Search results for: machine learning; medicinal plants

Authors: Sai Maniveer Adapa, Sai Guptha Perla, Adithya Reddy P.

Abstract:

Thyroid nodules can often be diagnosed with ultrasound imaging, although differentiating between benign and malignant nodules can be challenging for medical professionals. This work suggests a novel approach to increase the precision of thyroid nodule identification by combining machine learning and deep learning. The new approach first extracts information from the ultrasound pictures using a deep learning method known as a convolutional autoencoder. A support vector machine, a type of machine learning model, is then trained using these features. With an accuracy of 92.52%, the support vector machine can differentiate between benign and malignant nodules. This innovative technique may decrease the need for pointless biopsies and increase the accuracy of thyroid nodule detection.

Keywords: thyroid tumor diagnosis, ultrasound images, deep learning, machine learning, convolutional auto-encoder, support vector machine

Procedia PDF Downloads 30

Authors: Alok Kalra

Abstract:

Consumers and practitioners (medical herbalists, pharmacists, and aromatherapists) with strong and increased awareness about health and environment demand organically grown medicinal and aromatic plants (MAPs) to offer a valued product. As the system does not permit the use of synthetic fertilizers the use of nutrient rich organic manures is extremely important. CSIR-CIMAP has developed a complete recycling package for managing distillation and agro-waste of medicinal and aromatic plants for production of superior quality vermicompost involving microbes capable of producing high amounts of humic acid. The major benefits being faster composting period and nutrient rich vermicompost; a nutrient advantage of about 100-150% over the most commonly used organic manure (FYM). At CSIR-CIMAP, strains of microbial inoculants with multiple activities especially strains useful both as biofertilizers and biofungicide and consortia of microbes possessing diverse functional activities have been developed. CSIR-CIMAP has also initiated a program where a large number of accessions are being screened for identifying organic proficient genotypes in mints, ashwagandha, geranium and safed musli. Some of the natural plant growth promoters like calliterpenones from the plant Callicarpa macrophylla has been tested successfully for induction of rooting in stem cuttings and improving growth and yield of various crops. Some of the microbes especially the endophytes have even been identified improving the active constituents of medicinal and aromatic plants. The above said scientific interventions making organic farming a charming proposition would be discussed in details.

Keywords: organic agriculture, microbial inoculants, organic fertilizers, natural plant growth promoters

Procedia PDF Downloads 213

Authors: Christodoulou Christos, Politis Anastasios

Abstract:

A large majority of users favoured to wireless LAN connection since it was so simple to use. A wireless network can be the target of numerous attacks. Class hijacking is a well-known attack that is fairly simple to execute and has significant repercussions on users. The statistical flow analysis based on machine learning (ML) techniques is a promising categorization methodology. In a given dataset, which in the context of this paper is a collection of components representing frames belonging to various flows, machine learning (ML) can offer a technique for identifying and characterizing structural patterns. It is possible to classify individual packets using these patterns. It is possible to identify fraudulent conduct, such as class hijacking, and take necessary action as a result. In this study, we explore a way to use machine learning approaches to thwart this attack.

Keywords: wireless lan, quality of service, machine learning, class hijacking, EDCA remapping

Procedia PDF Downloads 33

Authors: Hamza Zidoum

Abstract:

This paper investigates the impact of human genetic variation on the function of human proteins using machine-learning algorithms. Single-Nucleotide Polymorphism represents the most common form of human genome variation. We focus on the single amino-acid polymorphism located in the coding region as they can affect the protein function leading to pathologic phenotypic change. We use several supervised Machine Learning methods to identify structural properties correlated with increased risk of the missense mutation being damaging. SVM associated with Principal Component Analysis give the best performance.

Keywords: single-nucleotide polymorphism, machine learning, feature selection, SVM

Procedia PDF Downloads 355

Authors: Noshaba Dilbar, Maria Jabbar

Abstract:

Medicinal plants are considered to be the richest source of drug discovery. The main cause of medicinal properties of plants is the presence of bioactive compounds in them. Phytochemical screening is the valuable process that detects bioactive compounds(secondary metabolites) in plants. The present study was carried out to determine phytochemical profile and ethnobotanical importance of Capparidaceae species. ( Capparis spinosa and Dipterygium glaucum). The selection of plants was made on basis of traditional knowledge of their usage in ayurvedic medicines. Different type of solvents(ethanol, methanol, chloroform, benzene and petroleum ether) were used to make extracts of dry and fresh plants. Phytochemical screening was made by using various standard techniques. Results reveal the presence of large range of bioactive compounds i.e alakloids, saponins, flavonoids, terpenoids, glycosides, phenols and steroids. Methanol, petroleum ether and chloroform extracts showed high extractability of bioactive compounds. The results obtained ensure these plants a reliable source of pharmacological industry and can be used in making of various biological friendly drugs.

