality of 460, but NMF-LSM and NMF-BFV required dimensionalities of 10 and 10, respectively. Combining the basic features, NMF-LSM and NMF-BFV together with the SVM with a radial basis function (RBF) kernel produced the significantly higher classification accuracy of 88.3% with a feature dimensionality of 480.

Keywords: mel-frequency cepstral coefficient (MFCC), music genre classification, non-negative matrix factorization (NMF), support vector machine (SVM)

Procedia PDF Downloads 272

Authors: Syed Basit Ali Shah Bukhari, Yan Qiang, Saad Abdul Rauf, Syed Saqlaina Bukhari

Abstract:

Text Classification is the methodology to classify any given text into the respective category from a given set of categories. It is highly important and vital to use proper set of pre-processing , feature selection and classification techniques to achieve this purpose. In this paper we have used different ensemble techniques along with variance in feature selection parameters to see the change in overall accuracy of the result and also on some other individual class based features which include precision value of each individual category of the text. After subjecting our data through pre-processing and feature selection techniques , different individual classifiers were tested first and after that classifiers were combined to form ensembles to increase their accuracy. Later we also studied the impact of decreasing the classification categories on over all accuracy of data. Text classification is highly used in sentiment analysis on social media sites such as twitter for realizing people’s opinions about any cause or it is also used to analyze customer’s reviews about certain products or services. Opinion mining is a vital task in data mining and text categorization is a back-bone to opinion mining.

Keywords: Natural Language Processing, Ensemble Classifier, Bagging Classifier, AdaBoost

Procedia PDF Downloads 208

Authors: Lenuta Kloetzer, Alexandra C. Blaga, Dan Cascaval, Alexandra Tucaliuc, Anca I. Galaction

Abstract:

Rosmarinic acid, an ester of caffeic acid and 3-(3,4-dihydroxyphenyl) lactic acid, is considered a valuable compound for the pharmaceutical and cosmetic industries due to its antimicrobial, antioxidant, antiviral, anti-allergic, and anti-inflammatory effects. It can be obtained by extraction from vegetable or animal materials, by chemical synthesis and biosynthesis. Indifferent of the method used for rosmarinic acid production, the separation and purification process implies high amount of raw materials and laborious stages leading to high cost for and limitations of the separation technology. This study focused on separation of rosmarinic acid by synergic reactive extraction with a mixture of two extractants, one acidic (acid di-(2ethylhexyl) phosphoric acid, D2EHPA) and one with basic character (Amberlite LA-2). The studies were performed in experimental equipment consisting of an extraction column where the phases’ mixing was made by mean of a perforated disk with 45 mm diameter and 20% free section, maintained at the initial contact interface between the aqueous and organic phases. The vibrations had a frequency of 50 s⁻¹ and 5 mm amplitude. The extraction was carried out in two solvents with different dielectric constants (n-heptane and dichloromethane) in which the extractants mixture of varying concentration was dissolved. The pH-value of initial aqueous solution was varied between 1 and 7. The efficiency of the studied extraction systems was quantified by distribution and synergic coefficients. For calculating these parameters, the rosmarinic acid concentration in the initial aqueous solution and in the raffinate have been measured by HPLC. The influences of extractants concentrations and solvent polarity on the efficiency of rosmarinic acid separation by synergic extraction with a mixture of Amberlite LA-2 and D2EHPA have been analyzed. In the reactive extraction system with a constant concentration of Amberlite LA-2 in the organic phase, the increase of D2EHPA concentration leads to decrease of the synergic coefficient. This is because the increase of D2EHPA concentration prevents the formation of amine adducts and, consequently, affects the hydrophobicity of the interfacial complex with rosmarinic acid. For these reasons, the diminution of synergic coefficient is more important for dichloromethane. By maintaining a constant value of D2EHPA concentration and increasing the concentration of Amberlite LA-2, the synergic coefficient could become higher than 1, its highest values being reached for n-heptane. Depending on the solvent polarity and D2EHPA amount in the solvent phase, the synergic effect is observed for Amberlite LA-2 concentrations over 20 g/l dissolved in n-heptane. Thus, by increasing the concentration of D2EHPA from 5 to 40 g/l, the minimum concentration value of Amberlite LA-2 corresponding to synergism increases from 20 to 40 g/l for the solvent with lower polarity, namely, n-heptane, while there is no synergic effect recorded for dichloromethane. By analysing the influences of the main factors (organic phase polarity, extractant concentration in the mixture) on the efficiency of synergic extraction of rosmarinic acid, the most important synergic effect was found to correspond to the extractants mixture containing 5 g/l D2EHPA and 40 g/l Amberlite LA-2 dissolved in n-heptane.

