Search results for: artificial neural networks; crop water stress index; canopy temperature

Authors: Renu Yadav, Sanjeev Kumar

Abstract:

In northern India, chickpea (Cicer arietinum L.) come across with terminal high-temperature stress during reproductive stage which leads to reduced yield. Hence, stable production of chickpea will depend on the development of new methods like ‘priming’ which allow improved adaptation to the drought and heat stress. In the present experiment, 11-day chickpea seedling was primed with mild drought stress and put on recovery stage by irrigating and finally 30-day seedlings were exposed to heat stress 38°C (4 hours), 35°C (8 hours) and 32°C (12 hours). To study the effect of combinatorial stress, heat and drought stress was applied simultaneously. Analyses of various physiological parameters like membrane damage assay, photosynthetic pigments, antioxidative enzyme, total sugars were estimated at all stages. To study the effect of heat stress on the metabolites of the plants, GC-MS and HPLC were performed, while at transcriptional level Real-Time PCR of predicted heat stress-related genes was done. It was concluded that the heat stress significantly affected the chickpea plant at physiological and molecular level in all the five varieties. Results also show less damaging effect in primed plants by increasing the activity of antioxidative enzymes and increased expression of heat shock proteins and heat shock factors.

Keywords: chickpea, combinatorial stress, heat stress, oxidative stress, priming, RT-PCR

Procedia PDF Downloads 161

Authors: Tzu-Ping Lin, Shing-Ru Yang

Abstract:

Climate change has a significant impact on human living environment, while the traditional settlement may suffer extreme thermal stress due to its specific building type and living behavior. This study selected Lutaoyang, which is the largest settlement in mountainous areas of Tainan County, for the investigation area. The microclimate parameters, such as air temperature, relative humidity, wind speed, and mean radiant temperature. The micro climate parameters were also simulated by the ENVI-met model. The results showed the banyan tree area providing good thermal comfort condition due to the shading. On the contrary, the courtyard (traditionally for the crops drying) surrounded by low rise building and consisted of artificial pavement contributing heat stress especially in summer noon. In the climate change simulations, the courtyard will become very hot and are not suitable for residents activities. These analytical results will shed light on the sustainability related to thermal environment in traditional settlements and develop adaptive measure towards sustainable development under the climate change challenges.

Keywords: thermal environment, traditional settlement, ENVI-met, Taiwan

Procedia PDF Downloads 479

Authors: Hailyie Tekleselase

Abstract:

Deep learning is increasingly used as a building block of security systems. However, neural networks are hard to interpret and typically solid to the practitioner. This paper presents a detail survey of computing methods in cyber security, and analyzes the prospects of enhancing the cyber security capabilities by suggests that of accelerating the intelligence of the security systems. There are many AI-based applications used in industrial scenarios such as Internet of Things (IoT), smart grids, and edge computing. Machine learning technologies require a training process which introduces the protection problems in the training data and algorithms. We present machine learning techniques currently applied to the detection of intrusion, malware, and spam. Our conclusions are based on an extensive review of the literature as well as on experiments performed on real enterprise systems and network traffic. We conclude that problems can be solved successfully only when methods of artificial intelligence are being used besides human experts or operators.

Keywords: artificial intelligence, machine learning, deep learning, cyber security, big data

Procedia PDF Downloads 126

Authors: Panpan Fan, Bo Ming, Niels Anten, Jochem Evers, Yaoyao Li, Shaokun Li, Ruizhi xie

Abstract:

Nitrogen (N) utilization for crop production under N deficiency conditions is subject to a trade-off between maintaining specific leaf N content (SLN), important for radiation-use efficiency (RUE), versus maintaining leaf area (LA) development, important for light capture. This paper aims to explore how maize deals with this trade-off through responses in SLN, LA and their underlying traits during the vegetative and reproductive growth stages. In a ten-year N fertilization trial in Jilin province, Northeast China, three N fertilizer levels have been maintained: N-deficiency (N0), low N supply (N1), and high N supply (N2). We analyzed data from years 8 and 10 of this experiment for two common hybrids. Under N deficiency, maize plants maintained LA and decreased SLN during vegetative stages, while both LA and SLN decreased comparably during reproductive stages. Canopy-average specific leaf area (SLA) decreased sharply during vegetative stages and slightly during reproductive stages, mainly because senesced leaves in the lower canopy had a higher SLA. In the vegetative stage, maize maintained leaf area at low N by maintaining leaf biomass (albeit hence having N content/mass) and slightly increasing SLA. These responses to N deficiency were stronger in maize hybrid XY335 than in ZD958. We conclude the main strategy of maize to cope with low N is to maintain plant growth, mainly by increasing SLA throughout the plant during early growth. N was too limiting for either strategy to be followed during later growth stages.

