Search results for: trained graphic designers

Authors: Soyon Kim, Edward Kim

Abstract:

In order to retrieve information from the massive stream of songs in the music industry, music search by title, lyrics, artist, mood, and genre has become more important. Despite the subjectivity and controversy over the definition of music genres across different nations and cultures, automatic genre classification systems that facilitate the process of music categorization have been developed. Manual genre selection by music producers is being provided as statistical data for designing automatic genre classification systems. In this paper, an automatic music genre classification system utilizing non-negative matrix factorization (NMF) is proposed. Short-term characteristics of the music signal can be captured based on the timbre features such as mel-frequency cepstral coefficient (MFCC), decorrelated filter bank (DFB), octave-based spectral contrast (OSC), and octave band sum (OBS). Long-term time-varying characteristics of the music signal can be summarized with (1) the statistical features such as mean, variance, minimum, and maximum of the timbre features and (2) the modulation spectrum features such as spectral flatness measure, spectral crest measure, spectral peak, spectral valley, and spectral contrast of the timbre features. Not only these conventional basic long-term feature vectors, but also NMF based feature vectors are proposed to be used together for genre classification. In the training stage, NMF basis vectors were extracted for each genre class. The NMF features were calculated in the log spectral magnitude domain (NMF-LSM) as well as in the basic feature vector domain (NMF-BFV). For NMF-LSM, an entire full band spectrum was used. However, for NMF-BFV, only low band spectrum was used since high frequency modulation spectrum of the basic feature vectors did not contain important information for genre classification. In the test stage, using the set of pre-trained NMF basis vectors, the genre classification system extracted the NMF weighting values of each genre as the NMF feature vectors. A support vector machine (SVM) was used as a classifier. The GTZAN multi-genre music database was used for training and testing. It is composed of 10 genres and 100 songs for each genre. To increase the reliability of the experiments, 10-fold cross validation was used. For a given input song, an extracted NMF-LSM feature vector was composed of 10 weighting values that corresponded to the classification probabilities for 10 genres. An NMF-BFV feature vector also had a dimensionality of 10. Combined with the basic long-term features such as statistical features and modulation spectrum features, the NMF features provided the increased accuracy with a slight increase in feature dimensionality. The conventional basic features by themselves yielded 84.0% accuracy, but the basic features with NMF-LSM and NMF-BFV provided 85.1% and 84.2% accuracy, respectively. The basic features required dimensionality of 460, but NMF-LSM and NMF-BFV required dimensionalities of 10 and 10, respectively. Combining the basic features, NMF-LSM and NMF-BFV together with the SVM with a radial basis function (RBF) kernel produced the significantly higher classification accuracy of 88.3% with a feature dimensionality of 480.

Keywords: mel-frequency cepstral coefficient (MFCC), music genre classification, non-negative matrix factorization (NMF), support vector machine (SVM)

Procedia PDF Downloads 274

Authors: Halkiopoulos Constantinos, Koutsopoulou Ioanna, Gkintoni Evgenia, Antonopoulou Hera

Abstract:

Immunization appears to be an essential part of health care service in times of pandemics such as covid-19 and aims not only to protect the health of the population but also the health and sustainability of the economies of the countries affected. It is reported that more than 3.44 billion doses have been administered so far, which accounts for 45 doses for 100 people. Vaccination programs in various countries have been promoted and accepted by people differently and therefore they proceeded in different ways and speed; most countries directing them towards people with vulnerable chronic or recent health statuses. Large scale restriction measures or lockdown, personal protection measures such as masks and gloves and a decrease in leisure and sports activities were also implemented around the world as part of the protection health strategies against the covid-19 pandemic. This research aims to present an analysis based on variations on people’s attitudes towards vaccination based on demographic, social and epidemiological characteristics, and health status on the one hand and perception of health, health satisfaction, pain, and quality of life on the other hand. 1500 Greek e-consumers participated in the research, mainly through social media who took part in an online-based survey voluntarily. The questionnaires included demographic, social and medical characteristics of the participants, and questions asking people’s willingness to be vaccinated and their opinion on whether there should be a vaccine against covid-19. Other stressor factors were also reported in the questionnaires and participants’ loss of someone close due to covid-19, or staying at home quarantine due to being infected from covid-19. WHOQUOL-BREF and GLOBAL PSYCHOTRAUMA SCREEN- GPS were used with kind permission from WHO and from the International Society for Traumatic Stress Studies in this study. Attitudes towards vaccination varied significantly related to aging, level of education, health status and consumer behavior. Health professionals’ attitudes also varied in relation to age, level of education, profession, health status and consumer needs. Vaccines have been the most common technological aid of human civilization so far in the fight against viruses. The results of this study can be used for health managers and digital marketers of pharmaceutical companies and also other staff involved in vaccination programs and for designing health policy immunization strategies during pandemics in order to achieve positive attitudes towards vaccination and larger populations being vaccinated in shorter periods of time after the break out of pandemic. Health staff needs to be trained, aided and supervised to go through with vaccination programs and to be protected through vaccination programs themselves. Feedback in each country’s vaccination program, short backs, deficiencies and delays should be addressed and worked out.

Keywords: consumer behavior, cognitive models, vaccination policy, pandemic, Covid-19, Greece

Procedia PDF Downloads 173

Authors: Dolly Kumari, H. Lhungdim

Abstract:

Maternal health is one of the crucial health indicators for any country. 5th goal of Millennium Development Goals is also emphasising on improvement of maternal health. Soon after Independence government of India realizing the importance of maternal and child health care services, and took steps to strengthen in 1st and 2nd five year plans. In past decade the other health indicator which is life expectancy at birth has been observed remarkable improvement. But still maternal mortality is high in India and in some states it is observe much higher than national average. Government of India pour lots of fund and initiate National Rural Health Mission (NRHM) in 2005 to improve maternal health in country by providing affordable and accessible health care services. Accredited Social Heath Activist (ASHA) is one of the key components of the NRHM. Mainly ASHAs are selected female aged 25-45 years from village itself and accountable for the monitoring of maternal health care for the same village. ASHA are trained to works as an interface between the community and public health system. This study tries to assess the role of ASHA in utilizing maternal health care services and to see the level of awareness about benefits given under JSY scheme and utilization of those benefits by eligible women. For the study concurrent evaluation data from National Rural health Mission (NRHM), initiated by government of India in 2005 has been used. This study is based on 78205 currently married women from 70 different districts of India. Descriptive statistics, chi2 test and binary logistic regression have been used for analysis. The probability of institutional delivery increases by 2.03 times (p<0.001) while if ASHA arranged or helped in arranging transport facility the probability of institutional delivery is increased by 1.67 times (p<0.01) than if she is not arranging transport facility. Further if ASHA facilitated to get JSY card to the pregnant women probability of going for full ANC is increases by 1.36 times (p<0.05) than reference. However if ASHA discuses about institutional delivery and approaches to get register than probability of getting TT injection is 1.88 and 1.64 times (p<0.01) higher than that if she did not discus. Further, Probability of benefits from JSY schemes is 1.25 times (p<0.001) higher among women who get married after 18 years. The probability of benefits from JSY schemes is 1.25 times (p<0.001) higher among women who get married after 18 year of age than before 18 years, it is also 1.28 times (p<0.001) and 1.32 times (p<0.001) higher among women have 1 to 8 year of schooling and with 9 and above years of schooling respectively than the women who never attended school. Those women who are working have 1.13 times (p<0.001) higher probability of getting benefits from JSY scheme than not working women. Surprisingly women belongs to wealthiest quintile are .53times (P<0.001) less aware about JSY scheme. Results conclude that work done by ASHA has great influence on maternal health care utilization in India. But results also show that still substantial numbers of needed population are far from utilization of these services. Place of delivery is significantly influenced by referral and transport facility arranged by ASHA.

