Search results for: synthetic dataset

Authors: Assel Jaxylykova, Alexnder Pak

Abstract:

This study utilized a Self-Organizing Map (SOM) for unsupervised learning on the CONLL-2003 dataset for Named Entity Recognition (NER). The process involved encoding words into 300-dimensional vectors using FastText. These vectors were input into a SOM grid, where training adjusted node weights to minimize distances. The SOM provided a topological representation for identifying and clustering named entities, demonstrating its efficacy without labeled examples. Results showed an F1-measure of 0.86, highlighting SOM's viability. Although some methods achieve higher F1 measures, SOM eliminates the need for labeled data, offering a scalable and efficient alternative. The SOM's ability to uncover hidden patterns provides insights that could enhance existing supervised methods. Further investigation into potential limitations and optimization strategies is suggested to maximize benefits.

Keywords: named entity recognition, natural language processing, self-organizing map, CONLL-2003, semantics

Procedia PDF Downloads 45

Authors: Nassib Abdallah, Pierre Chauvet, Abd El Salam Hajjar, Bassam Daya

Abstract:

In this paper, we propose an optimized brain computer interface (BCI) system for unspoken speech recognition, based on the fact that the constructions of unspoken words rely strongly on the Wernicke area, situated in the temporal lobe. Our BCI system has four modules: (i) the EEG Acquisition module based on a non-invasive headset with 14 electrodes; (ii) the Preprocessing module to remove noise and artifacts, using the Common Average Reference method; (iii) the Features Extraction module, using Wavelet Packet Transform (WPT); (iv) the Classification module based on a one-hidden layer artificial neural network. The present study consists of comparing the recognition accuracy of 5 Arabic words, when using all the headset electrodes or only the 4 electrodes situated near the Wernicke area, as well as the selection effect of the subbands produced by the WPT module. After applying the articial neural network on the produced database, we obtain, on the test dataset, an accuracy of 83.4% with all the electrodes and all the subbands of 8 levels of the WPT decomposition. However, by using only the 4 electrodes near Wernicke Area and the 6 middle subbands of the WPT, we obtain a high reduction of the dataset size, equal to approximately 19% of the total dataset, with 67.5% of accuracy rate. This reduction appears particularly important to improve the design of a low cost and simple to use BCI, trained for several words.

Keywords: brain-computer interface, speech recognition, artificial neural network, electroencephalography, EEG, wernicke area

Procedia PDF Downloads 270

Authors: Pei-Chann Chang, Jhen-Fu Liao, Chin-Hung Teng, Meng-Hui Chen

Abstract:

This research combines artificial immune system with user and item based collaborative filtering to create an efficient and accurate recommendation system. By applying the characteristic of antibodies and antigens in the artificial immune system and using Pearson correlation coefficient as the affinity threshold to cluster the data, our collaborative filtering can effectively find useful users and items for rating prediction. This research uses MovieLens dataset as our testing target to evaluate the effectiveness of the algorithm developed in this study. The experimental results show that the algorithm can effectively and accurately predict the movie ratings. Compared to some state of the art collaborative filtering systems, our system outperforms them in terms of the mean absolute error on the MovieLens dataset.

Keywords: artificial immune system, collaborative filtering, recommendation system, similarity

Procedia PDF Downloads 535

Authors: Rajkumar Kolangarakandy

Abstract:

Feature extraction and selection is the primary part of any mammogram classification algorithms. The choice of feature, attribute or measurements have an important influence in any classification system. Discrete Wavelet Transformation (DWT) coefficients are one of the prominent features for representing images in frequency domain. The features obtained after the decomposition of the mammogram images using wavelet transformations have higher dimension. Even though the features are higher in dimension, they were highly correlated and redundant in nature. The dimensionality reduction techniques play an important role in selecting the optimum number of features from the higher dimension data, which are highly correlated. PCA is a mathematical tool that reduces the dimensionality of the data while retaining most of the variation in the dataset. In this paper, a multilevel classification of mammogram images using reduced discrete wavelet transformation coefficients and lazy classifiers is proposed. The classification is accomplished in two different levels. In the first level, mammogram ROIs extracted from the dataset is classified as normal and abnormal types. In the second level, all the abnormal mammogram ROIs is classified into benign and malignant too. A further classification is also accomplished based on the variation in structure and intensity distribution of the images in the dataset. The Lazy classifiers called Kstar, IBL and LWL are used for classification. The classification results obtained with the reduced feature set is highly promising and the result is also compared with the performance obtained without dimension reduction.

