Search results for: content classification
7062 Distangling Biological Noise in Cellular Images with a Focus on Explainability
Authors: Manik Sharma, Ganapathy Krishnamurthi
Abstract:
The cost of some drugs and medical treatments has risen in recent years, that many patients are having to go without. A classification project could make researchers more efficient. One of the more surprising reasons behind the cost is how long it takes to bring new treatments to market. Despite improvements in technology and science, research and development continues to lag. In fact, finding new treatment takes, on average, more than 10 years and costs hundreds of millions of dollars. If successful, we could dramatically improve the industry's ability to model cellular images according to their relevant biology. In turn, greatly decreasing the cost of treatments and ensure these treatments get to patients faster. This work aims at solving a part of this problem by creating a cellular image classification model which can decipher the genetic perturbations in cell (occurring naturally or artificially). Another interesting question addressed is what makes the deep-learning model decide in a particular fashion, which can further help in demystifying the mechanism of action of certain perturbations and paves a way towards the explainability of the deep-learning model.Keywords: cellular images, genetic perturbations, deep-learning, explainability
Procedia PDF Downloads 1007061 Antioxidant Activities, Chemical Components, Physicochemical, and Sensory Characteristics of Kecombrang Tea (Etlingera elatior)
Authors: Rifda Naufalin, Nurul Latifasari, Siti Nuryanti, Muna Ridha Hanifah
Abstract:
Kecombrang is a Zingiberaceae plant which has antioxidant properties. The high antioxidant content in kecombrang flowers has the potential to be processed as a functional beverage raw material so that it can be used as an ingredient in making herbal teas. The purpose of this study was to determine the chemical components, physicochemistry, antioxidant activity and sensory characteristics of kecombrang tea. The research methodology was carried out by using a completely randomized design with processing factors of kecombrang tea namely blanching and non-blanching, fermentation and non-fermentation, and the optimal time for drying kecombrang tea. The best treatment combination based on the effective index method is the treatment of the blanching process followed by drying at a temperature of 50ᵒC until the 2% moisture content can produce kecombrang tea with a total phenol content of 5.95 mg Tannic Acid Equivalent (TAE) / gram db, total flavonoid 3%, pH 4.5, and antioxidant activity 82.95%, red color, distinctive aroma of tea, fresh taste, and preferred by panelists.Keywords: kecombrang tea, blanching, fermentation, total phenol, and antioxidant activity
Procedia PDF Downloads 1367060 Detection and Classification of Rubber Tree Leaf Diseases Using Machine Learning
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 697059 Screening of Antiviral Compounds in Medicinal Plants: Non-Volatiles
Authors: Tomas Drevinskas, Ruta Mickiene, Audrius Maruska, Nicola Tiso, Algirdas Salomskas, Raimundas Lelesius, Agneta Karpovaite, Ona Ragazinskiene, Loreta Kubiliene
Abstract:
Antiviral effect of substances accumulated by plants and natural products is known to ethno-pharmacy and modern day medicine. Antiviral properties are usually assigned to volatile compounds and polyphenols. This research work is divided into several parts and the task of this part was to investigate potential plants, potential substances and potential preparation conditions that can be used for the preparation of antiviral agents. Sixteen different medicinal plants, their parts and two types of propolis were selected for screening. Firstly, extraction conditions of non-volatile compounds were investigated: 3 pre-selected plants were extracted with 5 different ethanol – water mixtures (96%, 75%, 60%, 40%, 20 %, vol.) and bidistilled water. Total phenolic content, total flavonoid content and radical scavenging activity was determined. The results indicated that optimal extrahent is 40%, vol. of ethanol – water mixture. Further investigations were performed with the extrahent of 40%, vol. ethanol – water mixture. All 16 of selected plants, their parts and two types of propolis were extracted using selected extrahent. Determined total phenolic content, total flavonoid content and radical scavenging activity indicated that extracts of Origanum Vulgare L., Mentha piperita L., Geranium macrorrhizum L., Melissa officinalis L. and Desmodium canadence L. contains highest amount of extractable phenolic compounds (7.31, 5.48, 7.88, 8.02 and 7.16 rutin equivalents (mg/ ml) respectively), flavonoid content (2.14, 2.23, 2.49, 0.79 and 1.51 rutin equivalents (mg/ml) respectively) and radical scavenging activity (11.98, 8.72, 13.47, 13.22 and 12.22 rutin equivalents (mg/ml) respectively). Composition of the extracts is analyzed using HPLC.Keywords: antiviral effect, plants, propolis, phenols
Procedia PDF Downloads 3177058 Classifications of Sleep Apnea (Obstructive, Central, Mixed) and Hypopnea Events Using Wavelet Packet Transform and Support Vector Machines (VSM)
Authors: Benghenia Hadj Abd El Kader
Abstract:
Sleep apnea events as obstructive, central, mixed or hypopnea are characterized by frequent breathing cessations or reduction in upper airflow during sleep. An advanced method for analyzing the patterning of biomedical signals to recognize obstructive sleep apnea and hypopnea is presented. In the aim to extract characteristic parameters, which will be used for classifying the above stated (obstructive, central, mixed) sleep apnea and hypopnea, the proposed method is based first on the analysis of polysomnography signals such as electrocardiogram signal (ECG) and electromyogram (EMG), then classification of the (obstructive, central, mixed) sleep apnea and hypopnea. The analysis is carried out using the wavelet transform technique in order to extract characteristic parameters whereas classification is carried out by applying the SVM (support vector machine) technique. The obtained results show good recognition rates using characteristic parameters.Keywords: obstructive, central, mixed, sleep apnea, hypopnea, ECG, EMG, wavelet transform, SVM classifier