Keywords: leaf N content per unit leaf area, N deficiency, specific leaf area, maize strateg

Procedia PDF Downloads 92

Authors: R. A. Eman Elsheikh, Bart Schultz, Abraham Mehari Haile, Hussein S. Adam

Abstract:

A field experiment was conducted at Gezira research station farm during the winter season in the third week of November 2012, in WadMedani, Sudan (Lat 14.23 W, Long 33.39 E and altitude 405 m above sea level, in deep cracking alkaline heavy clay Vertisols). The objective of this study was to determine the effect of three different irrigation for 10 days (W1), 15 days (W2) and 20 days (W3) and for two rows of 30 cm (S1) and 40 cm (S2), respectively. The experimental design was split plot with three replicates. The sunflower test variety was Hysun 33 cultivar. The seasonal water applied during the study was 6898, 6647, 5256, 5435, 5214, 5416 m3/ha for W1S1, W1S2, W2S1, W2S2, W3S1 and W3S2 respectively. The seed yield obtained for the above treatment in that sequence was 4208, 5542, 5167, 4579, 2931, 2936 kg/ha. The corresponding computed water productivity was 0.61, 0.82, 0.87, 0.95, 0.54, 0.56 kg/m3. The study clearly indicated that the highest seed yield was obtained when the crop was sown at 40 cm row spacing and was irrigated every 10 days (W1S2), followed by W2S1.

Keywords: water productivity, water deficit, sunflower, plant spacing

Procedia PDF Downloads 349

Authors: Piotr A. Kowalski, Kasper Sapala, Wiktor Warchalowski

Abstract:

PM10 is a suspended dust that primarily has a negative effect on the respiratory system. PM10 is responsible for attacks of coughing and wheezing, asthma or acute, violent bronchitis. Indirectly, PM10 also negatively affects the rest of the body, including increasing the risk of heart attack and stroke. Unfortunately, Poland is a country that cannot boast of good air quality, in particular, due to large PM concentration levels. Therefore, based on the dense network of Airly sensors, it was decided to deal with the problem of prediction of suspended particulate matter concentration. Due to the very complicated nature of this issue, the Machine Learning approach was used. For this purpose, Convolution Neural Network (CNN) neural networks have been adopted, these currently being the leading information processing methods in the field of computational intelligence. The aim of this research is to show the influence of particular CNN network parameters on the quality of the obtained forecast. The forecast itself is made on the basis of parameters measured by Airly sensors and is carried out for the subsequent day, hour after hour. The evaluation of learning process for the investigated models was mostly based upon the mean square error criterion; however, during the model validation, a number of other methods of quantitative evaluation were taken into account. The presented model of pollution prediction has been verified by way of real weather and air pollution data taken from the Airly sensor network. The dense and distributed network of Airly measurement devices enables access to current and archival data on air pollution, temperature, suspended particulate matter PM1.0, PM2.5, and PM10, CAQI levels, as well as atmospheric pressure and air humidity. In this investigation, PM2.5, and PM10, temperature and wind information, as well as external forecasts of temperature and wind for next 24h served as inputted data. Due to the specificity of the CNN type network, this data is transformed into tensors and then processed. This network consists of an input layer, an output layer, and many hidden layers. In the hidden layers, convolutional and pooling operations are performed. The output of this system is a vector containing 24 elements that contain prediction of PM10 concentration for the upcoming 24 hour period. Over 1000 models based on CNN methodology were tested during the study. During the research, several were selected out that give the best results, and then a comparison was made with the other models based on linear regression. The numerical tests carried out fully confirmed the positive properties of the presented method. These were carried out using real ‘big’ data. Models based on the CNN technique allow prediction of PM10 dust concentration with a much smaller mean square error than currently used methods based on linear regression. What's more, the use of neural networks increased Pearson's correlation coefficient (R²) by about 5 percent compared to the linear model. During the simulation, the R² coefficient was 0.92, 0.76, 0.75, 0.73, and 0.73 for 1st, 6th, 12th, 18th, and 24th hour of prediction respectively.