Keywords: Amberlite LA-2, di(2-ethylhexyl) phosphoric acid, rosmarinic acid, synergic effect

Procedia PDF Downloads 264

Authors: Akkasit Jongjareonrak, Supansa Namchaiya

Abstract:

Unripe green coffee cherry (UGCC) accounting about 5 % of total raw material weight receiving to the coffee bean production process and is, in general, sorting out and dump as waste. The UGCC is known to rich in phenolic compounds such as caffeoylquinic acids, feruloylquinic acids, chlorogenic acid (CGA), etc. CGA is one of the potent bioactive compounds using in the nutraceutical and functional food industry. Therefore, this study aimed at optimization the extraction condition of CGA from UGCC using Accelerated Solvent Extractor (ASE). The ethanol/water mixture at various ethanol concentrations (50, 60 and 70 % (v/v)) was used as an extraction solvent at elevated pressure (10.34 MPa) and temperatures (90, 120 and 150 °C). The recovery yield of UGCC crude extract, total phenolic content, CGA content and some bioactivities of UGCC extract were investigated. Using of ASE at lower temperature with higher ethanol concentration provided higher CGA content in the UGCC crude extract. The maximum CGA content was observed at the ethanol concentration of 70% ethanol and 90 °C. The further purification of UGCC crude extract gave a higher purity of CGA with a purified CGA yield of 4.28 % (w/w, of dried UGCC sample) containing 72.52 % CGA equivalent. The antioxidant activity and antimicrobial activity of purified CGA extract were determined. The purified CGA exhibited the 2,2-Diphenyl-1-picrylhydrazyl (DPPH) radical scavenging activity at 0.88 mg Trolox equivalent/mg purified CGA sample. The antibacterial activity against Escherichia coli was observed with the minimum inhibitory concentration (MIC) at 3.12 mg/ml and minimum bactericidal concentration (MBC) at 12.5 mg/ml. These results suggested that using of high concentration of ethanol and low temperature under elevated pressure of ASE condition could accelerate the extraction of CGA from UGCC. The purified CGA extract could be a promising alternative source of bioactive compound using for nutraceutical and functional food industry.

Keywords: bioactive, chlorogenic acid, coffee, extraction

Procedia PDF Downloads 233

Authors: Sandra Mitrovic, Gaurav Singh

Abstract:

In many industries, including telecommunications, churn prediction has been a topic of active research. A lot of attention has been drawn on devising the most informative features, and this area of research has gained even more focus with spread of (social) network analytics. The call detail records (CDRs) have been used to construct customer networks and extract potentially useful features. However, to the best of our knowledge, no studies including network features have yet proposed a generic way of representing network information. Instead, ad-hoc and dataset dependent solutions have been suggested. In this work, we build upon a recently presented method (node2vec) to obtain representations for nodes in observed network. The proposed approach is generic and applicable to any network and domain. Unlike node2vec, which assumes a static network, we consider a dynamic and time-evolving network. To account for this, we propose an approach that constructs the feature representation of each node by generating its node2vec representations at different timestamps, concatenating them and finally compressing using an auto-encoder-like method in order to retain reasonably long and informative feature vectors. We test the proposed method on churn prediction task in telco domain. To predict churners at timestamp ts+1, we construct training and testing datasets consisting of feature vectors from time intervals [t1, ts-1] and [t2, ts] respectively, and use traditional supervised classification models like SVM and Logistic Regression. Observed results show the effectiveness of proposed approach as compared to ad-hoc feature selection based approaches and static node2vec.

Keywords: churn prediction, dynamic networks, node2vec, auto-encoders

Procedia PDF Downloads 292

Authors: Vaibhav V. Dixit, Shubham Ajay Karwa

Abstract:

Diabetic foot ulcers speak to a critical medical problem. Right now, clinicians and medical caretakers primarily construct their injury evaluation in light of visual examination of wound size and mending status, while the patients themselves rarely have a chance to play a dynamic part. Henceforth, love quantitative and practical examination technique that empowers the patients and their parental figures to take a more dynamic part in every day wound care possibly can quicken wound recuperating, spare travel cost and diminish human services costs. Considering the commonness of cell phones with a high-determination computerized camera, evaluating wounds by breaking down pictures of ceaseless foot ulcers is an alluring choice. In this paper, we propose a novel injury picture examination framework actualized using feature extraction and color segmentation. Here we are using the Normalized minimum distance classifier for classifying the output.

Keywords: diabetic, Gabor wavelet, normalized minimum distance classifier, quantiable parameters

Procedia PDF Downloads 248

Authors: Jarek Krajewski, Andre Wittenborn, Martin Sauerland

Abstract:

This abstract describes a promising approach for estimating post-traumatic stress disorder (PTSD) based on prosodic speech characteristics. It illustrates the validity of this method by briefly discussing results from an Arabic refugee sample (N= 47, 32 m, 15 f). A well-established standardized self-report scale “Reaction of Adolescents to Traumatic Stress” (RATS) was used to determine the ground truth level of PTSD. The speech material was prompted by telling about autobiographical related sadness inducing experiences (sampling rate 16 kHz, 8 bit resolution). In order to investigate PTSD-induced speech changes, a self-developed set of 136 prosodic speech features was extracted from the .wav files. This set was adapted to capture traumatization related speech phenomena. An artificial neural network (ANN) machine learning model was applied to determine the PTSD level and reached a correlation of r = .37. These results indicate that our classifiers can achieve similar results to those seen in speech-based stress research.