Keywords: bioactive compounds, Capparidaceae, phytochemical screening, secondary metabolites

Procedia PDF Downloads 144

Authors: Geeta, Richa, M. L. Sharma

Abstract:

Himachal Pradesh, a hilly State of India located in the Western Himalayas, with varied altitudinal gradients and climatic conditions, is a repository of plant diversity and the traditional knowledge associated with plants. The State is inhabited by various tribal communities who usually depend upon local plants for curing various ailments. Utilization of plant resources in their day-to-day life has been an age old practice of the people inhabiting this State. The present study pertains to the tribal district Kinnaur of Himachal Pradesh, located between 77°45’ and 79°00’35” east longitudes and between 31°05’50” and 32°05’15” north altitudes. Being a remote area with only very basic medical facilities, local people mostly use traditional herbal medicines for primary healthcare needs. Traditional healers called “Amji” are usually very secretive in revealing their medicinal knowledge to novice and pass on their knowledge to next generation orally. As a result, no written records of healing herbs are available. The aim of present study was to collect and consolidate the ethno-medicinal knowledge of local people of the district about the use of plants for treating gastrointestinal ailments. The ethnobotanical information was collected from the local practitioners, herbal healers and elderly people having rich knowledge about the medicinal herbs through semi-structured questionnaire and key informant discussions. A total 46 plant species belonging to 40 genera and 24 families have been identified which are used as cure for gastrointestinal ailments. Among the parts used for gastointestinal ailments, aerial parts (14%) were followed by the whole plant (13%), root (8%), leaves (6%), flower (5%), fruit and seed (3%) and tuber (1%). These plant species could be prioritized for conservation and subject to further studies related to phytochemical screening for their authenticity. Most of the medicinal plants of the region are collected from the wild and are often harvested for trade. Sustainable harvesting and domestication of the highly traded species from the study area is needed.

Keywords: Amji, gastrointestinal, Kinnaur, medicinal plants, traditional knowledge

Procedia PDF Downloads 372

Authors: Anush Patric, M. Jadeyegowda, M. N. Ramesh, M. Ravikumar, C. R. Ajay

Abstract:

Kodagu district which is situated in Central Western Ghats regions falls in one of the hottest of hot spots of biodiversity which is recognised by UNESCO. The district has one of the highest densities of community managed sacred forests in the world with rich floral and faunal diversity. It is a habitat for more than ten different types of Ethnic Indigenous tribal groups commonly called ‘Girijanas’ (Soligas, Yarvas, Jenukuruba, Bettakuruba etc.), who are having the rich knowledge of medicinal value of the plants that are commonly available in the forest. The tribal men of this region are the treasure house of the traditional plant knowledge and health care practices. An ethnobotanical survey was undertaken in tribal areas of the district to collect information about some of the indigenous medicinal plant knowledge of tribal people by semi-structured interviews, ranking exercises and field observations on their native habitat in order to evaluate the potential medicinal uses of local plants. The study revealed that, the ethnobotanical information of 83 plant species belonging to 45 families, of the total 83 species documented, most plants used in the treatment were trees (11 species), shrubs (41 species), herbs (22 species) and rarely climbers (9 species) which are used in the treatment of Hyperacidity, Respiratory disorders, Snake bite Abortifacient, Anthelmintic, Paralysis, Antiseptic, Fever, Chest pain, Stomachic, Jaundice, Piles, Asthma, Malaria, Renal disorders, Malaria and many other diseases. Maximum of 6 plant species each of Acanthaceae, Apiaceae and were used for drug preparation, followed by Asclepiadaceae, Liliaceae, Fabaceae, Verbenaceae, Caesalpinaceae, Bombaceae, Papilonaceae, Solanaceae, Rubiaceae, Myrtaceae, Amaranthaceae, Asteraceae, Ascelepidaceae, Cucurbitaceae, Apocyanaceae, and Solanaceae etc. In our present study, only medicinal plants and their local medicinal uses are recorded and presented. Information was obtained by local informants having the knowledge about medicinal plants. About 23 local tribes were interviewed. For each plant, necessary information like botanical name, family of plant species, local name and uses are given. Recent trend shows a decline in the number of traditional herbal healers in the tribal areas since the younger generation is not interested to continue this tradition. Hence, there is an urgent need to record and preserve all information on plants used by different ethnic/tribal communities for various purposes before it reaches to verge of extinction. In addition, several wild medicinal plants are declining in numbers due to deforestation and forest fires. There is need for phytochemical analysis and conservation measures to be taken for conserving medicinal plant species which is far better than allopathic medicines and these do not cause any side effects as they are the natural disease healers. So, conservation strategies have to be practiced in all levels and sectors by creating awareness about the value of such medicinal plants, and it is necessary to save the disappearing plants to strengthen the document and to conserve them for future generation.