Keywords: air pollution prediction (forecasting), machine learning, regression task, convolution neural networks

Procedia PDF Downloads 149

Authors: Na Li, Samuel Simon Araya, Søren Knudsen Kær

Abstract:

This study investigates the effects of operating parameters of different current density, temperature and pressure on the performance of a proton exchange membrane (PEM) water electrolysis stack. A 7-cell PEM water electrolysis stack was assembled and tested under different operation modules. The voltage change and polarization curves under different test conditions, namely current density, temperature and pressure, were recorded. Results show that higher temperature has positive effect on overall stack performance, where temperature of 80 ℃ improved the cell performance greatly. However, the cathode pressure and current density has little effect on stack performance.

Keywords: PEM electrolysis stack, current density, temperature, pressure

Procedia PDF Downloads 201

Authors: Oluwaponmile David Alao

Abstract:

Due to an increase in the death rate as a result of heart attack. There is need to develop a system that can be useful in the diagnosis of the disease at the medical centre. This system will help in preventing misdiagnosis that may occur from the medical practitioner or the physicians. In this research work, heart disease dataset obtained from UCI repository has been used to develop an intelligent prediction diagnosis system. The system is modeled on a feedforwad neural network and trained with back propagation neural network. A recognition rate of 86% is obtained from the testing of the network.

Keywords: heart disease, artificial neural network, diagnosis, prediction system

Procedia PDF Downloads 450

Authors: Yudhajit Datta

Abstract:

Will is a phenomenon that has puzzled humanity for a long time. It is a belief that Will Power of an individual affects the success achieved by an individual in life. It is thought that a person endowed with great will power can overcome even the most crippling setbacks of life while a person with a weak will cannot make the most of life even the greatest assets. Behavioral aspects of the human experience such as will are rarely subjected to quantitative study owing to the numerous uncontrollable parameters involved. This work is an attempt to subject the phenomena of will to the test of an artificial neural network. The claim being tested is that will power of an individual largely determines success achieved in life. In the study, an attempt is made to incorporate the behavioral phenomenon of will into a computational model using data pertaining to the success of individuals obtained from an experiment. A neural network is to be trained using data based upon part of the model, and subsequently used to make predictions regarding will corresponding to data points of success. If the prediction is in agreement with the model values, the model is to be retained as a candidate. Ultimately, the best-fit model from among the many different candidates is to be selected, and used for studying the correlation between success and will.

Keywords: will power, will, success, apathy factor, random factor, characteristic function, life story

Procedia PDF Downloads 379

Authors: Rose-Michelle Smith, Musandji Fuamba, Salomon Salumu

Abstract:

Water is vital for life. Access to drinking water and sanitation for humans is one of the Sustainable Development Goals (specifically the sixth) approved by United Nations Member States in September 2015. There are various problems identified relating to water: insufficient fresh water, inequitable distribution of water resources, poor water management in certain places on the planet, detection of water-borne diseases due to poor water quality, and the negative impacts of climate change on water. One of the major challenges in the world is finding ways to ensure that people and the environment have enough water resources to sustain and support their existence. Thus, this research project aims to develop a tool to assess the availability, quality and needs of water in current and future situations with regard to climate change. This tool was tested using threshold values for three regions in three countries: the Metropolitan Community of Montreal (Canada), Normandie Region (France) and North Department (Haiti). The WEAP software was used to evaluate the available quantity of water resources. For water quality, two models were performed: the Canadian Council of Ministers of the Environment (CCME) and the Malaysian Water Quality Index (WQI). Preliminary results showed that the ratio of the needs could be estimated at 155, 308 and 644 m3/capita in 2023 for Normandie, Cap-Haitian and CMM, respectively. Then, the Water Quality Index (WQI) varied from one country to another. Other simulations regarding the water availability and quality are still in progress. This tool will be very useful in decision-making on projects relating to water use in the future; it will make it possible to estimate whether the available resources will be able to satisfy the needs.