Keywords: speech prosody, PTSD, machine learning, feature extraction

Procedia PDF Downloads 70

Authors: Hanifa Taher, Sulaiman Al-Zuhair, Ali H. Al-Marzouqi, Yousef Haik, Mohammed Farid

Abstract:

Biodiesel, as an alternative renewable fuel, has been receiving increasing attention due to the limited supply of fossil fuels and the increasing need for energy. Microalgae is a promising source for lipids, which can be converted to biodiesel. The biodiesel production from microalgae lipids using lipase catalyzed reaction in supercritical CO2 medium has several advantages over conventional production processes. However, identifying the optimum microalgae lipid extraction and transesterification conditions is still a challenge. In this study, the lipids extracted from Scenedesmus sp. and their enzymatic transesterification using supercritical carbon dioxide have been investigated. The effect of extraction variables (temperature, pressure and solvent flow rate) and reaction variables (enzyme loading, incubation time, methanol to lipids molar ratio and temperature) were considered. Process parameters and their effects were studied using a full factorial analysis of both. Response Surface Methodology (RSM) and was used to determine the optimum conditions for the extraction and reaction steps. For extraction, the optimum conditions were 53 °C and 500 bar, whereas for the reaction the optimum conditions were 35% enzyme loading, 4 h reaction, 9:1 molar ratio and 50 oC. At these optimum conditions, the highest biodiesel production yield was found to be 82 %. The fuel properties of the produced biodiesel, at optimum reaction condition, were determined and compared to ASTM standards. The properties were found to comply with the limits, and showed a low glycerol content, without any separation step.

Keywords: biodiesel, lipase, supercritical CO2, standards

Procedia PDF Downloads 466

Authors: Mohammed R. Elkobaisi, Abdelsalam Maatuk

Abstract:

The search engines are the large scale information retrieval tools from the Web that are currently freely available to all. This paper explains how to convert the raw resulted number of search engines into useful information. This represents a new method for data gathering comparing with traditional methods. When a query is submitted for a multiple numbers of keywords, this take a long time and effort, hence we develop a user interface program to automatic search by taking multi-keywords at the same time and leave this program to collect wanted data automatically. The collected raw data is processed using mathematical and statistical theories to eliminate unwanted data and converting it to usable data.

Keywords: search engines, information extraction, agent system

Procedia PDF Downloads 400

Authors: Sivananth Murugesan, I. Regupathi, B. Vishwas Prabhu, Ankit Devatwal, Vishnu Sivan Pillai

Abstract:

Pectinase is an important enzyme which has a wide range of applications including textile processing and bioscouring of cotton fibers, coffee and tea fermentation, purification of plant viruses, oil extraction etc. Selective separation and purification of pectinase from fermentation broth and recover the enzyme form process stream for reuse are cost consuming process in most of the enzyme based industries. It is difficult to identify a suitable medium to enhance enzyme activity and retain its enzyme characteristics during such processes. The cost effective, selective separation of enzymes through the modified Liquid-liquid extraction is of current research interest worldwide. Reverse micellar extraction, globally acclaimed Liquid-liquid extraction technique is well known for its separation and purification of solutes from the feed which offers higher solute specificity and partitioning, ease of operation and recycling of extractants used. Surfactant concentrations above critical micelle concentration to an apolar solvent form micelles and addition of micellar phase to water in turn forms reverse micelles or water-in-oil emulsions. Since, electrostatic interaction plays a major role in the separation/purification of solutes using reverse micelles. These interaction parameters can be altered with the change in pH, addition of cosolvent, surfactant and electrolyte and non-electrolyte. Even though many chemical based commercial surfactant had been utilized for this purpose, the biosurfactants are more suitable for the purification of enzymes which are used in food application. The present work focused on the partitioning of pectinase from the synthetic aqueous solution within the reverse micelle phase formed by a biosurfactant, Soybean Lecithin dissolved in chloroform. The critical micelle concentration of soybean lecithin/chloroform solution was identified through refractive index and density measurements. Effect of surfactant concentrations above and below the critical micelle concentration was considered to study its effect on enzyme activity, enzyme partitioning within the reverse micelle phase. The effect of pH and electrolyte salts on the partitioning behavior was studied by varying the system pH and concentration of different salts during forward and back extraction steps. It was observed that lower concentrations of soybean lecithin enhanced the enzyme activity within the water core of the reverse micelle with maximizing extraction efficiency. The maximum yield of pectinase of 85% with a partitioning coefficient of 5.7 was achieved at 4.8 pH during forward extraction and 88% yield with a partitioning coefficient of 7.1 was observed during backward extraction at a pH value of 5.0. However, addition of salt decreased the enzyme activity and especially at higher salt concentrations enzyme activity declined drastically during both forward and back extraction steps. The results proved that reverse micelles formed by Soybean Lecithin and chloroform may be used for the extraction of pectinase from aqueous solution. Further, the reverse micelles can be considered as nanoreactors to enhance enzyme activity and maximum utilization of substrate at optimized conditions, which are paving a way to process intensification and scale-down.