Keywords: institutional delivery, JSY beneficiaries, referral faculty, public health

Procedia PDF Downloads 309

Authors: Isabelle Gobatto

Abstract:

Based on an anthropological approach, this paper explores the medical profession and the construction of medical practices by considering the multiform articulations between structural poverty and the production of care from a low-resource francophone West African country, Burkina Faso. This country is considered in its exemplary dimension of culturally differentiated countries of the African continent that share the same situation of structural poverty. The objective is to expose the effects of structural poverty on the ways of constructing professional knowledge and thinking about the sense of the medical profession. If doctors are trained to have the same capacities in South and West countries, which are to treat and save lives whatever the cultural contexts of the practice of medicine, the ways of investing their role and of dealing with this context of action fracture the homogenization of the medical profession. In the line of anthropology of biomedicine, this paper outlines the complex effects of structural poverty on health care, care relations, and the moral economy of doctors. The materials analyzed are based on an ethnography including two temporalities located thirty years apart (1990-1994 and 2020-2021), based on long-term observations of care practices conducted in healthcare institutions, interviews coupled with the life histories of physicians. The findings reveal that disabilities faced by doctors to deliver care are interpreted as policy gaps, but they are also considered by physicians as constitutive of the social and cultural characteristics of patients, making their capacities and incapacities in terms of accompanying caregivers in the production of care. These perceptions have effects on know-how, structured around the need to act even when diagnoses are not made so as not to see patients desert health structures if the costs of care are too high for them. But these interpretations of highly individualizing dimensions of these difficulties place part of the blame on patients for the difficulties in using learned knowledge and delivering effective care. These situations challenge the ethics of caregivers but also of ethnologists. Firstly because the interpretations of disabilities prevent caregivers from considering vulnerabilities of care as constituting a common condition shared with their patients in these health systems, affecting them in an identical way although in different places in the production of care. Correlatively, these results underline that these professional conceptions prevent the emergence of a figure of victim, which could be shared between patients and caregivers who, together, undergo working and care conditions at the limit of the acceptable. This dimension directly involves politics. Secondly, structural poverty and its effects on care challenge the ethics of the anthropologist who observes caregivers producing, without intent to arm, experiences of care marked by an ordinary violence, by not giving them the care they need. It is worth asking how anthropologists could get doctors to think in this light in west-African societies.

Keywords: Africa, care, ethics, poverty

Procedia PDF Downloads 47

Authors: Julia Ive, Lucia Specia

Abstract:

Understanding and detecting toxicity is an important problem to support safer human interactions online. Our work focuses on the important problem of contextual toxicity detection, where automated classifiers are tasked with determining whether a short textual segment (usually a sentence) is toxic within its conversational context. We use “toxicity” as an umbrella term to denote a number of variants commonly named in the literature, including hate, abuse, offence, among others. Detecting toxicity in context is a non-trivial problem and has been addressed by very few previous studies. These previous studies have analysed the influence of conversational context in human perception of toxicity in controlled experiments and concluded that humans rarely change their judgements in the presence of context. They have also evaluated contextual detection models based on state-of-the-art Deep Learning and Natural Language Processing (NLP) techniques. Counterintuitively, they reached the general conclusion that computational models tend to suffer performance degradation in the presence of context. We challenge these empirical observations by devising better contextual predictive models that also rely on NLP data augmentation techniques to create larger and better data. In our study, we start by further analysing the human perception of toxicity in conversational data (i.e., tweets), in the absence versus presence of context, in this case, previous tweets in the same conversational thread. We observed that the conclusions of previous work on human perception are mainly due to data issues: The contextual data available does not provide sufficient evidence that context is indeed important (even for humans). The data problem is common in current toxicity datasets: cases labelled as toxic are either obviously toxic (i.e., overt toxicity with swear, racist, etc. words), and thus context does is not needed for a decision, or are ambiguous, vague or unclear even in the presence of context; in addition, the data contains labeling inconsistencies. To address this problem, we propose to automatically generate contextual samples where toxicity is not obvious (i.e., covert cases) without context or where different contexts can lead to different toxicity judgements for the same tweet. We generate toxic and non-toxic utterances conditioned on the context or on target tweets using a range of techniques for controlled text generation(e.g., Generative Adversarial Networks and steering techniques). On the contextual detection models, we posit that their poor performance is due to limitations on both of the data they are trained on (same problems stated above) and the architectures they use, which are not able to leverage context in effective ways. To improve on that, we propose text classification architectures that take the hierarchy of conversational utterances into account. In experiments benchmarking ours against previous models on existing and automatically generated data, we show that both data and architectural choices are very important. Our model achieves substantial performance improvements as compared to the baselines that are non-contextual or contextual but agnostic of the conversation structure.

Keywords: contextual toxicity detection, data augmentation, hierarchical text classification models, natural language processing

Procedia PDF Downloads 143

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 83

Authors: Shahrzad Zolfagharnassab, Abdul Rashid Mohamed Shariff, Siti Khairunniza Bejo

Abstract:

Conventional methods for nutrient soil mapping are based on laboratory tests of samples that are obtained from surveys. The time and cost involved in gathering and analyzing soil samples are the reasons that researchers use Predictive Soil Mapping (PSM). PSM can be defined as the development of a numerical or statistical model of the relationship among environmental variables and soil properties, which is then applied to a geographic database to create a predictive map. Kriging is a group of geostatistical techniques to spatially interpolate point values at an unobserved location from observations of values at nearby locations. The main problem with using kriging as an interpolator is that it is excessively data-dependent and requires a large number of closely spaced data points. Hence, there is a need to minimize the number of data points without sacrificing the accuracy of the results. In this paper, an Artificial Neural Networks (ANN) scheme was used to predict macronutrient values at un-sampled points. ANN has become a popular tool for prediction as it eliminates certain difficulties in soil property prediction, such as non-linear relationships and non-normality. Back-propagation multilayer feed-forward network structures were used to predict nitrogen, phosphorous and potassium values in the soil of the study area. A limited number of samples were used in the training, validation and testing phases of ANN (pattern reconstruction structures) to classify soil properties and the trained network was used for prediction. The soil analysis results of samples collected from the soil survey of block C of Sawah Sempadan, Tanjung Karang rice irrigation project at Selangor of Malaysia were used. Soil maps were produced by the Kriging method using 236 samples (or values) that were a combination of actual values (obtained from real samples) and virtual values (neural network predicted values). For each macronutrient element, three types of maps were generated with 118 actual and 118 virtual values, 59 actual and 177 virtual values, and 30 actual and 206 virtual values, respectively. To evaluate the performance of the proposed method, for each macronutrient element, a base map using 236 actual samples and test maps using 118, 59 and 30 actual samples respectively produced by the Kriging method. A set of parameters was defined to measure the similarity of the maps that were generated with the proposed method, termed the sample reduction method. The results show that the maps that were generated through the sample reduction method were more accurate than the corresponding base maps produced through a smaller number of real samples. For example, nitrogen maps that were produced from 118, 59 and 30 real samples have 78%, 62%, 41% similarity, respectively with the base map (236 samples) and the sample reduction method increased similarity to 87%, 77%, 71%, respectively. Hence, this method can reduce the number of real samples and substitute ANN predictive samples to achieve the specified level of accuracy.

