Search results for: tree algorithms

Authors: Mohsen Dourandish

Abstract:

Iran has a huge pipeline network in every state of country which is the longest and vastest pipeline network after Russia and USA (360,000 Km high pressure pipelines and 250,000 Km distribution networks). Furthermore in recent years National Iranian Gas Company is planning to develop natural gas network to cover all cities and villages above 20 families, in a way that 97 percent of Iran population will be gas consumer by 2020. In this condition, network resiliency will be the first priority of NIGC and due to that several planning for increasing resiliency of gas network is under construction. The most important strategy of NIGC is converting tree form pattern network to loop gas networks and developing underground gas storage near main gas consuming centers. In this regard NIGC is planning for construction of over 3500 km high-pressure pipeline and also 10 TCM gas storage capacities in UGSs.

Keywords: Iranian gas network, peak shaving, resiliency, underground gas storage

Procedia PDF Downloads 319

Authors: D. Augutis, M. Balalaikins, D. Bastyte, R. Ferenca, A. Gintaras, R. Karpuska, G. Svitra, U. Valainis

Abstract:

Osmoderma species complex (consisting of Osmoderma eremita, O. barnabita, O. lassallei and O. cristinae) is a scarab beetle serving as indicator species in nature conservation. Osmoderma inhabits cavities containing sufficient volume of wood mould usually caused by brown rot in veteran deciduous trees. As the species, having high demands for the habitat quality, they indicate the suitability of the habitat for a number of other specialized saproxylic species. Since typical habitat needed for Osmoderma and other species associated with hollow veteran trees is rapidly declining, the species complex is protected under various legislation, such as Bern Convention, EU Habitats Directive and the Red Lists of many European states. Natura 2000 sites are the main tool for conservation of O. barnabita in Lithuania, currently 17 Natura 2000 sites are designated for the species, where monitoring is implemented once in 3 years according to the approved methodologies. Despite these monitoring efforts in species reports, provided to EU according to the Article 17 of the Habitats Directive, it is defined on the national level, that overall assessment of O. barnabita is inadequate and future prospects are poor. Therefore, research on the distribution and habitat status of O. barnabita was launched on the national level in 2016, which was complemented by preparatory actions of LIFE OSMODERMA project. The research was implemented in the areas equally distributed in the whole area of Lithuania, where O. barnabita was previously not observed, or not observed in the last 10 years. 90 areas, such as Habitats of European importance (9070 Fennoscandian wooded pastures, 9180 Tilio-Acerion forests of slopes, screes, and ravines), Woodland key habitats (B1 broad-leaved forest, K1 single giant tree) and old manor parks, were chosen for the research after review of habitat data from the existing national databases. The first part of field inventory of the habitats was carried out in 2016 and 2017 autumn and winter seasons, when relative abundance of O. barnabita was estimated according to larval faecal pellets in the tree cavities or around the trees. The state of habitats was evaluated according to the density of suitable and potential trees, percentage of not overshadowed trees and amount of undergrowth. The second part of the field inventory was carried out in the summer with pheromone traps baited with (R)-(+)-γ –decalactone. Results of the research show not only occurrence and habitat status of O. barnabita, but also help to clarify O. barnabita habitat requirements in Lithuania, define habitat size, its structure and distribution. Also, it compares habitat needs between the regions in Lithuania and inside and outside Natura 2000 areas designated for the species.

Keywords: habitat status, insect conservation, Osmoderma barnabita, veteran trees

Procedia PDF Downloads 129

Authors: Sergo Tsiramua, Sulkhan Sulkhanishvili, Elisabed Asabashvili, Lazare Kvirtia

Abstract:

The paper presents logical-probabilistic methods, models, and algorithms for reliability assessment of complex systems, based on which a web application for structural analysis and reliability assessment of systems was created. It is important to design systems based on structural analysis, research, and evaluation of efficiency indicators. One of the important efficiency criteria is the reliability of the system, which depends on the components of the structure. Quantifying the reliability of large-scale systems is a computationally complex process, and it is advisable to perform it with the help of a computer. Logical-probabilistic modeling is one of the effective means of describing the structure of a complex system and quantitatively evaluating its reliability, which was the basis of our application. The reliability assessment process included the following stages, which were reflected in the application: 1) Construction of a graphical scheme of the structural reliability of the system; 2) Transformation of the graphic scheme into a logical representation and modeling of the shortest ways of successful functioning of the system; 3) Description of system operability condition with logical function in the form of disjunctive normal form (DNF); 4) Transformation of DNF into orthogonal disjunction normal form (ODNF) using the orthogonalization algorithm; 5) Replacing logical elements with probabilistic elements in ODNF, obtaining a reliability estimation polynomial and quantifying reliability; 6) Calculation of “weights” of elements of system. Using the logical-probabilistic methods, models and algorithms discussed in the paper, a special software was created, by means of which a quantitative assessment of the reliability of systems of a complex structure is produced. As a result, structural analysis of systems, research, and designing of optimal structure systems are carried out.

Keywords: complex systems, logical-probabilistic methods, orthogonalization algorithm, reliability of systems, “weights” of elements

Procedia PDF Downloads 57

Authors: Zanele Ntshidi, Sebinasi Dzikiti, Dominic Mazvimavi

Abstract:

South Africa is a dry country and yet it is ranked as the 8th largest exporter of fresh apples (Malus Domestica) globally. Prime apple producing regions are in the Eastern and Western Cape Provinces of the country where all the fruit is grown under irrigation. Climate change models predict increasingly drier future conditions in these regions and the frequency and severity of droughts is expected to increase. For the sustainability and growth of the fruit industry it is important to minimize non-beneficial water losses from the orchard floor. The aims of this study were firstly to compare the water use of cover crop species used in South African orchards for which there is currently no information. The second aim was to investigate how orchard water use (evapotranspiration) was partitioned into beneficial (tree transpiration) and non-beneficial (orchard floor evaporation) water uses for micro-sprinkler irrigated orchards with different canopy covers. This information is important in order to explore opportunities to minimize non-beneficial water losses. Six cover crop species (four exotic and two indigenous) were grown in 2 L pots in a greenhouse. Cover crop transpiration was measured using the gravimetric method on clear days. To establish how water use was partitioned in orchards, evapotranspiration (ET) was measured using an open path eddy covariance system, while tree transpiration was measured hourly throughout the season (October to June) on six trees per orchard using the heat ratio sap flow method. On selected clear days, soil evaporation was measured hourly from sunrise to sunset using six micro-lysimeters situated at different wet/dry and sun/shade positions on the orchard floor. Transpiration of cover crops was measured using miniature (2 mm Ø) stem heat balance sap flow gauges. The greenhouse study showed that exotic cover crops had significantly higher (p < 0.01) average transpiration rates (~3.7 L/m2/d) than the indigenous species (~ 2.2 L/m²/d). In young non-bearing orchards, orchard floor evaporative fluxes accounted for more than 60% of orchard ET while this ranged from 10 to 30% in mature orchards with a high canopy cover. While exotic cover crops are preferred by most farmers, this study shows that they use larger quantities of water than indigenous species. This in turn contributes to a larger orchard floor evaporation flux. In young orchards non-beneficial losses can be minimized by adopting drip or short range micro-sprinkler methods that reduce the wetted soil fraction thereby conserving water.

Keywords: evapotranspiration, sap flow, soil evaporation, transpiration

Procedia PDF Downloads 380

Authors: Lanchi Xie, Zhihui Li, Zhigang Li, Guiqiang Wang, Lei Xu, Yuwen Yan

Abstract:

Image-based facial features can be classified into category recognition features and individual recognition features. Current automated face recognition systems extract a specific feature vector of different dimensions from a facial image according to their pre-trained neural network. However, to improve the efficiency of parameter calculation, an algorithm generally reduces the image details by pooling. The operation will overlook the details concerned much by forensic experts. In our experiment, we adopted a variety of face recognition algorithms based on deep learning, compared a large number of naturally collected face images with the known data of the same person's frontal ID photos. Downscaling and manual handling were performed on the testing images. The results supported that the facial recognition algorithms based on deep learning detected structural and morphological information and rarely focused on specific markers such as stains and moles. Overall performance, distribution of genuine scores and impostor scores, and likelihood ratios were tested to evaluate the accuracy of biometric systems and forensic experts. Experiments showed that the biometric systems were skilled in distinguishing category features, and forensic experts were better at discovering the individual features of human faces. In the proposed approach, a fusion was performed at the score level. At the specified false accept rate, the framework achieved a lower false reject rate. This paper contributes to improving the interpretability of the objective method of facial comparison and provides a novel method for human-machine collaboration in this field.

Keywords: likelihood ratio, automated facial recognition, facial comparison, biometrics

Procedia PDF Downloads 119

Authors: Mostafa Mjahed

Abstract:

This paper concerns the control of a nonlinear system using two different methods, reference model and genetic algorithm. The quadcopter is a nonlinear unstable system, which is a part of aerial robots. It is constituted by four rotors placed at the end of a cross. The center of this cross is occupied by the control circuit. Its motions are governed by six degrees of freedom: three rotations around 3 axes (roll, pitch and yaw) and the three spatial translations. The control of such system is complex, because of nonlinearity of its dynamic representation and the number of parameters, which it involves. Numerous studies have been developed to model and stabilize such systems. The classical PID and LQ correction methods are widely used. If the latter represent the advantage to be simple because they are linear, they reveal the drawback to require the presence of a linear model to synthesize. It also implies the complexity of the established laws of command because the latter must be widened on all the domain of flight of these quadcopter. Note that, if the classical design methods are widely used to control aeronautical systems, the Artificial Intelligence methods as genetic algorithms technique receives little attention. In this paper, we suggest comparing two PID design methods. Firstly, the parameters of the PID are calculated according to the reference model. In a second phase, these parameters are established using genetic algorithms. By reference model, we mean that the corrected system behaves according to a reference system, imposed by some specifications: settling time, zero overshoot etc. Inspired from the natural evolution of Darwin's theory advocating the survival of the best, John Holland developed this evolutionary algorithm. Genetic algorithm (GA) possesses three basic operators: selection, crossover and mutation. We start iterations with an initial population. Each member of this population is evaluated through a fitness function. Our purpose is to correct the behavior of the quadcopter around three axes (roll, pitch and yaw) with 3 PD controllers. For the altitude, we adopt a PID controller.

Keywords: quadcopter, genetic algorithm, PID, fitness, model, control, nonlinear system

Procedia PDF Downloads 419

Authors: Supria Sarkar, Vasit Sagan, Sourav Bhadra, Meghnath Pokharel, Felix B.Fritschi

Abstract:

Soybean and their derivatives are very important agricultural commodities around the world because of their wide applicability in human food, animal feed, biofuel, and industries. However, the significance of soybean production depends on the quality of the soybean seeds rather than the yield alone. Seed composition is widely dependent on plant physiological properties, aerobic and anaerobic environmental conditions, nutrient content, and plant phenological characteristics, which can be captured by high temporal resolution remote sensing datasets. Planet scope (PS) satellite images have high potential in sequential information of crop growth due to their frequent revisit throughout the world. In this study, we estimate soybean seed composition while the plants are in the field by utilizing PlanetScope (PS) satellite images and different machine learning algorithms. Several experimental fields were established with varying genotypes and different seed compositions were measured from the samples as ground truth data. The PS images were processed to extract 462 hand-crafted vegetative and textural features. Four machine learning algorithms, i.e., partial least squares (PLSR), random forest (RFR), gradient boosting machine (GBM), support vector machine (SVM), and two recurrent neural network architectures, i.e., long short-term memory (LSTM) and gated recurrent unit (GRU) were used in this study to predict oil, protein, sucrose, ash, starch, and fiber of soybean seed samples. The GRU and LSTM architectures had two separate branches, one for vegetative features and the other for textures features, which were later concatenated together to predict seed composition. The results show that sucrose, ash, protein, and oil yielded comparable prediction results. Machine learning algorithms that best predicted the six seed composition traits differed. GRU worked well for oil (R-Squared: of 0.53) and protein (R-Squared: 0.36), whereas SVR and PLSR showed the best result for sucrose (R-Squared: 0.74) and ash (R-Squared: 0.60), respectively. Although, the RFR and GBM provided comparable performance, the models tended to extremely overfit. Among the features, vegetative features were found as the most important variables compared to texture features. It is suggested to utilize many vegetation indices for machine learning training and select the best ones by using feature selection methods. Overall, the study reveals the feasibility and efficiency of PS images and machine learning for plot-level seed composition estimation. However, special care should be given while designing the plot size in the experiments to avoid mixed pixel issues.