Keywords: pectinase, reverse micelles, soybean lecithin, selective partitioning

Procedia PDF Downloads 347

Authors: Yang Zhang, Jian He

Abstract:

Heart disease is one of the leading causes of death in the world, and coronary heart disease (CHD) is one of the major heart diseases. Electrocardiogram (ECG) is widely used in the detection of heart diseases, but the traditional manual method for CHD prediction by analyzing ECG requires lots of professional knowledge for doctors. This paper introduces sliding window and continuous wavelet transform (CWT) to transform ECG signals into images, and then ResNet and Bi-LSTM are introduced to build the ECG feature extraction network (namely ECGNet). At last, an auxiliary system for coronary heart disease prediction was developed based on modified ResNet18 and Bi-LSTM, and the public ECG dataset of CHD from MIMIC-3 was used to train and test the system. The experimental results show that the accuracy of the method is 83%, and the F1-score is 83%. Compared with the available methods for CHD prediction based on ECG, such as kNN, decision tree, VGGNet, etc., this method not only improves the prediction accuracy but also could avoid the degradation phenomenon of the deep learning network.

Keywords: Bi-LSTM, CHD, ECG, ResNet, sliding window

Procedia PDF Downloads 61

Authors: Khadri Sihem, Abbaci Nafissa, Zerari Labiba

Abstract:

In the context of the search for new bioactive natural products, we were interested in evaluating some antibacterial properties of two plant extracts: total phenols and flavonoids of Algerian medicinal plant. Our study occurs in two axes: The first concerns the extraction of phenolic compounds and flavonoids with methanol by liquid-liquid extraction, followed by quantification of the levels of these compounds in the end the analysis of the chemical composition of extracts. In the second axis, we studied the antibacterial power of the studied plant extracts.

Keywords: antibacterial activity, flavonoids, medicinal plants, polyphenols

Procedia PDF Downloads 530

Authors: Pajaree Donkhampa, Fuangfa Unob

Abstract:

Ceftazidime is an antibiotic drug commonly used to treat several human and veterinary infections. However, the presence of ceftazidime residues in the environment may induce microbial resistance and cause side effects to humans. Therefore, monitoring the level of ceftazidime in environmental resources is important. In this work, a melamine foam platform was proposed for simultaneous extraction and colorimetric detection of ceftazidime based on the azo dye formation on the surface. The melamine foam was chemically modified with polyethyleneimine (PEI) and characterized by scanning electron microscopy (SEM) and Fourier transform infrared spectroscopy (FTIR). Ceftazidime is a sample that was extracted on the PEI-modified melamine foam and further reacted with nitrite in an acidic medium to form an intermediate diazonium ion. The diazotized molecule underwent an azo coupling reaction with chromotropic acid to generate a red-colored compound. The material color changed from pale yellow to pink depending on the ceftazidime concentration. The photo of the obtained material was taken by a smartphone camera and the color intensity was determined by Image J software. The material fabrication and ceftazidime extraction and detection procedures were optimized. The detection of a sub-ppm level of ceftazidime was achieved without using a complex analytical instrument.

Keywords: colorimetric detection, ceftazidime, melamine foam, extraction, azo dye

Procedia PDF Downloads 152

Authors: Yesim Özogul, Fethiye Takadaş, Mustafa Durmus, Yılmaz Ucar, Ali Rıza Köşker, Gulsun Özyurt, Fatih Özogul

Abstract:

It has been well documented that polyunsaturated fatty acids (PUFAs), especially eicosapentaenoic acid (EPA) and docosahexaenoic acid (DHA) have beneficial effects on health, regarding prevention of cardiovascular diseases, cancer and autoimmune disorders, development the brain and retina and treatment of major depressive disorder etc. Thus, an adequate intake of omega PUFA is essential and generally marine fish are the richest sources of PUFA in human diet. Thus, this study was conducted to evaluate the efficiency of different extraction methods (Bligh and Dyer, soxhlet, microwave and ultrasonics) on the fat content and fatty acid profiles of marine fish species (Mullus babatus, Upeneus moluccensis, Mullus surmuletus, Anguilla anguilla, Pagellus erythrinus and Saurida undosquamis). Fish species were caught by trawl in Mediterranean Sea and immediately iced. After that, fish were transported to laboratory in ice and stored at -18oC in a freezer until the day of analyses. After extracting lipid from fish by different methods, lipid samples were converted to their constituent fatty acid methyl esters. The fatty acid composition was analysed by a GC Clarus 500 with an autosampler (Perkin Elmer, Shelton, CT, USA) equipped with a flame ionization detector and a fused silica capillary SGE column (30 m x 0.32 mm ID x 0.25 mm BP20 0.25 UM, USA). The results showed that there were significant differences (P < 0.05) in fatty acids of all species and also extraction methods affected fat contents and fatty acid profiles of fish species.

