Search results for: inputs
72 An Artificially Intelligent Teaching-Agent to Enhance Learning Interactions in Virtual Settings
Authors: Abdulwakeel B. Raji
Abstract:
This paper introduces a concept of an intelligent virtual learning environment that involves communication between learners and an artificially intelligent teaching agent in an attempt to replicate classroom learning interactions. The benefits of this technology over current e-learning practices is that it creates a virtual classroom where real time adaptive learning interactions are made possible. This is a move away from the static learning practices currently being adopted by e-learning systems. Over the years, artificial intelligence has been applied to various fields, including and not limited to medicine, military applications, psychology, marketing etc. The purpose of e-learning applications is to ensure users are able to learn outside of the classroom, but a major limitation has been the inability to fully replicate classroom interactions between teacher and students. This study used comparative surveys to gain information and understanding of the current learning practices in Nigerian universities and how they compare to these practices compare to the use of a developed e-learning system. The study was conducted by attending several lectures and noting the interactions between lecturers and tutors and as an aftermath, a software has been developed that deploys the use of an artificial intelligent teaching-agent alongside an e-learning system to enhance user learning experience and attempt to create the similar learning interactions to those found in classroom and lecture hall settings. Dialogflow has been used to implement a teaching-agent, which has been developed using JSON, which serves as a virtual teacher. Course content has been created using HTML, CSS, PHP and JAVASCRIPT as a web-based application. This technology can run on handheld devices and Google based home technologies to give learners an access to the teaching agent at any time. This technology also implements the use of definite clause grammars and natural language processing to match user inputs and requests with defined rules to replicate learning interactions. This technology developed covers familiar classroom scenarios such as answering users’ questions, asking ‘do you understand’ at regular intervals and answering subsequent requests, taking advanced user queries to give feedbacks at other periods. This software technology uses deep learning techniques to learn user interactions and patterns to subsequently enhance user learning experience. A system testing has been undergone by undergraduate students in the UK and Nigeria on the course ‘Introduction to Database Development’. Test results and feedback from users shows that this study and developed software is a significant improvement on existing e-learning systems. Further experiments are to be run using the software with different students and more course contents.Keywords: virtual learning, natural language processing, definite clause grammars, deep learning, artificial intelligence
Procedia PDF Downloads 12971 Assessing Sydney Tar Ponds Remediation and Natural Sediment Recovery in Nova Scotia, Canada
Authors: Tony R. Walker, N. Devin MacAskill, Andrew Thalhiemer
Abstract:
Sydney Harbour, Nova Scotia has long been subject to effluent and atmospheric inputs of metals, polycyclic aromatic hydrocarbons (PAHs), and polychlorinated biphenyls (PCBs) from a large coking operation and steel plant that operated in Sydney for nearly a century until closure in 1988. Contaminated effluents from the industrial site resulted in the creation of the Sydney Tar Ponds, one of Canada’s largest contaminated sites. Since its closure, there have been several attempts to remediate this former industrial site and finally, in 2004, the governments of Canada and Nova Scotia committed to remediate the site to reduce potential ecological and human health risks to the environment. The Sydney Tar Ponds and Coke Ovens cleanup project has become the most prominent remediation project in Canada today. As an integral part of remediation of the site (i.e., which consisted of solidification/stabilization and associated capping of the Tar Ponds), an extensive multiple media environmental effects program was implemented to assess what effects remediation had on the surrounding environment, and, in particular, harbour sediments. Additionally, longer-term natural sediment recovery rates of select contaminants predicted for the harbour sediments were compared to current conditions. During remediation, potential contributions to sediment quality, in addition to remedial efforts, were evaluated which included a significant harbour dredging project, propeller wash from harbour traffic, storm events, adjacent loading/unloading of coal and municipal wastewater treatment discharges. Two sediment sampling methodologies, sediment grab and gravity corer, were also compared to evaluate the detection of subtle changes in sediment quality. Results indicated that overall spatial distribution pattern of historical contaminants remains unchanged, although at much lower concentrations than previously reported, due to natural recovery. Measurements of sediment indicator parameter concentrations confirmed that natural recovery rates of Sydney Harbour sediments were in broad agreement with predicted concentrations, in spite of ongoing remediation activities. Overall, most measured parameters in sediments showed little temporal variability even when using different sampling methodologies, during three years of remediation compared to baseline, except for the detection of significant increases in total PAH concentrations noted during one year of remediation monitoring. The data confirmed the effectiveness of mitigation measures implemented during construction relative to harbour sediment quality, despite other anthropogenic activities and the dynamic nature of the harbour.Keywords: contaminated sediment, monitoring, recovery, remediation
Procedia PDF Downloads 23470 Option Pricing Theory Applied to the Service Sector
Authors: Luke Miller
Abstract:
This paper develops an options pricing methodology to value strategic pricing strategies in the services sector. More specifically, this study provides a unifying taxonomy of current service sector pricing practices, frames these pricing decisions as strategic real options, demonstrates accepted option valuation techniques to assess service sector pricing decisions, and suggests future research areas where pricing decisions and real options overlap. Enhancing revenue in the service sector requires proactive decision making in a world of uncertainty. In an effort to strategically price service products, revenue enhancement necessitates a careful study of the service costs, customer base, competition, legalities, and shared economies with the market. Pricing decisions involve the quality of inputs, manpower, and best practices to maintain superior service. These decisions further hinge on identifying relevant pricing strategies and understanding how these strategies impact a firm’s value. A relatively new area of research applies option pricing theory to investments in real assets and is commonly known as real options. The real options approach is based on the premise that many corporate decisions to invest or divest in assets are simply an option wherein the firm has the right to make an investment without any obligation to act. The decision maker, therefore, has more flexibility and the value of this operating flexibility should be taken into consideration. The real options framework has already been applied to numerous areas including manufacturing, inventory, natural resources, research and development, strategic decisions, technology, and stock valuation. Additionally, numerous surveys have identified a growing need for the real options decision framework within all areas of corporate decision-making. Despite the wide applicability of real options, no study has been carried out linking service sector pricing decisions and real options. This is surprising given the service sector comprises 80% of the US employment and Gross Domestic Product (GDP). Identifying real options as a practical tool to value different service sector pricing strategies is believed to have a significant impact on firm decisions. This paper identifies and discusses four distinct pricing strategies available to the service sector from an options’ perspective: (1) Cost-based profit margin, (2) Increased customer base, (3) Platform pricing, and (4) Buffet pricing. Within each strategy lie several pricing tactics available to the service firm. These tactics can be viewed as options the decision maker has to best manage a strategic position in the market. To demonstrate the effectiveness of including flexibility in the pricing decision, a series of pricing strategies were developed and valued using a real options binomial lattice structure. The options pricing approach discussed in this study allows service firms to directly incorporate market-driven perspectives into the decision process and thus synchronizing service operations with organizational economic goals.Keywords: option pricing theory, real options, service sector, valuation
Procedia PDF Downloads 35269 An Integrated Framework for Wind-Wave Study in Lakes
Authors: Moien Mojabi, Aurelien Hospital, Daniel Potts, Chris Young, Albert Leung
Abstract:
The wave analysis is an integral part of the hydrotechnical assessment carried out during the permitting and design phases for coastal structures, such as marinas. This analysis aims in quantifying: i) the Suitability of the coastal structure design against Small Craft Harbour wave tranquility safety criterion; ii) Potential environmental impacts of the structure (e.g., effect on wave, flow, and sediment transport); iii) Mooring and dock design and iv) Requirements set by regulatory agency’s (e.g., WSA section 11 application). While a complex three-dimensional hydrodynamic modelling approach can be applied on large-scale projects, the need for an efficient and reliable wave analysis method suitable for smaller scale marina projects was identified. As a result, Tetra Tech has developed and applied an integrated analysis framework (hereafter TT approach), which takes the advantage of the state-of-the-art numerical models while preserving the level of simplicity that fits smaller scale projects. The present paper aims to describe the TT approach and highlight the key advantages of using this integrated framework in lake marina projects. The core of this methodology is made by integrating wind, water level, bathymetry, and structure geometry data. To respond to the needs of specific projects, several add-on modules have been added to the core of the TT approach. The main advantages of this method over the simplified analytical approaches are i) Accounting for the proper physics of the lake through the modelling of the entire lake (capturing real lake geometry) instead of a simplified fetch approach; ii) Providing a more realistic representation of the waves by modelling random waves instead of monochromatic waves; iii) Modelling wave-structure interaction (e.g. wave transmission/reflection application for floating structures and piles amongst others); iv) Accounting for wave interaction with the lakebed (e.g. bottom friction, refraction, and breaking); v) Providing the inputs for flow and sediment transport assessment at the project site; vi) Taking in consideration historical and geographical variations of the wind field; and vii) Independence of the scale of the reservoir under study. Overall, in comparison with simplified analytical approaches, this integrated framework provides a more realistic and reliable estimation of wave parameters (and its spatial distribution) in lake marinas, leading to a realistic hydrotechnical assessment accessible to any project size, from the development of a new marina to marina expansion and pile replacement. Tetra Tech has successfully utilized this approach since many years in the Okanagan area.Keywords: wave modelling, wind-wave, extreme value analysis, marina
Procedia PDF Downloads 7568 Exploration into Bio Inspired Computing Based on Spintronic Energy Efficiency Principles and Neuromorphic Speed Pathways
Authors: Anirudh Lahiri
Abstract:
Neuromorphic computing, inspired by the intricate operations of biological neural networks, offers a revolutionary approach to overcoming the limitations of traditional computing architectures. This research proposes the integration of spintronics with neuromorphic systems, aiming to enhance computational performance, scalability, and energy efficiency. Traditional computing systems, based on the Von Neumann architecture, struggle with scalability and efficiency due to the segregation of memory and processing functions. In contrast, the human brain exemplifies high efficiency and adaptability, processing vast amounts of information with minimal energy consumption. This project explores the use of spintronics, which utilizes the electron's spin rather than its charge, to create more energy-efficient computing systems. Spintronic devices, such as magnetic tunnel junctions (MTJs) manipulated through spin-transfer torque (STT) and spin-orbit torque (SOT), offer a promising pathway to reducing power consumption and enhancing the speed of data processing. The integration of these devices within a neuromorphic framework aims to replicate the efficiency and adaptability of biological systems. The research is structured into three phases: an exhaustive literature review to build a theoretical foundation, laboratory experiments to test and optimize the theoretical models, and iterative refinements based on experimental results to finalize the system. The initial phase focuses on understanding the current state of neuromorphic and spintronic technologies. The second phase involves practical experimentation with spintronic devices and the development of neuromorphic systems that mimic synaptic plasticity and other biological processes. The final phase focuses on refining the systems based on feedback from the testing phase and preparing the findings for publication. The expected contributions of this research are twofold. Firstly, it aims to significantly reduce the energy consumption of computational systems while maintaining or increasing processing speed, addressing a critical need in the field of computing. Secondly, it seeks to enhance the learning capabilities of neuromorphic systems, allowing them to adapt more dynamically to changing environmental inputs, thus better mimicking the human brain's functionality. The integration of spintronics with neuromorphic computing could revolutionize how computational systems are designed, making them more efficient, faster, and more adaptable. This research aligns with the ongoing pursuit of energy-efficient and scalable computing solutions, marking a significant step forward in the field of computational technology.Keywords: material science, biological engineering, mechanical engineering, neuromorphic computing, spintronics, energy efficiency, computational scalability, synaptic plasticity.