Keywords: agriculture, computer vision, data science, geospatial technology

Procedia PDF Downloads 126

Authors: K. E. Ch. Vidyasagar, M. Moghavvemi, T. S. S. T. Prabhat

Abstract:

Epilepsy is a global problem, and with seizures eluding even the smartest of diagnoses a requirement for automatic detection of the same using electroencephalogram (EEG) would have a huge impact in diagnosis of the disorder. Among a multitude of methods for automatic epilepsy detection, one should find the best method out, based on accuracy, for classification. This paper reasons out, and rationalizes, the best methods for classification. Accuracy is based on the classifier, and thus this paper discusses classifiers like quadratic discriminant analysis (QDA), classification and regression tree (CART), support vector machine (SVM), naive Bayes classifier (NBC), linear discriminant analysis (LDA), K-nearest neighbor (KNN) and artificial neural networks (ANN). Results show that ANN is the most accurate of all the above stated classifiers with 97.7% accuracy, 97.25% specificity and 98.28% sensitivity in its merit. This is followed closely by SVM with 1% variation in result. These results would certainly help researchers choose the best classifier for detection of epilepsy.

Keywords: classification, seizure, KNN, SVM, LDA, ANN, epilepsy

Procedia PDF Downloads 506

Authors: Dali Gaganidze, Ekaterine Abashidze

Abstract:

Potato is one of the main agricultural crops in Georgia. Georgia produces early and late potato varieties in almost all regions. In traditional potato growing regions (Svaneti, Samckhet javaheti and Tsalka), the yield is higher than 30-35 t/ha. Among the plant pests that limit potato production and quality, the potato cyst nematodes (PCN) are harmful around the world. Yield losses caused by PCN are estimated up to 30%. Rout surveys conducted in two geographically distinct regions of Georgia producing potatoes - Samtskhe - Javakheti and Svaneti revealed potato cyst nematode Globodera rostochiensi. The aim of the study was the Phylogenetic analyses of Globodera rostochiensi revealed in Georgia by the amplification and sequencing of 28S gen in the D3 region and intergenic ITS1-15.8S-ITS2 region. Identification of all the samples from the two Globodera populations (Samtskhe - Javakheti and Svaneti), i.e., G. rostochiensis (20 isolates) were confirmed by conventional multiplex PCR with ITS 5 universal and PITSp4, PITSr3 specific primers of the cyst nematodes’ (G. pallida, G. rostochiensis). The size of PCR fragment 434 bp confirms that PCN samples from two populations, Samtskhe- Javakheti and Svaneti, belong to G. rostochiensi . The ITS1–5.8S-ITS2 regions were amplified using prime pairs: rDNA1 ( 5’ -TTGATTACGTCCCTGCCCTTT-3’ and rDNA2( 5’ TTTCACTCGCCGTTACTAAGG-3’), D3 expansion regions were amplified using primer pairs: D3A (5’ GACCCCTCTTGAAACACGGA-3’) and D3B (5’-TCGGAAGGAACCAGCTACTA-3’. PCR products of each region were cleaned up and sequenced using an ABI 3500xL Genetic Analyzer. Obtained sequencing results were analyzed by computer program BLASTN (https://blast.ncbi.nlm.nih.gov/Blast.cg). Phylogenetic analyses to resolve the relationships between the isolates were conducted in MEGA7 using both distance- and character-based methods. Based on analysis of G.rostochiensis isolate`s D3 expansion regions are grouped in three major clades (A, B and C) on the phylogenetic tree. Clade A is divided into three subclades; clade C is divided into two subclades. Isolates from the Samtckhet-javakheti population are in subclade 1 of clade A and isolates in subclade 1 of clade C. Isolates) from Svaneti populations are in subclade 2 of clade A and in clad B. In Clade C, subclade two is presented by three isolates from Svaneti and by one isolate (GL17) from Samckhet-Javakheti. . Based on analysis of G.rostochiensis isolate`s ITS1–5.8S-ITS2 regions are grouped in two main clades, the first contained 20 Georgian isolates of Globodera rostochiensis from Svaneti . The second clade contained 15 isolates of Globodera rostochiensis from Samckhet javakheti. Our investigation showed of high genetic variation of D3 and ITS1–5.8S-ITS2 region of rDNA of the isolates of G. rostochiensis from different geographic origins (Svameti, Samckhet-Javakheti) of Georgia. Acknowledgement: The research has been supported by the Shota Rustaveli National Scientific Foundation of Georgia : Project # FR17_235

Keywords: globodera rostochiensi, PCR, phylogenetic tree, sequencing

Procedia PDF Downloads 189

Authors: Vadim Vagin, Marina Fomina, Oleg Morosin

Abstract:

This paper contains the description of argumentation approach for the problem of inductive concept formation. It is proposed to use argumentation, based on defeasible reasoning with justification degrees, to improve the quality of classification models, obtained by generalization algorithms. The experiment’s results on both clear and noisy data are also presented.

Keywords: argumentation, justification degrees, inductive concept formation, noise, generalization

Procedia PDF Downloads 431

Authors: Nguyen J. M., Lucas G., Ruan S., Digonnet H., Antonioli D.