Keywords: extraction methods, fatty acids, marine fish, PUFA

Procedia PDF Downloads 240

Authors: Zelalem Fantahun

Abstract:

Part-of-speech tagging is the process of assigning a part-of-speech or other lexical class marker to each word into naturally occurring text. Part-of-speech tagging is the most fundamental and basic task almost in all natural language processing. In natural language processing, the problem of providing large amount of manually annotated data is a knowledge acquisition bottleneck. Since, Amharic is one of under-resourced language, the availability of tagged corpus is the bottleneck problem for natural language processing especially for POS tagging. A promising direction to tackle this problem is to provide a system that does not require manually tagged data. In unsupervised learning, the learner is not provided with classifications. Unsupervised algorithms seek out similarity between pieces of data in order to determine whether they can be characterized as forming a group. This paper explicates the development of unsupervised part-of-speech tagger using K-Means clustering for Amharic language since large amount of data is produced in day-to-day activities. In the development of the tagger, the following procedures are followed. First, the unlabeled data (raw text) is divided into 10 folds and tokenization phase takes place; at this level, the raw text is chunked at sentence level and then into words. The second phase is feature extraction which includes word frequency, syntactic and morphological features of a word. The third phase is clustering. Among different clustering algorithms, K-means is selected and implemented in this study that brings group of similar words together. The fourth phase is mapping, which deals with looking at each cluster carefully and the most common tag is assigned to a group. This study finds out two features that are capable of distinguishing one part-of-speech from others these are morphological feature and positional information and show that it is possible to use unsupervised learning for Amharic POS tagging. In order to increase performance of the unsupervised part-of-speech tagger, there is a need to incorporate other features that are not included in this study, such as semantic related information. Finally, based on experimental result, the performance of the system achieves a maximum of 81% accuracy.

Keywords: POS tagging, Amharic, unsupervised learning, k-means

Procedia PDF Downloads 416

Authors: Mafarja Majdi, Salwani Abdullah, Najmeh S. Jaddi

Abstract:

One of the global combinatorial optimization problems in machine learning is feature selection. It concerned with removing the irrelevant, noisy, and redundant data, along with keeping the original meaning of the original data. Attribute reduction in rough set theory is an important feature selection method. Since attribute reduction is an NP-hard problem, it is necessary to investigate fast and effective approximate algorithms. In this paper, we proposed two feature selection mechanisms based on memetic algorithms (MAs) which combine the genetic algorithm with a fuzzy record to record travel algorithm and a fuzzy controlled great deluge algorithm to identify a good balance between local search and genetic search. In order to verify the proposed approaches, numerical experiments are carried out on thirteen datasets. The results show that the MAs approaches are efficient in solving attribute reduction problems when compared with other meta-heuristic approaches.

Keywords: rough set theory, attribute reduction, fuzzy logic, memetic algorithms, record to record algorithm, great deluge algorithm

Procedia PDF Downloads 424

Authors: Kavyadevi N., Kaviya G., Gowsalya P., Janani M., Mohanraj S.

Abstract:

Hevea brasiliensis, also known as the rubber tree, is one of the foremost assets of crops in the world. One of the most significant advantages of the Rubber Plant in terms of air oxygenation is its capacity to reduce the likelihood of an individual developing respiratory allergies like asthma. To construct such a system that can properly identify crop diseases and pests and then create a database of insecticides for each pest and disease, we must first give treatment for the illness that has been detected. We shall primarily examine three major leaf diseases since they are economically deficient in this article, which is Bird's eye spot, algal spot and powdery mildew. And the recommended work focuses on disease identification on rubber tree leaves. It will be accomplished by employing one of the superior algorithms. Input, Preprocessing, Image Segmentation, Extraction Feature, and Classification will be followed by the processing technique. We will use time-consuming procedures that they use to detect the sickness. As a consequence, the main ailments, underlying causes, and signs and symptoms of diseases that harm the rubber tree are covered in this study.

Keywords: image processing, python, convolution neural network (CNN), machine learning

Procedia PDF Downloads 52

Authors: Ihsan Burak Cam, Ferhan Balci-Torun, Ayhan Topuz, Esin Ari, Ismail Gokhan Deniz, Ilker Genc

Abstract:

The seeds of Vaccaria hispanica have been used in food and pharmaceutical industry. It is an important product due to its superior starch granules, triterpenic saponins, and cyclopeptides suitable for drug delivery. V. hispanica naturally grows in different climatic regions and has genotypes that differ in terms of seed content and composition. Sixty-six V. hispanica seed specimens were collected based on the representation of the distribution in all regions of Turkey and the determination of possible genotypic differences between regions. The seeds, collected from each of the 66 locations, were grown in greenhouse conditions in Akdeniz University, Antalya. Saponin and cyclopeptide contents of the V. hispanica seeds were determined after harvest. Accelerated solvent extraction (ASE) was applied for the extraction of saponins and cyclopeptides. Cyclopeptide (segetalin A) and saponin content of V. hispanica seeds were found in the range of 0.165-0.654 g/100 g and 0.15-1.14 g/100 g, respectively. The results were found to be promising for the seeds from Turkey in terms of saponin content and quality. Acknowledgment: This study was supported by the Scientific and Research Council of Turkey (TUBITAK) (project no 112 O 136).