Keywords: PCA, wavelet transformation, lazy classifiers, Kstar, IBL, LWL

Procedia PDF Downloads 335

Authors: Mirza Adil Ahmad Mughal

Abstract:

Transcendental analytics, in the critique of pure reason, combines space and time as conditions of the possibility of the phenomenon from the transcendental aesthetic with the pure magnitude-intuition notion. The property of continuity as a qualitative result of the additive magnitude brings the possibility of connecting with experience, even though only as a potential because of the a priori necessity from assumption, as syntheticity of the a priori task of a scientific method of philosophy given by Kant, which precludes the application of categories to something not empirically reducible to the content of such a category's corresponding and possible object. This continuity as the qualitative result of a priori constructed notion of magnitude lies as a fundamental assumption and property of, what in Microeconomic theory is called as, 'choice rules' which combine the potentially-empirical and practical budget-price pairs with preference relations. This latter result is the purest qualitative side of the choice rules', otherwise autonomously, quantitative nature. The theoretical, barring the empirical, nature of this qualitative result is a synthetic a priori truth, which, if at all, it should be, if the axiomatic structure of the economic theory is held to be correct. It has a potentially verifiable content as its possible object in the form of quantitative price-budget pairs. Yet, the object that serves the respective Kantian category is qualitative itself, which is utility. This article explores the validity of Kantian qualifications for this application of 'categories' to the economic structure of society.

Keywords: categories of understanding, continuity, convexity, psyche, revealed preferences, synthetic a priori

Procedia PDF Downloads 98

Authors: Cam Nguyen

Abstract:

Rapid, accurate, and safe sensing and imaging of physical quantities or structures finds many applications and is of significant interest to society. Sensing and imaging using radio-frequency (RF) techniques, particularly, has gone through significant development and subsequently established itself as a unique territory in the sensing world. RF sensing and imaging has played a critical role in providing us many sensing and imaging abilities beyond our human capabilities, benefiting both civilian and military applications - for example, from sensing abnormal conditions underneath some structures’ surfaces to detection and classification of concealed items, hidden activities, and buried objects. We present the developments of several sensing and imaging systems implementing RF technologies like ultra-wide band (UWB), synthetic-pulse, and interferometry. These systems are fabricated completely using RF integrated circuits. The UWB impulse system operates over multiple pulse durations from 450 to 1170 ps with 5.5-GHz RF bandwidth. It performs well through tests of various samples, demonstrating its usefulness for subsurface sensing. The synthetic-pulse system operating from 0.6 to 5.6 GHz can assess accurately subsurface structures. The synthetic-pulse system operating from 29.72-37.7 GHz demonstrates abilities for various surface and near-surface sensing such as profile mapping, liquid-level monitoring, and anti-personnel mine locating. The interferometric system operating at 35.6 GHz demonstrates its multi-functional capability for measurement of displacements and slow velocities. These RF sensors are attractive and useful for various surface and subsurface sensing applications. This paper was made possible by NPRP grant # 6-241-2-102 from the Qatar National Research Fund (a member of Qatar Foundation). The statements made herein are solely the responsibility of the authors.

Keywords: RF sensors, radars, surface sensing, subsurface sensing

Procedia PDF Downloads 316

Authors: Gherbi Nabil

Abstract:

Detection of ground targets in SAR radar images is an important area for radar information processing. In the literature, various algorithms have been discussed in this context. However, most of them are of low robustness and accuracy. To this end, we discuss target detection in SAR images based on compressive sensing. Firstly, traditional SAR image target detection algorithms are discussed, and their limitations are highlighted. Secondly, a compressive sensing method is proposed based on the sparsity of SAR images. Next, the detection problem is solved using Multiple Measurements Vector configuration. Furthermore, a robust Alternating Direction Method of Multipliers (ADMM) is developed to solve the optimization problem. Finally, the detection results obtained using raw complex data are presented. Experimental results on real SAR images have verified the effectiveness of the proposed algorithm.

Keywords: compressive sensing, raw complex data, synthetic aperture radar, ADMM

Procedia PDF Downloads 18

Authors: Mehrnoosh Omati, Mahmod Reza Sahebi

Abstract:

The information on land use/land cover changing plays an essential role for environmental assessment, planning and management in regional development. Remotely sensed imagery is widely used for providing information in many change detection applications. Polarimetric Synthetic aperture radar (PolSAR) image, with the discrimination capability between different scattering mechanisms, is a powerful tool for environmental monitoring applications. This paper proposes a new boundary-based segmentation algorithm as a fundamental step for land cover change detection. In this method, first, two PolSAR images are segmented using integration of marker-controlled watershed algorithm and coupled Markov random field (MRF). Then, object-based classification is performed to determine changed/no changed image objects. Compared with pixel-based support vector machine (SVM) classifier, this novel segmentation algorithm significantly reduces the speckle effect in PolSAR images and improves the accuracy of binary classification in object-based level. The experimental results on Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) polarimetric images show a 3% and 6% improvement in overall accuracy and kappa coefficient, respectively. Also, the proposed method can correctly distinguish homogeneous image parcels.