Abstract:

Introduction: Deep Learning (DL) is a very powerful tool for analyzing image data. But for tabular data, it cannot compete with machine learning methods like XGBoost. The research question becomes: can tabular data be transformed into images that can be analyzed by simple CNNs (Convolutional Neuron Networks)? Will DL be the absolute tool for data classification? All current solutions consist in repositioning the variables in a 2x2 matrix using their correlation proximity. In doing so, it obtains an image whose pixels are the variables. We implement a technology, DeepNIC, that offers the possibility of obtaining an image for each variable, which can be analyzed by simple CNNs. Material and method: The 'ROP' (Regression OPtimized) model is a binary and atypical decision tree whose nodes are managed by a new artificial neuron, the Neurop. By positioning an artificial neuron in each node of the decision trees, it is possible to make an adjustment on a theoretically infinite number of variables at each node. From this new decision tree whose nodes are artificial neurons, we created the concept of a 'Random Forest of Perfect Trees' (RFPT), which disobeys Breiman's concepts by assembling very large numbers of small trees with no classification errors. From the results of the RFPT, we developed a family of 10 statistical information criteria, Nguyen Information Criterion (NICs), which evaluates in 3 dimensions the predictive quality of a variable: Performance, Complexity and Multiplicity of solution. A NIC is a probability that can be transformed into a grey level. The value of a NIC depends essentially on 2 super parameters used in Neurops. By varying these 2 super parameters, we obtain a 2x2 matrix of probabilities for each NIC. We can combine these 10 NICs with the functions AND, OR, and XOR. The total number of combinations is greater than 100,000. In total, we obtain for each variable an image of at least 1166x1167 pixels. The intensity of the pixels is proportional to the probability of the associated NIC. The color depends on the associated NIC. This image actually contains considerable information about the ability of the variable to make the prediction of Y, depending on the presence or absence of other variables. A basic CNNs model was trained for supervised classification. Results: The first results are impressive. Using the GSE22513 public data (Omic data set of markers of Taxane Sensitivity in Breast Cancer), DEEPNic outperformed other statistical methods, including XGBoost. We still need to generalize the comparison on several databases. Conclusion: The ability to transform any tabular variable into an image offers the possibility of merging image and tabular information in the same format. This opens up great perspectives in the analysis of metadata.

Keywords: tabular data, CNNs, NICs, DeepNICs, random forest of perfect trees, classification

Procedia PDF Downloads 108

Authors: Sakshi Singh, Shampa Chakraverty

Abstract:

One of the essential characteristics of Blockchain is the ability to validate the integrity of new transactions added to the Blockchain. Moreover, one of the essential consensus algorithms, Proof of Work, performs this job. In this work, we implemented the Proof of Work consensus method on the block formed by performing the transaction using Ganache. The primary goal of this implementation is to understand the process and record how Proof of Work works in reality on newly created blocks.

Keywords: proof of work, blockchain, ganache, smart contract

Procedia PDF Downloads 155

Authors: Sergey Sorokin, Irina Sorokina, Alexander Yazenin

Abstract:

We present a solution to the Maxmin u/E parameters estimation problem of possibility distributions in m-dimensional case. Our method is based on geometrical approach, where minimal area enclosing ellipsoid is constructed around the sample. Also we demonstrate that one can improve results of well-known algorithms in fuzzy model identification task using Maxmin u/E parameters estimation.

Keywords: possibility distribution, parameters estimation, Maxmin u\E estimator, fuzzy model identification

Procedia PDF Downloads 463

Authors: Shivahari Revathi Venkateswaran

Abstract:

Segmenting customers plays a significant role in churn prediction. It helps the marketing team with proactive and reactive customer retention. For the reactive retention, the retention team reaches out to customers who already showed intent to disconnect by giving some special offers. When coming to proactive retention, the marketing team uses churn prediction model, which ranks each customer from rank 1 to 100, where 1 being more risk to churn/disconnect (high ranks have high propensity to churn). The churn prediction model is built by using XGBoost model. However, with the churn rank, the marketing team can only reach out to the customers based on their individual ranks. To profile different groups of customers and to frame different marketing strategies for targeted groups of customers are not possible with the churn ranks. For this, the customers must be grouped in different segments based on their profiles, like demographics and other non-controllable attributes. This helps the marketing team to frame different offer groups for the targeted audience and prevent them from disconnecting (proactive retention). For segmentation, machine learning approaches like k-mean clustering will not form unique customer segments that have customers with same attributes. This paper finds an alternate approach to find all the combination of unique segments that can be formed from the user attributes and then finds the segments who have uplift (churn rate higher than the baseline churn rate). For this, search algorithms like fast search and recursive search are used. Further, for each segment, all customers can be targeted using individual churn ranks from the churn prediction model. Finally, a UI (User Interface) is developed for the marketing team to interactively search for the meaningful segments that are formed and target the right set of audience for future marketing campaigns and prevent them from disconnecting.

Keywords: churn prediction modeling, XGBoost model, uplift segments, proactive marketing, search algorithms, retention, k-mean clustering

Procedia PDF Downloads 66

Authors: Seyed Abolhasan Naeini, Hamidreza Rahmani

Abstract:

Laboratory consolidated undrained triaxial (CU) tests were carried out to study the strength behavior of silty soil reinforced with randomly plastic waste bottle chips. Specimens mixed with plastic waste chips in triaxial compression tests with 0.25, 0.50, 0.75, 1.0, and 1.25% by dry weight of soil and tree different length including 4, 8, and 12 mm. In all of the samples, the width and thickness of plastic chips were kept constant. According to the results, the amount and size of plastic waste bottle chips played an important role in the increasing of the strength parameters of reinforced silt compared to the pure soil. Because of good results, the suggested method of soil improvement can be used in many engineering problems such as increasing the bearing capacity and settlement reduction in foundations.

Keywords: reinforcement, silt, soil improvement, triaxial test, waste bottle chips

Procedia PDF Downloads 277

Authors: Zinhle Cindi, Collet Dandara, Mpiko Ntsekhe, Edson Makambwa, Miguel Larceda

Abstract:

Background: Warfarin is the most commonly used drug in the management of thromboembolic disease. However, there is a huge variability in the time, number of doses or starting doses for patients to achieve the required international normalised ratio (INR) which is compounded by a narrow therapeutic index. Many genetic-association studies have reported on European and Asian populations which have led to the designing of specific algorithms that are now being used to assist in warfarin dosing. However, very few or no studies have looked at the pharmacogenetics of warfarin in African populations, yet, huge differences in dosage requirements to reach the same INR have been observed. Objective: We set out to investigate the distribution of 3 SNPs CYP4F2 c.1347C > T, VKORC1 g.-1639G > A and VKORC1 c.1173C > T among South African Mixed Ancestry (MA) and Black African patients. Methods: DNA was extracted from 383 participants and subsequently genotyped using PCR/RFLP for the CYP4F2 c.1347 (V433M) (rs2108622), VKORC1 g.-1639 (rs9923231) and VKORC1 c.1173 (rs9934438) SNPs. Results: Comparing the Black and MA groups, significant differences were observed in the distribution of the following genotypes; CYP4F2 c.1347C/T (23% vs. 39% p=0.03). All VKORC1 g.-1639G > A genotypes (p < 0.006) and all VKORC1 c.1173C > T genotypes (p < 0.007). Conclusion: CYP4F2 c.1347T (V433M) reduces CYP4F2 protein levels and therefore expected to affect the amount of warfarin needed to block vitamin k recycling. The VKORC1 g-1639A variant alters transcriptional regulation therefore affecting the function of vitamin k epoxide reductase in vitamin k production. The VKORC1 c.1173T variant reduces the enzyme activity of VKORC1 consequently enhancing the effectiveness of warfarin. These are preliminary results; more genetic characterization is required to understand all the genetic determinants affecting how patients respond to warfarin.