Procedia PDF Downloads 3657057 Effect of Aluminium Content on Bending Properties and Microstructure of AlₓCoCrFeNi Alloy Fabricated by Induction Melting
Authors: Marzena Tokarewicz, Malgorzata Gradzka-Dahlke
Abstract:
High-entropy alloys (HEAs) have gained significant attention due to their great potential as functional and structural materials. HEAs have very good mechanical properties (in particular, alloys based on CoCrNi). They also show the ability to maintain their strength at high temperatures, which is extremely important in some applications. AlCoCrFeNi alloy is one of the most studied high-entropy alloys. Scientists often study the effect of changing the aluminum content in this alloy because it causes significant changes in phase presence and microstructure and consequently affects its hardness, ductility, and other properties. Research conducted by the authors also investigates the effect of aluminium content in AlₓCoCrFeNi alloy on its microstructure and mechanical properties. AlₓCoCrFeNi alloys were prepared by vacuum induction melting. The obtained samples were examined for chemical composition, microstructure, and microhardness. The three-point bending method was carried out to determine the bending strength, bending modulus, and conventional bending yield strength. The obtained results confirm the influence of aluminum content on the properties of AlₓCoCrFeNi alloy. Most studies on AlₓCoCrFeNi alloy focus on the determination of mechanical properties in compression or tension, much less in bending. The achieved results provide valuable information on the bending properties of AlₓCoCrFeNi alloy and lead to interesting conclusions.Keywords: bending properties, high-entropy alloys, induction melting, microstructure
Procedia PDF Downloads 1407056 Discrimination and Classification of Vestibular Neuritis Using Combined Fisher and Support Vector Machine Model
Authors: Amine Ben Slama, Aymen Mouelhi, Sondes Manoubi, Chiraz Mbarek, Hedi Trabelsi, Mounir Sayadi, Farhat Fnaiech
Abstract:
Vertigo is a sensation of feeling off balance; the cause of this symptom is very difficult to interpret and needs a complementary exam. Generally, vertigo is caused by an ear problem. Some of the most common causes include: benign paroxysmal positional vertigo (BPPV), Meniere's disease and vestibular neuritis (VN). In clinical practice, different tests of videonystagmographic (VNG) technique are used to detect the presence of vestibular neuritis (VN). The topographical diagnosis of this disease presents a large diversity in its characteristics that confirm a mixture of problems for usual etiological analysis methods. In this study, a vestibular neuritis analysis method is proposed with videonystagmography (VNG) applications using an estimation of pupil movements in the case of an uncontrolled motion to obtain an efficient and reliable diagnosis results. First, an estimation of the pupil displacement vectors using with Hough Transform (HT) is performed to approximate the location of pupil region. Then, temporal and frequency features are computed from the rotation angle variation of the pupil motion. Finally, optimized features are selected using Fisher criterion evaluation for discrimination and classification of the VN disease.Experimental results are analyzed using two categories: normal and pathologic. By classifying the reduced features using the Support Vector Machine (SVM), 94% is achieved as classification accuracy. Compared to recent studies, the proposed expert system is extremely helpful and highly effective to resolve the problem of VNG analysis and provide an accurate diagnostic for medical devices.Keywords: nystagmus, vestibular neuritis, videonystagmographic system, VNG, Fisher criterion, support vector machine, SVM
Procedia PDF Downloads 1317055 Machine Learning Techniques in Bank Credit Analysis
Authors: Fernanda M. Assef, Maria Teresinha A. Steiner
Abstract:
The aim of this paper is to compare and discuss better classifier algorithm options for credit risk assessment by applying different Machine Learning techniques. Using records from a Brazilian financial institution, this study uses a database of 5,432 companies that are clients of the bank, where 2,600 clients are classified as non-defaulters, 1,551 are classified as defaulters and 1,281 are temporarily defaulters, meaning that the clients are overdue on their payments for up 180 days. For each case, a total of 15 attributes was considered for a one-against-all assessment using four different techniques: Artificial Neural Networks Multilayer Perceptron (ANN-MLP), Artificial Neural Networks Radial Basis Functions (ANN-RBF), Logistic Regression (LR) and finally Support Vector Machines (SVM). For each method, different parameters were analyzed in order to obtain different results when the best of each technique was compared. Initially the data were coded in thermometer code (numerical attributes) or dummy coding (for nominal attributes). The methods were then evaluated for each parameter and the best result of each technique was compared in terms of accuracy, false positives, false negatives, true positives and true negatives. This comparison showed that the best method, in terms of accuracy, was ANN-RBF (79.20% for non-defaulter classification, 97.74% for defaulters and 75.37% for the temporarily defaulter classification). However, the best accuracy does not always represent the best technique. For instance, on the classification of temporarily defaulters, this technique, in terms of false positives, was surpassed by SVM, which had the lowest rate (0.07%) of false positive classifications. All these intrinsic details are discussed considering the results found, and an overview of what was presented is shown in the conclusion of this study.Keywords: artificial neural networks (ANNs), classifier algorithms, credit risk assessment, logistic regression, machine Learning, support vector machines