Keywords: climate change, water needs, balance sheet, water quality

Procedia PDF Downloads 75

Authors: Hang Meng, Wen-Bin Liu, Bi Xiao, Kai-Jun Ma, Jian-Hui Xie, Geng Fei, Tian-Ye Zhang, Lu-Yi Xu, Dong-Chuan Zhang

Abstract:

The victims in water are often found in the coastal region, along river region or the region with lakes. In China, the examination for the bodies of victims in the water is conducted by forensic doctors working in the public security bureau. Because the enter water time for most of the victims are not clear, and often lack of monitor images and other information, so to find out the corpse enter water time for victims is very difficult. After the corpse of the victim enters the water, it sinks first, then corruption gas produces, which can make the density of the corpse to be less than water, and thus rise again. So the factor that determines the corpse floating time is temperature. On the basis of the temperature data obtained in Shanghai region of China (Shanghai is a north subtropical marine monsoon climate, with an average annual temperature of about 17.1℃. The hottest month is July, the average monthly temperature is 28.6℃, and the coldest month is January, the average monthly temperature is 4.8℃). This study selected about 100 cases with definite corpse enter water time and corpse floating time, analyzed the cases and obtained the empirical law of the corpse floating time. For example, in the Shanghai region, on June 15th and October 15th, the corpse floating time is about 1.5 days. In early December, the bodies who entered the water will go up around January 1st of the following year, and the bodies who enter water in late December will float in March of next year. The results of this study can be used to roughly estimate the water enter time of the victims in Shanghai. Forensic doctors around the world can also draw on the results of this study to infer the time when the corpses of the victims in the water go up.

Keywords: corpse enter water time, corpse floating time, drowning, forensic pathology, victims in the water

Procedia PDF Downloads 196

Authors: John Goodhue, Xiaonan Wei

Abstract:

Current legal decisions and policies regarding the naming as artificial intelligence as inventor are reviewed with emphasis on the recent decisions by the European Patent Office regarding the DABUS inventions holding that an artificial intelligence machine cannot be an inventor. Next, a set of hypotheticals is introduced and examined to better understand how artificial intelligence might be used to create or assist in creating new inventions and how application of existing or proposed changes in the law would affect the ability to protect these inventions including due to restrictions on artificial intelligence for being named as inventors, ownership of inventions made by artificial intelligence, and the effects on legal standards for inventiveness or obviousness.

Keywords: Artificial intelligence, innovation, invention, patent

Procedia PDF Downloads 173

Authors: Seyed Sadegh Naseralavi, Najmeh Bemani

Abstract:

In this paper, different concrete codes including America, New Zealand, Mexico, Italy, India, Canada, Hong Kong, Euro Code and Britain are compared with the Iranian concrete design code. First, by using Adaptive Neuro Fuzzy Inference System (ANFIS), the codes having the most correlation with the Iranian ninth issue of the national regulation are determined. Consequently, two anticipated methods are used for comparing the codes: Artificial Neural Network (ANN) and Multi-variable regression. The results show that ANN performs better. Predicting is done by using only tensile steel ratio and with ignoring the compression steel ratio.

Keywords: adaptive neuro fuzzy inference system, anticipate method, artificial neural network, concrete design code, multi-variable regression

Procedia PDF Downloads 284

Authors: Antti Nurminen, Avleen Malhi

Abstract:

Significant progress in intelligent systems in combination with exceedingly wide application domains having machine learning as the core technology are usually opaque, non-intuitive, and commonly complex for human users. We use innovative IoT technology which monitors and analyzes moisture, humidity, luminosity and temperature levels to assist end users for optimization of environmental conditions for their houseplants. For plant health monitoring, we construct a system yielding the Normalized Difference Vegetation Index (NDVI), supported by visual validation by users. We run the system for a selected plant, basil, in varying environmental conditions to cater for typical home conditions, and bootstrap our AI with the acquired data. For end users, we implement a web based user interface which provides both instructions and explanations.

Keywords: explainable artificial intelligence, intelligent agent, IoT, NDVI

Procedia PDF Downloads 163

Authors: Zhi-Jun Lu, Qi Lu, Meng Wu, Qian Xiang, Jun Gu

Abstract:

The analysis of perforated steel members is a 3D problem in nature, therefore the traditional analytical expressions for the ultimate load of thin-walled steel sections cannot be used for the perforated steel member design. In this study, finite element method (FEM) and artificial neural network (ANN) were used to simulate the process of stub column tests based on specific codes. Results show that compared with those of the FEM model, the ultimate load predictions obtained from ANN technique were much closer to those obtained from the physical experiments. The ANN model for the solving the hard problem of complex steel perforated sections is very promising.