Keywords: artificial neural network, kriging, macro nutrient, pattern recognition, precision farming, soil mapping

Procedia PDF Downloads 52

Authors: Zermina Q., Wasif Y., Naeem S., Urooj S., Sajid R. A.

Abstract:

Land degradation, a leading environemtnal problem and a decrease in the quality of land has become a major global issue, caused by human activities. By land degradation, more than half of the world’s drylands are affected. The worldwide scope of main saline soils is approximately 955 M ha, whereas inferior salinization affected approximately 77 M ha. In irrigated areas, a total of 58% of these soils is found. As most of the vegetation types requires fertile soil for their growth and quality production, salinity causes serious problem to the production of these vegetation types and agriculture demands. This research aims to identify the salt affected areas in the selected part of Indus Delta, Sindh province, Pakistan. This particular mangroves dominating coastal belt is important to the local community for their crop growth. Object based image analysis approach has been adopted on Landsat TM imagery of year 2011 by incorporating different mathematical band ratios, thermal radiance and salinity index. Accuracy assessment of developed salinity landcover map was performed using Erdas Imagine Accuracy Assessment Utility. Rain factor was also considered before acquiring satellite imagery and conducting field survey, as wet soil can greatly affect the condition of saline soil of the area. Dry season considered best for the remote sensing based observation and monitoring of the saline soil. These areas were trained with the ground truth data w.r.t pH and electric condutivity of the soil samples. The results were obtained from the object based image analysis of Keti bunder and Kharo chan shows most of the region under low saline soil.Total salt affected soil was measured to be 46,581.7 ha in Keti Bunder, which represents 57.81 % of the total area of 80,566.49 ha. High Saline Area was about 7,944.68 ha (9.86%). Medium Saline Area was about 17,937.26 ha (22.26 %) and low Saline Area was about 20,699.77 ha (25.69%). Where as total salt affected soil was measured to be 52,821.87 ha in Kharo Chann, which represents 55.87 % of the total area of 94,543.54 ha. High Saline Area was about 5,486.55 ha (5.80 %). Medium Saline Area was about 13,354.72 ha (14.13 %) and low Saline Area was about 33980.61 ha (35.94 %). These results show that the area is low to medium saline in nature. Accuracy of the soil salinity map was found to be 83 % with the Kappa co-efficient of 0.77. From this research, it was evident that this area as a whole falls under the category of low to medium saline area and being close to coastal area, mangrove forest can flourish. As Mangroves are salt tolerant plant so this area is consider heaven for mangrove plantation. It would ultimately benefit both the local community and the environment. Increase in mangrove forest control the problem of soil salinity and prevent sea water to intrude more into coastal area. So deforestation of mangrove should be regularly monitored.

Keywords: indus delta, object based image analysis, soil salinity, thematic mapper

Procedia PDF Downloads 594

Authors: Isabell Koinig, Sandra Diehl

Abstract:

In recent years, the health-care context has not been left unaffected by technological developments. In recent years, the Internet of Medical Things (IoMT)has not only led to a collaboration between disease management and advanced care coordination but also to more personalized health care and patient empowerment. With more than 40 % of all health technology being IoMT-related by 2020, questions regarding privacy become more prevalent, even more so during COVID-19when apps allowing for an intensive tracking of people’s whereabouts and their personal contacts cause privacy advocates to protest and revolt. There is a widespread tendency that even though users may express concerns and fears about their privacy, they behave in a manner that appears to contradict their statements by disclosing personal data. In literature, this phenomenon is discussed as a privacy paradox. While there are some studies investigating the privacy paradox in general, there is only scarce research related to the privacy paradox in the health sector and, to the authors’ knowledge, no empirical study investigating young people’s attitudes toward data security when using wearables and health apps. The empirical study presented in this paper tries to reduce this research gap by focusing on the area of digital and mobile health. It sets out to investigate the degree of importance individuals attribute to protecting their privacy and individual privacy protection strategies. Moreover, the question to which degree individuals between the ages of 20 and 30 years are willing to grant commercial parties access to their private data to use digital health services and apps are put to the test. To answer this research question, results from 6 focus groups with 40 participants will be presented. The focus was put on this age segment that has grown up in a digitally immersed environment. Moreover, it is particularly the young generation who is not only interested in health and fitness but also already uses health-supporting apps or gadgets. Approximately one-third of the study participants were students. Subjects were recruited in August and September 2019 by two trained researchers via email and were offered an incentive for their participation. Overall, results indicate that the young generation is well informed about the growing data collection and is quite critical of it; moreover, they possess knowledge of the potential side effects associated with this data collection. Most respondents indicated to cautiously handle their data and consider privacy as highly relevant, utilizing a number of protective strategies to ensure the confidentiality of their information. Their willingness to share information in exchange for services was only moderately pronounced, particularly in the health context, since health data was seen as valuable and sensitive. The majority of respondents indicated to rather miss out on using digital and mobile health offerings in order to maintain their privacy. While this behavior might be an unintended consequence, it is an important piece of information for app developers and medical providers, who have to find a way to find a user base for their products against the background of rising user privacy concerns.

Keywords: digital health, privacy, privacy paradox, IoMT

Procedia PDF Downloads 115

Authors: Yu-Chi Liao, Nai-Wen Guo, Chun‑Hung Lee, Yung-Chin Lu, Cheng-Hung Ko

Abstract:

Objective: The incidence of behavioral addictions, especially substance use disorders (SUDs), is gradually be taken seriously with various physical health problems. Mindfulness-based relapse prevention (MBRP) is a treatment option for promoting long-term health behavior change in recent years. MBRP is a structured protocol that integrates formal meditation practices with the cognitive-behavioral approach of relapse prevention treatment by teaching participants not to engage in reappraisal or savoring techniques. However, considering SUDs as a complex brain disease, questionnaires and symptom evaluation are not sufficient to evaluate the effect of MBRP. Neurophysiological biomarkers such as quantitative electroencephalogram (QEEG) may improve accurately represent the curative effects. This study attempted to find out the neurophysiological indicator of MBRP in various severity SUD involuntary clients. Participants and Methods: Thirteen participants (all males) completed 8-week mindfulness-based treatment provided by trained, licensed clinical psychologists. The behavioral data were from the Severity of Dependence Scale (SDS) and Negative Mood Regulation Scale (NMR) before and afterMBRP treatment. The QEEG data were simultaneously recorded with executive attention tasks, called comprehensive nonverbal attention test(CNAT). The two-way repeated-measures (treatment * severity) ANOVA and independent t-test were used for statistical analysis. Results: Thirteen participants regrouped into high substance dependence (HS) and low substance dependence (LS) by SDS cut-off. The HS group showed more SDS total score and lower gamma wave in the Go/No Go task of CNAT at pretest. Both groups showed the main effect that they had a lower frontal theta/beta ratio (TBR) during the simple reaction time task of CNAT. The main effect showed that the delay errors of CNAT were lower after MBRP. There was no other difference in CNAT between groups. However, after MBRP, compared to LS, the HS group have resonant progress in improving SDS and NMR scores. The neurophysiological index, the frontal TBR of the HS during the Go/No Go task of CNATdecreased than that of the LS group. Otherwise, the LS group’s gamma wave was a significant reduction on the Go/No Go task of CNAT. Conclusion: The QEEG data supports the MBRP can restore the prefrontal function of involuntary addicts and lower their errors in executive attention tasks. However, the improvement of MBRPfor the addict with high addiction severity is significantly more than that with low severity, including QEEG’s indicators and negative emotion regulation. Future directions include investigating the reasons for differences in efficacy among different severity of the addiction.