Keywords: algorithms, pharmacogenetics, thromboembolic disease, warfarin

Procedia PDF Downloads 249

Authors: Valentin Père, Mathieu Milhé, Fabien Baillon, Jean-Louis Dirion

Abstract:

Microgrids offer potential solutions to meet the need for local grid stability and increase isolated networks autonomy with the integration of intermittent renewable energy production and storage facilities. In such a context, sizing production and storage for a given network is a complex task, highly depending on input data such as power load profile and renewable resource availability. This work aims at developing an operating cost computation methodology for different microgrid designs based on the use of deep reinforcement learning (RL) algorithms to tackle the optimal operation problem in stochastic environments. RL is a data-based sequential decision control method based on Markov decision processes that enable the consideration of random variables for control at a chosen time scale. Agents trained via RL constitute a promising class of Energy Management Systems (EMS) for the operation of microgrids with energy storage. Microgrid sizing (or design) is generally performed by minimizing investment costs and operational costs arising from the EMS behavior. The latter might include economic aspects (power purchase, facilities aging), social aspects (load curtailment), and ecological aspects (carbon emissions). Sizing variables are related to major constraints on the optimal operation of the network by the EMS. In this work, an islanded mode microgrid is considered. Renewable generation is done with photovoltaic panels; an electrochemical battery ensures short-term electricity storage. The controllable unit is a hydrogen tank that is used as a long-term storage unit. The proposed approach focus on the transfer of agent learning for the near-optimal operating cost approximation with deep RL for each microgrid size. Like most data-based algorithms, the training step in RL leads to important computer time. The objective of this work is thus to study the potential of Batch-Constrained Q-learning (BCQ) for the optimal sizing of microgrids and especially to reduce the computation time of operating cost estimation in several microgrid configurations. BCQ is an off-line RL algorithm that is known to be data efficient and can learn better policies than on-line RL algorithms on the same buffer. The general idea is to use the learned policy of agents trained in similar environments to constitute a buffer. The latter is used to train BCQ, and thus the agent learning can be performed without update during interaction sampling. A comparison between online RL and the presented method is performed based on the score by environment and on the computation time.

Keywords: batch-constrained reinforcement learning, control, design, optimal

Procedia PDF Downloads 114

Authors: Mehmet Hakan Karaata

Abstract:

In this paper, we first coin a new graph theocratic problem with numerous applications. Second, we provide two algorithms for the problem. The first solution is using a brute-force techniques, whereas the second solution is based on an initial identification of the cycles in the given graph. We then provide a correctness proof of the algorithm. The applications of the problem include graph analysis, graph drawing and network structuring.

Keywords: algorithm, cycle, graph algorithm, graph theory, network structuring

Procedia PDF Downloads 376

Authors: C. A. Barros, Ana P. Barroso

Abstract:

Any industrial company needs to determine the amount of variation that exists within its measurement process and guarantee the reliability of their data, studying the performance of their measurement system, in terms of linearity, bias, repeatability and reproducibility and stability. This issue is critical for automotive industry suppliers, who are required to be certified by the 16949:2016 standard (replaces the ISO/TS 16949) of International Automotive Task Force, defining the requirements of a quality management system for companies in the automotive industry. Measurement System Analysis (MSA) is one of the mandatory tools. Frequently, the measurement system in companies is not connected to the equipment and do not incorporate the methods proposed by the Automotive Industry Action Group (AIAG). To address these constraints, an R&D project is in progress, whose objective is to develop a web and cloud-based MSA tool. This MSA tool incorporates Industry 4.0 concepts, such as, Internet of Things (IoT) protocols to assure the connection with the measuring equipment, cloud computing, artificial intelligence, statistical tools, and advanced mathematical algorithms. This paper presents the preliminary findings of the project. The web and cloud-based MSA tool is innovative because it implements all statistical tests proposed in the MSA-4 reference manual from AIAG as well as other emerging methods and techniques. As it is integrated with the measuring devices, it reduces the manual input of data and therefore the errors. The tool ensures traceability of all performed tests and can be used in quality laboratories and in the production lines. Besides, it monitors MSAs over time, allowing both the analysis of deviations from the variation of the measurements performed and the management of measurement equipment and calibrations. To develop the MSA tool a ten-step approach was implemented. Firstly, it was performed a benchmarking analysis of the current competitors and commercial solutions linked to MSA, concerning Industry 4.0 paradigm. Next, an analysis of the size of the target market for the MSA tool was done. Afterwards, data flow and traceability requirements were analysed in order to implement an IoT data network that interconnects with the equipment, preferably via wireless. The MSA web solution was designed under UI/UX principles and an API in python language was developed to perform the algorithms and the statistical analysis. Continuous validation of the tool by companies is being performed to assure real time management of the ‘big data’. The main results of this R&D project are: MSA Tool, web and cloud-based; Python API; New Algorithms to the market; and Style Guide of UI/UX of the tool. The MSA tool proposed adds value to the state of the art as it ensures an effective response to the new challenges of measurement systems, which are increasingly critical in production processes. Although the automotive industry has triggered the development of this innovative MSA tool, other industries would also benefit from it. Currently, companies from molds and plastics, chemical and food industry are already validating it.