Procedia PDF Downloads 2267 Characterization of Phenolic Compounds from Carménère Wines during Aging with Oak Wood (Staves, Chips and Barrels)
Authors: E. Obreque-Slier, J. Laqui-Estaña, A. Peña-Neira, M. Medel-Marabolí
Abstract:
Wine is an important source of polyphenols. Red wines show important concentrations of nonflavonoid (gallic acid, ellagic acid, caffeic acid and coumaric acid) and flavonoid compounds [(+)-catechin, (-)-epicatechin, (+)-gallocatechin and (-)-epigallocatechin]. However, a significant variability in the quantitative and qualitative distribution of chemical constituents in wine has to be expected depending on an array of important factors, such as the varietal differences of Vitis vinifera and cultural practices. It has observed that Carménère grapes present a differential composition and evolution of phenolic compounds when compared to other varieties and specifically with Cabernet Sauvignon grapes. Likewise, among the cultural practices, the aging in contact with oak wood is a high relevance factor. Then, the extraction of different polyphenolic compounds from oak wood into wine during its ageing process produces both qualitative and quantitative changes. Recently, many new techniques have been introduced in winemaking. One of these involves putting new pieces of wood (oak chips or inner staves) into inert containers. It offers some distinct and previously unavailable flavour advantages, as well as new options in wine handling. To our best knowledge, there is not information about the behaviour of Carménère wines (Chilean emblematic cultivar) in contact with oak wood. In addition, the effect of aging time and wood product (barrels, chips or staves) on the phenolic composition in Carménère wines has not been studied. This study aims at characterizing the condensed and hydrolyzable tannins from Carménère wines during the aging with staves, chips and barrels from French oak wood. The experimental design was completely randomized with two independent assays: aging time (0-12 month) and different formats of wood (barrel, chips and staves). The wines were characterized by spectrophotometric (total tannins and fractionation of proanthocyanidins into monomers, oligomers and polymers) and HPLC-DAD (ellagitannins) analysis. The wines in contact with different products of oak wood showed a similar content of total tannins during the study, while the control wine (without oak wood) presented a lower content of these compounds. In addition, it was observed that the polymeric proanthocyanidin fraction was the most abundant, while the monomeric fraction was the less abundant fraction in all treatments in two sample. However, significative differences in each fractions were observed between wines in contact from barrel, chips, and staves in two sample dates. Finally, the wine from barrels presented the highest content of the ellagitannins from the fourth to the last sample date. In conclusion, the use of alternative formats of oak wood affects the chemical composition of wines during aging, and these enological products are an interesting alternative to contribute with tannins to wine.Keywords: enological inputs, oak wood aging, polyphenols, red wine
Procedia PDF Downloads 15466 Self-Supervised Learning for Hate-Speech Identification
Authors: Shrabani Ghosh
Abstract:
Automatic offensive language detection in social media has become a stirring task in today's NLP. Manual Offensive language detection is tedious and laborious work where automatic methods based on machine learning are only alternatives. Previous works have done sentiment analysis over social media in different ways such as supervised, semi-supervised, and unsupervised manner. Domain adaptation in a semi-supervised way has also been explored in NLP, where the source domain and the target domain are different. In domain adaptation, the source domain usually has a large amount of labeled data, while only a limited amount of labeled data is available in the target domain. Pretrained transformers like BERT, RoBERTa models are fine-tuned to perform text classification in an unsupervised manner to perform further pre-train masked language modeling (MLM) tasks. In previous work, hate speech detection has been explored in Gab.ai, which is a free speech platform described as a platform of extremist in varying degrees in online social media. In domain adaptation process, Twitter data is used as the source domain, and Gab data is used as the target domain. The performance of domain adaptation also depends on the cross-domain similarity. Different distance measure methods such as L2 distance, cosine distance, Maximum Mean Discrepancy (MMD), Fisher Linear Discriminant (FLD), and CORAL have been used to estimate domain similarity. Certainly, in-domain distances are small, and between-domain distances are expected to be large. The previous work finding shows that pretrain masked language model (MLM) fine-tuned with a mixture of posts of source and target domain gives higher accuracy. However, in-domain performance of the hate classifier on Twitter data accuracy is 71.78%, and out-of-domain performance of the hate classifier on Gab data goes down to 56.53%. Recently self-supervised learning got a lot of attention as it is more applicable when labeled data are scarce. Few works have already been explored to apply self-supervised learning on NLP tasks such as sentiment classification. Self-supervised language representation model ALBERTA focuses on modeling inter-sentence coherence and helps downstream tasks with multi-sentence inputs. Self-supervised attention learning approach shows better performance as it exploits extracted context word in the training process. In this work, a self-supervised attention mechanism has been proposed to detect hate speech on Gab.ai. This framework initially classifies the Gab dataset in an attention-based self-supervised manner. On the next step, a semi-supervised classifier trained on the combination of labeled data from the first step and unlabeled data. The performance of the proposed framework will be compared with the results described earlier and also with optimized outcomes obtained from different optimization techniques.Keywords: attention learning, language model, offensive language detection, self-supervised learning
Procedia PDF Downloads 10065 Crop Breeding for Low Input Farming Systems and Appropriate Breeding Strategies
Authors: Baye Berihun Getahun, Mulugeta Atnaf Tiruneh, Richard G. F. Visser
Abstract:
Resource-poor farmers practice low-input farming systems, and yet, most breeding programs give less attention to this huge farming system, which serves as a source of food and income for several people in developing countries. The high-input conventional breeding system appears to have failed to adequately meet the needs and requirements of 'difficult' environments operating under this system. Moreover, the unavailability of resources for crop production is getting for their peaks, the environment is maltreated by excessive use of agrochemicals, crop productivity reaches its plateau stage, particularly in the developed nations, the world population is increasing, and food shortage sustained to persist for poor societies. In various parts of the world, genetic gain at the farmers' level remains low which could be associated with low adoption of crop varieties, which have been developed under high input systems. Farmers usually use their local varieties and apply minimum inputs as a risk-avoiding and cost-minimizing strategy. This evidence indicates that the conventional high-input plant breeding system has failed to feed the world population, and the world is moving further away from the United Nations' goals of ending hunger, food insecurity, and malnutrition. In this review, we discussed the rationality of focused breeding programs for low-input farming systems and, the technical aspect of crop breeding that accommodates future food needs and its significance for developing countries in the decreasing scenario of resources required for crop production. To this end, the application of exotic introgression techniques like polyploidization, pan-genomics, comparative genomics, and De novo domestication as a pre-breeding technique has been discussed in the review to exploit the untapped genetic diversity of the crop wild relatives (CWRs). Desired recombinants developed at the pre-breeding stage are exploited through appropriate breeding approaches such as evolutionary plant breeding (EPB), rhizosphere-related traits breeding, and participatory plant breeding approaches. Populations advanced through evolutionary breeding like composite cross populations (CCPs) and rhizosphere-associated traits breeding approach that provides opportunities for improving abiotic and biotic soil stress, nutrient acquisition capacity, and crop microbe interaction in improved varieties have been reviewed. Overall, we conclude that low input farming system is a huge farming system that requires distinctive breeding approaches, and the exotic pre-breeding introgression techniques and the appropriate breeding approaches which deploy the skills and knowledge of both breeders and farmers are vital to develop heterogeneous landrace populations, which are effective for farmers practicing low input farming across the world.Keywords: low input farming, evolutionary plant breeding, composite cross population, participatory plant breeding
Procedia PDF Downloads 3564 Educational Institutional Approach for Livelihood Improvement and Sustainable Development
Authors: William Kerua
Abstract:
The PNG University of Technology (Unitech) has mandatory access to teaching, research and extension education. Given such function, the Agriculture Department has established the ‘South Pacific Institute of Sustainable Agriculture and Rural Development (SPISARD)’ in 2004. SPISARD is established as a vehicle to improve farming systems practiced in selected villages by undertaking pluralistic extension method through ‘Educational Institutional Approach’. Unlike other models, SPISARD’s educational institutional approach stresses on improving the whole farming systems practiced in a holistic manner and has a two-fold focus. The first is to understand the farming communities and improve the productivity of the farming systems in a sustainable way to increase income, improve nutrition and food security as well as livelihood enhancement trainings. The second is to enrich the Department’s curriculum through teaching, research, extension and getting inputs from farming community. SPISARD has established number of model villages in various provinces in Papua New Guinea (PNG) and with many positive outcome and success stories. Adaption of ‘educational institutional approach’ thus binds research, extension and training into one package with the use of students and academic staff through model village establishment in delivering development and extension to communities. This centre (SPISARD) coordinates the activities of the model village programs and linkages. The key to the development of the farming systems is establishing and coordinating linkages, collaboration, and developing partnerships both within and external institutions, organizations and agencies. SPISARD has a six-point step strategy for the development of sustainable agriculture and rural development. These steps are (i) establish contact and identify model villages, (ii) development of model village resource centres for research and trainings, (iii) conduct baseline surveys to identify problems/needs of model villages, (iv) development of solution strategies, (v) implementation and (vi) evaluation of impact of solution programs. SPISARD envisages that the farming systems practiced being improved if the villages can be made the centre of SPISARD activities. Therefore, SPISARD has developed a model village approach to channel rural development. The model village when established become the conduit points where teaching, training, research, and technology transfer takes place. This approach is again different and unique to the existing ones, in that, the development process take place in the farmers’ environment with immediate ‘real time’ feedback mechanisms based on the farmers’ perspective and satisfaction. So far, we have developed 14 model villages and have conducted 75 trainings in 21 different areas/topics in 8 provinces to a total of 2,832 participants of both sex. The aim of these trainings is to directly participate with farmers in the pursuit to improving their farming systems to increase productivity, income and to secure food security and nutrition, thus to improve their livelihood.Keywords: development, educational institutional approach, livelihood improvement, sustainable agriculture