Procedia PDF Downloads 957054 Sustainable Energy Production from Microalgae in Queshm Island, Persian Gulf
Authors: N. Moazami, R. Ranjbar, A. Ashori
Abstract:
Out of hundreds of microalgal strains reported, only very few of them are capable for production of high content of lipid. Therefore, the key technical challenges include identifying the strains with the highest growth rates and oil contents with adequate composition, which were the main aims of this work. From 147 microalgae screened for high biomass and oil productivity, the Nannochloropsis sp. PTCC 6016, which attained 52% lipid content, was selected for large scale cultivation in Persian Gulf Knowledge Island. Nannochloropsis strain PTCC 6016 belongs to Eustigmatophyceae (Phylum heterokontophyta) isolated from Mangrove forest area of Qheshm Island and Persian Gulf (Iran) in 2008. The strain PTCC 6016 had an average biomass productivity of 2.83 g/L/day and 52% lipid content. The biomass productivity and the oil production potential could be projected to be more than 200 tons biomass and 100000 L oil per hectare per year, in an outdoor algal culture (300 day/year) in the Persian Gulf climate.Keywords: biofuels, microalgae, Nannochloropsis, raceway open pond, bio-jet
Procedia PDF Downloads 4697053 Validity and Reliability of a Questionaire for Measuring Behaviour Change of Low Performance Employee
Authors: Hazaila Binti Hassan, Abu Yazid Bin Abu Bakar, Salleh Amat
Abstract:
This study is to get the validity and reliability of the questionnaire for behaviour change on low-performing officers. This study aimed to develop and evaluate the behaviour of low performing officers. There are 75 items in this questionnaire which involves 5 subscales, which are the 5 dimensions intended to be studied: 1st emotional stability, 2nd psycho-spiritual enhancement, 3rd social skills development, 4th cognitive and rationality improvement and 5th behavioural alignment and adjustment. There are 2 processes in this research whereby to check the validity and reliability. Both use quantitative methods. Validity content testing has been conducted to validate the behavioural change questionnaire of the low performing officers. For the face validity, 4 people are involved, two are psychologists who carried out the program and the other two are officers of the same rank, i.e. supporting officers. They are involved in correction of sentences, languages, and grammar as well as the sentence structures so that it tallies with the purpose of studies. The questionnaire underwent content validity by the experts. Five experts are appointed to attend this session, 3 are directly involved in the construction of this questionnaire and 2 others are experts from the university with a background in questionnaire development. The result shows that the content validity obtained a high coefficient of 0.745 with a minimum and maximum value of more than 0.60 which satisfies the characteristic of Content Value Ratio. The Cronbach’s alpha result is 0.867. The highest scores are the behavioural alignment and adjustment sub-scale recorded the highest value, followed by social skills development sub-scale, cognitive and rational improvements sub-scale, psycho-spiritual enhancement sub-scale, and lastly emotional stability. Therefore, both of validity and reliability result were accepted that this questionnaire is valid and reliable can be used in the study of behaviour changes of low performing officers in the civil service.Keywords: content validity, reliability, five dimension, low-performing officers, questionnaire
Procedia PDF Downloads 2687052 Study on the Thermal Conductivity about Porous Materials in Wet State
Authors: Han Yan, Jieren Luo, Qiuhui Yan, Xiaoqing Li
Abstract:
The thermal conductivity of porous materials is closely related to the thermal and moisture environment and the overall energy consumption of the building. The study of thermal conductivity of porous materials has great significance for the realization of low energy consumption building and economic construction building. Based on the study of effective thermal conductivity of porous materials at home and abroad, the thermal conductivity under a variety of different density of polystyrene board (EPS), plastic extruded board (XPS) and polyurethane (PU) and phenolic resin (PF) in wet state through theoretical analysis and experimental research has been studied. Initially, the moisture absorption and desorption properties of specimens had been discussed under different density, which led a result indicates the moisture absorption of four porous materials all have three stages, fast, stable and gentle. For the moisture desorption, there are two types. One is the existence of the rapid phase of the stage, such as XPS board, PU board. The other one does not have the fast desorption, instead, it is more stabilized, such as XPS board, PF board. Furthermore, the relationship between water content and thermal conductivity of porous materials had been studied and fitted, which figured out that in the wake of the increasing water content, the thermal conductivity of porous material is continually improving. At the same time, this result also shows, in different density, when the same kind of materials decreases, the saturated moisture content increases. Finally, the moisture absorption and desorption properties of the four kinds of materials are compared comprehensively, and it turned out that the heat preservation performance of PU board is the best, followed by EPS board, XPS board, PF board.Keywords: porous materials, thermal conductivity, moisture content, transient hot-wire method
Procedia PDF Downloads 1757051 Machine Learning Approach for Yield Prediction in Semiconductor Production
Authors: Heramb Somthankar, Anujoy Chakraborty