Keywords: coupled Markov random field (MRF), environment, object-based analysis, polarimetric SAR (PolSAR) images

Procedia PDF Downloads 217

Authors: Rida Nasir, Waseem Iqbal

Abstract:

Due to the constant revolution in technology and the increase in anti-forensic techniques used by attackers to remove their traces, professionals often struggle to choose the best tool to be used in digital forensic investigations. This paper compares two of the most well-known and widely used licensed commercial tools, i.e., Encase & FTK. The comparison was drawn on various parameters and features to provide an authentic evaluation of licensed versions of these well-known commercial tools against various real-world scenarios. In order to discover the popularity of these tools within the digital forensic community, a survey was conducted publicly to determine the preferred choice. The dataset used is the Computer Forensics Reference Dataset (CFReDS). A total of 70 features were selected from various categories. Upon comparison, both FTK and EnCase produce remarkable results. However, each tool has some limitations, and none of the tools is declared best. The comparison drawn is completely unbiased, based on factual data.

Keywords: digital forensics, commercial tools, investigation, forensic evaluation

Procedia PDF Downloads 19

Authors: Charline David, Alexandre Blondin Massé, Arnaud Zinflou

Abstract:

In 2016, Clements, Hurn, and Li proposed a multiple equation time series approach for the short-term load forecasting, reporting an average mean absolute percentage error (MAPE) of 1.36% on an 11-years dataset for the Queensland region in Australia. We present an adaptation of their model to the electrical power load consumption for the whole Quebec province in Canada. More precisely, we take into account two additional meteorological variables — cloudiness and wind speed — on top of temperature, as well as the use of multiple meteorological measurements taken at different locations on the territory. We also consider other minor improvements. Our final model shows an average MAPE score of 1:79% over an 8-years dataset.

Keywords: short-term load forecasting, special days, time series, multiple equations, parallelization, clustering

Procedia PDF Downloads 103

Authors: Tanwi Priya, Brijesh Kumar Mishra

Abstract:

Occurrence of aromatic fractions of Natural Organic Matter (NOM) led to formation of carcinogenic disinfection by products such as trihalomethanes in chlorinated water. In the present study, the efficiency of aluminium based electrocoagulation on the removal of prominent aromatic groups such as phenol, hydrophobic auxochromes, and carboxyl groups from NOM enriched synthetic water has been evaluated using various spectral indices. The effect of electrocoagulation on turbidity has also been discussed. The variation in coagulation performance as a function of pH has been studied. Our result suggests that electrocoagulation can be considered as appropriate remediation approach to reduce trihalomethanes formation in water. It has effectively reduced hydrophobic fractions from NOM enriched low turbid water. The charge neutralization and enmeshment of dispersed colloidal particles inside metallic hydroxides is the possible mechanistic approach in electrocoagulation.

Keywords: aromatic fractions, electrocoagulation, natural organic matter, spectral indices

Procedia PDF Downloads 277

Authors: Tooba Aslam, Efthalia Chatzisymeon

Abstract:

Untreated Municipal Wastewater (MWW) is renowned as the utmost harmful pollution caused to environmental water due to the high presence of nutrients and organic contaminants. Removal of Chemical Oxygen Demand (COD) from synthetic as well as municipal wastewater is investigated by using acid mine drainage as a source of iron to initiate the solar photo-Fenton treatment of municipal wastewater. In this study, Acid Mine Drainage (AMD) and different minerals enriched in iron, such as goethite, hematite, magnetite, and magnesite, have been used as the source of iron to initiate the photo-Fenton process. Co-treatment of real municipal wastewater and acid mine drainage /minerals is widely examined. The effects of different parameters such as minerals recovery from AMD, AMD as a source of iron, H₂O₂ concentration, and COD concentrations on the COD percentage removal of the process are studied. The results show that, out of all the four minerals, only hematite (1g/L) could remove 30% of the pollutants at about 100 minutes and 1000 ppm of H₂O₂. The addition of AMD as a source of iron is performed and compared with both synthetic as well as real wastewater from South Africa under the same conditions, i.e., 1000 ppm of H₂O₂, ambient temperature, 2.8 pH, and solar simulator. In the case of synthetic wastewater, the maximum removal (56%) is achieved with 50 ppm of iron (AMD source) at 160 minutes. On the other hand, in real wastewater, the removal efficiency is 99% with 30 ppm of iron at 90 minutes and 96% with 50 ppm of iron at 120 minutes. In conclusion, overall, the co-treatment of AMD and MWW by solar photo-Fenton treatment appears to be an effective and promising method to remove organic materials from Municipal wastewater.

Keywords: municipal wastewater treatment, acid mine drainage, co-treatment, COD removal, solar photo-Fenton, circular economy

Procedia PDF Downloads 88

Authors: Plessen Mogens Graf

Abstract:

Within the context of multivariate time series segmentation, this paper proposes a method inspired by a posteriori optimal trading. After a normalization step, time series are treated channelwise as surrogate stock prices that can be traded optimally a posteriori in a virtual portfolio holding either stock or cash. Linear transaction costs are interpreted as hyperparameters for noise filtering. Trading signals, as well as trading signals obtained on the reversed time series, are used for unsupervised channelwise labeling before a consensus over all channels is reached that determines the final segmentation time instants. The method is model-free such that no model prescriptions for segments are made. Benefits of proposed approach include simplicity, computational efficiency, and adaptability to a wide range of different shapes of time series. Performance is demonstrated on synthetic and real-world data, including a large-scale dataset comprising a multivariate time series of dimension 1000 and length 2709. Proposed method is compared to a popular model-based bottom-up approach fitting piecewise affine models and to a recent model-based top-down approach fitting Gaussian models and found to be consistently faster while producing more intuitive results in the sense of segmenting time series at peaks and valleys.