Keywords: diseases, ethnic groups, folk medicine, Kodagu, medicinal plants

Procedia PDF Downloads 247

Authors: Muna Jalal Ali, Essam A. Makky, Mashitah M. Yusoff

Abstract:

Objectives: The aim of this study to evaluate the antimicrobial susceptibility of combined toothpaste with medicinal plants and the relations between the commercial toothpaste to its price and the patient age as well. Materials and Methods: Oral isolates of different patients aged 3 to 60 years were obtained, purified, and tested against four different ethnomedicinal plant extracts for antimicrobial activity. A total of 10 different commercial toothpastes (different brands and prices) were collected from the market, and the combined action of the medicinal plants and toothpaste was studied. Results: We found a higher bacterial population in the age group of 3–40 years than the group of 40–60 years, with approximately 44% and 32%, respectively. The combined action of ethanolic extract (alone) against oral isolates showed a synergistic effect, with 32.20, 30.50, and 25.42% for combinations A (Ci/Ca), B (Ci/Ca/P), and C (Ci/Ca/P/N), respectively. By contrast, the combined action of ethnomedicinal plants with 10 different toothpastes improved the antimicrobial sensitivity by 60, 100, and 0% for combinations A, B, and C respectively. Clinical relevance: The ethanolic extract of only combinations A and B with commercial toothpaste showed high antibacterial activity against oral isolates and the effectiveness of toothpaste is not related to the price.

Keywords: microbial evolution, oral isolates, ethnomedicinal plants, antimicrobial activity, toothpaste

Procedia PDF Downloads 286

Authors: Mehmet Akif Bütüner, İlhan Koşalay

Abstract:

Hydroelectric power plants (HEPPs) are renewable energy power plants with the highest installed power in the world. While the control systems operating in these power plants ensure that the system operates at the desired operating point, it is also responsible for stopping the relevant unit safely in case of any malfunction. While these control systems are expected not to miss signals that require stopping, on the other hand, it is desired not to cause unnecessary stops. In traditional control systems including modern systems with SCADA infrastructure, alarm conditions to create warnings or trip conditions to put relevant unit out of service automatically are usually generated with predefined limits regardless of different operating conditions. This approach results in alarm/trip conditions to be less likely to detect minimal changes which may result in serious malfunction scenarios in near future. With the methods proposed in this research, routine behavior of the oil circulation of hydraulic governor of a HEPP will be modeled with machine learning methods using historical data obtained from SCADA system. Using the created model and recently gathered data from control system, oil pressure of hydraulic accumulators will be estimated. Comparison of this estimation with the measurements made and recorded instantly by the SCADA system will help to foresee failure before becoming worse and determine remaining useful life. By using model outputs, maintenance works will be made more planned, so that undesired stops are prevented, and in case of any malfunction, the system will be stopped or several alarms are triggered before the problem grows.

Keywords: hydroelectric, governor, anomaly detection, machine learning, regression

Procedia PDF Downloads 65

Authors: Enock E. Goler, Emmanuel H. Kwon-Ndung, Gbenga F. Akomolafe, Terna T. Paul, Markus Musa, Joshua I. Waya, James H. Okogbaa

Abstract:

An ethno-medicinal survey of plants used in treating various diseases and ailments was carried out in the study area of Nasarawa State, North Central Nigeria to obtain information on their uses and potentials. The ethno-medicinal survey was administered through structured questionnaires among local inhabitants from areas with high plant density and diversity within the various Local Government Areas of the State. A total of 84 (Eighty four) plant species belonging to 45 (Forty five) families were found to be useful in treatment of various ailments such as diabetes, measles, fever, asthma, jaundice, pneumonia, sexually transmitted diseases (STDs), aches, diarrhea, cough, arthritis, yellow fever, typhoid, erectile dysfunction and excessive bleeding. Different parts of the plant such as the roots, leaves and stems are used in preparing herbal remedies which could be from dry or freshly collected plants. The main methods of preparation are decoction or infusion, while in some cases the plant parts used are consumed directly. Residents in the study areas find the herbal remedy cheaper and more accessible and claimed that there are no side effects compared to orthodox medicine. This study has confirmed the need towards the conscious conservation of plant genetic resources in order to ensure sustained access to these ethno-medicinal plant materials.

Keywords: ethno-medicinal, Nasarawa, plants, survey

Procedia PDF Downloads 252

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

The widespread use of machine learning applications in production is significantly accelerated by improved computing power and increasing data availability. Predictive quality enables the assurance of product quality by using machine learning models as a basis for decisions on test results. The use of real Bosch production data based on geometric gauge blocks from machining, mating data from assembly and hydraulic measurement data from final testing of directional valves is a promising approach to classifying the quality characteristics of workpieces.