Keywords: mindfulness, involuntary clients, QEEG, emotion regulation

Procedia PDF Downloads 130

Authors: Virginia Vettori, Chiara Lorini, Vieri Lastrucci, Giulia Di Pisa, Alessia De Blasi, Sara Giuggioli, Guglielmo Bonaccorsi

Abstract:

The design of the Nutrition Literacy Assessment Instrument (NLit) responds to the need to provide a tool to adequately assess the construct of nutrition literacy (NL), which is strictly connected to the quality of the diet and nutritional health status. The NLit was originally developed and validated in the US context, and it was recently validated for Italian people too (NLit-IT), involving a sample of N = 74 adults. The results of the cross-cultural adaptation of the tool confirmed its validity since it was established that the level of NL contributed to predicting the level of adherence to the Mediterranean Diet (convergent validity). Additionally, results obtained proved that Internal Consistency and reliability of the NLit-IT were good (Cronbach’s alpha (ρT) = 0.78; 95% CI, 0.69–0.84; Intraclass Correlation Coefficient (ICC) = 0.68, 95% CI, 0.46–0.85). However, the Subscale 3 of the NLit-IT “Household Food Measurement” showed lower values of ρT and ICC (ρT = 0.27; 95% CI, 0.1–0.55; ICC = 0.19, 95% CI, 0.01–0.63) than the entire instrument. Subscale 3 includes nine items which are constituted by written questions and the corresponding pictures of the meals. In particular, items 2, 3, and 8 of Subscale 3 had the lowest level of correct answers. The purpose of the present study was to identify the factors that influenced the Internal Consistency and reliability of Subscale 3 of NLit-IT using the methodology of a focus group. A panel of seven experts was formed, involving professionals in the field of public health nutrition, dietetics, and health promotion and all of them were trained on the concepts of nutrition literacy and food appearance. A member of the group drove the discussion, which was oriented in the identification of the reasons for the low levels of reliability and Internal Consistency. The members of the group discussed the level of comprehension of the items and how they could be readapted. From the discussion, it emerges that the written questions were clear and easy to understand, but it was observed that the representations of the meal needed to be improved. Firstly, it has been decided to introduce a fork or a spoon as a reference dimension to better understand the dimension of the food portion (items 1, 4 and 8). Additionally, the flat plate of items 3 and 5 should be substituted with a soup plate because, in the Italian national context, it is common to eat pasta or rice on this kind of plate. Secondly, specific measures should be considered for some kind of foods such as the brick of yogurt instead of a cup of yogurt (items 1 and 4). Lastly, it has been decided to redo the photos of the meals basing on professional photographic techniques. In conclusion, we noted that the graphical representation of the items strictly influenced the level of participants’ comprehension of the questions; moreover, the research group agreed that the level of knowledge about nutrition and food portion size is low in the general population.

Keywords: nutritional literacy, cross cultural adaptation, misinformation, food design

Procedia PDF Downloads 142

Authors: R. B. B. Samantha Ramachandra, L. D. J. Upul Senarath, S. H. Padmal De Silva

Abstract:

Dietary pattern largely differs over countries and even within a country, it shows cultural differences. The dietary pattern changes the energy consumption and micronutrient intake, directly affects the pregnancy outcome. The dietary diversity was used as an indirect measure to assess micronutrient adequacy for pregnant mothers in this study. The study was conducted as a baseline survey with the objective of designing an intervention to improve the dietary diversity of pregnant mothers in Sri Lanka. The survey was conducted in Kalutara district of Sri Lanka in 2015 among 769 pregnant mothers at different gestational ages. Dietary diversity questionnaire developed by Food and Agricultural Organization’s (FAO) Food and Nutrition technical Assistance (FANTA) II project, recommended for cross-country use with adaptations was used for data collection. Trained data collectors met pregnant mothers at field ante-natal clinic and questioned on last 24hr dietary recall with portion size and coded food items to identify the diversity. Pregnant mothers were identified from randomly selected 21 clusters of public health midwife areas. 81.5% mothers (n=627) in the sample had been registered at Public Health Midwife (PHM) before 8 weeks of gestation. 24.4% of mothers were with low starting BMI and 22.7% mothers were with high starting BMI. 47.6% (n=388) mothers had abstained from at least one food item during the pregnancy. The food group with the highest consumption was rice (98.4%) followed by sugar (89.9%). 76.1% mothers had consumed milk, 73% consumed fish and sea foods. Consumption of green leaves was 52% and Vit A rich foods consumed only by 49% mothers. Animal organs, flesh meat and egg all showed low prevalence as 4.7%, 21.6% and 20% respectively. Consumption of locally grown roots, nut, legumes all showed very low prevalence. Consumption of 6 or more food groups was considered as good dietary diversity (DD), 4 to 5 food groups as moderate diversity and 3 or less food groups as poor diversity by FAO FANTA II project. 42.1% mothers demonstrated good DD while another 42.1% recorded moderate diversity. Working mothers showed better DD (51.6%, n=82/159) compared to housewives in the sample (chi = 10.656a,. df=2, p=0.005). The good DD showed gradual improvement from 43.1% to 55.5% along the poorest to richest wealth index (Chi=48.045, df=8 and p=0.000). DD showed significant association with the ethnicity and Moors showed the lowest DD. DD showed no association with the home gardening even though where better diversity expected among those who have home gardening (p=0.548). Sri Lanka is a country where many food items can be grown in the garden and semi-urban setting have adequate space for gardening. Many Sri Lankan mothers do not add homegrown items in their meal. At the same time, their consumption of animal food shows low prevalence. The DD of most of the mothers being either moderate or low (58%) may result from inadequate micro nutrient intake during pregnancy. It is recommended that adding green leaves, locally grown vegetables, roots, nuts and legumes can help increasing the DD of Sri Lankan mothers at low cost.