Keywords: Vaccaria hispanica, saponin, cyclopeptid, cow cockle seeds

Procedia PDF Downloads 264

Authors: Swapnil A. Dharaskar, Kailas L. Wasewar, Mahesh N. Varma, Diwakar Z. Shende

Abstract:

Owing to the stringent environmental regulations in many countries for production of ultra low sulfur petroleum fractions intending to reduce sulfur emissions results in enormous interest in this area among the scientific community. The requirement of zero sulfur emissions enhances the prominence for more advanced techniques in desulfurization. Desulfurization by extraction is a promising approach having several advantages over conventional hydrodesulphurization. Present work is dealt with various new approaches for desulfurization of ultra clean gasoline, diesel and other liquid fuels by extraction with ionic liquids. In present paper experimental data on extractive desulfurization of liquid fuel using trihexyl tetradecyl phosphonium chloride has been presented. The FTIR, 1H-NMR, and 13C-NMR have been discussed for the molecular confirmation of synthesized ionic liquid. Further, conductivity, solubility, and viscosity analysis of ionic liquids were carried out. The effects of reaction time, reaction temperature, sulfur compounds, ultrasonication, and recycling of ionic liquid without regeneration on removal of dibenzothiphene from liquid fuel were also investigated. In extractive desulfurization process, the removal of dibenzothiophene in n-dodecane was 84.5% for mass ratio of 1:1 in 30 min at 30OC under the mild reaction conditions. Phosphonium ionic liquids could be reused five times without a significant decrease in activity. Also, the desulfurization of real fuels, multistage extraction was examined. The data and results provided in present paper explore the significant insights of phosphonium based ionic liquids as novel extractant for extractive desulfurization of liquid fuels.

Keywords: ionic liquid, PPIL, desulfurization, liquid fuel, extraction

Procedia PDF Downloads 588

Authors: Krishan Kumar, Mohit Mittal, Pramod Kumar

Abstract:

Wireless sensor network is one of the most promising communication networks for monitoring remote environmental areas. In this network, all the sensor nodes are communicated with each other via radio signals. The sensor nodes have capability of sensing, data storage and processing. The sensor nodes collect the information through neighboring nodes to particular node. The data collection and processing is done by data aggregation techniques. For the data aggregation in sensor network, clustering technique is implemented in the sensor network by implementing self-organizing feature map (SOFM) neural network. Some of the sensor nodes are selected as cluster head nodes. The information aggregated to cluster head nodes from non-cluster head nodes and then this information is transferred to base station (or sink nodes). The aim of this paper is to manage the huge amount of data with the help of SOM neural network. Clustered data is selected to transfer to base station instead of whole information aggregated at cluster head nodes. This reduces the battery consumption over the huge data management. The network lifetime is enhanced at a greater extent.

Keywords: artificial neural network, data clustering, self organization feature map, wireless sensor network

Procedia PDF Downloads 488

Authors: Neziha Jaouedi, Noureddine Boujnah, Mohamed Salim Bouhlel

Abstract:

In the framework of human machine interaction systems enhancement, we focus throw this paper on human behavior analysis and action recognition. Human behavior is characterized by actions and reactions duality (movements, psychological modification, verbal and emotional expression). It’s worth noting that many information is hidden behind gesture, sudden motion points trajectories and speeds, many research works reconstructed an information retrieval issues. In our work we will focus on motion extraction, tracking and action recognition using wavelet network approaches. Our contribution uses an analysis of human subtraction by Gaussian Mixture Model (GMM) and body movement through trajectory models of motion constructed from kalman filter. These models allow to remove the noise using the extraction of the main motion features and constitute a stable base to identify the evolutions of human activity. Each modality is used to recognize a human action using wavelets of derived beta distributions approach. The proposed approach has been validated successfully on a subset of KTH and UCF sports database.

Keywords: feautures extraction, human action classifier, wavelet neural network, beta wavelet

Procedia PDF Downloads 386

Authors: Chakkrit Poonpakdee, Jing-Hua Tzen, Ya-Zhen Huang, Yao-Tung Lin

Abstract:

Potassium (K) is a known macro nutrient and essential element for plant growth. Single leaching and modified sequential extraction schemes have been developed to estimate the relative phase associations of soil samples. The sequential extraction process is a step in analyzing the partitioning of metals affected by environmental conditions, but it is not a tool for estimation of K bioavailability. While, traditional single leaching method has been used to classify K speciation for a long time, it depend on its availability to the plants and use for potash fertilizer recommendation rate. Clay mineral in soil is a factor for controlling soil fertility. The change of the micro-structure of clay minerals during various environment (i.e. swelling or shrinking) is characterized using Transmission X-Ray Microscopy (TXM). The objective of this study are to 1) compare the distribution of K speciation between single leaching and sequential extraction process 2) determined clay particle flocculation structure before/after suspension with K+ using TXM. Four tropical soil samples: farming without K fertilizer (10 years), long term applied K fertilizer (10 years; 168-240 kg K2O ha-1 year-1), red soil (450-500 kg K2O ha-1 year-1) and forest soil were selected. The results showed that the amount of K speciation by single leaching method were high in mineral K, HNO3 K, Non-exchangeable K, NH4OAc K, exchangeable K and water soluble K respectively. Sequential extraction process indicated that most K speciations in soil were associated with residual, organic matter, Fe or Mn oxide and exchangeable fractions and K associate fraction with carbonate was not detected in tropical soil samples. In farming long term applied K fertilizer and red soil were higher exchangeable K than farming long term without K fertilizer and forest soil. The results indicated that one way to increase the available K (water soluble K and exchangeable K) should apply K fertilizer and organic fertilizer for providing available K. The two-dimension of TXM image of clay particles suspension with K+ shows that the aggregation structure of clay mineral closed-void cellular networks. The porous cellular structure of soil aggregates in 1 M KCl solution had large and very larger empty voids than in 0.025 M KCl and deionized water respectively. TXM nanotomography is a new technique can be useful in the field as a tool for better understanding of clay mineral micro-structure.