Keywords: machine learning, classification, predictive quality, hydraulics, supervised learning

Procedia PDF Downloads 173

Authors: Kwanchai Ratanamanee, Pattra Ahmadi Pirshahid, Yaowaluk Khamphan, Sirinan Thubthimthad

Abstract:

Obesity is a main global health problem. The obesity rated has continued to be higher and higher. It causes to serious systems, diabetes, coronary artery disease, stroke, and some types of cancer. Oristat is one of the best drugs worldwide used as a pancreatic lipase inhibitor. To develop the new therapeutic drugs from medicinal plant always explored. In this study, 24 medicinal plants were investigated for their pancreatic lipase and cholesterol esterase inhibitory effects with Fluorometer assay and oristat as a positive control. It showed that the ethanolic extract of pods of Acacia concinna (Willd.) D.C., possess pancreatic lipase and cholesterol esterase inhibitory activities of IC50 at 2.73 and 3.77 mg/ml respectively as well as oral acute toxicity of the extract (LD50) was 6,300 mg/kg body weight. The extract of A.concinna should be further investigated in animal testing. The results of pancreatic lipase and cholesterol esterase inhibitor of the extracts will lead us to utilize A.concinna for developing as obesity dietary supplement from a medicinal plant.

Keywords: Acacia concinna (Willd.) D. C., cholesterol esterase, obesity, pancreatic lipase

Procedia PDF Downloads 448

Authors: Anil F. Felek, Mehmet M. Ozcan, Faruk Akyazi

Abstract:

Volatile oils of medicinal and aromatic plants are important for managing nematological problems in agriculture. In present study, volatile oils extracted from five medicinal and aromatic plants including Origanum onites (flower+steam+leaf), Salvia officinalis (leaf), Lippia citriodora (leaf+seed), Mentha spicata (leaf) and Mentha longifolia (leaf) were tested for egg hatching inhibition activity against root-knot nematode Meloidogyne hapla under laboratory conditions. The essential oils were extracted using water distillation method with a Clevenger system. For the homogenisation process of the oils, 2% gum arabic solution was used and 4 µl oils was added into 1ml filtered gum arabic solution to prepare the last stock solution. 5 ml of stock solution and 1 ml of M. hapla egg suspension (about 100 eggs) were added into petri dishes. Gum arabic solution was used as control. Seven days after exposure to oils at room temperature (26±2 °C), the cumulative hatched and unhatched eggs were counted under 40X inverted light microscope and Abbott’s formula was used to calculate egg hatching inhibition rates. As a result, the highest inhibition rate was found as 54% for O. onites. In addition, the other inhibition rates varied as 31.4%, 21.6%, 23.8%, 25.67% for the other plants, S. officinalis, M. longifolia, M. spicata and L. citriodora, respectively. Carvacrol was found as the main component (68.8%) of O. onites followed by Thujone 27.77% for S. officinalis, I-Menthone 76.92% for M. longifolia, Carvone 27.05% for M. spicata and Citral 19.32% for L. citriodora.

Keywords: egg hatching, Meloidogyne hapla, medicinal and aromatic plants, root-knot nematodes, volatile oils

Procedia PDF Downloads 236

Authors: Nassima Elyebdri, Asma Boumediou, Soumia Addoun

Abstract:

Traditional medicine has been part of the Algerian culture for decades. In particular, the city of Tlemcen still retains practices based on phytotherapy to the present day, as this kind of medicine fulfills the needs of its followers among the local population. The toxic plants contain diverse natural substances which supplied a lot of medicine in the pharmaceutical industry. In order to explore new medicinal sources among toxic plants, an ethnobotanical study was carried out on the use of these plants by the population, at Emir Abdelkader Square of the city of Tlemcen, a rather busy place with a high number of traditional health practitioners and herbalists. This is a descriptive and transversal study aimed at estimating the frequency of using toxic plants among the studied population, for a period of 4 months. The information was collected, using self-anonymous questionnaires, and analyzed by the IBM SPSS Statistics software used for statistical analysis. A sample of 200 people, including 120 women and 80 men, were interviewed. The mean age was 41 ± 16 years. Among those questioned, 83.5% used plants; 8% of them used toxic plants and 35% used plants that can be toxic under certain conditions. Some improvements were observed in 88% of the cases where toxic plants were used. 80 medicinal plants, belonging to 36 botanical families, were listed, identified and classified. The most frequent indications for these plants were for respiratory diseases in 64.7% of cases, and for digestive disorders in 51.5% of cases. 11% of these plants are toxic, 26% could be toxic under certain conditions. Among toxics plants, the most common ones are Berberis vulgaris with 5.4%, indicated in the treatment of uterine fibroids and thyroid, Rhamnus alaternus with 4.8% for hepatic jaundice, Nerium oleander with 3% for hemorrhoids, Ruta chalepensis with 1.2%, indicated for digestive disorders and dysmenorrhea, and Viscum album with 1.2%, indicated for respiratory diseases. The most common plants that could be toxic are Mentha pulegium (15.6%), Eucalyptus globulus (11.4%), and Pimpinella anisum (10.2%). This study revealed interesting results on the use of toxic plants, which are likely to serve as a basis for further ethno-pharmacological investigations in order to get new drug sources.