Keywords: artificial neural network (ANN), finite element method (FEM), perforated sections, thin-walled Steel, ultimate load

Procedia PDF Downloads 352

Authors: P. Prasannakumar, L. Myoung Young, G. Seung Kye, P. Sang Hun, S. Chul Gyu

Abstract:

In this paper, we discussed the coupling medium in the optoacoustic imaging. The coupling medium is placed between the scanned object and the ultrasound transducers. Water with varying temperature was used as the coupling medium. The water temperature is gradually varied between 25 to 40 degrees. This heating process is taken with care in order to avoid the bubble formation. Rise in the photoacoustic signal is noted through an unfocused transducer with frequency of 2.25 MHz as the temperature increases. The temperature rise is monitored using a NTC thermistor and the values in degrees are calculated using an embedded evaluation kit. Also the temperature is transmitted to PC through a serial communication. All these processes are synchronized using a trigger signal from the laser source.

Keywords: embedded, optoacoustic, ultrasound , unfocused transducer

Procedia PDF Downloads 349

Authors: S. M. A. Bekkouche, T. Benouaz, M. K. Cherier, M. Hamdani, M. R. Yaiche, N. Benamrane

Abstract:

Most codes of building energy simulation neglect the humidity or well represent it with a very simplified method. It is for this reason that we have developed a new approach to the description and modeling of multizone buildings in Saharan climate. The thermal nodal method was used to apprehend thermoaeraulic behavior of air subjected to varied solicitations. In this contribution, analyzing the building geometry introduced the concept of index compactness as "quotient of external walls area and volume of the building". Physical phenomena that we have described in this paper, allow to build the model of the coupled thermoaeraulic behavior. The comparison shows that the found results are to some extent satisfactory. The result proves that temperature and specific humidity depending on compactness and geometric shape. Proper use of compactness index and building geometry parameters will noticeably minimize building energy.

Keywords: multizone model, nodal method, compactness index, specific humidity, temperature

Procedia PDF Downloads 410

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 195

Authors: Shara Toibayeva, Irbulat Utepbergenov, Lyazzat Issabekova, Aidana Bodesova

Abstract:

The article discusses the importance of quality assessment as a strategic tool in business and emphasizes the significance of the effectiveness of quality management systems (QMS) for enterprises. The evaluation of these systems takes into account the specificity of quality indicators, the multilevel nature of the system, and the need for optimal selection of the number of indicators and evaluation of the system state, which is critical for making rational management decisions. Methods and models of automated enterprise quality management are proposed, including an intelligent automated quality management system integrated with the Management Information and Control System. These systems make it possible to automate the implementation and support of QMS, increasing the validity, efficiency, and effectiveness of management decisions by automating the functions performed by decision makers and personnel. The paper also emphasizes the use of recurrent neural networks to improve automated quality management. Recurrent neural networks (RNNs) are used to analyze and process sequences of data, which is particularly useful in the context of document quality assessment and non-conformance detection in quality management systems. These networks are able to account for temporal dependencies and complex relationships between different data elements, which improves the accuracy and efficiency of automated decisions. The project was supported by a grant from the Ministry of Education and Science of the Republic of Kazakhstan under the Zhas Galym project No. AR 13268939, dedicated to research and development of digital technologies to ensure consistency of QMS regulatory documents.

Keywords: automated control system, quality management, document structure, formal language

Procedia PDF Downloads 39

Authors: Giselle Maggie-Fer Castañeda Lozano

Abstract:

The main objective of this research was to explore the role of neural network architectures in simulating behavioral phenomena as a potential explanation for selective associations, specifically related to biological constraints on learning. Biological constraints on learning refer to the limitations observed in conditioning procedures, where learning is expected to occur. The study involved simulations of five different experiments exploring various phenomena and sources of biological constraints in learning. These simulations included the interaction between response and reinforcer, stimulus and reinforcer, specificity of stimulus-reinforcer associations, species differences, neuroanatomical constraints, and learning in uncontrolled conditions. The overall results demonstrated that by manipulating neural network architectures, conditions can be created to model and explain diverse biological constraints frequently reported in comparative psychology literature as learning typicities. Additionally, the simulations offer predictive content worthy of experimental testing in the pursuit of new discoveries regarding the specificity of learning. The implications and limitations of these findings are discussed. Finally, it is suggested that this research could inaugurate a line of inquiry involving the use of neural networks to study biological factors in behavior, fostering the development of more ethical and precise research practices.