Keywords: dietary diversity, pregnant mothers, micro-nutrient, food groups

Procedia PDF Downloads 148

Authors: Colin Schmidt, Adrien Lecossier, Pascal Crubleau, Simon Richir

Abstract:

Introduction:The widespread availability of artificial intelligence, exemplified by Generative Pre-trained Transformers (GPT) relying on large language models (LLM), has caused a seismic shift in the realm of knowledge. Everyone now has the capacity to swiftly learn how these models can either serve them well or not. Today, conversational AI like ChatGPT is grounded in neural transformer models, a significant advance in natural language processing facilitated by the emergence of renowned LLMs constructed using neural transformer architecture. Inventiveness of an LLM : OpenAI's GPT-3 stands as a premier LLM, capable of handling a broad spectrum of natural language processing tasks without requiring fine-tuning, reliably producing text that reads as if authored by humans. However, even with an understanding of how LLMs respond to questions asked, there may be lurking behind OpenAI’s seemingly endless responses an inventive model yet to be uncovered. There may be some unforeseen reasoning emerging from the interconnection of neural networks here. Just as a Soviet researcher in the 1940s questioned the existence of Common factors in inventions, enabling an Under standing of how and according to what principles humans create them, it is equally legitimate today to explore whether solutions provided by LLMs to complex problems also share common denominators. Theory of Inventive Problem Solving (TRIZ) : We will revisit some fundamentals of TRIZ and how Genrich ALTSHULLER was inspired by the idea that inventions and innovations are essential means to solve societal problems. It's crucial to note that traditional problem-solving methods often fall short in discovering innovative solutions. The design team is frequently hampered by psychological barriers stemming from confinement within a highly specialized knowledge domain that is difficult to question. We presume ChatGPT Utilizes TRIZ 40. Hence, the objective of this research is to decipher the inventive model of LLMs, particularly that of ChatGPT, through a comparative study. This will enhance the efficiency of sustainable innovation processes and shed light on how the construction of a solution to a complex problem was devised. Description of the Experimental Protocol : To confirm or reject our main hypothesis that is to determine whether ChatGPT uses TRIZ, we will follow a stringent protocol that we will detail, drawing on insights from a panel of two TRIZ experts. Conclusion and Future Directions : In this endeavor, we sought to comprehend how an LLM like GPT addresses complex challenges. Our goal was to analyze the inventive model of responses provided by an LLM, specifically ChatGPT, by comparing it to an existing standard model: TRIZ 40. Of course, problem solving is our main focus in our endeavours.

Keywords: artificial intelligence, Triz, ChatGPT, inventiveness, problem-solving

Procedia PDF Downloads 41

Authors: Eric Morettin

Abstract:

Cybersecurity and digital literacy are pressing issues among Canadian citizens, yet formal education does not provide today’s students with the necessary knowledge and skills needed to adapt to these challenging issues within the physical and digital labor-market. Canada’s current education systems do not highlight the importance of these respective fields, aside from using technology for learning management systems and alternative methods of assignment completion. Educators are not properly trained to integrate technology into the compulsory courses within public education, to better prepare their learners in these topics and Canada’s digital economy. ICTC addresses these gaps in education and training through cross-Canadian educational programming in digital literacy and competency, cybersecurity and coding which is bridged with Canada’s provincially regulated K-12 curriculum guidelines. After analyzing Canada’s provincial education, it is apparent that there are gaps in learning related to technology, as well as inconsistent educational outcomes that do not adequately represent the current Canadian and global economies. Presently only New Brunswick, Nova Scotia, Ontario, and British Columbia offer curriculum guidelines for cybersecurity, computer programming, and digital literacy. The remaining provinces do not address these skills in their curriculum guidelines. Moreover, certain courses across some provinces not being updated since the 1990’s. The three territories respectfully take curriculum strands from other provinces and use them as their foundation in education. Yukon uses all British Columbia curriculum. Northwest Territories and Nunavut respectfully use a hybrid of Alberta and Saskatchewan curriculum as their foundation of learning. Education that is provincially regulated does not allow for consistency across the country’s educational outcomes and what Canada’s students will achieve – especially when curriculum outcomes have not been updated to reflect present day society. Through this, ICTC has aligned Canada’s provincially regulated curriculum and created opportunities for focused education in the realm of technology to better serve Canada’s present learners and teachers; while addressing inequalities and applicability within curriculum strands and outcomes across the country. As a result, lessons, units, and formal assessment strategies, have been created to benefit students and teachers in this interdisciplinary, cross-curricular, practice - as well as meeting their compulsory education requirements and developing skills and literacy in cyber education. Teachers can access these lessons and units through ICTC’s website, as well as receive professional development regarding the assessment and implementation of these offerings from ICTC’s education coordinators, whose combines experience exceeds 50 years of teaching in public, private, international, and Indigenous schools. We encourage you to take this opportunity that will benefit students and educators, and will bridge the learning and curriculum gaps in Canadian education to better reflect the ever-changing public, social, and career landscape that all citizens are a part of. Students are the future, and we at ICTC strive to ensure their futures are bright and prosperous.

Keywords: cybersecurity, education, curriculum, teachers

Procedia PDF Downloads 60

Authors: Eyob Seife

Abstract:

Immunization is a life-saving intervention which prevents needless suffering through sickness, disability, and death. Emphasis on data quality and use will become even stronger with the development of the immunization agenda 2030 (IA2030). Quality of data is a key factor in generating reliable health information that enables monitoring progress, financial planning, vaccine forecasting capacities, and making decisions for continuous improvement of the national immunization program. However, ensuring data of sufficient quality and promoting an information-use culture at the point of the collection remains critical and challenging, especially in hard-to-reach and pastoralist areas where Degehabur district is selected based on a hypothesis of ‘there is no difference in reported and recounted immunization data consistency. Data quality is dependent on different factors where organizational, behavioral, technical, and contextual factors are the mentioned ones. A cross-sectional quantitative study was conducted on September 2022 in the Degehabur district. The study used the world health organization (WHO) recommended data quality self-assessment (DQS) tools. Immunization tally sheets, registers, and reporting documents were reviewed at 5 health facilities (2 health centers and 3 health posts) of primary health care units for one fiscal year (12 months) to determine the accuracy ratio. The data was collected by trained DQS assessors to explore the quality of monitoring systems at health posts, health centers, and the district health office. A quality index (QI) was assessed, and the accuracy ratio formulated were: the first and third doses of pentavalent vaccines, fully immunized (FI), and the first dose of measles-containing vaccines (MCV). In this study, facility-level results showed both over-reporting and under-reporting were observed at health posts when computing the accuracy ratio of the tally sheet to health post reports found at health centers for almost all antigens verified where pentavalent 1 was 88.3%, 60.4%, and 125.6% for Health posts A, B, and C respectively. For first-dose measles-containing vaccines (MCV), similarly, the accuracy ratio was found to be 126.6%, 42.6%, and 140.9% for Health posts A, B, and C, respectively. The accuracy ratio for fully immunized children also showed 0% for health posts A and B and 100% for health post-C. A relatively better accuracy ratio was seen at health centers where the first pentavalent dose was 97.4% and 103.3% for health centers A and B, while a first dose of measles-containing vaccines (MCV) was 89.2% and 100.9% for health centers A and B, respectively. A quality index (QI) of all facilities also showed results between the maximum of 33.33% and a minimum of 0%. Most of the verified immunization data accuracy ratios were found to be relatively better at the health center level. However, the quality of the monitoring system is poor at all levels, besides poor data accuracy at all health posts. So attention should be given to improving the capacity of staff and quality of monitoring system components, namely recording, reporting, archiving, data analysis, and using information for decision at all levels, especially in pastoralist areas where such kinds of study findings need to be improved beside to improving the data quality at root and health posts level.