Procedia PDF Downloads 15263 Bayesian Structural Identification with Systematic Uncertainty Using Multiple Responses
Authors: André Jesus, Yanjie Zhu, Irwanda Laory
Abstract:
Structural health monitoring is one of the most promising technologies concerning aversion of structural risk and economic savings. Analysts often have to deal with a considerable variety of uncertainties that arise during a monitoring process. Namely the widespread application of numerical models (model-based) is accompanied by a widespread concern about quantifying the uncertainties prevailing in their use. Some of these uncertainties are related with the deterministic nature of the model (code uncertainty) others with the variability of its inputs (parameter uncertainty) and the discrepancy between a model/experiment (systematic uncertainty). The actual process always exhibits a random behaviour (observation error) even when conditions are set identically (residual variation). Bayesian inference assumes that parameters of a model are random variables with an associated PDF, which can be inferred from experimental data. However in many Bayesian methods the determination of systematic uncertainty can be problematic. In this work systematic uncertainty is associated with a discrepancy function. The numerical model and discrepancy function are approximated by Gaussian processes (surrogate model). Finally, to avoid the computational burden of a fully Bayesian approach the parameters that characterise the Gaussian processes were estimated in a four stage process (modular Bayesian approach). The proposed methodology has been successfully applied on fields such as geoscience, biomedics, particle physics but never on the SHM context. This approach considerably reduces the computational burden; although the extent of the considered uncertainties is lower (second order effects are neglected). To successfully identify the considered uncertainties this formulation was extended to consider multiple responses. The efficiency of the algorithm has been tested on a small scale aluminium bridge structure, subjected to a thermal expansion due to infrared heaters. Comparison of its performance with responses measured at different points of the structure and associated degrees of identifiability is also carried out. A numerical FEM model of the structure was developed and the stiffness from its supports is considered as a parameter to calibrate. Results show that the modular Bayesian approach performed best when responses of the same type had the lowest spatial correlation. Based on previous literature, using different types of responses (strain, acceleration, and displacement) should also improve the identifiability problem. Uncertainties due to parametric variability, observation error, residual variability, code variability and systematic uncertainty were all recovered. For this example the algorithm performance was stable and considerably quicker than Bayesian methods that account for the full extent of uncertainties. Future research with real-life examples is required to fully access the advantages and limitations of the proposed methodology.Keywords: bayesian, calibration, numerical model, system identification, systematic uncertainty, Gaussian process
Procedia PDF Downloads 32262 Mass Flux and Forensic Assessment: Informed Remediation Decision Making at One of Canada’s Most Polluted Sites
Authors: Tony R. Walker, N. Devin MacAskill, Andrew Thalhiemer
Abstract:
Sydney Harbour, Nova Scotia, Canada has long been subject to effluent and atmospheric inputs of contaminants, including thousands of tons of PAHs from a large coking and steel plant which operated in Sydney for nearly a century. Contaminants comprised of coal tar residues which were discharged from coking ovens into a small tidal tributary, which became known as the Sydney Tar Ponds (STPs), and subsequently discharged into Sydney Harbour. An Environmental Impact Statement concluded that mobilization of contaminated sediments posed unacceptable ecological risks, therefore immobilizing contaminants in the STPs using solidification and stabilization was identified as a primary source control remediation option to mitigate against continued transport of contaminated sediments from the STPs into Sydney Harbour. Recent developments in contaminant mass flux techniques focus on understanding “mobile” vs. “immobile” contaminants at remediation sites. Forensic source evaluations are also increasingly used for understanding origins of PAH contaminants in soils or sediments. Flux and forensic source evaluation-informed remediation decision-making uses this information to develop remediation end point goals aimed at reducing off-site exposure and managing potential ecological risk. This study included reviews of previous flux studies, calculating current mass flux estimates and a forensic assessment using PAH fingerprint techniques, during remediation of one of Canada’s most polluted sites at the STPs. Historically, the STPs was thought to be the major source of PAH contamination in Sydney Harbour with estimated discharges of nearly 800 kg/year of PAHs. However, during three years of remediation monitoring only 17-97 kg/year of PAHs were discharged from the STPs, which was also corroborated by an independent PAH flux study during the first year of remediation which estimated 119 kg/year. The estimated mass efflux of PAHs from the STPs during remediation was in stark contrast to ~2000 kg loading thought necessary to cause a short term increase in harbour sediment PAH concentrations. These mass flux estimates during remediation were also between three to eight times lower than PAHs discharged from the STPs a decade prior to remediation, when at the same time, government studies demonstrated on-going reduction in PAH concentrations in harbour sediments. Flux results were also corroborated using forensic source evaluations using PAH fingerprint techniques which found a common source of PAHs for urban soils, marine and aquatic sediments in and around Sydney. Coal combustion (from historical coking) and coal dust transshipment (from current coal transshipment facilities), are likely the principal source of PAHs in these media and not migration of PAH laden sediments from the STPs during a large scale remediation project.Keywords: contaminated sediment, mass flux, forensic source evaluations, remediation
Procedia PDF Downloads 23661 Alternative Fuel Production from Sewage Sludge
Authors: Jaroslav Knapek, Kamila Vavrova, Tomas Kralik, Tereza Humesova
Abstract:
The treatment and disposal of sewage sludge is one of the most important and critical problems of waste water treatment plants. Currently, 180 thousand tonnes of sludge dry matter are produced in the Czech Republic, which corresponds to approximately 17.8 kg of stabilized sludge dry matter / year per inhabitant of the Czech Republic. Due to the fact that sewage sludge contains a large amount of substances that are not beneficial for human health, the conditions for sludge management will be significantly tightened in the Czech Republic since 2023. One of the tested methods of sludge liquidation is the production of alternative fuel from sludge from sewage treatment plants and paper production. The paper presents an analysis of economic efficiency of alternative fuel production from sludge and its use for fluidized bed boiler with nominal consumption of 5 t of fuel per hour. The evaluation methodology includes the entire logistics chain from sludge extraction, through mechanical moisture reduction to about 40%, transport to the pelletizing line, moisture drying for pelleting and pelleting itself. For economic analysis of sludge pellet production, a time horizon of 10 years corresponding to the expected lifetime of the critical components of the pelletizing line is chosen. The economic analysis of pelleting projects is based on a detailed analysis of reference pelleting technologies suitable for sludge pelleting. The analysis of the economic efficiency of pellet is based on the simulation of cash flows associated with the implementation of the project over the life of the project. For the entered value of return on the invested capital, the price of the resulting product (in EUR / GJ or in EUR / t) is searched to ensure that the net present value of the project is zero over the project lifetime. The investor then realizes the return on the investment in the amount of the discount used to calculate the net present value. The calculations take place in a real business environment (taxes, tax depreciation, inflation, etc.) and the inputs work with market prices. At the same time, the opportunity cost principle is respected; waste disposal for alternative fuels includes the saved costs of waste disposal. The methodology also respects the emission allowances saved due to the displacement of coal by alternative (bio) fuel. Preliminary results of testing of pellet production from sludge show that after suitable modifications of the pelletizer it is possible to produce sufficiently high quality pellets from sludge. A mixture of sludge and paper waste has proved to be a more suitable material for pelleting. At the same time, preliminary results of the analysis of the economic efficiency of this sludge disposal method show that, despite the relatively low calorific value of the fuel produced (about 10-11 MJ / kg), this sludge disposal method is economically competitive. This work has been supported by the Czech Technology Agency within the project TN01000048 Biorefining as circulation technology.Keywords: Alternative fuel, Economic analysis, Pelleting, Sewage sludge
Procedia PDF Downloads 12660 Distribution and Ecological Risk Assessment of Trace Elements in Sediments along the Ganges River Estuary, India
Authors: Priyanka Mondal, Santosh K. Sarkar
Abstract:
The present study investigated the spatiotemporal distribution and ecological risk assessment of trace elements of surface sediments (top 0 - 5 cm; grain size ≤ 0.63 µm) in relevance to sediment quality characteristics along the Ganges River Estuary, India. Sediment samples were collected during ebb tide from intertidal regions covering seven sampling sites of diverse environmental stresses. The elements were analyzed with the help of ICPAES. This positive, mixohaline, macro-tidal estuary has global significance contributing ecological and economic services. Presence of fine-clayey particle (47.03%) enhances the adsorption as well as transportation of trace elements. There is a remarkable inter-metallic variation (mg kg-1 dry weight) in the distribution pattern in the following manner: Al (31801± 15943) > Fe (23337± 7584) > Mn (461±147) > S(381±235) > Zn(54 ±18) > V(43 ±14) > Cr(39 ±15) > As (34±15) > Cu(27 ±11) > Ni (24 ±9) > Se (17 ±8) > Co(11 ±3) > Mo(10 ± 2) > Hg(0.02 ±0.01). An overall trend of enrichment of majority of trace elements was very much pronounced at the site Lot 8, ~ 35km upstream of the estuarine mouth. In contrast, the minimum concentration was recorded at site Gangasagar, mouth of the estuary, with high energy profile. The prevalent variations in trace element distribution are being liable for a set of cumulative factors such as hydrodynamic conditions, sediment dispersion pattern and textural variations as well as non-homogenous input of contaminants from point and non-point sources. In order to gain insight into the trace elements distribution, accumulation, and their pollution status, geoaccumulation index (Igeo) and enrichment factor (EF) were used. The Igeo indicated that surface sediments were moderately polluted with As (0.60) and Mo (1.30) and strongly contaminated with Se (4.0). The EF indicated severe pollution of Se (53.82) and significant pollution of As (4.05) and Mo (6.0) and indicated the influx of As, Mo and Se in sediments from anthropogenic sources (such as industrial and municipal sewage, atmospheric deposition, agricultural run-off, etc.). The significant role of the megacity Calcutta in relevance to the untreated sewage discharge, atmospheric inputs and other anthropogenic activities is worthwhile to mention. The ecological risk for different trace elements was evaluated using sediment quality guidelines, effects range low (ERL), and effect range median (ERM). The concentration of As, Cu and Ni at 100%, 43% and 86% of the sampling sites has exceeded the ERL value while none of the element concentration exceeded ERM. The potential ecological risk index values revealed that As at 14.3% of the sampling sites would pose relatively moderate risk to benthic organisms. The effective role of finer clay particles for trace element distribution was revealed by multivariate analysis. The authors strongly recommend regular monitoring emphasizing on accurate appraisal of the potential risk of trace elements for effective and sustainable management of this estuarine environment.Keywords: pollution assessment, sediment contamination, sediment quality, trace elements
Procedia PDF Downloads 25459 A New Perspective in Cervical Dystonia: Neurocognitive Impairment
Authors: Yesim Sucullu Karadag, Pinar Kurt, Sule Bilen, Nese Subutay Oztekin, Fikri Ak
Abstract:
Background: Primary cervical dystonia is thought to be a purely motor disorder. But recent studies revealed that patients with dystonia had additional non-motor features. Sensory and psychiatric disturbances could be included into the non-motor spectrum of dystonia. The Basal Ganglia receive inputs from all cortical areas and throughout the thalamus project to several cortical areas, thus participating to circuits that have been linked to motor as well as sensory, emotional and cognitive functions. However, there are limited studies indicating cognitive impairment in patients with cervical dystonia. More evidence is required regarding neurocognitive functioning in these patients. Objective: This study is aimed to investigate neurocognitive profile of cervical dystonia patients in comparison to healthy controls (HC) by employing a detailed set of neuropsychological tests in addition to self-reported instruments. Methods: Totally 29 (M/F: 7/22) cervical dystonia patients and 30 HC (M/F: 10/20) were included into the study. Exclusion criteria were depression and not given informed consent. Standard demographic, educational data and clinical reports (disease duration, disability index) were recorded for all patients. After a careful neurological evaluation, all subjects were given a comprehensive battery of neuropsychological tests: Self report of neuropsychological condition (by visual analogue scale-VAS, 0-100), RAVLT, STROOP, PASAT, TMT, SDMT, JLOT, DST, COWAT, ACTT, and FST. Patients and HC were compared regarding demographic, clinical features and neurocognitive tests. Also correlation between disease duration, disability index and self report -VAS were assessed. Results: There was no difference between patients and HCs regarding socio-demographic variables such as age, gender and years of education (p levels were 0.36, 0.436, 0.869; respectively). All of the patients were assessed at the peak of botulinum toxine effect and they were not taking an anticholinergic agent or benzodiazepine. Dystonia patients had significantly impaired verbal learning and memory (RAVLT, p<0.001), divided attention and working memory (ACTT, p<0.001), attention speed (TMT-A and B, p=0.008, 0.050), executive functions (PASAT, p<0.001; SDMT, p= 0.001; FST, p<0.001), verbal attention (DST, p=0.001), verbal fluency (COWAT, p<0.001), visio-spatial processing (JLOT, p<0.001) in comparison to healthy controls. But focused attention (STROOP-spontaneous correction) was not different between two groups (p>0.05). No relationship was found regarding disease duration and disability index with any neurocognitive tests. Conclusions: Our study showed that neurocognitive functions of dystonia patients were worse than control group with the similar age, sex, and education independently clinical expression like disease duration and disability index. This situation may be the result of possible cortical and subcortical changes in dystonia patients. Advanced neuroimaging techniques might be helpful to explain these changes in cervical dystonia patients.Keywords: cervical dystonia, neurocognitive impairment, neuropsychological test, dystonia disability index
Procedia PDF Downloads 40858 Recycling Service Strategy by Considering Demand-Supply Interaction
Authors: Hui-Chieh Li
Abstract:
Circular economy promotes greater resource productivity and avoids pollution through greater recycling and re-use which bring benefits for both the environment and the economy. The concept is contrast to a linear economy which is ‘take, make, dispose’ model of production. A well-design reverse logistics service strategy could enhance the willingness of recycling of the users and reduce the related logistics cost as well as carbon emissions. Moreover, the recycle brings the manufacturers most advantages as it targets components for closed-loop reuse, essentially converting materials and components from worn-out product into inputs for new ones at right time and right place. This study considers demand-supply interaction, time-dependent recycle demand, time-dependent surplus value of recycled product and constructs models on recycle service strategy for the recyclable waste collector. A crucial factor in optimizing a recycle service strategy is consumer demand. The study considers the relationships between consumer demand towards recycle and product characteristics, surplus value and user behavior. The study proposes a recycle service strategy which differs significantly from the conventional and typical uniform service strategy. Periods with considerable demand and large surplus product value suggest frequent and short service cycle. The study explores how to determine a recycle service strategy for recyclable waste collector in terms of service cycle frequency and duration and vehicle type for all service cycles by considering surplus value of recycled product, time-dependent demand, transportation economies and demand-supply interaction. The recyclable waste collector is responsible for the collection of waste product for the manufacturer. The study also examines the impacts of utilization rate on the cost and profit in the context of different sizes of vehicles. The model applies mathematical programming methods and attempts to maximize the total profit of the distributor during the study period. This study applies the binary logit model, analytical model and mathematical programming methods to the problem. The model specifically explores how to determine a recycle service strategy for the recycler by considering product surplus value, time-dependent recycle demand, transportation economies and demand-supply interaction. The model applies mathematical programming methods and attempts to minimize the total logistics cost of the recycler and maximize the recycle benefits of the manufacturer during the study period. The study relaxes the constant demand assumption and examines how service strategy affects consumer demand towards waste recycling. Results of the study not only help understanding how the user demand for recycle service and product surplus value affects the logistics cost and manufacturer’s benefits, but also provide guidance such as award bonus and carbon emission regulations for the government.Keywords: circular economy, consumer demand, product surplus value, recycle service strategy
Procedia PDF Downloads 38857 Technology Management for Early Stage Technologies
Authors: Ming Zhou, Taeho Park
Abstract:
Early stage technologies have been particularly challenging to manage due to high degrees of their numerous uncertainties. Most research results directly out of a research lab tend to be at their early, if not the infant stage. A long while uncertain commercialization process awaits these lab results. The majority of such lab technologies go nowhere and never get commercialized due to various reasons. Any efforts or financial resources put into managing these technologies turn fruitless. High stake naturally calls for better results, which make a patenting decision harder to make. A good and well protected patent goes a long way for commercialization of the technology. Our preliminary research showed that there was not a simple yet productive procedure for such valuation. Most of the studies now have been theoretical and overly comprehensive where practical suggestions were non-existent. Hence, we attempted to develop a simple and highly implementable procedure for efficient and scalable valuation. We thoroughly reviewed existing research, interviewed practitioners in the Silicon Valley area, and surveyed university technology offices. Instead of presenting another theoretical and exhaustive research, we aimed at developing a practical guidance that a government agency and/or university office could easily deploy and get things moving to later steps of managing early stage technologies. We provided a procedure to thriftily value and make the patenting decision. A patenting index was developed using survey data and expert opinions. We identified the most important factors to be used in the patenting decision using survey ratings. The rating then assisted us in generating good relative weights for the later scoring and weighted averaging step. More importantly, we validated our procedure by testing it with our practitioner contacts. Their inputs produced a general yet highly practical cut schedule. Such schedule of realistic practices has yet to be witnessed our current research. Although a technology office may choose to deviate from our cuts, what we offered here at least provided a simple and meaningful starting point. This procedure was welcomed by practitioners in our expert panel and university officers in our interview group. This research contributed to our current understanding and practices of managing early stage technologies by instating a heuristically simple yet theoretical solid method for the patenting decision. Our findings generated top decision factors, decision processes and decision thresholds of key parameters. This research offered a more practical perspective which further completed our extant knowledge. Our results could be impacted by our sample size and even biased a bit by our focus on the Silicon Valley area. Future research, blessed with bigger data size and more insights, may want to further train and validate our parameter values in order to obtain more consistent results and analyze our decision factors for different industries.Keywords: technology management, early stage technology, patent, decision
Procedia PDF Downloads 34056 A Review on Assessment on the Level of Development of Macedonia and Iran Organic Agriculture as Compared to Nigeria
Authors: Yusuf Ahmad Sani, Adamu Alhaji Yakubu, Alhaji Abdullahi Jamilu, Joel Omeke, Ibrahim Jumare Sambo
Abstract:
With the rising global threat of food security, cancer, and related diseases (carcinogenic) because of increased usage of inorganic substances in agricultural food production, the Ministry of Food Agriculture and Livestock of the Republic of Turkey organized an International Workshop on Organic Agriculture between 8 – 12th December 2014 at the International Agricultural Research and Training Center, Izmir. About 21 countries, including Nigeria, were invited to attend the training workshop. Several topics on organic agriculture were presented by renowned scholars, ranging from regulation, certification, crop, animal, seed production, pest and disease management, soil composting, and marketing of organic agricultural products, among others. This paper purposely selected two countries (Macedonia and Iran) out of the 21 countries to assess their level of development in terms of organic agriculture as compared to Nigeria. Macedonia, with a population of only 2.1 million people as of 2014, started organic agriculture in 2005 with only 266ha of land and has grown significantly to over 5,000ha in 2010, covering such crops as cereals (62%), forage (20%) fruit orchard (7%), vineyards (5%), vegetables (4%), oil seed and industrial crops (1%) each. Others are organic beekeeping from 110 hives to over 15,000 certified colonies. As part of government commitment, the level of government subsidy for organic products was 30% compared to the direct support for conventional agricultural products. About 19 by-laws were introduced on organic agricultural production that was fully consistent with European Union regulations. The republic of Iran, on the other hand, embarked on organic agriculture for the fact, that the country recorded the highest rate of cancer disease in the world, with over 30,000 people dying every year and 297 people diagnosed every day. However, the host country, Turkey, is well advanced in organic agricultural production and now being the largest exporter of organic products to Europe and other parts of the globe. A technical trip to one of the villages that are under the government scheme on organic agriculture reveals that organic agriculture was based on market-demand-driven and the support of the government was very visible, linking the farmers with private companies that provide inputs to them while the companies purchase the products at harvest with high premium price. However, in Nigeria, research on organic agriculture was very recent, and there was very scanty information on organic agriculture due to poor documentation and very low awareness, even among the elites. The paper, therefore, recommends that the government should provide funds to NARIs to conduct research on organic agriculture and to establish clear government policy and good pre-conditions for sustainable organic agricultural production in the country.Keywords: organic agriculture, food security, food safety, food nutrition
Procedia PDF Downloads 3455 Developing Motorized Spectroscopy System for Tissue Scanning
Authors: Tuba Denkceken, Ayse Nur Sarı, Volkan Ihsan Tore, Mahmut Denkceken
Abstract:
The aim of the presented study was to develop a newly motorized spectroscopy system. Our system is composed of probe and motor parts. The probe part consists of bioimpedance and fiber optic components that include two platinum wires (each 25 micrometer in diameter) and two fiber cables (each 50 micrometers in diameter) respectively. Probe was examined on tissue phantom (polystyrene microspheres with different diameters). In the bioimpedance part of the probe current was transferred to the phantom and conductivity information was obtained. Adjacent two fiber cables were used in the fiber optic part of the system. Light was transferred to the phantom by fiber that was connected to the light source and backscattered light was collected with the other adjacent fiber for analysis. It is known that the nucleus expands and the nucleus-cytoplasm ratio increases during the cancer progression in the cell and this situation is one of the most important criteria for evaluating the tissue for pathologists. The sensitivity of the probe to particle (nucleus) size in phantom was tested during the study. Spectroscopic data obtained from our system on phantom was evaluated by multivariate statistical analysis. Thus the information about the particle size in the phantom was obtained. Bioimpedance and fiber optic experiments results which were obtained from polystyrene microspheres showed that the impedance value and the oscillation amplitude were increasing while the size of particle was enlarging. These results were compatible with the previous studies. In order to motorize the system within the motor part, three driver electronic circuits were designed primarily. In this part, supply capacitors were placed symmetrically near to the supply inputs which were used for balancing the oscillation. Female capacitors were connected to the control pin. Optic and mechanic switches were made. Drivers were structurally designed as they could command highly calibrated motors. It was considered important to keep the drivers’ dimension as small as we could (4.4x4.4x1.4 cm). Then three miniature step motors were connected to each other along with three drivers. Since spectroscopic techniques are quantitative methods, they yield more objective results than traditional ones. In the future part of this study, it is planning to get spectroscopic data that have optic and impedance information from the cell culture which is normal, low metastatic and high metastatic breast cancer. In case of getting high sensitivity in differentiated cells, it might be possible to scan large surface tissue areas in a short time with small steps. By means of motorize feature of the system, any region of the tissue will not be missed, in this manner we are going to be able to diagnose cancerous parts of the tissue meticulously. This work is supported by The Scientific and Technological Research Council of Turkey (TÜBİTAK) through 3001 project (115E662).Keywords: motorized spectroscopy, phantom, scanning system, tissue scanning
Procedia PDF Downloads 18854 A Literature Review Evaluating the Use of Online Problem-Based Learning and Case-Based Learning Within Dental Education
Authors: Thomas Turner
Abstract:
Due to the Covid-19 pandemic alternative ways of delivering dental education were required. As a result, many institutions moved teaching online. The impact of this is poorly understood. Is online problem-based learning (PBL) and case-based learning (CBL) effective and is it suitable in the post-pandemic era? PBL and CBL are both types of interactive, group-based learning which are growing in popularity within many dental schools. PBL was first introduced in the 1960’s and can be defined as learning which occurs from collaborative work to resolve a problem. Whereas CBL encourages learning from clinical cases, encourages application of knowledge and helps prepare learners for clinical practice. To evaluate the use of online PBL and CBL. A literature search was conducted using the CINAHL, Embase, PubMed and Web of Science databases. Literature was also identified from reference lists. Studies were only included from dental education. Seven suitable studies were identified. One of the studies found a high learner and facilitator satisfaction rate with online CBL. Interestingly one study found learners preferred CBL over PBL within an online format. A study also found, that within the context of distance learning, learners preferred a hybrid curriculum including PBL over a traditional approach. A further study pointed to the limitations of PBL within an online format, such as reduced interaction, potentially hindering the development of communication skills and the increased time and technology support required. An audience response system was also developed for use within CBL and had a high satisfaction rate. Interestingly one study found achievement of learning outcomes was correlated with the number of student and staff inputs within an online format. Whereas another study found the quantity of learner interactions were important to group performance, however the quantity of facilitator interactions was not. This review identified generally favourable evidence for the benefits of online PBL and CBL. However, there is limited high quality evidence evaluating these teaching methods within dental education and there appears to be limited evidence comparing online and faceto-face versions of these sessions. The importance of the quantity of learner interactions is evident, however the importance of the quantity of facilitator interactions appears to be questionable. An element to this may be down to the quality of interactions, rather than just quantity. Limitations of online learning regarding technological issues and time required for a session are also highlighted, however as learners and facilitators get familiar with online formats, these may become less of an issue. It is also important learners are encouraged to interact and communicate during these sessions, to allow for the development of communication skills. Interestingly CBL appeared to be preferred to PBL in an online format. This may reflect the simpler nature of CBL, however further research is required to explore this finding. Online CBL and PBL appear promising, however further research is required before online formats of these sessions are widely adopted in the post-pandemic era.Keywords: case-based learning, online, problem-based learning, remote, virtual
Procedia PDF Downloads 7053 Using Convolutional Neural Networks to Distinguish Different Sign Language Alphanumerics
Authors: Stephen L. Green, Alexander N. Gorban, Ivan Y. Tyukin
Abstract:
Within the past decade, using Convolutional Neural Networks (CNN)’s to create Deep Learning systems capable of translating Sign Language into text has been a breakthrough in breaking the communication barrier for deaf-mute people. Conventional research on this subject has been concerned with training the network to recognize the fingerspelling gestures of a given language and produce their corresponding alphanumerics. One of the problems with the current developing technology is that images are scarce, with little variations in the gestures being presented to the recognition program, often skewed towards single skin tones and hand sizes that makes a percentage of the population’s fingerspelling harder to detect. Along with this, current gesture detection programs are only trained on one finger spelling language despite there being one hundred and forty-two known variants so far. All of this presents a limitation for traditional exploitation for the state of current technologies such as CNN’s, due to their large number of required parameters. This work aims to present a technology that aims to resolve this issue by combining a pretrained legacy AI system for a generic object recognition task with a corrector method to uptrain the legacy network. This is a computationally efficient procedure that does not require large volumes of data even when covering a broad range of sign languages such as American Sign Language, British Sign Language and Chinese Sign Language (Pinyin). Implementing recent results on method concentration, namely the stochastic separation theorem, an AI system is supposed as an operate mapping an input present in the set of images u ∈ U to an output that exists in a set of predicted class labels q ∈ Q of the alphanumeric that q represents and the language it comes from. These inputs and outputs, along with the interval variables z ∈ Z represent the system’s current state which implies a mapping that assigns an element x ∈ ℝⁿ to the triple (u, z, q). As all xi are i.i.d vectors drawn from a product mean distribution, over a period of time the AI generates a large set of measurements xi called S that are grouped into two categories: the correct predictions M and the incorrect predictions Y. Once the network has made its predictions, a corrector can then be applied through centering S and Y by subtracting their means. The data is then regularized by applying the Kaiser rule to the resulting eigenmatrix and then whitened before being split into pairwise, positively correlated clusters. Each of these clusters produces a unique hyperplane and if any element x falls outside the region bounded by these lines then it is reported as an error. As a result of this methodology, a self-correcting recognition process is created that can identify fingerspelling from a variety of sign language and successfully identify the corresponding alphanumeric and what language the gesture originates from which no other neural network has been able to replicate.Keywords: convolutional neural networks, deep learning, shallow correctors, sign language