Keywords: comparative psychology, connectionism, conditioning, experimental analysis of behavior, neural networks

Procedia PDF Downloads 71

Authors: Abbas Ahmadi, Bijan Raie, Mohammad Reza Neyshabouri, Mohammad Ali Ghorbani, Farrokh Asadzadeh

Abstract:

In recent years, vast areas of Urmia Lake in Dasht-e-Tabriz has dried up leading to saline sediments exposure on the surface lake coastal areas being highly susceptible to wind erosion. This study was conducted to investigate wind erosion and its relevance to soil physicochemical properties and also modeling of wind erodibility (WE) using artificial intelligence techniques. For this purpose, 96 soil samples were collected from 0-5 cm depth in 414000 hectares using stratified random sampling method. To measure the WE, all samples (<8 mm) were exposed to 5 different wind velocities (9.5, 11, 12.5, 14.1 and 15 m s-1 at the height of 20 cm) in wind tunnel and its relationship with soil physicochemical properties was evaluated. According to the results, WE varied within the range of 76.69-9.98 (g m-2 min-1)/(m s-1) with a mean of 10.21 and coefficient of variation of 94.5% showing a relatively high variation in the studied area. WE was significantly (P<0.01) affected by soil physical properties, including mean weight diameter, erodible fraction (secondary particles smaller than 0.85 mm) and percentage of the secondary particle size classes 2-4.75, 1.7-2 and 0.1-0.25 mm. Results showed that the mean weight diameter, erodible fraction and percentage of size class 0.1-0.25 mm demonstrated stronger relationship with WE (coefficients of determination were 0.69, 0.67 and 0.68, respectively). This study also compared efficiency of multiple linear regression (MLR), gene expression programming (GEP), artificial neural network (MLP), artificial neural network based on genetic algorithm (MLP-GA) and artificial neural network based on whale optimization algorithm (MLP-WOA) in predicting of soil wind erodibility in Dasht-e-Tabriz. Among 32 measured soil variable, percentages of fine sand, size classes of 1.7-2.0 and 0.1-0.25 mm (secondary particles) and organic carbon were selected as the model inputs by step-wise regression. Findings showed MLP-WOA as the most powerful artificial intelligence techniques (R2=0.87, NSE=0.87, ME=0.11 and RMSE=2.9) to predict soil wind erodibility in the study area; followed by MLP-GA, MLP, GEP and MLR and the difference between these methods were significant according to the MGN test. Based on the above finding MLP-WOA may be used as a promising method to predict soil wind erodibility in the study area.

Keywords: wind erosion, erodible fraction, gene expression programming, artificial neural network

Procedia PDF Downloads 71

Authors: M. Macchiaroli, V. Pellecchia, L. Dolores

Abstract:

Within any European and world model of management of the integrated water service (in Italy only since 2012 is regulated by a national Authority, that is ARERA), a significant part is covered by the development of assets in terms of hydraulic networks and wastewater collection networks, including all their relative building works. The process of selecting the investments to be made starts from the preventive analysis of critical issues (water losses, unserved areas, low service standards, etc.) who occur in the managed territory of the Operator. Through the Program of Interventions (Provision by ARERA n. 580/2019/R/idr), the Operator provides to program the projects that can meet the emerged needs to determine the improvement of the water service levels. This phase (analyzed and solved by the author with a work published in 2019) involves the use of evaluation techniques (cost-benefit analysis, multi-criteria, and multi-objective techniques, neural networks, etc.) useful in selecting the most appropriate design answers to the different criticalities. However, at this point, the problem of establishing the time priorities between the various works deemed necessary remains open. That is, it is necessary to hierarchize the investments. In this decision-making moment, the interests of the private Operator are often opposed, which favors investments capable of generating high profitability, compared to those of the public controller (ARERA), which favors investments in greater social impact. In support of the concertation between these two actors, the protocol set out in the research has been developed, based on the AHP and capable of borrowing from the programmatic documents an orientation path for the settlement of the conflict. The protocol is applied to a case study of the Campania Region in Italy and has been professionally applied in the shared decision process between the manager and the local Authority.

Keywords: analytic hierarchy process, decision making, economic evaluation of projects, integrated water service

Procedia PDF Downloads 123

Authors: Melby Chacko, Jagannath Nayak

Abstract:

The aging behaviour of 6061 Al-15 vol% SiC composite was investigated using Rockwell B hardness measurement. The composite was solutionized at 350°C and quenched in water. The composite was aged at room temperature (T4 treatment) and also at 140°C, 160°C, 180°C and 200°C (T6 treatment). The natural and artificial aging behaviour of composite was studied using aging curves determined at different temperatures. The aging period for peak aging for different temperatures was identified. The time required for attaining peak aging decreased with increase in the aging temperature. The peak hardness was found to increase with increase with aging temperature and the highest peak hardness was observed at 180ºC. Beyond 180ºC the peak hardness was found to be decreasing.