Keywords: ethnobotany, phytotherapy, Tlemcen, toxic plants

Procedia PDF Downloads 295

Authors: Matthew Omoniyi Adebola, Jude E Amadi

Abstract:

Ground nut (Arachis hypogaea) is one of the most popular commercial crops in Nigeria. Its suc-cessful production has been drastically affected by early leaf spot disease caused by Mycosphae-rella arachidis Deighton. In vitro control of the pathogen by six medicinal plants (Entada afri-cana, Vitex doniana, Lawsonia inermis, Azadirachta indica, Acalypha hispida and Nuaclea lati-folia) was assessed in this study. The extracts of the plants were prepared using cold and hot wa-ter and alcohol. The pathogen was isolated from ground nut infected with early leaf spot disease. The results revealed a great significant difference (P<0.05) in yield of extracts between cold water, hot water, and alcohol extracts. A significant difference (P<0.05) was observed in percentage concentrations of the various phytochemical constituents present in the extracts. Flavonoids per-centage concentration was the highest (0.68 - 1.95%) followed by saponnin(0.09-1.53%) in N. latifolia extracts. Steroiods had the least percentage concentrations (0.00- 0.09%)followed by terpenoids(0.02–0.71%) and proanthocyannin (0.05 – 0.86%). N. latifolia extracts produced the highest percentage concentrations (0.07–1.95%) of all the phytochemicals followed by A. indi-ca(0.05–1.64%)and least concentrations were obtained in A. hispidia(0.09 – 0.87%)and V. do-niana (0.00–0.88%). The extracts inhibited spore germination and growth of M. arachidis. The inhibition by alcohol extracts was high and significantly different (P>0.05) from cold and hot water extracts. Alcohol extract of L. inermis gave 100% spore germination inhibition followed by N. latifolia and A.indica with 97.75% and 85.60% inhibition respectively. Therefore, field trials of these six medicinal plants on the control of early leaf spot disease of ground nut are rec-ommended.

Keywords: groundnut, phytochemicals, medicinal plants, extracts, inhibition

Procedia PDF Downloads 269

Authors: Tesleem Adewale Ibrahim

Abstract:

Introduction: The prevalence of methicillin-resistant Staphylococcus aureus (MRSA) has been slowly rising in Nigeria for the past few decades. Therefore, novel classes of antibiotics are indispensable to combat the increased incidence of newly emerging multidrug-resistant bacteria like MRSA. Plants have been commonly used in popular medicine of most cultures for the treatment of disease. The in vitro antibacterial activity of some Nigerian common medicinal plants used in traditional medicine has been reported. The aim of this study was to investigate the antibacterial and anti-biofilm of these native plants (Entada abysinnica (leaves), Croton macrostachyus (leaves), Bridelia speciosa (seeds, bark), and Aframomum melegueta (leaves, seeds, and stem) collected in Southwestern Nigeria against a panel of seven biofilm-forming MRSA. Methods: Minimum inhibitory concentrations (MIC) and minimum bactericidal concentrations (MBC) of the plant extracts against MRSA were determined by the broth dilution method, and the anti-biofilm assay of the most potent plant extract was performed. Result: The results revealed that, of the four plants, water extracts of leaves of Entada abysinnica, leaves of Croton macrostachyus, seeds and bark Bridelia speciosa, and seeds of Aframomum melegueta exhibited significant antibacterial activity. Based on the MIC/MBC ratio, the extracts of these plants were determined to be bacteriostatic in nature. Anti-biofilm assay showed that the extract of seeds of Aframomum melegueta and leaves of Croton macrostachyus fairly inhibited the growth of MRSA in the preformed biofilm matrix. Conclusion: These four medicinal plant species may represent a source of alternative drugs derived from plant extracts based on folklore use and ethnobotanical knowledge from southwest Nigeria.

Keywords: extract, MRSA, antibacterial, biofilm, medicinal plants

Procedia PDF Downloads 104

Authors: Sadia Nasrin Tisha, Mushfika Sharmin Rahman, Javier Orduz

Abstract:

Machine learning is applied in a variety of fields throughout the world. The healthcare sector has benefited enormously from it. One of the most effective approaches for predicting human heart diseases is to use machine learning applications to classify data and predict the outcome as a classification. However, with the rapid advancement of quantum technology, quantum computing has emerged as a potential game-changer for many applications. Quantum algorithms have the potential to execute substantially faster than their classical equivalents, which can lead to significant improvements in computational performance and efficiency. In this study, we applied quantum machine learning concepts to predict coronary heart diseases from text data. We experimented thrice with three different features; and three feature sets. The data set consisted of 100 data points. We pursue to do a comparative analysis of the two approaches, highlighting the potential benefits of quantum machine learning for predicting heart diseases.