Procedia PDF Downloads 9652 Deficient Multisensory Integration with Concomitant Resting-State Connectivity in Adult Attention Deficit/Hyperactivity Disorder (ADHD)
Authors: Marcel Schulze, Behrem Aslan, Silke Lux, Alexandra Philipsen
Abstract:
Objective: Patients with Attention Deficit/Hyperactivity Disorder (ADHD) often report that they are being flooded by sensory impressions. Studies investigating sensory processing show hypersensitivity for sensory inputs across the senses in children and adults with ADHD. Especially the auditory modality is affected by deficient acoustical inhibition and modulation of signals. While studying unimodal signal-processing is relevant and well-suited in a controlled laboratory environment, everyday life situations occur multimodal. A complex interplay of the senses is necessary to form a unified percept. In order to achieve this, the unimodal sensory modalities are bound together in a process called multisensory integration (MI). In the current study we investigate MI in an adult ADHD sample using the McGurk-effect – a well-known illusion where incongruent speech like phonemes lead in case of successful integration to a new perceived phoneme via late top-down attentional allocation . In ADHD neuronal dysregulation at rest e.g., aberrant within or between network functional connectivity may also account for difficulties in integrating across the senses. Therefore, the current study includes resting-state functional connectivity to investigate a possible relation of deficient network connectivity and the ability of stimulus integration. Method: Twenty-five ADHD patients (6 females, age: 30.08 (SD:9,3) years) and twenty-four healthy controls (9 females; age: 26.88 (SD: 6.3) years) were recruited. MI was examined using the McGurk effect, where - in case of successful MI - incongruent speech-like phonemes between visual and auditory modality are leading to a perception of a new phoneme. Mann-Whitney-U test was applied to assess statistical differences between groups. Echo-planar imaging-resting-state functional MRI was acquired on a 3.0 Tesla Siemens Magnetom MR scanner. A seed-to-voxel analysis was realized using the CONN toolbox. Results: Susceptibility to McGurk was significantly lowered for ADHD patients (ADHDMdn:5.83%, ControlsMdn:44.2%, U= 160.5, p=0.022, r=-0.34). When ADHD patients integrated phonemes, reaction times were significantly longer (ADHDMdn:1260ms, ControlsMdn:582ms, U=41.0, p<.000, r= -0.56). In functional connectivity medio temporal gyrus (seed) was negatively associated with primary auditory cortex, inferior frontal gyrus, precentral gyrus, and fusiform gyrus. Conclusion: MI seems to be deficient for ADHD patients for stimuli that need top-down attentional allocation. This finding is supported by stronger functional connectivity from unimodal sensory areas to polymodal, MI convergence zones for complex stimuli in ADHD patients.Keywords: attention-deficit hyperactivity disorder, audiovisual integration, McGurk-effect, resting-state functional connectivity
Procedia PDF Downloads 11951 Contribution to the Study of Automatic Epileptiform Pattern Recognition in Long Term EEG Signals
Authors: Christine F. Boos, Fernando M. Azevedo
Abstract:
Electroencephalogram (EEG) is a record of the electrical activity of the brain that has many applications, such as monitoring alertness, coma and brain death; locating damaged areas of the brain after head injury, stroke and tumor; monitoring anesthesia depth; researching physiology and sleep disorders; researching epilepsy and localizing the seizure focus. Epilepsy is a chronic condition, or a group of diseases of high prevalence, still poorly explained by science and whose diagnosis is still predominantly clinical. The EEG recording is considered an important test for epilepsy investigation and its visual analysis is very often applied for clinical confirmation of epilepsy diagnosis. Moreover, this EEG analysis can also be used to help define the types of epileptic syndrome, determine epileptiform zone, assist in the planning of drug treatment and provide additional information about the feasibility of surgical intervention. In the context of diagnosis confirmation the analysis is made using long term EEG recordings with at least 24 hours long and acquired by a minimum of 24 electrodes in which the neurophysiologists perform a thorough visual evaluation of EEG screens in search of specific electrographic patterns called epileptiform discharges. Considering that the EEG screens usually display 10 seconds of the recording, the neurophysiologist has to evaluate 360 screens per hour of EEG or a minimum of 8,640 screens per long term EEG recording. Analyzing thousands of EEG screens in search patterns that have a maximum duration of 200 ms is a very time consuming, complex and exhaustive task. Because of this, over the years several studies have proposed automated methodologies that could facilitate the neurophysiologists’ task of identifying epileptiform discharges and a large number of methodologies used neural networks for the pattern classification. One of the differences between all of these methodologies is the type of input stimuli presented to the networks, i.e., how the EEG signal is introduced in the network. Five types of input stimuli have been commonly found in literature: raw EEG signal, morphological descriptors (i.e. parameters related to the signal’s morphology), Fast Fourier Transform (FFT) spectrum, Short-Time Fourier Transform (STFT) spectrograms and Wavelet Transform features. This study evaluates the application of these five types of input stimuli and compares the classification results of neural networks that were implemented using each of these inputs. The performance of using raw signal varied between 43 and 84% efficiency. The results of FFT spectrum and STFT spectrograms were quite similar with average efficiency being 73 and 77%, respectively. The efficiency of Wavelet Transform features varied between 57 and 81% while the descriptors presented efficiency values between 62 and 93%. After simulations we could observe that the best results were achieved when either morphological descriptors or Wavelet features were used as input stimuli.Keywords: Artificial neural network, electroencephalogram signal, pattern recognition, signal processing
Procedia PDF Downloads 52350 Phenolic Composition of Wines from Cultivar Carménère during Aging with Inserts to Barrels
Authors: E. Obreque-Slier, P. Osorio-Umaña, G. Vidal-Acevedo, A. Peña-Neira, M. Medel-Marabolí
Abstract:
Sensory and nutraceutical characteristics of a wine are determined by different chemical compounds, such as organic acids, sugars, alcohols, polysaccharides, aromas, and polyphenols. The polyphenols correspond to secondary metabolites that are associated with the prevention of several pathologies, and those are responsible for color, aroma, bitterness, and astringency in wines. These compounds come from grapes and wood during aging in barrels, which correspond to the format of wood most widely used in wine production. However, the barrels is a high-cost input with a limited useful life (3-4 years). For this reason, some oenological products have been developed in order to renew the barrels and increase their useful life in some years. These formats are being used slowly because limited information exists about the effect on the wine chemical characteristics. The objective of the study was to evaluate the effect of different laubarrel renewal systems (staves and zigzag) on the polyphenolic characteristics of a Carménère wine (Vitis vinifera), an emblematic cultivar of Chile. For this, a completely randomized experimental design with 5 treatments and three replicates per treatment was used. The treatments were: new barrels (T0), used barrels during 4 years (T1), scraped used barrels (T2), used barrels with staves (T3) and used barrels with zigzag (T4). The study was performed for 12 months, and different spectrophotometric parameters (phenols, anthocyanins, and total tannins) and HPLC-DAD (low molecular weight phenols) were evaluated. The wood inputs were donated by Toneleria Nacional and corresponded to products from the same production batch. The total phenols content increased significantly after 40 days, while the total tannin concentration decreased gradually during the study. The anthocyanin concentration increased after 120 days of the assay in all treatments. Comparatively, it was observed that the wine of T2 presented the lowest values of these polyphenols, while the T0 and T4 presented the highest total phenol contents. Also, T1 presented the highest values of total tannins in relation to the rest of the treatments in some samples. The low molecular weight phenolic compounds identified by HPLC-DAD were 7 flavonoids (epigallocatechin, catechin, procyanidin gallate, epicatechin, quercetin, rutin and myricetin) and 14 non-flavonoids (gallic, protocatechuic, hydroxybenzoic, trans-cutaric, vanillinic, caffeic, syringic, p-coumaric and ellagic acids; tyrosol, vanillin, syringaldehyde, trans-resveratrol and cis-resveratrol). Tyrosol was the most abundant compound, whereas ellagic acid was the lowest in the samples. Comparatively, it was observed that the wines of T2 showed the lowest concentrations of flavonoid and non-flavonoid phenols during the study. In contrast, wines of T1, T3, and T4 presented the highest contents of non-flavonoid polyphenols. In summary, the use of barrel renovators (zig zag and staves) is an interesting alternative which would emulate the contribution of polyphenols from the barrels to the wine.Keywords: barrels, oak wood aging, polyphenols, red wine
Procedia PDF Downloads 18749 Emerging Issues for Global Impact of Foreign Institutional Investors (FII) on Indian Economy
Authors: Kamlesh Shashikant Dave
Abstract:
The global financial crisis is rooted in the sub-prime crisis in U.S.A. During the boom years, mortgage brokers attracted by the big commission, encouraged buyers with poor credit to accept housing mortgages with little or no down payment and without credit check. A combination of low interest rates and large inflow of foreign funds during the booming years helped the banks to create easy credit conditions for many years. Banks lent money on the assumptions that housing price would continue to rise. Also the real estate bubble encouraged the demand for houses as financial assets .Banks and financial institutions later repackaged these debts with other high risk debts and sold them to worldwide investors creating financial instruments called collateral debt obligations (CDOs). With the rise in interest rate, mortgage payments rose and defaults among the subprime category of borrowers increased accordingly. Through the securitization of mortgage payments, a recession developed in the housing sector and consequently it was transmitted to the entire US economy and rest of the world. The financial credit crisis has moved the US and the global economy into recession. Indian economy has also affected by the spill over effects of the global financial crisis. Great saving habit among people, strong fundamentals, strong conservative and regulatory regime have saved Indian economy from going out of gear, though significant parts of the economy have slowed down. Industrial activity, particularly in the manufacturing and infrastructure sectors decelerated. The service sector too, slow in construction, transport, trade, communication, hotels and restaurants sub sectors. The financial crisis has some adverse impact on the IT sector. Exports had declined in absolute terms in October. Higher inputs costs and dampened demand have dented corporate margins while the uncertainty surrounding the crisis has affected business confidence. To summarize, reckless subprime lending, loose monetary policy of US, expansion of financial derivatives beyond acceptable norms and greed of Wall Street has led to this exceptional global financial and economic crisis. Thus, the global credit crisis of 2008 highlights the need to redesign both the global and domestic financial regulatory systems not only to properly address systematic risk but also to support its proper functioning (i.e financial stability).Such design requires: 1) Well managed financial institutions with effective corporate governance and risk management system 2) Disclosure requirements sufficient to support market discipline. 3)Proper mechanisms for resolving problem institution and 4) Mechanisms to protect financial services consumers in the event of financial institutions failure.Keywords: FIIs, BSE, sensex, global impact
Procedia PDF Downloads 43548 Designing Entrepreneurship Education Contents for Entrepreneurial Intention Building among Undergraduates in India
Authors: Sumita Srivastava
Abstract:
Despite several measures taken by the Government of India, entrepreneurship is still not perceived as a viable career option by the young generation. Although the rate of startups has improved a little after the penetration of e portals as business platforms, still the numbers are not very significant. It is also important to note that entrepreneurial initiatives are mostly taken up by graduates of premier institutions of India like Indian Institute of Technology (IITs) and Indian Institute of Management (IIMs). The scenario is not very satisfactory amongst the masses graduating from mainstream universities of the country. Indian youth at large are not attracted towards entrepreneurship as a career choice. The reason probably lies in the social fabric of the country and inappropriate education system which does not support the entrepreneurship at large amongst youth in the country. Education is critical to the development of an economy from the poverty level to the level of self-sustenance and development. The current curriculum in the majority of business schools in India prepares the average graduate to become employed by the available firms or business owners in society. For graduates in other streams, employment opportunities are very limited. The aim of this study was to identify and design entrepreneurship education contents to encourage undergraduates to pursue entrepreneurship as a career choice. This comprehensive study was conducted in multiple stages. Extensive research was conducted at each stage with an appropriate methodology. These stages of the project study were interconnected with each other, and each preceding stage provided inputs for the following stage of the study. In the first stage of the study, an empirical analysis was conducted to understand the current state of entrepreneurial intentions of undergraduates of Agra city. Various stakeholders were contacted at the stage, including students (n = 500), entrepreneurs (n = 20) and academicians and field experts (n = 10). At the second stage of the project study, a systems science technique, Nominal Group Technique (NGT) was used to identify the critical elements of entrepreneurship education in India based upon the findings of stage 1. The application of the Nominal Group Technique involved a workshop format; 15 domain experts participated in the workshop. Throughout the process, a democratic process was followed to avoid individual dominance and premature focusing on a single idea. The study obtained 63 responses from experts for effective entrepreneurship education in India. The responses were reduced to seven elements after a few thematic iterations. These elements were then segregated into content (knowledge, skills and attitude) and learning interaction on the basis of experts’ responses. After identifying critical elements of entrepreneurship education in the previous stage, the course was designed and validated at stage 3 of the project. Scientific methods were used at this stage to validate the curriculum contents and training interventions experimentally. The educational and training interventions designed through this study would not only help in developing entrepreneurial intentions but also creating skills relevant to the local entrepreneurial opportunities in the vicinity.Keywords: curriculum design, entrepreneurial intention, entrepreneuship education, nominal group technique
Procedia PDF Downloads 12447 Assessment of Heavy Metals Contamination Levels in Groundwater: A Case Study of the Bafia Agricultural Area, Centre Region Cameroon
Authors: Carine Enow-Ayor Tarkang, Victorine Neh Akenji, Dmitri Rouwet, Jodephine Njdma, Andrew Ako Ako, Franco Tassi, Jules Remy Ngoupayou Ndam
Abstract:
Groundwater is the major water resource in the whole of Bafia used for drinking, domestic, poultry and agricultural purposes, and being an area of intense agriculture, there is a great necessity to do a quality assessment. Bafia is one of the main food suppliers in the Centre region of Cameroon, and so to meet their demands, the farmers make use of fertilizers and other agrochemicals to increase their yield. Less than 20% of the population in Bafia has access to piped-borne water due to the national shortage, according to the authors best knowledge very limited studies have been carried out in the area to increase awareness of the groundwater resources. The aim of this study was to assess heavy metal contamination levels in ground and surface waters and to evaluate the effects of agricultural inputs on water quality in the Bafia area. 57 water samples (including 31 wells, 20 boreholes, 4 rivers and 2 springs) were analyzed for their physicochemical parameters, while collected samples were filtered, acidified with HNO3 and analyzed by ICP-MS for their heavy metal content (Fe, Ti, Sr, Al, Mn). Results showed that most of the water samples are acidic to slightly neutral and moderately mineralized. Ti concentration was significantly high in the area (mean value 130µg/L), suggesting another Ti source besides the natural input from Titanium oxides. The high amounts of Mn and Al in some cases also pointed to additional input, probably from fertilizers that are used in the farmlands. Most of the water samples were found to be significantly contaminated with heavy metals exceeding the WHO allowable limits (Ti-94.7%, Al-19.3%, Mn-14%, Fe-5.2% and Sr-3.5% above limits), especially around farmlands and topographic low areas. The heavy metal concentration was evaluated using the heavy metal pollution index (HPI), heavy metal evaluation index (HEI) and degree of contamination (Cd), while the Ficklin diagram was used for the water based on changes in metal content and pH. The high mean values of HPI and Cd (741 and 5, respectively), which exceeded the critical limit, indicate that the water samples are highly contaminated, with intense pollution from Ti, Al and Mn. Based on the HPI and Cd, 93% and 35% of the samples, respectively, are unacceptable for drinking purposes. The lowest HPI value point also had the lowest EC (50 µS/cm), indicating lower mineralization and less anthropogenic influence. According to the Ficklin diagram, 89% of the samples fell within the near-neutral low-metal domain, while 9% fell in the near-neutral extreme-metal domain. Two significant factors were extracted from the PCA, explaining 70.6% of the total variance. The first factor revealed intense anthropogenic activity (especially from fertilizers), while the second factor revealed water-rock interactions. Agricultural activities thus have an impact on the heavy metal content of groundwater in the area; hence, much attention should be given to the affected areas in order to protect human health/life and thus sustainably manage this precious resource.Keywords: Bafia, contamination, degree of contamination, groundwater, heavy metal pollution index
Procedia PDF Downloads 7546 The Budget Impact of the DISCERN™ Diagnostic Test for Alzheimer’s Disease in the United States
Authors: Frederick Huie, Lauren Fusfeld, William Burchenal, Scott Howell, Alyssa McVey, Thomas F. Goss
Abstract:
Alzheimer’s Disease (AD) is a degenerative brain disease characterized by memory loss and cognitive decline that presents a substantial economic burden for patients and health insurers in the US. This study evaluates the payer budget impact of the DISCERN™ test in the diagnosis and management of patients with symptoms of dementia evaluated for AD. DISCERN™ comprises three assays that assess critical factors related to AD that regulate memory, formation of synaptic connections among neurons, and levels of amyloid plaques and neurofibrillary tangles in the brain and can provide a quicker, more accurate diagnosis than tests in the current diagnostic pathway (CDP). An Excel-based model with a three-year horizon was developed to assess the budget impact of DISCERN™ compared with CDP in a Medicare Advantage plan with 1M beneficiaries. Model parameters were identified through a literature review and were verified through consultation with clinicians experienced in diagnosis and management of AD. The model assesses direct medical costs/savings for patients based on the following categories: •Diagnosis: costs of diagnosis using DISCERN™ and CDP. •False Negative (FN) diagnosis: incremental cost of care avoidable with a correct AD diagnosis and appropriately directed medication. •True Positive (TP) diagnosis: AD medication costs; cost from a later TP diagnosis with the CDP versus DISCERN™ in the year of diagnosis, and savings from the delay in AD progression due to appropriate AD medication in patients who are correctly diagnosed after a FN diagnosis.•False Positive (FP) diagnosis: cost of AD medication for patients who do not have AD. A one-way sensitivity analysis was conducted to assess the effect of varying key clinical and cost parameters ±10%. An additional scenario analysis was developed to evaluate the impact of individual inputs. In the base scenario, DISCERN™ is estimated to decrease costs by $4.75M over three years, equating to approximately $63.11 saved per test per year for a cohort followed over three years. While the diagnosis cost is higher with DISCERN™ than with CDP modalities, this cost is offset by the higher overall costs associated with CDP due to the longer time needed to receive a TP diagnosis and the larger number of patients who receive a FN diagnosis and progress more rapidly than if they had received appropriate AD medication. The sensitivity analysis shows that the three parameters with the greatest impact on savings are: reduced sensitivity of DISCERN™, improved sensitivity of the CDP, and a reduction in the percentage of disease progression that is avoided with appropriate AD medication. A scenario analysis in which DISCERN™ reduces the utilization for patients of computed tomography from 21% in the base case to 16%, magnetic resonance imaging from 37% to 27% and cerebrospinal fluid biomarker testing, positive emission tomography, electroencephalograms, and polysomnography testing from 4%, 5%, 10%, and 8%, respectively, in the base case to 0%, results in an overall three-year net savings of $14.5M. DISCERN™ improves the rate of accurate, definitive diagnosis of AD earlier in the disease and may generate savings for Medicare Advantage plans.Keywords: Alzheimer’s disease, budget, dementia, diagnosis.