Keywords: automotive Industry, industry 4.0, Internet of Things, IATF 16949:2016, measurement system analysis

Procedia PDF Downloads 208

Authors: Langa Hendrick Musawenkosi, Twala Bhekisipho

Abstract:

The success or failure of students is a concern for every academic institution, college, university, governments and students themselves. Several approaches have been researched to address this concern. In this paper, a view is held that when a student enters a university or college or an academic institution, he or she enters an academic environment. The academic environment is unique concept used to develop the solution for making predictions effectively. This paper presents a model to determine the propensity of a student to succeed or fail in the French South African Schneider Electric Education Center (FSASEC) at the Vaal University of Technology (VUT). The Decision Tree algorithm is used to implement the model at FSASEC.

Keywords: FSASEC, academic environment model, decision trees, k-nearest neighbor, machine learning, popularity index, support vector machine

Procedia PDF Downloads 194

Authors: Catherine K. Derow

Abstract:

Possibly a slime mold somehow mutated or already was mutated at progeniture and so stayed as a metazoan when it developed into the fruiting stage and so the slime mold(s) we are evolved and similar to are genetically differ from the slime molds in existence now. This may be why there are genetic links between humans and other metazoa now alive and slime molds now alive but we are now divergent branches of the evolutionary tree compared to the original slime mold, or perhaps slime mold-like organisms, that gave rise to metazoan animalia and perhaps algae and plantae as slime molds were undifferentiated enough in many ways that could allow their descendants to evolve into these three separate phylogenetic categories. Or it may be a slime mold was born or somehow progenated as multicellular, as the particular organism was mutated enough to have say divided in a a 'pseudo-embryonic' stage, and this could have happened for algae, plantae as well as animalia or all the branches may be from the same line but the missing link might be covered in 'phylogenetic sequence comparison noise'.

Keywords: metazoan evolution, unicellular bridge to metazoans, evolution, slime mold

Procedia PDF Downloads 218

Authors: Igor V. Grigoriev

Abstract:

Understanding of biological processes encoded in fungi is instrumental in addressing future food, feed, and energy demands of the growing human population. Genomics is a powerful and quickly evolving tool to understand these processes. The Fungal Genomics Program of the US Department of Energy Joint Genome Institute (JGI) partners with researchers around the world to explore fungi in several large scale genomics projects, changing the fungal genomics landscape. The key trends of these changes include: (i) rapidly increasing scale of sequencing and analysis, (ii) developing approaches to go beyond culturable fungi and explore fungal ‘dark matter,’ or unculturables, and (iii) functional genomics and multi-omics data integration. Power of comparative genomics has been recently demonstrated in several JGI projects targeting mycorrhizae, plant pathogens, wood decay fungi, and sugar fermenting yeasts. The largest JGI project ‘1000 Fungal Genomes’ aims at exploring the diversity across the Fungal Tree of Life in order to better understand fungal evolution and to build a catalogue of genes, enzymes, and pathways for biotechnological applications. At this point, at least 65% of over 700 known families have one or more reference genomes sequenced, enabling metagenomics studies of microbial communities and their interactions with plants. For many of the remaining families no representative species are available from culture collections. To sequence genomes of unculturable fungi two approaches have been developed: (a) sequencing DNA from fruiting bodies of ‘macro’ and (b) single cell genomics using fungal spores. The latter has been tested using zoospores from the early diverging fungi and resulted in several near-complete genomes from underexplored branches of the Fungal Tree, including the first genomes of Zoopagomycotina. Genome sequence serves as a reference for transcriptomics studies, the first step towards functional genomics. In the JGI fungal mini-ENCODE project transcriptomes of the model fungus Neurospora crassa grown on a spectrum of carbon sources have been collected to build regulatory gene networks. Epigenomics is another tool to understand gene regulation and recently introduced single molecule sequencing platforms not only provide better genome assemblies but can also detect DNA modifications. For example, 6mC methylome was surveyed across many diverse fungi and the highest among Eukaryota levels of 6mC methylation has been reported. Finally, data production at such scale requires data integration to enable efficient data analysis. Over 700 fungal genomes and other -omes have been integrated in JGI MycoCosm portal and equipped with comparative genomics tools to enable researchers addressing a broad spectrum of biological questions and applications for bioenergy and biotechnology.

Keywords: fungal genomics, single cell genomics, DNA methylation, comparative genomics

Procedia PDF Downloads 195

Authors: Mayank Gupta, Siba Prasad Samal, Vasu Kakkirala

Abstract:

The internet world and its priorities have changed considerably in the last decade. Browsing on smart phones has increased manifold and is set to explode much more. Users spent considerable time browsing different websites, that gives a great deal of insight into user’s preferences. Instead of plain information classifying different aspects of browsing like Bookmarks, History, and Download Manager into useful categories would improve and enhance the user’s experience. Most of the classification solutions are server side that involves maintaining server and other heavy resources. It has security constraints and maybe misses on contextual data during classification. On device, classification solves many such problems, but the challenge is to achieve accuracy on classification with resource constraints. This on device classification can be much more useful in personalization, reducing dependency on cloud connectivity and better privacy/security. This approach provides more relevant results as compared to current standalone solutions because it uses content rendered by browser which is customized by the content provider based on user’s profile. This paper proposes a Naive Bayes based lightweight classification engine targeted for a resource constraint devices. Our solution integrates with Web Browser that in turn triggers classification algorithm. Whenever a user browses a webpage, this solution extracts DOM Tree data from the browser’s rendering engine. This DOM data is a dynamic, contextual and secure data that can’t be replicated. This proposal extracts different features of the webpage that runs on an algorithm to classify into multiple categories. Naive Bayes based engine is chosen in this solution for its inherent advantages in using limited resources compared to other classification algorithms like Support Vector Machine, Neural Networks, etc. Naive Bayes classification requires small memory footprint and less computation suitable for smartphone environment. This solution has a feature to partition the model into multiple chunks that in turn will facilitate less usage of memory instead of loading a complete model. Classification of the webpages done through integrated engine is faster, more relevant and energy efficient than other standalone on device solution. This classification engine has been tested on Samsung Z3 Tizen hardware. The Engine is integrated into Tizen Browser that uses Chromium Rendering Engine. For this solution, extensive dataset is sourced from dmoztools.net and cleaned. This cleaned dataset has 227.5K webpages which are divided into 8 generic categories ('education', 'games', 'health', 'entertainment', 'news', 'shopping', 'sports', 'travel'). Our browser integrated solution has resulted in 15% less memory usage (due to partition method) and 24% less power consumption in comparison with standalone solution. This solution considered 70% of the dataset for training the data model and the rest 30% dataset for testing. An average accuracy of ~96.3% is achieved across the above mentioned 8 categories. This engine can be further extended for suggesting Dynamic tags and using the classification for differential uses cases to enhance browsing experience.