Keywords: potassium, sequential extraction process, clay mineral, TXM

Procedia PDF Downloads 263

Authors: Shashikant R. Kuchekar, Shivaji D. Pulate, Vishwas B. Gaikwad

Abstract:

A simple and selective method is developed for solvent extraction spectrophotometric determination of antimony(III) using O-Methylphenyl Thiourea (OMPT) as a sensitive chromogenic chelating agent. The basis of proposed method is formation of antimony(III)-OMPT complex was extracted with 0.0025 M OMPT in chloroform from aqueous solution of antimony(III) in 1.0 M perchloric acid. The absorbance of this complex was measured at 297 nm against reagent blank. Beer’s law was obeyed up to 15µg mL-1 of antimony(III). The Molar absorptivity and Sandell’s sensitivity of the antimony(III)-OMPT complex in chloroform are 16.6730 × 103 L mol-1 cm-1 and 0.00730282 µg cm-2 respectively. The stoichiometry of antimony(III)-OMPT complex was established from slope ratio method, mole ratio method and Job’s continuous variation method was 1:2. The complex was stable for more than 48 h. The interfering effect of various foreign ions was studied and suitable masking agents are used wherever necessary to enhance selectivity of the method. The proposed method is successfully applied for determination of antimony(III) from real samples alloy and synthetic mixtures. Repetition of the method was checked by finding relative standard deviation (RSD) for 10 determinations which was 0.42%.

Keywords: solvent extraction, antimony, spectrophotometry, real sample analysis

Procedia PDF Downloads 312

Authors: Violina Angelova, Stefan Krustev

Abstract:

The aim of this work was to evaluate the effectiveness of different soil test extractants for the determination of available soil phosphorus in five internationally certified standard soils, sludge and clay (NCS DC 85104, NCS DC 85106, ISE 859, ISE 952, ISE 998). The certified samples were extracted with the following methods/extractants: CaCl₂, CaCl₂ and DTPA (CAT), double lactate (DL), ammonium lactate (AL), calcium acetate lactate (CAL), Olsen, Mehlich 3, Bray and Kurtz I, and Morgan, which are commonly used in soil testing laboratories. The phosphorus in soil extracts was measured colorimetrically using Spectroquant Pharo 100 spectrometer. The methods used in the study were evaluated according to the recovery of available phosphorus, facility of application and rapidity of performance. The relationships between methods are examined statistically. A good agreement of the results from different soil test was established for all certified samples. In general, the P values extracted by the nine extraction methods significantly correlated with each other. When grouping the soils according to pH, organic carbon content and clay content, weaker extraction methods showed analogous trends; also among the stronger extraction methods, common tendencies were found. Other factors influencing the extraction force of the different methods include soil: solution ratio, as well as the duration and power of shaking the samples. The mean extractable P in certified samples was found to be in the order of CaCl₂ < CAT < Morgan < Bray and Kurtz I < Olsen < CAL < DL < Mehlich 3 < AL. Although the nine methods extracted different amounts of P from the certified samples, values of P extracted by the different methods were strongly correlated among themselves. Acknowledgment: The financial support by the Bulgarian National Science Fund Projects DFNI Н04/9 and DFNI Н06/21 are greatly appreciated.

Keywords: available soil phosphorus, certified samples, determination, soil test extractants

Procedia PDF Downloads 121

Authors: Eman Alzahrani

Abstract:

Efficient extraction of proteins by removing interfering materials is necessary in proteomics, since most instruments cannot handle such contaminated sample matrices directly. In this study, chitosan-coated magnetic nanoparticles (CS-MNPs) for purification of myoglobin were successfully fabricated. First, chitosan (CS) was prepared by a deacetylation reaction during its extraction from shrimp-shell waste. Second, magnetic nanoparticles (MNPs) were synthesised, using the coprecipitation method, from aqueous Fe2+ and Fe3+ salt solutions by the addition of a base under an inert atmosphere, followed by modification of the surface of MNPs with chitosan. The morphology of the formed nanoparticles, which were about 23 nm in average diameter, was observed by transmission electron microscopy (TEM). In addition, nanoparticles were characterised using X-ray diffraction patterns (XRD), which showed the naked magnetic nanoparticles have a spinel structure and the surface modification did not result in phase change of the Fe3O4. The coating of MNPs was also demonstrated by scanning electron microscopy (SEM) analysis, energy dispersive analysis of X-ray spectroscopy (EDAX), and Fourier transform infrared (FT-IR) spectroscopy. The adsorption behaviour of MNPs and CS-MNPs towards myoglobin was investigated. It was found that the difference in adsorption capacity between MNPs and CS-MNPs was larger for CS-MNPs. This result makes CS-MNPs good adsorbents and attractive for using in protein extraction from biological samples.