Abstract:
This paper presents a classification study on yield prediction in semiconductor production using machine learning approaches. A complicated semiconductor production process is generally monitored continuously by signals acquired from sensors and measurement sites. A monitoring system contains a variety of signals, all of which contain useful information, irrelevant information, and noise. In the case of each signal being considered a feature, "Feature Selection" is used to find the most relevant signals. The open-source UCI SECOM Dataset provides 1567 such samples, out of which 104 fail in quality assurance. Feature extraction and selection are performed on the dataset, and useful signals were considered for further study. Afterward, common machine learning algorithms were employed to predict whether the signal yields pass or fail. The most relevant algorithm is selected for prediction based on the accuracy and loss of the ML model.Keywords: deep learning, feature extraction, feature selection, machine learning classification algorithms, semiconductor production monitoring, signal processing, time-series analysis
Procedia PDF Downloads 1017050 Pattern Recognition Based on Simulation of Chemical Senses (SCS)
Authors: Nermeen El Kashef, Yasser Fouad, Khaled Mahar
Abstract:
No AI-complete system can model the human brain or behavior, without looking at the totality of the whole situation and incorporating a combination of senses. This paper proposes a Pattern Recognition model based on Simulation of Chemical Senses (SCS) for separation and classification of sign language. The model based on human taste controlling strategy. The main idea of the introduced model is motivated by the facts that the tongue cluster input substance into its basic tastes first, and then the brain recognizes its flavor. To implement this strategy, two level architecture is proposed (this is inspired from taste system). The separation-level of the architecture focuses on hand posture cluster, while the classification-level of the architecture to recognizes the sign language. The efficiency of proposed model is demonstrated experimentally by recognizing American Sign Language (ASL) data set. The recognition accuracy obtained for numbers of ASL is 92.9 percent.Keywords: artificial intelligence, biocybernetics, gustatory system, sign language recognition, taste sense
Procedia PDF Downloads 2847049 Enrichment of the Antioxidant Activity of Decaffeinated Assam Green Tea by Herbal Plant: A Synergistic Effect
Authors: Abhijit Das, Runu Chakraborty
Abstract:
Tea is the most widely consumed beverage aside from water; it is grown in about 30 countries with a per capita worldwide consumption of approximately 0.12 liter per year. Green tea is of growing importance with its antioxidant contents associated with its health benefits. The various extraction methods can influence the polyphenol concentrations of green tea. The purpose of the study was to quantify the polyphenols, flavonoid and antioxidant activity of both caffeinated and decaffeinated form of tea manufactured commercially in Assam, North Eastern part of India. The results display that phenolic/flavonoid content well correlated with antioxidant activity which was performed by DPPH (2,2-diphenyl-1-picrylhydrazyl) and FRAP (Ferric reducing ability of plasma) assay. After decaffeination there is a decrease in the polyphenols concentration which also affects the antioxidant activity of green tea. For the enrichment of antioxidant activity of decaffeinated tea a herbal plant extract is used which shows a synergistic effect between green tea and herbal plant phenolic compounds.Keywords: antioxidant activity, decaffeination, green tea, flavonoid content, phenolic content, plant extract
Procedia PDF Downloads 3367048 Unearthing Air Traffic Control Officers Decision Instructional Patterns From Simulator Data for Application in Human Machine Teams
Authors: Zainuddin Zakaria, Sun Woh Lye
Abstract:
Despite the continuous advancements in automated conflict resolution tools, there is still a low rate of adoption of automation from Air Traffic Control Officers (ATCOs). Trust or acceptance in these tools and conformance to the individual ATCO preferences in strategy execution for conflict resolution are two key factors that impact their use. This paper proposes a methodology to unearth and classify ATCO conflict resolution strategies from simulator data of trained and qualified ATCOs. The methodology involves the extraction of ATCO executive control actions and the establishment of a system of strategy resolution classification based on ATCO radar commands and prevailing flight parameters in deconflicting a pair of aircraft. Six main strategies used to handle various categories of conflict were identified and discussed. It was found that ATCOs were about twice more likely to choose only vertical maneuvers in conflict resolution compared to horizontal maneuvers or a combination of both vertical and horizontal maneuvers.Keywords: air traffic control strategies, conflict resolution, simulator data, strategy classification system
Procedia PDF Downloads 1417047 Research and Innovation Centre
Authors: Krasimir Ivanov, Tonyo Tonev, Nguyen Nguyen, Alexander Peltekov, Anyo Mitkov
Abstract:
Maize is among the most economically important crops and at the same time one of the most sensitive to soil deficiency in zinc. In this paper, the impact of the foliar zinc application in the form of zinc hydroxy nitrate suspension on the micro and macro elements partitioning in maize leaves and grain was studied during spring maize season, 2017. The impact of the foliar zinc fertilization on the grain yield and quality was estimated too. The experiment was performed by the randomized block design with 8 variants in 3 replications. Seven suspension solutions whit different Zn concentration were used, including ZnO suspension and zinc hydroxyl nitrate alone or nixed with other nutrients. Fertilization and irrigation were the same for all variants. The Zn content and the content of selected micro (Cu, Fe) and macro (Ca, Mg, P and K) elements in maize leaves were determined two weeks after the first spraying (5-6 sheets), two weeks after the second spraying (9-10 sheets) and after harvesting. It was concluded that the synthesized zinc hydroxy nitrate demonstrates potential as the long-term foliar fertilizer. A significant (p < 0.05) effect of zinc accumulation in maize leaves by foliar zinc application during the first growth stage was found, followed by its reutilization to other plants organs during the second growth stage. Significant export of Cu, P, and K from lower and middle leaves was observed. The content of Ca and Mg remains constant in the whole longevity period, while the content of Fe decreases sharply.Keywords: foliar fertilization, zinc hydroxy nitrate, maize, zinc
Procedia PDF Downloads 1517046 Effects of Aging on Thermal Properties of Some Improved Varieties of Cassava (Manihot Esculenta) Roots
Authors: K. O. Oriola, A. O. Raji, O. E. Akintola, O. T. Ismail
Abstract:
Thermal properties of roots of three improved cassava varieties (TME419, TMS 30572, and TMS 0326) were determined on samples harvested at 12, 15 and 18 Months After Planting (MAP) conditioned to moisture contents of 50, 55, 60, 65, 70% (wb). Thermal conductivity at 12, 15 and 18 MAP ranged 0.4770 W/m.K to 0.6052W/m.K; 0.4804 W/m.K to 0.5530 W/m.K and 0.3764 to 0.6102 W/m.K respectively, thermal diffusivity from 1.588 to 2.426 x 10-7m2/s; 1.290 to 2.010 x 10-7m2/s and 0.1692 to 4.464 x 10-7m2/s and specific heat capacity from 2.3626 to 3.8991 kJ/kg.K; 1.8110 to 3.9703 kJ/kgK and 1.7311 to 3.8830 kJ/kg.K respectively within the range of moisture content studied across the varieties. None of the samples over the ages studied showed similar or definite trend in variation with others across the moisture content. However, second order polynomial models fitted all the data. Age on the other hand had a significant effect on the three thermal properties studied for TME 419 but not on thermal conductivity of TMS30572 and specific heat capacity of TMS 0326. Information obtained will provide better insight into thermal processing of cassava roots into stable products.Keywords: thermal conductivity, thermal diffusivity, specific heat capacity, moisture content, tuber age
Procedia PDF Downloads 5097045 Effect pH on Chemical and Physical Properties of Iranian Fetta Cheese
Authors: M. Dezyani, R. Ezzati, H. Mirzaei
Abstract:
The objectives of this study were to determine the effect of pH on chemical, structural, and functional properties of Fetta cheese, and to relate changes in structure to changes in cheese unctionality. Fetta cheese was obtained from a cheese-production facility and stored at 4°C. Ten days after manufacture, the cheese was cut into blocks that were vacuum-packaged and stored for 4 d at 4°C. Cheese blocks were then high-pressure injected one, three, or five times with a 20% (wt/wt) glucono-δ-lactone solution. Successive injections were performed 24 h apart. Cheese blocks were then analyzed after 40 d of storage at 4°C. Acidulant injection decreased cheese pH from 5.3 in the uninjected cheese to 4.7 after five injections. Decreased pH increased the content of soluble calcium and slightly decreased the total calcium content of cheese. At the highest level, injection of acidulant promoted syneresis. Thus, after five injections, the moisture content of cheese decreased from 34 to 31%, which esulted in decreased cheese weight. Lowered cheese pH, 4.7 compared with 5.3, also resulted in contraction of the protein matrix. Acidulant injection decreased cheese hardness and cohesiveness, and the cheese became more crumbly.Keywords: calcium, high-pressure injection, protein matrix, syneresis
Procedia PDF Downloads 4707044 Evaluation of the Capabilities of Saccharomyces cerevisiae and Lactobacillus plantarum in Improvement of Total Phenolic Content and Antioxidant Activity in Carob Kibble
Authors: Thi Huong Vu, Vijay Jayasena, Zhongxiang Fang, Gary Dykes
Abstract:
Carob kibble has recently received attention due to the presence of high level of polyphenol antioxidants. The capacity of microorganisms to improve antioxidant activities and total phenolics in carob kibble was investigated in the study. Two types of microorganisms including lactic acid bacteria Lactobacillus plantarum (L. plantarum) and yeast Saccharomyces cerevisiae (S. cerevisiae) were used in single and in their combination as starters. The total phenolic content was determined by the Folin–Ciocalteu method. Antioxidant activities were assessed scavenging capacity using 2,2-diphenyl-1-picrylhydrazyl (DPPH) and 2,2′-azinobis-(3-ethylbenzothiazoline-6-sulfonic acid (ABTS). The study found that S. cerevisiae alone considerably improved 55% total phenolics content at 15 h, while L. plantarum caused in a loss of 20% through the process. Antioxidant capacity of the yeast-fermented samples significantly increased by 43 % and 10 % in ABTS and DPPH assays, respectively. However, reduction of 13 % and 32 % inhibition were recorded in the carob treated with L. plantarum. In the combination of S. cerevisiae and L. plantarum (1:1), both total phenolic content and antioxidant activity of carob kibble were a similar trend as these of S. cerevisiae single, but a lower improvement. The antioxidant power of the extracts was linearly correlated to their total phenolic contents (R=0.75). The results suggested that S. cerevisiae alone was the better for enhancement of both total phenolic content and antioxidant activity in carob kibble using submerged fermentation. The efficiency of fermentation reached the highest at 15h. Thus submerged fermentation with S. cerevisiae offers a tool with simple and cost effective to further increase the bioactive potential of carob kibble, which is in use for food, cosmetic and pharmaceutical industries.Keywords: antioxidant activity, carob kibble, lactobacillus plantarum, saccharomyces cerevisiae, total phenolics