Keywords: accuracy ratio, Degehabur District, regular childhood immunization program, quality of monitoring system, Somali Region-Ethiopia

Procedia PDF Downloads 80

Authors: M. Sirhan, S. Bekhor, A. Sidess

Abstract:

In-service pavements deteriorate with time due to traffic wheel loads, environment, and climate conditions. Pavement deterioration leads to a reduction in their serviceability and structural behavior. Consequently, proper maintenance and rehabilitation (M&R) are necessary actions to keep the in-service pavement network at the desired level of serviceability. Due to resource and financial constraints, the pavement management system (PMS) prioritizes roads most in need of maintenance and rehabilitation action. It recommends a suitable action for each pavement based on the performance and surface condition of each road in the network. The pavement performance and condition are usually quantified and evaluated by different types of roughness-based and stress-based indices. Examples of such indices are Pavement Serviceability Index (PSI), Pavement Serviceability Ratio (PSR), Mean Panel Rating (MPR), Pavement Condition Rating (PCR), Ride Number (RN), Profile Index (PI), International Roughness Index (IRI), and Pavement Condition Index (PCI). PCI is commonly used in PMS as an indicator of the extent of the distresses on the pavement surface. PCI values range between 0 and 100; where 0 and 100 represent a highly deteriorated pavement and a newly constructed pavement, respectively. The PCI value is a function of distress type, severity, and density (measured as a percentage of the total pavement area). PCI is usually calculated iteratively using the 'Paver' program developed by the US Army Corps. The use of soft computing techniques, especially Artificial Neural Network (ANN), has become increasingly popular in the modeling of engineering problems. ANN techniques have successfully modeled the performance of the in-service pavements, due to its efficiency in predicting and solving non-linear relationships and dealing with an uncertain large amount of data. Typical regression models, which require a pre-defined relationship, can be replaced by ANN, which was found to be an appropriate tool for predicting the different pavement performance indices versus different factors as well. Subsequently, the objective of the presented study is to develop and train an ANN model that predicts the PCI values. The model’s input consists of percentage areas of 11 different damage types; alligator cracking, swelling, rutting, block cracking, longitudinal/transverse cracking, edge cracking, shoving, raveling, potholes, patching, and lane drop off, at three severity levels (low, medium, high) for each. The developed model was trained using 536,000 samples and tested on 134,000 samples. The samples were collected and prepared by The National Transport Infrastructure Company. The predicted results yielded satisfactory compliance with field measurements. The proposed model predicted PCI values with relatively low standard deviations, suggesting that it could be incorporated into the PMS for PCI determination. It is worth mentioning that the most influencing variables for PCI prediction are damages related to alligator cracking, swelling, rutting, and potholes.

Keywords: artificial neural networks, computer programming, pavement condition index, pavement management, performance prediction

Procedia PDF Downloads 117

Authors: Mikko Salminen, Niklas Ravaja

Abstract:

Emotional intelligence (EI) consists of skills for monitoring own emotions and emotions of others, skills for discriminating different emotions, and skills for using this information in thinking and actions. EI enhances, for example, work outcomes and organizational climate. We suggest that the role and manifestations of EI should also be studied in real leadership situations, especially during the emotional, social interaction. Leadership is essentially a process to influence others for reaching a certain goal. This influencing happens by managerial processes and computer-mediated communication (e.g. e-mail) but also by face-to-face, where facial expressions have a significant role in conveying emotional information. Persons with high EI are typically perceived more positively, and they have better social skills. We hypothesize, that during social interaction high EI enhances the ability to detect other’s emotional state and controlling own emotional expressions. We suggest, that emotionally intelligent leader’s experience less stress during social leadership situations, since they have better skills in dealing with the related emotional work. Thus the high-EI leaders would be more able to enjoy these situations, but also be more efficient in choosing appropriate expressions for building constructive dialogue. We suggest, that emotionally intelligent leaders show more positive emotional expressions than low-EI leaders. To study these hypotheses we observed performance review discussions of 40 leaders (24 female) with 78 (45 female) of their followers. Each leader held a discussion with two followers. Psychophysiological methods were chosen because they provide objective and continuous data from the whole duration of the discussions. We recorded sweating of the hands (electrodermal activation) by electrodes placed to the fingers of the non-dominant hand to assess the stress-related physiological arousal of the leaders. In addition, facial electromyography was recorded from cheek (zygomaticus major, activated during e.g. smiling) and periocular (orbicularis oculi, activated during smiling) muscles using electrode pairs placed on the left side of the face. Leader’s trait EI was measured with a 360 questionnaire, filled by each leader’s followers, peers, managers and by themselves. High-EI leaders had less sweating of the hands (p = .007) than the low-EI leaders. It is thus suggested that the high-EI leaders experienced less physiological stress during the discussions. Also, high scores in the factor “Using of emotions” were related to more facial muscle activation indicating positive emotional expressions (cheek muscle: p = .048; periocular muscle: p = .076, almost statistically significant). The results imply that emotionally intelligent managers are positively relaxed during s social leadership situations such as a performance review discussion. The current study also highlights the importance of EI in face-to-face social interaction, given the central role facial expressions have in interaction situations. The study also offers new insight to the biological basis of trait EI. It is suggested that the identification, forming, and intelligently using of facial expressions are skills that could be trained during leadership development courses.

Keywords: emotional intelligence, leadership, performance review discussion, psychophysiology, social interaction

Procedia PDF Downloads 230

Authors: Ipek Goktepe, Israa Elnemr, Hammad Asim, Hao Feng, Mosbah Kushad, Hee Park, Sheikha Alzeyara, Mohammad Alhajri

Abstract:

Food safety management in Qatar is under the shared oversight of multiple agencies in two government ministries (Ministry of Public Health and Ministry of Municipality and Environment). Despite the increasing number and diversity of the food service establishments, no systematic food surveillance system is in place in the country, which creates a gap in terms of determining the food safety attitudes and practices applied in the food service operations. Therefore, this study seeks to partially address this gap through determination of food safety knowledge among food handlers, specifically with respect to food preparation and handling practices, and sanitation methods applied in food service providers (FSPs) and a major market in Doha, Qatar. The study covered a sample of 53 FSPs randomly selected out of 200 FSPs. Face-to-face interviews with managers at participating FSPs were conducted using a 40-questions survey. Additionally, 120 produce handlers who are in direct contact with fresh produce at the major produce market in Doha were surveyed using a questionnaire containing 21 questions. A written informed consent was obtained from each survey participant. The survey data were analyzed using the chi-square test and correlation test. The significance was evaluated at p ˂ 0.05. The results from the FSPs surveys indicated that the average age of FSPs was 11 years, with the oldest and newest being established in 1982 and 2015, respectively. Most managers (66%) had college degree and 68% of them were trained on the food safety management system known as HACCP. These surveys revealed that FSP managers’ training and education level were highly correlated with the probability of their employees receiving food safety training while managers with lower education level had no formal training on food safety for themselves nor for their employees. Casual sit-in and fine dine-in restaurants consistently kept records (100%), followed by fast food (36%), and catering establishments (14%). The produce handlers’ survey results showed that none of the workers had any training on safe produce handling practices. The majority of the workers were in the age range of 31-40 years (37%) and only 38% of them had high-school degree. Over 64% of produce handlers claimed to wash their hands 4-5 times per day but field observations pointed limited handwashing as there was soap in the settings. This observation suggests potential food safety risks since a significant correlation (p ˂ 0.01) between the educational level and the hand-washing practices was determined. This assessment on food safety culture through determination of food and produce handlers' level of knowledge and practices, the first of its kind in Qatar, demonstrated that training and education are important factors which directly impact the food safety culture in FSPs and produce markets. These findings should help in identifying the need for on-site training of food handlers for effective food safety practices in food establishments in Qatar.