Keywords: time series segmentation, model-free, trading-inspired, multivariate data

Procedia PDF Downloads 136

Authors: Walid Cherif

Abstract:

Data mining has, over recent years, seen big advances because of the spread of internet, which generates everyday a tremendous volume of data, and also the immense advances in technologies which facilitate the analysis of these data. In particular, classification techniques are a subdomain of Data Mining which determines in which group each data instance is related within a given dataset. It is used to classify data into different classes according to desired criteria. Generally, a classification technique is either statistical or machine learning. Each type of these techniques has its own limits. Nowadays, current data are becoming increasingly heterogeneous; consequently, current classification techniques are encountering many difficulties. This paper defines new measure functions to quantify the resemblance between instances and then combines them in a new approach which is different from actual algorithms by its reliability computations. Results of the proposed approach exceeded most common classification techniques with an f-measure exceeding 97% on the IRIS Dataset.

Keywords: data mining, knowledge discovery, machine learning, similarity measurement, supervised classification

Procedia PDF Downloads 464

Authors: Won Young Choi, Kwan Kyu Park

Abstract:

Recently, the road depression happening in the urban area is different from the cause of the sink hole and the generation mechanism occurring in the limestone area. The main cause of sinkholes occurring in the city center is the loss of soil due to the damage of old underground buried materials and groundwater discharge due to large underground excavation works. The method of detecting the sinkhole in the urban area is mostly using the Ground Penetration Radar (GPR). However, it is challenging to implement compact system and detecting watery state since it is based on electromagnetic waves. Although many ultrasonic underground detection studies have been conducted, near-ground detection (several tens of cm to several meters) has been developed for bulk systems using geophones as a receiver. The goal of this work is to fabricate a miniaturized sinkhole detecting system based on low-cost ultrasonic transducers of 40 kHz resonant frequency with high transmission pressure and receiving sensitivity. Motived by biomedical ultrasonic imaging methods, we detect air layers below the ground such as asphalt through the pulse-echo method. To improve image quality using multi-channel, linear array system is implemented, and image is acquired by classical synthetic aperture imaging method. We present the successful feasibility test of multi-channel sinkhole detector based on ultrasonic transducer. In this work, we presented and analyzed image results which are imaged by single channel pulse-echo imaging, synthetic aperture imaging.

Keywords: road depression, sinkhole, synthetic aperture imaging, ultrasonic transducer

Procedia PDF Downloads 144

Authors: Sagheer A. Onaizi

Abstract:

The adsorption of anionic biosurfactant (surfactin) and anionic synthetic surfactant (sodium dodecylbenzenesulphonate, abbreviated as SDOBS) from phosphate buffer containing high concentrations of co- and counter-ions to the air-buffer interface has been investigated. The self-assembly of the two surfactants at the interface has been monitored through dynamic surface tension measurements. The equilibrium surface pressure-surfactant concentration data in the premicellar region were regressed using Gibbs adsorption equation. The predicted surface saturations for SDOBS and surfactin are and, respectively. The occupied area per an SDOBS molecule at the interface saturation condition is while that occupied by a surfactin molecule is. The surface saturations reported in this work for both surfactants are in a very good agreement with those obtained using expensive techniques such as neutron reflectometry, suggesting that the surface tension measurements coupled with appropriate theoretical analysis could provide useful information comparable to those obtained using highly sophisticated techniques.

Keywords: adsorption, air-liquid interface, biosurfactant, surface tension

Procedia PDF Downloads 713

Authors: Ksheeraj Sai Vepuri, Nada Attar

Abstract:

We as humans use words with accompanying visual and facial cues to communicate effectively. Classifying facial emotion using computer vision methodologies has been an active research area in the computer vision field. In this paper, we propose a simple method for facial expression recognition that enhances accuracy. We tested our method on the FER-2013 dataset that contains static images. Instead of using Histogram equalization to preprocess the dataset, we used Unsharp Mask to emphasize texture and details and sharpened the edges. We also used ImageDataGenerator from Keras library for data augmentation. Then we used Convolutional Neural Networks (CNN) model to classify the images into 7 different facial expressions, yielding an accuracy of 69.46% on the test set. Our results show that using image preprocessing such as the sharpening technique for a CNN model can improve the performance, even when the CNN model is relatively simple.