Procedia PDF Downloads 2787043 Structural Investigation of Na2O–B2O3–SiO2 Glasses Doped with NdF3
Authors: M. S. Gaafar, S. Y. Marzouk
Abstract:
Sodium borosilicate glasses doped with different content of NdF3 mol % have been prepared by rapid quenching method. Ultrasonic velocities (both longitudinal and shear) measurements have been carried out at room temperature and at ultrasonic frequency of 4 MHz. Elastic moduli, Debye temperature, softening temperature and Poisson's ratio have been obtained as a function of NdF3 modifier content. Results showed that the elastic moduli, Debye temperature, softening temperature and Poisson's ratio have very slight change with the change of NdF3 mol % content. Based on FTIR spectroscopy and theoretical (Bond compression) model, quantitative analysis has been carried out in order to obtain more information about the structure of these glasses. The study indicated that the structure of these glasses is mainly composed of SiO4 units with four bridging oxygens (Q4), and with three bridging and one nonbridging oxygens (Q3).Keywords: borosilicate glasses, ultrasonic velocity, elastic moduli, FTIR spectroscopy, bond compression model
Procedia PDF Downloads 3987042 Analysis of Sediment Distribution around Karang Sela Coral Reef Using Multibeam Backscatter
Authors: Razak Zakariya, Fazliana Mustajap, Lenny Sharinee Sakai
Abstract:
A sediment map is quite important in the marine environment. The sediment itself contains thousands of information that can be used for other research. This study was conducted by using a multibeam echo sounder Reson T20 on 15 August 2020 at the Karang Sela (coral reef area) at Pulau Bidong. The study aims to identify the sediment type around the coral reef by using bathymetry and backscatter data. The sediment in the study area was collected as ground truthing data to verify the classification of the seabed. A dry sieving method was used to analyze the sediment sample by using a sieve shaker. PDS 2000 software was used for data acquisition, and Qimera QPS version 2.4.5 was used for processing the bathymetry data. Meanwhile, FMGT QPS version 7.10 processes the backscatter data. Then, backscatter data were analyzed by using the maximum likelihood classification tool in ArcGIS version 10.8 software. The result identified three types of sediments around the coral which were very coarse sand, coarse sand, and medium sand.Keywords: sediment type, MBES echo sounder, backscatter, ArcGIS
Procedia PDF Downloads 747041 Population Diversity of Dalmatian Pyrethrum Based on Pyrethrin Content and Composition
Authors: Filip Varga, Nina Jeran, Martina Biosic, Zlatko Satovic, Martina Grdisa
Abstract:
Dalmatian pyrethrum (Tanacetum cinerariifolium /Trevir./ Sch. Bip.), a species endemic to the eastern Adriatic coastline, is the source of natural insecticide pyrethrin. Pyrethrin is a mixture of six compounds (pyrethrin I and II, cinerin I and II, jasmolin I and II) that exhibits high insecticidal activity with no detrimental effects to the environment. A recently optimized matrix-solid phase dispersion method (MSPD), using florisil as the sorbent, acetone-ethyl acetate (1:1, v/v) as the elution solvent, and sodium sulfate anhydrous as the drying agent was utilized to extract the pyrethrins from 10 wild populations (20 individuals per population) distributed along the Croatian coast. All six components in the extracts were qualitatively and quantitatively determined by high-performance liquid chromatography with a diode array detector (HPLC-DAD). Pearson’s correlation index was calculated between pyrethrin compounds, and differences between the populations using the analysis of variance were tested. Additionally, the correlation of each pyrethrin component with spatio-ecological variables (bioclimate, soil properties, elevation, solar radiation, and distance from the coastline) was calculated. Total pyrethrin content ranged from 0.10% to 1.35% of dry flower weight, averaging 0.58% across all individuals. Analysis of variance revealed significant differences between populations based on all six pyrethrin compounds and total pyrethrin content. On average, the lowest total pyrethrin content was found in the population from Pelješac peninsula (0.22% of dry flower weight) in which total pyrethrin content lower than 0.18% was detected in 55% of the individuals. The highest average total pyrethrin content was observed in the population from island Zlarin (0.87% of dry flower weight), in which total pyrethrin content higher than 1.00% was recorded in only 30% of the individuals. Pyrethrin I/pyrethrin II ratio as a measure of extract quality ranged from 0.21 (population from the island Čiovo) to 5.88 (population from island Mali Lošinj) with an average of 1.77 across all individuals. By far, the lowest quality of extracts was found in the population from Mt. Biokovo (pyrethrin I/II ratio lower than 0.72 in 40% of individuals) due to the high pyrethrin II content typical for this population. Pearson’s correlation index revealed a highly significant positive correlation between pyrethrin I content and total pyrethrin content and a strong negative correlation between pyrethrin I and pyrethrin II. The results of this research clearly indicate high intra- and interpopulation diversity of Dalmatian pyrethrum with regards to pyrethrin content and composition. The information obtained has potential use in plant genetic resources conservation and biodiversity monitoring. Possibly the largest potential lies in designing breeding programs aimed at increasing pyrethrin content in commercial breeding lines and reintroduction in agriculture in Croatia. Acknowledgment: This work has been fully supported by the Croatian Science Foundation under the project ‘Genetic background of Dalmatian pyrethrum (Tanacetum cinerariifolium /Trevir/ Sch. Bip.) insecticidal potential’ - (PyrDiv) (IP-06-2016-9034).Keywords: Dalmatian pyrethrum, HPLC, MSPD, pyrethrin
Procedia PDF Downloads 1287040 Inoculation of Cyanobacteria Improves the Lignin Content of Thymus vulgaris L.