Keywords: chromium, lightweight engine, mobile computing, Naive Bayes, Tizen, web browser, webpage classification

Procedia PDF Downloads 154

Authors: Amit Kumar Happy

Abstract:

This paper is motivated by the importance of multi-sensor image fusion with a specific focus on infrared (IR) and visual image (VI) fusion for various applications, including military reconnaissance. Image fusion can be defined as the process of combining two or more source images into a single composite image with extended information content that improves visual perception or feature extraction. These images can be from different modalities like visible camera & IR thermal imager. While visible images are captured by reflected radiations in the visible spectrum, the thermal images are formed from thermal radiation (infrared) that may be reflected or self-emitted. A digital color camera captures the visible source image, and a thermal infrared camera acquires the thermal source image. In this paper, some image fusion algorithms based upon multi-scale transform (MST) and region-based selection rule with consistency verification have been proposed and presented. This research includes the implementation of the proposed image fusion algorithm in MATLAB along with a comparative analysis to decide the optimum number of levels for MST and the coefficient fusion rule. The results are presented, and several commonly used evaluation metrics are used to assess the suggested method's validity. Experiments show that the proposed approach is capable of producing good fusion results. While deploying our image fusion algorithm approaches, we observe several challenges from the popular image fusion methods. While high computational cost and complex processing steps of image fusion algorithms provide accurate fused results, they also make it hard to become deployed in systems and applications that require a real-time operation, high flexibility, and low computation ability. So, the methods presented in this paper offer good results with minimum time complexity.

Keywords: image fusion, IR thermal imager, multi-sensor, multi-scale transform

Procedia PDF Downloads 104

Authors: Amine Alaoui Sanae, Tagjdid Reda, Loutfi Chafiqa, Melloul Merouane, Laloui Aziz, Touil Nadia, El Fahim, E. Mostafa

Abstract:

Background: Rotavirus group A (RVA) strains with G8P[14] specificities are usually detected in calves and goats. However, these strains have been reported globally in humans and have often been characterized as originating from zoonotic transmissions, particularly in area where ruminants and humans live side-by-side. Whether human P[14] genotypes are two-way and can be transmitted to animal species remains to be established. Here we describe VP4 deduced amino-acid relationships of three Moroccan P[14] genotypes originating from different species and the receptiveness of an alpine goat to a human G8P[14] through an experimental infection. Material/methods: the human MA31 RVA strain was originally identified in a four years old girl presenting an acute gastroenteritis hospitalized at the pediatric care unit in Rabat Hospital in 2011. The virus was isolated and propagated in MA104 cells in the presence of trypsin. Ch_10S and 8045_S animal RVA strains were identified in fecal samples of a 2-week-old native goat and 3-week-old calf with diarrhea in 2011 in Bouaarfa and My Bousselham respectively. Genomic RNAs of all strains were subjected to a two-step RT-PCR and sequenced using the consensus primers VP4. The phylogenetic tree for MA31, Ch_10S and 8045_S VP4 and a set of published P[14] genotypes was constructed using MEGA6 software. The receptivity of MA31 strain by an eight month-old alpine goat was assayed. The animal was orally and intraperitonally inoculated with a dose of 8.5 TCID50 of virus stock at passage level 3. The shedding of the virus was tested by a real time RT-PCR assay. Results: The phylogenetic tree showed that the three Moroccan strains MA31, Ch_10S and 8045_S VP4 were highly related to each other (100% similar at the nucleotide level). They were clustered together with the B10925, Sp813, PA77 and P169 strains isolated in Belgium, Spain and Italy respectively. The Belgian strain B10925 was the most closely related to the Moroccan strains. In contrast, the 8045_S and Ch_10S strains were clustered distantly from the Tunisian calf strain B137 and the goat strain cap455 isolated in South Africa respectively. The human MA31 RVA strain was able to induce bloody diarrhea at 2 days post infection (dpi) in the alpine goat kid. RVA virus shedding started by 2 dpi (Ct value of 28) and continued until 5 dpi (Ct value of 25) with a concomitant elevation in the body temperature. Conclusions: Our study while limited to one animal, is the first study proving experimentally that a human P[14] genotype causes diarrhea and virus shedding in the goat. This result reinforce the potential role of inter- species transmission in generating novel and rare rotavirus strains such G8P[14] which infect humans.

Keywords: interspecies transmission, rotavirus, goat, human

Procedia PDF Downloads 277

Authors: Seyed-Ali Sadegh-Zadeh, Mahboobe Bahrami, Sahar Ahmadi, Seyed-Yaser Mousavi, Hamed Atashbar, Amir M. Hajiyavand

Abstract:

This paper presents an investigation into the concept of neural reshaping, which is crucial for achieving strong artificial intelligence through the development of AI algorithms with very high plasticity. By examining the plasticity of both human and artificial neural networks, the study uncovers groundbreaking insights into how these systems adapt to new experiences and situations, ultimately highlighting the potential for creating advanced AI systems that closely mimic human intelligence. The uniqueness of this paper lies in its comprehensive analysis of the neural reshaping process in both human and artificial intelligence systems. This comparative approach enables a deeper understanding of the fundamental principles of neural plasticity, thus shedding light on the limitations and untapped potential of both human and AI learning capabilities. By emphasizing the importance of neural reshaping in the quest for strong AI, the study underscores the need for developing AI algorithms with exceptional adaptability and plasticity. The paper's findings have significant implications for the future of AI research and development. By identifying the core principles of neural reshaping, this research can guide the design of next-generation AI technologies that can enhance human and artificial intelligence alike. These advancements will be instrumental in creating a new era of AI systems with unparalleled capabilities, paving the way for improved decision-making, problem-solving, and overall cognitive performance. In conclusion, this paper makes a substantial contribution by investigating the concept of neural reshaping and its importance for achieving strong AI. Through its in-depth exploration of neural plasticity in both human and artificial neural networks, the study unveils vital insights that can inform the development of innovative AI technologies with high adaptability and potential for enhancing human and AI capabilities alike.