Keywords: 6061 Al-SiC composite, aging curve, Rockwell B hardness, T4, T6 treatments

Procedia PDF Downloads 267

Authors: C. H. Shashikanth, M. J. Davidson, V. Suresh Babu

Abstract:

The formability of metals depends on a number of variables such as strain, strain rate, and temperature. Though most of the metals are formable at room temperature, few are not. To evaluate the workability of such metals at elevated temperatures, thermomechanical experiments should be carried out to find out the forming temperatures and strain rates. Though a number of constitutive relations are available to correlate the material parameters and the corresponding formability at elevated temperatures, the constitutive rule proposed by Arrhenius has been used in this work. Thus, in the present work, the material constants such as A (constant), α (stress multiplier), β (constant), and n (stress exponent) of AA 2017 has been found by conducting a series of hot compression tests at different temperatures such as 400°C, 450°C, 500°C, and 550°C and at different strain rates such as 0.16, 0.18, and 0.2. True stress (σt), true strains (εt) deformation activation energy (Q), and the Zener-Hollomon parameter (Z value) were also calculated. The results indicate that the value of ln (Z) decreases as the temperature increases and it increases as the strain rate increases.

Keywords: hot compression test, aluminium alloy, flow stress, activation energy

Procedia PDF Downloads 621

Authors: Yonatan Sverdlov, Shimon Ullman

Abstract:

Artificial neural networks encounter a notable challenge known as continual learning, which involves acquiring knowledge of multiple tasks over an extended period. This challenge arises due to the tendency of previously learned weights to be adjusted to suit the objectives of new tasks, resulting in a phenomenon called catastrophic forgetting. Most approaches to this problem seek a balance between maximizing performance on the new tasks and minimizing the forgetting of previous tasks. In contrast, our approach attempts to maximize the performance of the new task, while ensuring zero forgetting. This is accomplished through the introduction of task-specific modulation parameters for each task, and only these parameters are learned for the new task, after a set of initial tasks have been learned. Through comprehensive experimental evaluations, our model demonstrates superior performance in acquiring and retaining novel tasks that pose difficulties for other multi-task models. This emphasizes the efficacy of our approach in preventing catastrophic forgetting while accommodating the acquisition of new tasks.

Keywords: continual learning, life-long learning, neural analogies, adaptive modulation

Procedia PDF Downloads 70

Authors: C. Slim

Abstract:

This paper presents an integrated model, which hybridized data envelopment analysis (DEA) and support vector machine (SVM) together, to class countries according to their efficiency and performance. This model takes into account aspects of multi-dimensional indicators, decision-making hierarchy and relativity of measurement. Starting from a set of indicators of performance as exhaustive as possible, a process of successive aggregations has been developed to attain an overall evaluation of a country’s competitiveness.

Keywords: Artificial Neural Networks (ANN), Support vector machine (SVM), Data Envelopment Analysis (DEA), Aggregations, indicators of performance

Procedia PDF Downloads 338

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

One of the most important challenges in the field of software code audit is the presence of vulnerabilities in software source code. Every year, more and more software flaws are found, either internally in proprietary code or revealed publicly. These flaws are highly likely exploited and lead to system compromise, data leakage, or denial of service. C and C++ open-source code are now available in order to create a largescale, machine-learning system for function-level vulnerability identification. We assembled a sizable dataset of millions of opensource functions that point to potential exploits. We developed an efficient and scalable vulnerability detection method based on deep neural network models that learn features extracted from the source codes. The source code is first converted into a minimal intermediate representation to remove the pointless components and shorten the dependency. Moreover, we keep the semantic and syntactic information using state-of-the-art word embedding algorithms such as glove and fastText. The embedded vectors are subsequently fed into deep learning networks such as LSTM, BilSTM, LSTM-Autoencoder, word2vec, BERT, and GPT-2 to classify the possible vulnerabilities. Furthermore, we proposed a neural network model which can overcome issues associated with traditional neural networks. Evaluation metrics such as f1 score, precision, recall, accuracy, and total execution time have been used to measure the performance. We made a comparative analysis between results derived from features containing a minimal text representation and semantic and syntactic information. We found that all of the deep learning models provide comparatively higher accuracy when we use semantic and syntactic information as the features but require higher execution time as the word embedding the algorithm puts on a bit of complexity to the overall system.