Authors: Nasim Rasuli, Akram Ahmadi, Hossein Riahi, Zeinab Shariatmadari, Majid Ghorbani Nohooji, Pooyan Mehraban Joubani
Abstract:
Cyanobacteria are one of the most promising sources of new biostimulants and have received much attention due to their diverse applications in biotechnology. These microorganisms enhance the growth and productivity of plants by producing plant growth stimulants and fixing atmospheric nitrogen. Thymus vulgaris L., a valuable medicinal plant from the Lamiaceae family, is widely distributed across the globe. essential oil of T. vulgaris is best characterized by the prominence of phenols, making them the key compounds in its composition. Lignin biosynthesis as a natural plant polyphenol plays a crucial role in promoting plant growth, strengthening cell walls, and increasing resistance to pathogens. In this study, the bioelicitor activity of five cyanobacterial suspensions including Anabaena torulosa ISB213, Nostoc calcicola ISB215, Nostoc ellipsosporum ISB217, Trichormus doliolum ISB214, and Oscillatoria sp. ISB2116 on the lignin content of the T. vulgaris L. was investigated. Pot experiments were performed by inoculation of a %2 algal extract to the soil of treated plants one week before planting and then every 20 days. After four months, the lignin content in the leaves of both treated and control plants was evaluated. The results demonstrated that the application of cyanobacteria significantly increased the lignin content in the leaves of treated plants compared to the control. The treatment with Oscillatoria sp. ISB216 and N. ellipsosporum ISB217 resulted in the highest lignin content, with an increase of 93.33% and 86.67%, respectively. These findings highlight the potential of cyanobacteria as bioelicitors, offering a viable alternative for enhancing the production of secondary metabolites in T. vulgaris. Consequently, this could contribute to the economic value of this medicinal plant.Keywords: cyanobacteria, bioelicitor, thymus vulgaris, lignin
Procedia PDF Downloads 757039 Personalized Email Marketing Strategy: A Reinforcement Learning Approach
Authors: Lei Zhang, Tingting Xu, Jun He, Zhenyu Yan
Abstract:
Email marketing is one of the most important segments of online marketing. It has been proved to be the most effective way to acquire and retain customers. The email content is vital to customers. Different customers may have different familiarity with a product, so a successful marketing strategy must personalize email content based on individual customers’ product affinity. In this study, we build our personalized email marketing strategy with three types of emails: nurture, promotion, and conversion. Each type of email has a different influence on customers. We investigate this difference by analyzing customers’ open rates, click rates and opt-out rates. Feature importance from response models is also analyzed. The goal of the marketing strategy is to improve the click rate on conversion-type emails. To build the personalized strategy, we formulate the problem as a reinforcement learning problem and adopt a Q-learning algorithm with variations. The simulation results show that our model-based strategy outperforms the current marketer’s strategy.Keywords: email marketing, email content, reinforcement learning, machine learning, Q-learning
Procedia PDF Downloads 1867038 Effect of Drying Condition on the Wheat Germ Stability Using Fluidized-Bed Dryer
Authors: J. M. Hung, J. S. Chan, M. I. Kuo, D. S. Chan, C. P. Lu
Abstract:
Wheat germ is a by-product obtained from wheat milling and it contains highly concentrated nutrients. Due to highly lipase and lipoxygenase activities, wheat germ products can easily turn into rancid flavor and cause a short life. The objective of this study is to control moisture content and retard lipid hydrolysis by fluidized-bed drying. The raw wheat germ of 2 kg was dried with a vertical batch fluidized bed with the following varying conditions, inlet air temperature of 50, 80 and 120°C, inlet air velocity of 3.62 m/s. The experiment was designed to obtain a final product at around 40°C with water activity of 0.3 ± 0.1. Changes in the moisture content, water activity, enzyme activity of dried wheat germ during storage were measured. Results showed the fluidized-bed drying was found to reduce moisture content, water activity and lipase activity of raw wheat germ. After drying wheat germ, moisture content and water activity were between 5.8% to 7.2% and 0.28 to 0.40 respectively during 12 weeks of storage. The variation range of water activity indicated to retard lipid oxidation. All drying treatments displayed inactivation of lipase, except for drying condition of 50°C which showed relative high enzyme activity. During storage, lipase activity increased slowly during the first 6 weeks of storage and reached a plateau for another 6 weeks. As a result, using a fluidized-bed dryer was found to be effective drying technique in improving storage stability of wheat germ.Keywords: wheat germ, fluidized-bed dryer, storage, lipase, stability
Procedia PDF Downloads 2657037 Classification of Political Affiliations by Reduced Number of Features
Authors: Vesile Evrim, Aliyu Awwal
Abstract:
By the evolvement in technology, the way of expressing opinions switched the direction to the digital world. The domain of politics as one of the hottest topics of opinion mining research merged together with the behavior analysis for affiliation determination in text which constitutes the subject of this paper. This study aims to classify the text in news/blogs either as Republican or Democrat with the minimum number of features. As an initial set, 68 features which 64 are constituted by Linguistic Inquiry and Word Count (LIWC) features are tested against 14 benchmark classification algorithms. In the later experiments, the dimensions of the feature vector reduced based on the 7 feature selection algorithms. The results show that Decision Tree, Rule Induction and M5 Rule classifiers when used with SVM and IGR feature selection algorithms performed the best up to 82.5% accuracy on a given dataset. Further tests on a single feature and the linguistic based feature sets showed the similar results. The feature “function” as an aggregate feature of the linguistic category, is obtained as the most differentiating feature among the 68 features with 81% accuracy by itself in classifying articles either as Republican or Democrat.Keywords: feature selection, LIWC, machine learning, politics