Keywords: facial expression recognittion, image preprocessing, deep learning, CNN

Procedia PDF Downloads 143

Authors: Gabriele Borg, Alexei De Bono, Charlie Abela

Abstract:

There on a constant rise in the availability of high volumes of data gathered from multiple sources, resulting in an abundance of unprocessed information that can be used to monitor patterns and trends in user behaviour. Similarly, year after year, Malta is also constantly experiencing ongoing population growth and an increase in mobilization demand. This research takes advantage of data which is continuously being sourced and converting it into useful information related to the traffic problem on the Maltese roads. The scope of this paper is to provide a methodology to create a custom dataset (MalTra - Malta Traffic) compiled from multiple participants from various locations across the island to identify the most common routes taken to expose the main areas of activity. This use of big data is seen being used in various technologies and is referred to as ITSs (Intelligent Transportation Systems), which has been concluded that there is significant potential in utilising such sources of data on a nationwide scale.

Keywords: Big Data, vehicular traffic, traffic management, mobile data patterns

Procedia PDF Downloads 109

Authors: Tonislav Ivanov, Oleksii Nedashkivskyi, Denis Babeshko, Vadim Pinskiy, Matthew Putman

Abstract:

Training a machine learning model for object detection that generalizes well is known to benefit from a training dataset with diverse examples. However, training datasets usually contain many repeats of common examples of a class and lack rarely seen examples. This is due to the process commonly used during human annotation where a person would proceed sequentially through a list of images labeling a sufficiently high total number of examples. Instead, the method presented involves an active process where, after the initial labeling of several images is completed, the next subset of images for labeling is selected by an algorithm. This process of algorithmic image selection and manual labeling continues in an iterative fashion. The algorithm used for the image selection is a deep learning algorithm, based on the U-shaped architecture, which quantifies the presence of unseen data in each image in order to find images that contain the most novel examples. Moreover, the location of the unseen data in each image is highlighted, aiding the labeler in spotting these examples. Experiments performed using semiconductor wafer data show that labeling a subset of the data, curated by this algorithm, resulted in a model with a better performance than a model produced from sequentially labeling the same amount of data. Also, similar performance is achieved compared to a model trained on exhaustive labeling of the whole dataset. Overall, the proposed approach results in a dataset that has a diverse set of examples per class as well as more balanced classes, which proves beneficial when training a deep learning model.

Keywords: computer vision, deep learning, object detection, semiconductor

Procedia PDF Downloads 136

Authors: P. Barreto, A. Guevara, V. Ibujes

Abstract:

In this study, the removal of arsenic from synthetic solutions and natural water from Papallacta Lagoon was evaluated, by using the rhizofiltration method with terrestrial and aquatic plant species. Ecuador is a country of high volcanic activity, that is why most of water sources come from volcanic glaciers. Therefore, it is necessary to find new, affordable and effective methods for treating water. The water from Papallacta Lagoon shows levels from 327 µg/L to 803 µg/L of arsenic. The evaluation for the removal of arsenic began with the selection of 16 different species of terrestrial and aquatic plants. These plants were immersed to solutions of 4500 µg/L arsenic concentration, for 48 hours. Subsequently, 3 terrestrial species and 2 aquatic species were selected based on the highest amount of absorbed arsenic they showed, analyzed by plasma optical emission spectrometry (ICP-OES), and their best capacity for adaptation into the arsenic solution. The chosen terrestrial species were cultivated from their seed with hydroponics methods, using coconut fiber and polyurethane foam as substrates. Afterwards, the species that best adapted to hydroponic environment were selected. Additionally, a control of the development for the selected aquatic species was carried out using a basic nutrient solution to provide the nutrients that the plants required. Following this procedure, 30 plants from the 3 types of species selected were exposed to a synthetic solution with levels of arsenic concentration of 154, 375 and 874 µg/L, for 15 days. Finally, the plant that showed the highest level of arsenic absorption was placed in 3 L of natural water, with arsenic levels of 803 µg/L. The plant laid in the water until it reached the desired level of arsenic of 10 µg/L. This experiment was carried out in a total of 30 days, in which the capacity of arsenic absorption of the plant was measured. As a result, the five species initially selected to be used in the last part of the evaluation were: sunflower (Helianthus annuus), clover (Trifolium), blue grass (Poa pratensis), water hyacinth (Eichhornia crassipes) and miniature aquatic fern (Azolla). The best result of arsenic removal was showed by the water hyacinth with a 53,7% of absorption, followed by the blue grass with 31,3% of absorption. On the other hand, the blue grass was the plant that best responded to the hydroponic cultivation, by obtaining a germination percentage of 97% and achieving its full growth in two months. Thus, it was the only terrestrial species selected. In summary, the final selected species were blue grass, water hyacinth and miniature aquatic fern. These three species were evaluated by immersing them in synthetic solutions with three different arsenic concentrations (154, 375 and 874 µg/L). Out of the three plants, the water hyacinth was the one that showed the highest percentages of arsenic removal with 98, 58 and 64%, for each one of the arsenic solutions. Finally, 12 plants of water hyacinth were chosen to reach an arsenic level up to 10 µg/L in natural water. This significant arsenic concentration reduction was obtained in 5 days. In conclusion, it was found that water hyacinth is the best plant to reduce arsenic levels in natural water.