Keywords: quantum machine learning, SVM, QSVM, matrix product state

Procedia PDF Downloads 67

Authors: Syed Farooq Adil, Merajuddinkhan, Mujeeb Khan, Hamad Z. Alkhathlan

Abstract:

Phytochemicals from plant extracts belong to an important source of natural products which have demonstrated excellent cytotoxic activities. However, plants of different origins exhibit diverse chemical compositions and bioactivities. Therefore, the discovery of plants based new anticancer agents from different parts of the world is always challenging. In this study, methanolic extracts of different parts of 11 plants from Saudi Arabia have been tested in vitro for their anticancer potential on human liver cancer cell line (HepG2). Particularly, for this study, plants from Asteraceae, Resedaceae, and Polygonaceae families were chosen on the basis of locally available ethnobotanical data and their medicinal properties. Among 12 tested extract samples, three samples obtained from Artemisia monosperma stem, Ochradenus baccatus aerial parts, and Pulicaria glutinosa stem have demonstrated interesting cytotoxic activities with a cell viability of 29.3%, 28.4% and 24.2%, respectively. Whereas, four plant extracts including Calendula arvensis aerial parts, Scorzonera musilii whole plant, A. monosperma leaves show moderate anticancer properties bearing a cell viability ranging from 11.9 to 16.7%. The remaining extracts have shown poor cytotoxic activities. Subsequently, GC-MS analysis of methanolic extracts of the four most active plants extracts such as C. comosum, O. baccatus, P. glutinosa and A. monosperma detected the presence of 41 phytomolecules. Among which 3-(4-hydroxyphenyl) propionitrile (1), 8,11-octadecadiynoic acid methyl ester (2), 6,7-dimethoxycoumarin (3), and 1-(2-hydroxyphenyl) ethenone (4) were found to be the lead compounds of C. comosum, O. baccatus P. glutinosa and A. monosperma, respectively.

Keywords: medicinal plants, asteraceae, polygonaceae, hepg2

Procedia PDF Downloads 105

Authors: Anita Khadka, Gregory Epiphaniou, Carsten Maple

Abstract:

There is a dramatic surge in the adoption of machine learning (ML) techniques in many areas, including the nuclear industry (such as fault diagnosis and fuel management in nuclear power plants), autonomous systems (including self-driving vehicles), space systems (space debris recovery, for example), medical surgery, network intrusion detection, malware detection, to name a few. With the application of learning methods in such diverse domains, artificial intelligence (AI) has become a part of everyday modern human life. To date, the predominant focus has been on developing underpinning ML algorithms that can improve accuracy, while factors such as resiliency and robustness of algorithms have been largely overlooked. If an adversarial attack is able to compromise the learning method or data, the consequences can be fatal, especially but not exclusively in safety-critical applications. In this paper, we present an in-depth analysis of five adversarial attacks and three defence methods on a crack detection ML model. Our analysis shows that it can be dangerous to adopt machine learning techniques in security-critical areas such as the nuclear industry without rigorous testing since they may be vulnerable to adversarial attacks. While common defence methods can effectively defend against different attacks, none of the three considered can provide protection against all five adversarial attacks analysed.

Keywords: adversarial machine learning, attacks, defences, nuclear industry, crack detection

Procedia PDF Downloads 133

Authors: Azene Zenebe

Abstract:

Deep learning is a subset of machine learning which incorporates techniques for the construction of artificial neural networks and found to be useful for modeling complex problems with large dataset. Deep learning requires a very high power computational and longer time for training. By aggregating computing power, high performance computer (HPC) has emerged as an approach to resolving advanced problems and performing data-driven research activities. Cyber threat intelligence (CIT) is actionable information or insight an organization or individual uses to understand the threats that have, will, or are currently targeting the organization. Results of review of literature will be presented along with results of experimental study that compares the performance of tree-based and function-base machine learning including deep learning algorithms using secondary dataset collected from darknet.

Keywords: deep-learning, cyber security, cyber threat modeling, tree-based machine learning, function-based machine learning, data science

Procedia PDF Downloads 131

Authors: Songul Cinaroglu

Abstract:

Machine learning regression methods are recommended as an alternative to classical regression methods in the existence of variables which are difficult to model. Data for health expenditure is typically non-normal and have a heavily skewed distribution. This study aims to compare machine learning regression methods by hyperparameter tuning to predict health expenditure per capita. A multiple regression model was conducted and performance results of Lasso Regression, Random Forest Regression and Support Vector Machine Regression recorded when different hyperparameters are assigned. Lambda (λ) value for Lasso Regression, number of trees for Random Forest Regression, epsilon (ε) value for Support Vector Regression was determined as hyperparameters. Study results performed by using 'k' fold cross validation changed from 5 to 50, indicate the difference between machine learning regression results in terms of R², RMSE and MAE values that are statistically significant (p < 0.001). Study results reveal that Random Forest Regression (R² ˃ 0.7500, RMSE ≤ 0.6000 ve MAE ≤ 0.4000) outperforms other machine learning regression methods. It is highly advisable to use machine learning regression methods for modelling health expenditures.