Procedia PDF Downloads 13645 The Impact of Shifting Trading Pattern from Long-Haul to Short-Sea to the Car Carriers’ Freight Revenues
Authors: Tianyu Wang, Nikita Karandikar
Abstract:
The uncertainty around cost, safety, and feasibility of the decarbonized shipping fuels has made it increasingly complex for the shipping companies to set pricing strategies and forecast their freight revenues going forward. The increase in the green fuel surcharges will ultimately influence the automobile’s consumer prices. The auto shipping demand (ton-miles) has been gradually shifting from long-haul to short-sea trade over the past years following the relocation of the original equipment manufacturer (OEM) manufacturing to regions such as South America and Southeast Asia. The objective of this paper is twofold: 1) to investigate the car-carriers freight revenue development over the years when the trade pattern is gradually shifting towards short-sea exports 2) to empirically identify the quantitative impact of such trade pattern shifting to mainly freight rate, but also vessel size, fleet size as well as Green House Gas (GHG) emission in Roll on-Roll Off (Ro-Ro) shipping. In this paper, a model of analyzing and forecasting ton-miles and freight revenues for the trade routes of AS-NA (Asia to North America), EU-NA (Europe to North America), and SA-NA (South America to North America) is established by deploying Automatic Identification System (AIS) data and the financial results of a selected car carrier company. More specifically, Wallenius Wilhelmsen Logistics (WALWIL), the Norwegian Ro-Ro carrier listed on Oslo Stock Exchange, is selected as the case study company in this paper. AIS-based ton-mile datasets of WALWIL vessels that are sailing into North America region from three different origins (Asia, Europe, and South America), together with WALWIL’s quarterly freight revenues as reported in trade segments, will be investigated and compared for the past five years (2018-2022). Furthermore, ordinary‐least‐square (OLS) regression is utilized to construct the ton-mile demand and freight revenue forecasting. The determinants of trade pattern shifting, such as import tariffs following the China-US trade war and fuel prices following the 0.1% Emission Control Areas (ECA) zone requirement after IMO2020 will be set as key variable inputs to the machine learning model. The model will be tested on another newly listed Norwegian Car Carrier, Hoegh Autoliner, to forecast its 2022 financial results and to validate the accuracy based on its actual results. GHG emissions on the three routes will be compared and discussed based on a constant emission per mile assumption and voyage distances. Our findings will provide important insights about 1) the trade-off evaluation between revenue reduction and energy saving with the new ton-mile pattern and 2) how the trade flow shifting would influence the future need for the vessel and fleet size.Keywords: AIS, automobile exports, maritime big data, trade flows
Procedia PDF Downloads 11644 Influence of a High-Resolution Land Cover Classification on Air Quality Modelling
Authors: C. Silveira, A. Ascenso, J. Ferreira, A. I. Miranda, P. Tuccella, G. Curci
Abstract:
Poor air quality is one of the main environmental causes of premature deaths worldwide, and mainly in cities, where the majority of the population lives. It is a consequence of successive land cover (LC) and use changes, as a result of the intensification of human activities. Knowing these landscape modifications in a comprehensive spatiotemporal dimension is, therefore, essential for understanding variations in air pollutant concentrations. In this sense, the use of air quality models is very useful to simulate the physical and chemical processes that affect the dispersion and reaction of chemical species into the atmosphere. However, the modelling performance should always be evaluated since the resolution of the input datasets largely dictates the reliability of the air quality outcomes. Among these data, the updated LC is an important parameter to be considered in atmospheric models, since it takes into account the Earth’s surface changes due to natural and anthropic actions, and regulates the exchanges of fluxes (emissions, heat, moisture, etc.) between the soil and the air. This work aims to evaluate the performance of the Weather Research and Forecasting model coupled with Chemistry (WRF-Chem), when different LC classifications are used as an input. The influence of two LC classifications was tested: i) the 24-classes USGS (United States Geological Survey) LC database included by default in the model, and the ii) CLC (Corine Land Cover) and specific high-resolution LC data for Portugal, reclassified according to the new USGS nomenclature (33-classes). Two distinct WRF-Chem simulations were carried out to assess the influence of the LC on air quality over Europe and Portugal, as a case study, for the year 2015, using the nesting technique over three simulation domains (25 km2, 5 km2 and 1 km2 horizontal resolution). Based on the 33-classes LC approach, particular emphasis was attributed to Portugal, given the detail and higher LC spatial resolution (100 m x 100 m) than the CLC data (5000 m x 5000 m). As regards to the air quality, only the LC impacts on tropospheric ozone concentrations were evaluated, because ozone pollution episodes typically occur in Portugal, in particular during the spring/summer, and there are few research works relating to this pollutant with LC changes. The WRF-Chem results were validated by season and station typology using background measurements from the Portuguese air quality monitoring network. As expected, a better model performance was achieved in rural stations: moderate correlation (0.4 – 0.7), BIAS (10 – 21µg.m-3) and RMSE (20 – 30 µg.m-3), and where higher average ozone concentrations were estimated. Comparing both simulations, small differences grounded on the Leaf Area Index and air temperature values were found, although the high-resolution LC approach shows a slight enhancement in the model evaluation. This highlights the role of the LC on the exchange of atmospheric fluxes, and stresses the need to consider a high-resolution LC characterization combined with other detailed model inputs, such as the emission inventory, to improve air quality assessment.Keywords: land use, spatial resolution, WRF-Chem, air quality assessment
Procedia PDF Downloads 14743 Use of Artificial Neural Networks to Estimate Evapotranspiration for Efficient Irrigation Management
Authors: Adriana Postal, Silvio C. Sampaio, Marcio A. Villas Boas, Josué P. Castro
Abstract:
This study deals with the estimation of reference evapotranspiration (ET₀) in an agricultural context, focusing on efficient irrigation management to meet the growing interest in the sustainable management of water resources. Given the importance of water in agriculture and its scarcity in many regions, efficient use of this resource is essential to ensure food security and environmental sustainability. The methodology used involved the application of artificial intelligence techniques, specifically Multilayer Perceptron (MLP) Artificial Neural Networks (ANNs), to predict ET₀ in the state of Paraná, Brazil. The models were trained and validated with meteorological data from the Brazilian National Institute of Meteorology (INMET), together with data obtained from a producer's weather station in the western region of Paraná. Two optimizers (SGD and Adam) and different meteorological variables, such as temperature, humidity, solar radiation, and wind speed, were explored as inputs to the models. Nineteen configurations with different input variables were tested; amidst them, configuration 9, with 8 input variables, was identified as the most efficient of all. Configuration 10, with 4 input variables, was considered the most effective, considering the smallest number of variables. The main conclusions of this study show that MLP ANNs are capable of accurately estimating ET₀, providing a valuable tool for irrigation management in agriculture. Both configurations (9 and 10) showed promising performance in predicting ET₀. The validation of the models with cultivator data underlined the practical relevance of these tools and confirmed their generalization ability for different field conditions. The results of the statistical metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R²), showed excellent agreement between the model predictions and the observed data, with MAE as low as 0.01 mm/day and 0.03 mm/day, respectively. In addition, the models achieved an R² between 0.99 and 1, indicating a satisfactory fit to the real data. This agreement was also confirmed by the Kolmogorov-Smirnov test, which evaluates the agreement of the predictions with the statistical behavior of the real data and yields values between 0.02 and 0.04 for the producer data. In addition, the results of this study suggest that the developed technique can be applied to other locations by using specific data from these sites to further improve ET₀ predictions and thus contribute to sustainable irrigation management in different agricultural regions. The study has some limitations, such as the use of a single ANN architecture and two optimizers, the validation with data from only one producer, and the possible underestimation of the influence of seasonality and local climate variability. An irrigation management application using the most efficient models from this study is already under development. Future research can explore different ANN architectures and optimization techniques, validate models with data from multiple producers and regions, and investigate the model's response to different seasonal and climatic conditions.Keywords: agricultural technology, neural networks in agriculture, water efficiency, water use optimization
Procedia PDF Downloads 35