Keywords: cyber security, vulnerability detection, neural networks, feature extraction

Procedia PDF Downloads 89

Authors: E. Khattab, S. Halla

Abstract:

Jojoba plants are characterized by a tolerance of water stress, but due to the conditions of the Sinai in which the water is less, an irrigation interval study was carried out the jojoba plant from water stress without affecting the yield of oil. The field experiment was carried out at Maghara Research Station at North Sinai, Desert Research Center, Ministry of Agriculture, Egypt, to study the effect of irrigation interval on five clones of jojoba plants S-L, S-610, S- 700, S-B and S-G on growth and yield characters. Results showed that the clone S-700 has increase of all growth and yield characters under all interval irrigation compare with other clones. All variable of studied confirmed that clones of jojoba had significant effect with irrigation interval at one week but decrease value with three weeks. Jojoba plants tolerance to water stress but irrigation interval every week increased seed yield.

Keywords: interval irrigation, growth and yield characters, oil, jojoba, Sinai

Procedia PDF Downloads 194

Authors: Imed Mezghani, Yousra Ben Salah, Mohamed Chaieb

Abstract:

Tricholaena teneriffae L. is a xerophytic perennial herb that belongs to the Poaceae family likely to be used for ecological restoration programs. It's a dominant and economically important species widely distributed in the Bou-Hedma National Park, Tunisia. Reintroduction and expansion of T. teneriffae depend solely on sexual reproduction. This makes the understanding of its germination requirements vital for conservation and management. To provide basic information for its conservation and reintroduction, we studied the influence of environmental factors on seed germination patterns. The germination responses of seeds were determined over a wide range of constant temperatures (15–35°C), polyethylene glycol solutions of different osmotic potentials (0 to −2 MPa) and salt solution (0 to 150 mM of NaCl). Results indicated that the optimum temperature germination was attained at 25°C which corresponds to temperatures prevailing during mid spring season in the Mediterranean area. Seeds germinated in Polyethylene Glycol solutions exhibited significantly lower germination than control especially when water potential fell below -0.6 MPa. Germination percentage and rate decreased with an increase NaCl concentration. Seeds germination was substantially delayed and reduced with an increase in NaCl to levels above 50 mM. T. teneriffae is moderately salt tolerant at germination stage.

Keywords: germination, temperature, Tricholaena teneriffae L., salt stress, water stress, rehabilitation

Procedia PDF Downloads 293

Authors: Hatem H.Saleh

Abstract:

The aim of the study was to examine the effect of different concentrations of crude actinidin enzyme extract from kiwifruit juice and distilled water on some quality attributes of Awassi rams meats. Twelve Awassi rams were divided into four groups, After exsanguinations of rams carcasses they were infused (10% body weight) with crude of actinidin enzyme extract of kiwifruit juice with 10 and 15% of extract, and other group was infused with distilled water and were compared with other groups a non infusion treatment which were acted as a control. Thereafter samples from two main muscles, namely longissimus dorsi (LD) and Semimembranosus (SM) of the carcasses was chilled then stored in freezing, until testing time . The results showed a decrease in the rate pH decline on LD and SM muscle which was measured at time (0, 3, 6, 9, 12, 24 hours) postmortem among different treatments, It also reported lower values of the rate pH on the LD and SM muscle during the first of 12 hrs postmortem. No significant differences of the rate internal meat temperature in LD and SM muscle were observed among treatments postmortem except decreased of internal meat temperature during 3 hours postmortem when treated with enzyme extract. The results recorded higher values of glycolysis rate (R-value) in LD and SM muscle when treated with enzyme extract. Treated LD and LM muscle samples with 10 and 15% of crude actinidin enzyme extract of kiwifruit juice led to improve water holding capacity and higher significant differences in total tyrosine/ tryptophan index (T.T/T) in LD and SM muscles comparison with treatment control. It could be concluded that extract of kiwifruit juice infusion is could be used to improve of meat tenderization.

Keywords: extract of kiwifruit, decline of pH and Temperature , R-value, tyrosine / tryptophan index, sheep meat

Procedia PDF Downloads 543