Keywords: food safety, food safety culture, food service providers, food handlers

Procedia PDF Downloads 317

Authors: Arzu Firlarer, Duygu Gocmen, Gokhan Uysal

Abstract:

There is currently a growing trend among universities towards blended learning. Blended learning is becoming increasingly important in higher education, with the aims of better accomplishing course learning objectives, meeting students’ changing needs and promoting effective learning both in a theoretical and practical dimension like interior architecture discipline. However, the practical dimension of the discipline cannot be supported in the university environment. During the undergraduate program, the practical training which is tried to be supported by two different internship programs cannot fully meet the requirements of the blended learning. The lack of education program frequently expressed by our graduates and employers is revealed in the practical knowledge and skills dimension of the profession. After a series of meetings for curriculum studies, interviews with the chambers of profession, meetings with interior architects, a gap between the theoretical and practical training modules is seen as a problem in all interior architecture departments. It is thought that this gap can be solved by a new education model which is formed by the cooperation of University-Industry in the concept of blended learning. In this context, it is considered that theoretical and applied knowledge accumulation can be provided by the creation of industry-supported educational environments at the university. In the application process of the Interior Architecture discipline, the use of materials and technical competence will only be possible with the cooperation of industry and participation of students in the production/manufacture processes as observers and practitioners. Wood manufacturing is an important part of interior architecture applications. Wood productions is a sustainable structural process where production details, material knowledge, and process details can be observed in the most effective way. From this point of view, after theoretical training about wooden materials, wood applications and production processes are given to the students, practical training for production/manufacture planning is supported by active participation and observation in the processes. With this blended model, we aimed to develop a training model in which theoretical and practical knowledge related to the production of wood works will be conveyed in a meaningful, lasting way by means of university-industry cooperation. The project is carried out in Ankara with Arcora Architecture and Furniture Company and Başkent University Department of Interior Design where university-industry cooperation is realized. Within the scope of the project, every week the video of that week’s lecture is recorded and prepared to be disseminated by digital medias such as Udemy. In this sense, the program is not only developed by the project participants, but also other institutions and people who are trained and practiced in the field of design. Both academicians from University and at least 15-year experienced craftsmen in the wood metal and dye sectors are preparing new training reference documents for interior architecture undergraduate programs. These reference documents will be a model for other Interior Architecture departments of the universities and will be used for creating an online education module.

Keywords: blended learning, interior design, sustainable training, effective learning.

Procedia PDF Downloads 118

Authors: Thomas Rockstuhl, Soon Ang, Kok Yee Ng, Linn Van Dyne

Abstract:

Intercultural interactions are often challenging and fraught with conflicts. To shed light on how to interact effectively across cultures, academics and practitioners alike have advanced a plethora of intercultural competence models. However, the majority of this work has emphasized distal outcomes, such as job performance and cultural adjustment, rather than proximal outcomes, such as how individuals resolve inevitable intercultural conflicts. As a consequence, the processes by which individuals negotiate challenging intercultural conflicts are not well understood. The current study advances theorizing on intercultural conflict resolution by exploring antecedents of how people resolve intercultural conflicts. To this end, we examine creativity – the generation of novel and useful ideas – in the context of resolving cultural conflicts in intercultural interactions. Based on the dual-identity theory of creativity, we propose that individuals with greater international experience will display greater creativity and that the relationship is accentuated by individual’s cultural intelligence. Two studies test these hypotheses. The first study comprises 84 senior university students, drawn from an international organizational behavior course. The second study replicates findings from the first study in a sample of 89 executives from eleven countries. Participants in both studies provided protocols of their strategies for resolving two intercultural conflicts, as depicted in two multimedia-vignettes of challenging intercultural work-related interactions. Two research assistants, trained in intercultural management but blind to the study hypotheses, coded all strategies for their novelty and usefulness following scoring procedures for creativity tasks. Participants also completed online surveys of demographic background information, including their international experience, and cultural intelligence. Hierarchical linear modeling showed that surprisingly, while international experience is positively associated with usefulness, it is unrelated to novelty. Further, a person’s cultural intelligence strengthens the positive effect of international experience on usefulness and mitigates the effect of international experience on novelty. Theoretically, our findings offer an important theoretical extension to the dual-identity theory of creativity by identifying cultural intelligence as an important individual difference moderator that qualifies the relationship between international experience and creative conflict resolution. In terms of novelty, individuals higher in cultural intelligence seem less susceptible to rigidity effects of international experiences. Perhaps they are more capable of assessing which aspects of culture are relevant and apply relevant experiences when they brainstorm novel ideas. For utility, individuals high in cultural intelligence are better able to leverage on their international experience to assess the viability of their ideas because their richer and more organized cultural knowledge structure allows them to assess possible options more efficiently and accurately. In sum, our findings suggest that cultural intelligence is an important and promising intercultural competence that fosters creative resolutions to intercultural conflicts. We hope that our findings stimulate future research on creativity and conflict resolution in intercultural contexts.

Keywords: cultural Intelligence, intercultural conflict, intercultural creativity, international experience

Procedia PDF Downloads 133

Authors: A. F. G. Van Woezik, L. M. A. Braakman-Jansen, O. A. Kulyk, J. E. W. C. Van Gemert-Pijnen

Abstract:

Background: Zoonoses pose a serious threat to public health and economies worldwide, especially as antimicrobial resistance grows and newly emerging zoonoses can cause unpredictable outbreaks. In order to prevent and control emerging and re-emerging zoonoses, collaboration between veterinary, human health and public health domains is essential. In reality however, there is a lack of cooperation between these three disciplines and uncertainties exist about their tasks and responsibilities. The objective of this ongoing research project (ZonMw funded, 2014-2018) is to develop an online education and communication One Health platform, “eZoon”, for the general public and professionals working in veterinary, human health and public health domains to support the risk communication of non-alimentary zoonoses in the Netherlands. The main focus is on education and communication in times of outbreak as well as in daily non-outbreak situations. Methods: A participatory development approach was used in which stakeholders from veterinary, human health and public health domains participated. Key stakeholders were identified using business modeling techniques previously used for the design and implementation of antibiotic stewardship interventions and consisted of a literature scan, expert recommendations, and snowball sampling. We used a stakeholder salience approach to rank stakeholders according to their power, legitimacy, and urgency. Semi-structured interviews were conducted with stakeholders (N=20) from all three disciplines to identify current problems in risk communication and stakeholder values for the One Health platform. Interviews were transcribed verbatim and coded inductively by two researchers. Results: The following key values were identified (but were not limited to): (a) need for improved awareness of veterinary and human health of each other’s fields, (b) information exchange between veterinary and human health, in particularly at a regional level; (c) legal regulations need to match with daily practice; (d) professionals and general public need to be addressed separately using tailored language and information; (e) information needs to be of value to professionals (relevant, important, accurate, and have financial or other important consequences if ignored) in order to be picked up; and (f) need for accurate information from trustworthy, centrally organised sources to inform the general public. Conclusion: By applying a participatory development approach, we gained insights from multiple perspectives into the main problems of current risk communication strategies in the Netherlands and stakeholder values. Next, we will continue the iterative development of the One Health platform by presenting key values to stakeholders for validation and ranking, which will guide further development. We will develop a communication platform with a serious game in which professionals at the regional level will be trained in shared decision making in time-critical outbreak situations, a smart Question & Answer (Q&A) system for the general public tailored towards different user profiles, and social media to inform the general public adequately during outbreaks.