Keywords: arsenic, natural water, plant species, rhizofiltration, synthetic solutions

Procedia PDF Downloads 123

Authors: Ivanor Zardo, Fernanda Walper Da Cunha, Júlia Sarkis, Ligia Damasceno Ferreira Marczak

Abstract:

Lipid oxidation is one of the most important deteriorating processes in oil industry, resulting in the losses of nutritional value of oils as well as changes in color, flavor and other physiological properties. Autoxidation of lipids occurs naturally between molecular oxygen and the unsaturation of fatty acids, forming fat-free radicals, peroxide free radicals and hydroperoxides. In order to avoid the lipid oxidation in vegetable oils, synthetic antioxidants such as butylated hydroxyanisole (BHA), butylated hydroxytoluene (BHT) and tertiary butyl hydro-quinone (TBHQ) are commonly used. However, the use of synthetic antioxidants has been associated with several health side effects and toxicity. The use of natural antioxidants as stabilizers of vegetable oils is being suggested as a sustainable alternative to synthetic antioxidants. The alternative that has been studied is the use of natural extracts obtained mainly from fruits, vegetables and seeds, which have a well-known antioxidant activity related mainly to the presence of phenolic compounds. The sunflower seed cake is rich in phenolic compounds (1 4% of the total mass), being the chlorogenic acid the major constituent. The aim of this study was to evaluate the in vitro application of the phenolic extract obtained from the sunflower seed cake as a retarder of the lipid oxidation reaction in soybean oil and to compare the results with a synthetic antioxidant. For this, the soybean oil, provided from the industry without any addition of antioxidants, was subjected to an accelerated storage test for 17 days at 65 °C. Six samples with different treatments were submitted to the test: control sample, without any addition of antioxidants; 100 ppm of synthetic antioxidant BHT; mixture of 50 ppm of BHT and 50 ppm of phenolic compounds; and 100, 500 and 1200 ppm of phenolic compounds. The phenolic compounds concentration in the extract was expressed in gallic acid equivalents. To evaluate the oxidative changes of the samples, aliquots were collected after 0, 3, 6, 10 and 17 days and analyzed for the peroxide, diene and triene conjugate values. The soybean oil sample initially had a peroxide content of 2.01 ± 0.27 meq of oxygen/kg of oil. On the third day of the treatment, only the samples treated with 100, 500 and 1200 ppm of phenolic compounds showed a considerable oxidation retard compared to the control sample. On the sixth day of the treatment, the samples presented a considerable increase in the peroxide value (higher than 13.57 meq/kg), and the higher the concentration of phenolic compounds, the lower the peroxide value verified. From the tenth day on, the samples had a very high peroxide value (higher than 55.39 meq/kg), where only the sample containing 1200 ppm of phenolic compounds presented significant oxidation retard. The samples containing the phenolic extract were more efficient to avoid the formation of the primary oxidation products, indicating effectiveness to retard the reaction. Similar results were observed for dienes and trienes. Based on the results, phenolic compounds, especially chlorogenic acid (the major phenolic compound of sunflower seed cake), can be considered as a potential partial or even total substitute for synthetic antioxidants.

Keywords: chlorogenic acid, natural antioxidant, vegetables oil deterioration, waste valorization

Procedia PDF Downloads 262

Authors: Angelo Lanzilotto, Martin Kuss-Petermann, Catherine E. Housecroft, Edwin C. Constable, Oliver S. Wenger

Abstract:

We recently described the synthesis of a new tetraphenylporphyrinatozinc(II)-conjugated 2,2':6',6"-terpyridine (1) in which the tpy domain enables the molecule to act as a metalloligand. The synthetic route to 1 has been optimized, the importance of selecting a particular sequence of synthetic steps will be discussed. Three homoleptic complexes have been prepared, [Zn(1)₂]²⁺, [Fe(1)₂]²⁺ and [Ru(1)₂]²⁺, and have been isolated as the hexafluoridophosphate salts. Spectroelectrochemical measurements have been performed and the spectral changes ascribed to redox processes are partitioned on either the porphyrin or the terpyridine units. Compound 1 undergoes a reversible one-electron oxidation/reduction. The removal/gain of a second electron leads to a further irreversible chemical transformation. For the homoleptic [M(1)₂]²⁺ complexes, a suitable potential can be chosen at which both the oxidation and the reduction of the {ZnTPP} core are reversible. When the homoleptic complex contains a redox active metal such as Fe or Ru, spectroelectrochemistry has been used to investigate the metal to ligand charge transfer (MLCT) transition. The latter is sensitive to the oxidation state of the metal, and electrochemical oxidation of the metal center suppresses it. Detailed spectroelectrochemical studies will be presented.