Keywords: machine learning, lasso regression, random forest regression, support vector regression, hyperparameter tuning, health expenditure

Procedia PDF Downloads 201

Authors: Luisa Cabezas, Karol Leal, Harold Mendoza, Fabio Trochez, Angel Lozada

Abstract:

According to the 2030 Agenda for Sustainable Development Goals (SDG) in which equal importance is given to economic, social, and environmental dimensions where the equality and dignity of each human person is placed at the center of discussion, changing the development concept for one with more responsibility with the environment. It can be found that the energy and food systems are deeply entangled, and they are transversal to the 17 proposed SDG. In this order of ideas, a research project is carried out at Unidad Central del Valle del Cauca (UCEVA) with these two systems in mind, on one hand the energy transition and, on the other hand the transformation of agri-food systems. This project it could be achieved by automation and control irrigation system of medicinal, aromatic, and condimentary plants (MACP) area within the UCEVA Agroecological Farm and located in rural area of Tulua municipality (Valle del Cauca Department, Colombia). This system have allowed to stablish a remote monitoring of MACP area, including MACP moisture measurement, and execute the required system actions. In addition, the electrical system of irrigation control system is powered by a scalable photovoltaic solar energy system based on its specifications. Thus, the developed system automates and control de irrigation system, which is energetically self-sustainable and allows to satisfy the MACP area requirements. Is important to highlight that at MACP area, several medicinal, aromatic, and condimentary plants species are preserved to become primary sources for the pharmaceutical industry and, in many occasions, the only medicines for many communities. Therefore, preserve medicinal plants area would generates medicinal security and preserve cultural heritage as these plants are part of ancestral knowledge that penetrate academic and research communities at UCEVA campus to other society sectors.

Keywords: ancestral knowledge, climate change, medicinal plants, solar energy

Procedia PDF Downloads 203

Authors: Sam Khozama, Ali M. Mayya

Abstract:

Breast cancer is one of the most common types in women. Early prediction of breast cancer helps physicians detect cancer in its early stages. Big cancer data needs a very powerful tool to analyze and extract predictions. Machine learning and deep learning are two of the most efficient tools for predicting cancer based on textual data. In this study, we developed a fusion model of two machine learning and deep learning models. To obtain the final prediction, Long-Short Term Memory (LSTM) and ensemble learning with hyper parameters optimization are used, and score-level fusion is used. Experiments are done on the Breast Cancer Surveillance Consortium (BCSC) dataset after balancing and grouping the class categories. Five different training scenarios are used, and the tests show that the designed fusion model improved the performance by 3.3% compared to the individual models.

Keywords: machine learning, deep learning, cancer prediction, breast cancer, LSTM, fusion

Procedia PDF Downloads 135

Authors: Vincent Liu

Abstract:

Machine learning algorithms (ML) can achieve high accuracy in predicting outcomes compared to classical models. Metaheuristic, nature-inspired algorithms can enhance traditional ML algorithms by optimizing them such as by performing feature selection. We compare ten ML algorithms to predict 30-day hospital readmission rates for diabetes patients in the US using a dataset from UCI Machine Learning Repository with feature selection performed by Greywolf nature-inspired algorithm. The baseline accuracy for the initial random forest model was 65%. After performing feature engineering, SMOTE for class balancing, and Greywolf optimization, the machine learning algorithms showed better metrics, including F1 scores, accuracy, and confusion matrix with improvements ranging in 10%-30%, and a best model of XGBoost with an accuracy of 95%. Applying machine learning this way can improve patient outcomes as unnecessary rehospitalizations can be prevented by focusing on patients that are at a higher risk of readmission.

Keywords: diabetes, machine learning, 30-day readmission, metaheuristic

Procedia PDF Downloads 32

Authors: Gemma A. Gruyal

Abstract:

Plants can contain a wide variety of substances with antioxidative properties which are associated to important health benefits. These positive health effects are of great importance at a time when the environment is laden with many toxic substances. Five selected herbal plants namely, Mimosa pudica, Phyllanthus niruri, Ceiba pentandra, Eleusine polydactyla and Trema amboinensis, were chosen for the experiment to investigate their total phenolics content and antioxidant activities using ABTS radical cation decolorization power, and ferric reducing antioxidant power. The total phenolic content of each herbal plants ranges from 0.84 to 42.59 mg gallic acid equivalent/g. The antioxidant activity in the ABTS radical cation decolorization power varies from 0.005 to 0.362 mg trolox equivalent/g and the FRAP ranges from 0.30 to 28.42 mg gallic acid equivalent/g. Among the five medicinal plants, Mimosa pudica has been an excellent performer in terms of the 3 parameters measured; it is followed by Phyllanthus niruri. The five herbal plants do not have equivalent antioxidant power. The relative high values for M. pudica and P. niruri supports the medicinal value of both plants. The total phenolics, ABTS and FRAP correlate strongly with one another.

Keywords: ABTS, FRAP, Leaf extracts, phenol

Procedia PDF Downloads 412

Authors: Rodrigo Aguiar, Adelino Ferreira

Abstract:

Road traffic accidents are the leading cause of unnatural death and injuries worldwide, representing a significant problem of road safety. In this context, the use of artificial intelligence with advanced machine learning techniques has gained prominence as a promising approach to predict traffic accidents. This article investigates the application of machine learning algorithms to develop traffic accident frequency prediction models. Models are evaluated based on performance metrics, making it possible to do a comparative analysis with traditional prediction approaches. The results suggest that machine learning can provide a powerful tool for accident prediction, which will contribute to making more informed decisions regarding road safety.