Keywords: neural plasticity, brain adaptation, artificial intelligence, learning, cognitive reshaping

Procedia PDF Downloads 40

Authors: Shweta Dhindhwal

Abstract:

Dopamine is an essential neurotransmitter in the central nervous system of all vertebrates and plays an important role in many processes such as motor function, learning and behavior, and sensory activity. One of the important functions of dopamine is release of pituitary hormones. It is synthesized from the amino acid tyrosine. Two types of dopamine receptors, D1-like and D2-like, have been reported in fish. The dopamine containing neurons are located in the olfactory bulbs, the ventral regions of the pre-optic area and tuberal hypothalamus. Distribution of the dopaminergic system has not been studied in the murrel, Channa punctatus. The present study deals with identification of D2 receptors in the brain of murrel. A phylogenetic tree has been constructed using partial sequence of D2 receptor. Distribution of putative dopaminergic neurons in the brain has been investigated. Also, formalin induced hypertrophy of neurosecretory cells in murrel has been studied.

Keywords: dopamine, fish, pre-optic area, murrel

Procedia PDF Downloads 413

Authors: Rui Wu

Abstract:

In the volatile modern manufacturing environment, new orders randomly occur at any time, while the pre-emptive methods are infeasible. This leads to a real-time scheduling method that can produce a reasonably good schedule quickly. The dynamic Flexible Job Shop problem is an NP-hard scheduling problem that hybrid the dynamic Job Shop problem with the Parallel Machine problem. A Flexible Job Shop contains different work centres. Each work centre contains parallel machines that can process certain operations. Many algorithms, such as genetic algorithms or simulated annealing, have been proposed to solve the static Flexible Job Shop problems. However, the time efficiency of these methods is low, and these methods are not feasible in a dynamic scheduling problem. Therefore, a dynamic rule selection scheduling system based on the reinforcement learning method is proposed in this research, in which the dynamic Flexible Job Shop problem is divided into several parallel machine problems to decrease the complexity of the dynamic Flexible Job Shop problem. Firstly, the features of jobs, machines, work centres, and flexible job shops are selected to describe the status of the dynamic Flexible Job Shop problem at each decision point in each work centre. Secondly, a framework of reinforcement learning algorithm using a double-layer deep Q-learning network is applied to select proper composite dispatching rules based on the status of each work centre. Then, based on the selected composite dispatching rule, an available operation is selected from the waiting buffer and assigned to an available machine in each work centre. Finally, the proposed algorithm will be compared with well-known dispatching rules on objectives of mean tardiness, mean flow time, mean waiting time, or mean percentage of waiting time in the real-time Flexible Job Shop problem. The result of the simulations proved that the proposed framework has reasonable performance and time efficiency.

Keywords: dynamic scheduling problem, flexible job shop, dispatching rules, deep reinforcement learning

Procedia PDF Downloads 94

Authors: C. Hamamura, V. Gialluca

Abstract:

Much of the Eclectricity Distributors has about 70% of its electricity interruptions arising from cause "trees", alone or associated with wind and rain and with or without falling branch and / or trees. This contributes inexorably and significantly to outages, resulting in high costs as compensation in addition to the operation and maintenance costs. On the other hand, there is little data structure and solutions to better organize the trees pruning plan effectively, minimizing costs and environmentally friendly. This work describes the development of an algorithm to provide data of trees associated to power grid. The method is accomplished on several steps using satellite imagery and geographically vectorized grid. A sliding window like approach is performed to seek the area around the grid. The proposed method counted 764 trees on a patch of the grid, which was very close to the 738 trees counted manually. The trees data was used as a part of a larger project that implements a system to optimize tree pruning plan.

Keywords: image pattern recognition, trees pruning, trees recognition, neural network

Procedia PDF Downloads 493

Authors: Bhojan Dhakal, Naba Raj Devkota, Chet Raj Upreti, Maheshwar Sapkota

Abstract:

A study was conducted to find out the production potential, nutrient composition, and the variability of the most commonly available fodder trees along with the varying altitude to help optimize the dry matter requirement during winter lean period. The study was carried out from March to June, 2012 in Lho and Prok Village Development Committee of Manaslu Conservation Area (MCA), located in Gorkha district of Nepal. The other objective of the research was to learn the impact of climate change on livestock production linking it with feed availability. The study was conducted in two parts: social and biological. Accordingly, a households (HHs) survey was conducted to collect primary data from 70 HHs, focusing on the perception of respondents on impacts of climatic variability on the feeding management. The next part consisted of understanding yield potential and nutrient composition of the four most commonly available fodder trees (M. azedirach, M. alba, F. roxburghii, F. nemoralis), within two altitudes range: (1500-2000 masl and 2000-2500 masl) by using a RCB design in 2*4 factorial combination of treatments, each replicated four times. Results revealed that majority of the farmers perceived the change in climatic phenomenon more severely within the past five years. Farmers were using different adaptation technologies such as collection of forage from jungle, reducing unproductive animals, fodder trees utilization, and crop by product feeding at feed scarcity period. Ranking of the different fodder trees on the basis of indigenous knowledge and experiences revealed that F. roxburghii was the best-preferred fodder tree species (index value 0.72) in terms overall preferability whereas M. azedirach had highest growth and productivity (index value 0.77), F. roxburghii had highest adoptability (index value 0.69) and palatability (index value 0.69) as well. Similarly, fresh yield and dry matter yield of the each fodder trees was significant (P < 0.01) between the altitude and within species. Fodder trees yield analysis revealed that the highest dry matter (DM) yield (28 kg/tree) was obtained for F. roxburghii but that remained statistically similar (P > 0.05) to the other treatment. On the other hand, most of the parameters: ether extract (EE), acid detergent lignin (ADL), acid detergent fibre (ADF), cell wall digestibility (CWD), relative digestibility (RD), digestible nutrient (TDN), and Calcium (Ca) among the treatments were highly significant (P < 0.01). This indicates the scope of introducing productive and nutritive fodder trees species even at the high altitude to help reduce fodder scarcity problem during winter. The finding also revealed the scope of promoting all available local fodder trees species as crude protein content of these species were similar.

Keywords: fodder trees, yield potential, climate change, nutrient composition

Procedia PDF Downloads 303