Keywords: homoleptic complexes, spectroelectrochemistry, tetraphenylporphyrinatozinc(II), 2, 2':6', 6"-terpyridine

Procedia PDF Downloads 219

Authors: Tan Yong Sheng Edgar, Yeong Wai Yee

Abstract:

Age-related macular degeneration (AMD) is one of the leading cause of blindness. It can cause severe visual loss due to damaged retinal pigment epithelium (RPE). RPE is an important component of the retinal tissue. It functions as a transducing boundary for visual perception making it an essential factor for sight. The RPE also functions as a metabolically complex and functional cell layer that is responsible for the local homeostasis and maintenance of the extra photoreceptor environment. Thus one of the suggested method of treating such diseases would be regenerating these RPE cells. As such, we intend to grow these cells using a synthetic scaffold to provide a stable environment that reduces the batch effects found in natural scaffolds. Stiffness of the scaffold will also be investigated to determine the optimal Young’s modulus for cultivating these cells. The cells will be generated into a monolayer cell sheet and their functions such as formation of tight junctions and gene expression patterns will be assessed to evaluate the cell sheet quality compared to a native RPE tissue.

Keywords: RPE, scaffold, characterization, biomaterials, colloids and nanomedicine

Procedia PDF Downloads 435

Authors: Somar Boubou, Tatsuo Narikiyo, Michihiro Kawanishi

Abstract:

In this work, we address the problem of 3D object recognition with depth sensors such as Kinect or Structure sensor. Compared with traditional approaches based on local descriptors, which depends on local information around the object key points, we propose a global features based descriptor. Proposed descriptor, which we name as Differential Histogram of Normal Vectors (DHONV), is designed particularly to capture the surface geometric characteristics of the 3D objects represented by depth images. We describe the 3D surface of an object in each frame using a 2D spatial histogram capturing the normalized distribution of differential angles of the surface normal vectors. The object recognition experiments on the benchmark RGB-D object dataset and a self-collected dataset show that our proposed descriptor outperforms two others descriptors based on spin-images and histogram of normal vectors with linear-SVM classifier.

Keywords: vision in control, robotics, histogram, differential histogram of normal vectors

Procedia PDF Downloads 279

Authors: Dongju Kim, Youngjoo Suh, Hyojin Kim, Gyeongyeong Kim

Abstract:

Acoustic Emission Testing (AET) is widely used to test the structural integrity of an operational hydrogen storage container, and clustering algorithms are frequently used in pattern recognition methods to interpret AET results. However, the interpretation of AET results can vary from user to user as the tuning of the relevant parameters relies on the user's experience and knowledge of AET. Therefore, it is necessary to use a deep learning model to identify patterns in acoustic emission (AE) signal data that can be used to classify defects instead. In this paper, a deep learning-based model for classifying the types of defects in hydrogen storage tanks, using AE sensor waveforms, is proposed. As hydrogen storage tanks are commonly constructed using carbon fiber reinforced polymer composite (CFRP), a defect classification dataset is collected through a tensile test on a specimen of CFRP with an AE sensor attached. The performance of the classification model, using one-dimensional convolutional neural network (1-D CNN) and synthetic minority oversampling technique (SMOTE) data augmentation, achieved 91.09% accuracy for each defect. It is expected that the deep learning classification model in this paper, used with AET, will help in evaluating the operational safety of hydrogen storage containers.

Keywords: acoustic emission testing, carbon fiber reinforced polymer composite, one-dimensional convolutional neural network, smote data augmentation

Procedia PDF Downloads 93

Authors: Chaima Babi, Said Gadri

Abstract:

The rapid increase in fake news continues to grow at a very fast rate; this requires implementing efficient techniques that allow testing the re-liability of online content. For that, the current research strives to illuminate the fake news problem using deep learning DL and machine learning ML ap-proaches. We have developed the traditional LSTM (Long short-term memory), and the bidirectional BiLSTM model. A such process is to perform a training task on almost of samples of the dataset, validate the model on a subset called the test set to provide an unbiased evaluation of the final model fit on the training dataset, then compute the accuracy of detecting classifica-tion and comparing the results. For the programming stage, we used Tensor-Flow and Keras libraries on Python to support Graphical Processing Units (GPUs) that are being used for developing deep learning applications.

Keywords: machine learning, deep learning, natural language, fake news, Bi-LSTM, LSTM, multiclass classification

Procedia PDF Downloads 95

Authors: Jindong Gu, Matthias Schubert, Volker Tresp

Abstract:

In many outlier detection tasks, only training data belonging to one class, i.e., the positive class, is available. The task is then to predict a new data point as belonging either to the positive class or to the negative class, in which case the data point is considered an outlier. For this task, we propose a novel corrupted Generative Adversarial Network (CorGAN). In the adversarial process of training CorGAN, the Generator generates outlier samples for the negative class, and the Discriminator is trained to distinguish the positive training data from the generated negative data. The proposed framework is evaluated using an image dataset and a real-world network intrusion dataset. Our outlier-detection method achieves state-of-the-art performance on both tasks.