Keywords: chitosan, magnetic nanoparticles, coprecipitation, adsorption

Procedia PDF Downloads 391

Authors: Seyed-Yaser Nabavi-Chashmi, Davood Asadi, Karim Ahmadi, Eren Demir

Abstract:

The landing phase of a UAV is very critical as there are many uncertainties in this phase, which can easily entail a hard landing or even a crash. In this paper, the estimation of relative distance and velocity to the ground, as one of the most important processes during the landing phase, is studied. Using accurate measurement sensors as an alternative approach can be very expensive for sensors like LIDAR, or with a limited operational range, for sensors like ultrasonic sensors. Additionally, absolute positioning systems like GPS or IMU cannot provide distance to the ground independently. The focus of this paper is to determine whether we can measure the relative distance and velocity of UAV and ground in the landing phase using just low-resolution images taken by a monocular camera. The Lucas-Konda feature detection technique is employed to extract the most suitable feature in a series of images taken during the UAV landing. Two different approaches based on Extended Kalman Filters (EKF) have been proposed, and their performance in estimation of the relative distance and velocity are compared. The first approach uses the kinematics of the UAV as the process and the calculated optical flow as the measurement; On the other hand, the second approach uses the feature’s projection on the camera plane (pixel position) as the measurement while employing both the kinematics of the UAV and the dynamics of variation of projected point as the process to estimate both relative distance and relative velocity. To verify the results, a sequence of low-quality images taken by a camera that is moving on a specifically developed testbed has been used to compare the performance of the proposed algorithm. The case studies show that the quality of images results in considerable noise, which reduces the performance of the first approach. On the other hand, using the projected feature position is much less sensitive to the noise and estimates the distance and velocity with relatively high accuracy. This approach also can be used to predict the future projected feature position, which can drastically decrease the computational workload, as an important criterion for real-time applications.

Keywords: altitude estimation, drone, image processing, trajectory planning

Procedia PDF Downloads 90

Authors: Mohammed M. Algaradah

Abstract:

A chelating mercapto- nanoscavenger has been developed exploiting the high surface area of monodisperse nano-sized mesoporous silica. The nanoscavenger acts as a solid phase trace metal extractant whilst suspended as a quasi-stable sol in aqueous samples. This mode of extraction requires no external agitation as the particles move naturally through the sample by Brownian motion, convection and slow sedimentation. Careful size selection enables the nanoscavenger to be easily recovered together with the extracted analyte by conventional filtration or centrifugation. The research describes the successful attachment of chelator mercapto to ca. 136 ± 15 nm high surface area (BET surface area = 1006 m2 g-1) mesoporous silica particles. The resulting material had a copper capacity of ca. 1.34 ± 0.10 mmol g-1 and was successfully applied to the collection of a trace element from water. Essentially complete recovery of Cu (II) has been achieved from freshwater samples giving typical preconcentration factors of 100 from 50 µg/l samples. Data obtained from a nanoscavenger-based extraction of copper from samples were not significantly different from those obtained by using a conventional colorimetric procedure employing complexation/solvent extraction.

Keywords: nano scavenger, mesoporous silica, trace metal, preconcentration

Procedia PDF Downloads 62

Authors: Yin Yuanling

Abstract:

A Deep Feedback Recurrent Neural Network (DFRNN) and Bidirectional Long Short-Term Memory (BiLSTM) are designed to address the problem of low accuracy of traditional relationship extraction models. This method combines a deep feedback-based recurrent neural network (DFRNN) with a bi-directional long short-term memory (BiLSTM) approach. The method combines DFRNN, which extracts local features of text based on deep feedback recurrent mechanism, BiLSTM, which better extracts global features of text, and Self-Attention, which extracts semantic information. Experiments show that the method achieves an F1 value of 76.69% on the CEC dataset, which is 0.0652 better than the BiLSTM+Self-ATT model, thus optimizing the performance of the deep learning method in the event relationship extraction task.

Keywords: event relations, deep learning, DFRNN models, bi-directional long and short-term memory networks

Procedia PDF Downloads 104

Authors: Khadijat T. Bamigbade, Olufade F. W. Onifade

Abstract:

The field of automatic facial expression analysis has been an active research area in the last two decades. Its vast applicability in various domains has drawn so much attention into developing techniques and dataset that mirror real life scenarios. Many techniques such as Local Binary Patterns and its variants (CLBP, LBP-TOP) and lately, deep learning techniques, have been used for facial expression recognition. However, the problem of occlusion has not been sufficiently handled, making their results not applicable in real life situations. This paper develops a simple, yet highly efficient method tagged Local Binary Pattern-Histogram of Gradient (LBP-HOG) with occlusion detection in face image, using a multi-class SVM for Action Unit and in turn expression recognition. Our method was evaluated on three publicly available datasets which are JAFFE, CK, SFEW. Experimental results showed that our approach performed considerably well when compared with state-of-the-art algorithms and gave insight to occlusion detection as a key step to handling expression in wild.

Keywords: automatic facial expression analysis, local binary pattern, LBP-HOG, occlusion detection

Procedia PDF Downloads 146