Keywords: machine learning, artificial intelligence, frequency of accidents, road safety

Procedia PDF Downloads 61

Authors: Seongjun Kim, Sanghoon Shim, Jinwooung Kim, Jaehwan Jung, Sung-Ah Kim

Abstract:

As the development of information and communication technology, the convergence of machine learning of the ICT area and design is attempted. In this way, it is possible to grasp the correlation between various design elements, which was difficult to grasp, and to reflect this in the design result. In architecture, there is an attempt to predict the performance, which is difficult to grasp in the past, by finding the correlation among multiple factors mainly through machine learning. In architectural design area, some attempts to predict the performance affected by various factors have been tried. With machine learning, it is possible to quickly predict performance. The aim of this study is to propose a model that predicts performance according to the block arrangement of apartment housing through machine learning and the design alternative which satisfies the performance such as the daylight hours in the most similar form to the alternative proposed by the designer. Through this study, a designer can proceed with the design considering various design alternatives and accurate performances quickly from the early design stage.

Keywords: apartment housing, machine learning, multi-objective optimization, performance prediction

Procedia PDF Downloads 452

Authors: Sajjad Ahmed, Knut Hinkelmann, Flavio Corradini

Abstract:

Fake news detection research is still in the early stage as this is a relatively new phenomenon in the interest raised by society. Machine learning helps to solve complex problems and to build AI systems nowadays and especially in those cases where we have tacit knowledge or the knowledge that is not known. We used machine learning algorithms and for identification of fake news; we applied three classifiers; Passive Aggressive, Naïve Bayes, and Support Vector Machine. Simple classification is not completely correct in fake news detection because classification methods are not specialized for fake news. With the integration of machine learning and text-based processing, we can detect fake news and build classifiers that can classify the news data. Text classification mainly focuses on extracting various features of text and after that incorporating those features into classification. The big challenge in this area is the lack of an efficient way to differentiate between fake and non-fake due to the unavailability of corpora. We applied three different machine learning classifiers on two publicly available datasets. Experimental analysis based on the existing dataset indicates a very encouraging and improved performance.

Keywords: fake news detection, natural language processing, machine learning, classification techniques.

Procedia PDF Downloads 135

Authors: Hamdi Belfeki, Belgacem Chandoul, Mnasser Hassouna, Mondher Mejri

Abstract:

Aqueous and ethanolic extracts of eight Tunisian aromatic and medicinal plants (TAMP) were characterized by studying their composition in polyphenols and also their antiradical and antioxidant capacities. In absence and in the presence of the various extracts, α-amylase from Bacillus subtlis activity, was measured in order to detect a potential inhibition. The total contents of polyphenols and flavonoid vary in function of TAMP and the mobile phase used for the extraction (distilled water or ethanol). The ethanolic extracts showed the most significant antiradical and antioxidant activities. Only the extracts from Coriandrum sativum showed a significant inhibiting effect on the α-amylase activity. This inhibiting capacity could be correlated with the chemical profile of the two extracts, due to the fact that they have the greatest amount of total flavonoid. The ethanolic extract has the most important antioxidant and anti-radicalizing activities among the sixteen extracts studied. The inhibition kinetics of the two coriander extracts were evaluated by pre-incubation method, using Lineweaver-Burk’s equation, obtained by linearization of Michaeilis-Menten’s expression. The results showed that both extracts exercised a competitive inhibition mechanism.

Keywords: α-amylase, antioxidant activity, aromatic and medicinal plants, inhibition

Procedia PDF Downloads 422

Authors: N. Nwachoko, E. B. Essien, E. O. Ayalogu

Abstract:

Owing to the outbreak of different diseases and microbial resistance to some available drugs, proper identification, and evaluation of plants have been encouraged. There have been claims worldwide by the traditional system that some plants possessed medicinal properties. Plants and their components have been said to be source of large amount of drugs which comprise of distinct groups such as antispasmodics, anticancer and antimicrobials. Researchers have reported that chemicals in plants are responsible for the medicinal uses of plants. Thus this study evaluated the protective effect of Aframomun chrysanthum seed aqueous extract in acetaminophen-induced liver toxicity in rats. A suspension of 750 mg/kg acetaminophen was administered once every 72 hours to induce toxicity in the rats. Oral administration of 500, 1000 and 2000 mg/kg body weight of the extract and 100 mg/kg of silymarin (reference drug) were administered for 10 days. Biochemical analysis showed significant (p < 0.05) increase in the activities of aspartate aminotransferase (AST), alanine aminotransferase (ALT)and alkaline phosphatase (ALP)as well as the concentrations of albumin (ALB) and total bilirubin (T.B.) levels in rats administered with acetaminophen only. The levels of these parameters were significantly (p < 0.05) decreased in the groups pretreated with the extract.

Keywords: Aframomun chrysanthum, silymarin, hepatoprotective, toxicity

Procedia PDF Downloads 365