Keywords: one-class classification, outlier detection, generative adversary networks, semi-supervised learning

Procedia PDF Downloads 151

Authors: Suzan Arslanturk, Mohammad-Reza Siadat, Theophilus Ogunyemi, Ananias Diokno

Abstract:

Missing data is a common challenge in statistical analyses of most clinical survey datasets. A variety of methods have been developed to enable analysis of survey data to deal with missing values. Imputation is the most commonly used among the above methods. However, in order to minimize the bias introduced due to imputation, one must choose the right imputation technique and apply it to the correct type of missing data. In this paper, we have identified different types of missing values: missing data due to skip pattern (SPMD), undetermined missing data (UMD), and genuine missing data (GMD) and applied rough set imputation on only the GMD portion of the missing data. We have used rough set imputation to evaluate the effect of such imputation on prediction by generating several simulation datasets based on an existing epidemiological dataset (MESA). To measure how well each dataset lends itself to the prediction model (logistic regression), we have used p-values from the Wald test. To evaluate the accuracy of the prediction, we have considered the width of 95% confidence interval for the probability of incontinence. Both imputed and non-imputed simulation datasets were fit to the prediction model, and they both turned out to be significant (p-value < 0.05). However, the Wald score shows a better fit for the imputed compared to non-imputed datasets (28.7 vs. 23.4). The average confidence interval width was decreased by 10.4% when the imputed dataset was used, meaning higher precision. The results show that using the rough set method for missing data imputation on GMD data improve the predictive capability of the logistic regression. Further studies are required to generalize this conclusion to other clinical survey datasets.

Keywords: rough set, imputation, clinical survey data simulation, genuine missing data, predictive index

Procedia PDF Downloads 168

Authors: Recep Karadag

Abstract:

Natural dyeing had started since pre-historical times for dyeing of textile materials. The natural dyeing had continued to beginning of 20th century. At the end of 19th century some synthetic dyes were synthesized. Although development of dyeing technologies and methods, natural dyeing was not developed in recent years. Despite rapid advances of synthetic dyestuff industries, natural dye processes have not developed. Therefore natural dyeing was not competed against synthetic dyes. At the same time, it was very difficult that large quantities of coloured textile was dyed with natural dyes And it was very difficult to get reproducible results in the natural dyeing using classical and traditional processes. However, natural dyeing has used slightly in the textile handicraft up to now. It is very important view that re-using of natural dyes to create awareness in textiles in recent years. Natural dyes have got many awareness and sustainability properties. Natural dyes are more eco-friendly than synthetic dyes. A lot of natural dyes have got antioxidant, antibacterial, antimicrobial, antifungal and anti –UV properties. It had been known that were obtained limited numbers colours with natural dyes in the past. On the contrary, colour scale is too wide with natural dyes. Except fluorescent colours, numerous colours can be obtained with natural dyes. Fastnesses of dyed textiles with natural dyes are good that there are light, washing, rubbing, etc. The fastness values can be improved depend on dyeing processes. Thanks to these properties mass production can be made with natural dyes in textiles. Therefore fabric dyeing machine was designed. This machine is too suitable for natural dyeing and mass production. Also any dyeing machine can be modified for natural dyeing. Although dye extraction and dyeing are made separately in the traditional natural dyeing processes and these procedures are become by designed this machine. Firstly, colouring compounds are extracted from natural dye resources, then dyeing is made with extracted colouring compounds. The colouring compounds are moderately dissolved in water. Less water is used in the extraction of colouring compounds from dye resources and dyeing with this new technique on the contrary much quantity water needs to use for dissolve of the colouring compounds in the traditional dyeing. This dyeing technique is very useful method for mass productions with natural dyes in traditional natural dyeing that use less energy, less dye materials, less water, etc. than traditional natural dyeing techniques. In this work, cotton, silk, linen and wool fabrics were dyed with some natural dye plants by the technique. According to the analysis very good results were obtained by this new technique. These results are shown sustainability and awareness of natural dyes for textiles.

Keywords: antibacterial, antimicrobial, natural dyes, sustainability

Procedia PDF Downloads 522

Authors: Walid Moudani, Ahmad Shahin

Abstract:

This research presents a study to handle the recruitment services system. It aims to enhance a business intelligence system by embedding data mining in its core engine and to facilitate the link between job searchers and recruiters companies. The purpose of this study is to present an intelligent management system for supporting recruitment services based on data mining methods. It consists to apply segmentation on the extracted job postings offered by the different recruiters. The details of the job postings are associated to a set of relevant features that are extracted from the web and which are based on critical criterion in order to define consistent clusters. Thereafter, we assign the job searchers to the best cluster while providing a ranking according to the job postings of the selected cluster. The performance of the proposed model used is analyzed, based on a real case study, with the clustered job postings dataset and classified job searchers dataset by using some metrics.

Keywords: job postings, job searchers, clustering, genetic algorithms, business intelligence

Procedia PDF Downloads 329