Procedia PDF Downloads 3777036 Improving Fake News Detection Using K-means and Support Vector Machine Approaches
Authors: Kasra Majbouri Yazdi, Adel Majbouri Yazdi, Saeid Khodayi, Jingyu Hou, Wanlei Zhou, Saeed Saedy
Abstract:
Fake news and false information are big challenges of all types of media, especially social media. There is a lot of false information, fake likes, views and duplicated accounts as big social networks such as Facebook and Twitter admitted. Most information appearing on social media is doubtful and in some cases misleading. They need to be detected as soon as possible to avoid a negative impact on society. The dimensions of the fake news datasets are growing rapidly, so to obtain a better result of detecting false information with less computation time and complexity, the dimensions need to be reduced. One of the best techniques of reducing data size is using feature selection method. The aim of this technique is to choose a feature subset from the original set to improve the classification performance. In this paper, a feature selection method is proposed with the integration of K-means clustering and Support Vector Machine (SVM) approaches which work in four steps. First, the similarities between all features are calculated. Then, features are divided into several clusters. Next, the final feature set is selected from all clusters, and finally, fake news is classified based on the final feature subset using the SVM method. The proposed method was evaluated by comparing its performance with other state-of-the-art methods on several specific benchmark datasets and the outcome showed a better classification of false information for our work. The detection performance was improved in two aspects. On the one hand, the detection runtime process decreased, and on the other hand, the classification accuracy increased because of the elimination of redundant features and the reduction of datasets dimensions.Keywords: clustering, fake news detection, feature selection, machine learning, social media, support vector machine
Procedia PDF Downloads 1677035 DenseNet and Autoencoder Architecture for COVID-19 Chest X-Ray Image Classification and Improved U-Net Lung X-Ray Segmentation
Authors: Jonathan Gong
Abstract:
Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.Keywords: artificial intelligence, convolutional neural networks, deep learning, image processing, machine learning
Procedia PDF Downloads 1217034 Classification of Health Risk Factors to Predict the Risk of Falling in Older Adults
Authors: L. Lindsay, S. A. Coleman, D. Kerr, B. J. Taylor, A. Moorhead
Abstract:
Cognitive decline and frailty is apparent in older adults leading to an increased likelihood of the risk of falling. Currently health care professionals have to make professional decisions regarding such risks, and hence make difficult decisions regarding the future welfare of the ageing population. This study uses health data from The Irish Longitudinal Study on Ageing (TILDA), focusing on adults over the age of 50 years, in order to analyse health risk factors and predict the likelihood of falls. This prediction is based on the use of machine learning algorithms whereby health risk factors are used as inputs to predict the likelihood of falling. Initial results show that health risk factors such as long-term health issues contribute to the number of falls. The identification of such health risk factors has the potential to inform health and social care professionals, older people and their family members in order to mitigate daily living risks.Keywords: classification, falls, health risk factors, machine learning, older adults
Procedia PDF Downloads 1377033 Antioxidant Activity Of Gracilaria Fisheri Extract
Authors: Paam Bidaya
Abstract:
The red seaweed Gracilaria fisheri, widely distributed along Thailand's southern coastlines, has been discovered to be edible. Sulfated polysaccharides from G. fisheri were extracted in low-temperature (25 °C) water. Seaweed polysaccharides (SPs) have been shown to have various advantageous biological effects. This study aims to investigate total phenolic content and antioxidant capacity of G. fisheri extract. The total phenolic content of G. fisheri extract was determined using Folin-Cioucalteu method and calculated as gallic acid equivalents (GAE). The antioxidant activity of G. fisheri extract was performed via 2, 2-diphenyl-1- picrylhydrazyl (DPPH) free radical scavenging assay and 2,2’-azino-bis(3-ethylbenzothiazoline-6-sulfonic acid) (ABTS) radical scavenging capacity assays. The findings exhibited a strong correlation between antioxidant activity and the total phenol contents. In addition, DPPH and ABTS assays showed that G. fisheri extract showed antioxidant activities as a concentration-dependent manner. The IC50 values of G. fisheri extract were 902.19 μg/mL ± 0.785 and 727.98 μg/mL ± 0.822 for DPPH and ABTS, respectively. Vitamin C was used as a positive control in DPPH assay, while Trolox was used as a positive control in ABTS assay. To conclude, G. fisheri extract consists of a high amount of total phenolic content, which exhibit a significant antioxidant activity. However, further investigation regarding antioxidant activity should be performed in order to identify the mechanism of Gracilaria fisheri action.Keywords: ABTS assay, DPPH assay, sulfated polysaccharides, total phenolic content
Procedia PDF Downloads 188