Keywords: ehealth, one health, risk communication, stakeholder, zoonosis

Procedia PDF Downloads 261

Authors: Paul Moses Ndegwa, Teresia Kabucho, Lucy Wanjiru, Esther Wanjiru, Brian Githaiga, Jecinta Wambui

Abstract:

Health outcome has improved in the country since 2013 following the adoption of the new constitution in Kenya with devolved governance with administration and health planning functions transferred to county governments. 2018-2022 development agenda prioritized universal healthcare coverage, food security, and nutrition, however, the emergence of Covid-19 and the increase of non-communicable diseases pose a challenge and constrain in an already overwhelmed health system. A study was conducted July-November 2021 to establish key challenges in achieving universal healthcare coverage within the county and best practices for improved non-communicable disease control. 14 health workers ranging from nurses, doctors, public health officers, clinical officers, and pharmaceutical technologists were purposely engaged to provide critical information through questionnaires by a trained duo observing ethical procedures on confidentiality. Data analysis. Communicable diseases are major causes of morbidity and mortality. Non-communicable diseases contribute to approximately 39% of deaths. More than 45% of the population does not have access to safe drinking water. Study noted geographic inequality with respect to distribution and use of health resources including competing non-health priorities. 56% of health workers are nurses, 13% clinical officers, 7% doctors, 9%public health workers, 2% are pharmaceutical technologists. Poor-quality data limits the validity of disease-burdened estimates and research activities. Risk factors include unsafe water, sanitation, hand washing, unsafe sex, and malnutrition. Key challenge in achieving universal healthcare coverage is the rise in the relative contribution of non-communicable diseases. Improve targeted disease control with effective and equitable resource allocation. Develop high infectious disease control mechanisms. Improvement of quality data for decision making. Strengthen electronic data-capture systems. Increase investments in the health workforce to improve health service provision and achievement of universal health coverage. Create a favorable environment to retain health workers. Fill in staffing gaps resulting in shortages of doctors (7%). Develop a multi-sectional approach to health workforce planning and management. Need to invest in mechanisms that generate contextual evidence on current and future health workforce needs. Ensure retention of qualified, skilled, and motivated health workforce. Deliver integrated people-centered health services.

Keywords: multi-sectional approach, equity, people-centered, health workforce retention

Procedia PDF Downloads 81

Authors: D. Pugazhenthi, B. Sree Vidya

Abstract:

Cloud computing is one of the emerging technologies that enables end users to use the services of cloud on ‘pay per usage’ strategy. This technology grows in a fast pace and so is its security threat. One among the various services provided by cloud is storage. In this service, security plays a vital factor for both authenticating legitimate users and protection of information. This paper brings in efficient ways of authenticating users as well as securing information on the cloud. Initial phase proposed in this paper deals with an authentication technique using multi-factor and multi-dimensional authentication system with multi-level security. Unique identification and slow intrusive formulates an advanced reliability on user-behaviour based biometrics than conventional means of password authentication. By biometric systems, the accounts are accessed only by a legitimate user and not by a nonentity. The biometric templates employed here do not include single trait but multiple, viz., iris and finger prints. The coordinating stage of the authentication system functions on Ensemble Support Vector Machine (SVM) and optimization by assembling weights of base SVMs for SVM ensemble after individual SVM of ensemble is trained by the Artificial Fish Swarm Algorithm (AFSA). Thus it helps in generating a user-specific secure cryptographic key of the multimodal biometric template by fusion process. Data security problem is averted and enhanced security architecture is proposed using encryption and decryption system with double key cryptography based on Fuzzy Neural Network (FNN) for data storing and retrieval in cloud computing . The proposing scheme aims to protect the records from hackers by arresting the breaking of cipher text to original text. This improves the authentication performance that the proposed double cryptographic key scheme is capable of providing better user authentication and better security which distinguish between the genuine and fake users. Thus, there are three important modules in this proposed work such as 1) Feature extraction, 2) Multimodal biometric template generation and 3) Cryptographic key generation. The extraction of the feature and texture properties from the respective fingerprint and iris images has been done initially. Finally, with the help of fuzzy neural network and symmetric cryptography algorithm, the technique of double key encryption technique has been developed. As the proposed approach is based on neural networks, it has the advantage of not being decrypted by the hacker even though the data were hacked already. The results prove that authentication process is optimal and stored information is secured.

Keywords: artificial fish swarm algorithm (AFSA), biometric authentication, decryption, encryption, fingerprint, fusion, fuzzy neural network (FNN), iris, multi-modal, support vector machine classification

Procedia PDF Downloads 237

Authors: Ammar Asma, Bouafia Nabiha, Dhahri Meriem, Ben Cheikh Asma, Ezzi Olfa, Chafai Rim, Njah Mansour

Abstract:

Despite recent advances in treatment of the lung cancer patients, the prognosis remains poor. Information is limited regarding health related quality of life (QOL) status of advanced lung cancer patients. The purposes of this study were: to assess patient reported symptom burden, to measure their QOL, and to identify determinant factors associated with QOL. Materials/Methods: A cross sectional study of 60 patients was carried out from over the period of 03 months from February 1st to 30 April 2016. Patients were recruited in two department of health care: Pneumology department in a university hospital in Sousse and an oncology unit in a University Hospital in Kairouan. Patients with advanced stage (III and IV) of lung cancer who were hospitalized or admitted in the day hospital were recruited by convenience sampling. We used a questionnaire administrated and completed by a trained interviewer. This questionnaire is composed of three parts: demographic, clinical and therapeutic information’s, QOL measurements: based on the SF-36 questionnaire, Symptom’s burden measurement using the Lung Cancer Symptom Scale (LCSS). To assess Correlation between symptoms burden and QOL, we compared the scores of two scales two by two using the Pearson correlation. To identify factors influencing QOL in Lung cancer, a univariate statistical analysis then, a stepwise backward approach, wherein the variables with p< 0.2, were carried out to determine the association between SF-36 scores and different variables. Results: During the study period, 60 patients consented to complete symptom and quality of life questionnaires at a single point time (72% were recruited from day hospital). The majority of patients were male (88%), age ranged from 21 to 79 years with a mean of 60.5 years. Among patients, 48 (80%) were diagnosed as having non-small cell lung carcinoma (NSCLC). Approximately, 60 % (n=36) of patients were in stage IV, 25 % in stage IIIa and 15 % in stage IIIb. For symptom burden, the symptom burden index was 43.07 (Standard Deviation, 21.45). Loss of appetite and fatigue were rated as the most severe symptoms with mean scores (SD): 49.6 (25.7) and 58.2 (15.5). The average overall score of SF36 was 39.3 (SD, 15.4). The physical and emotional limitations had the lowest scores. Univariate analysis showed that factors which influence negatively QOL were: married status (p<0.03), smoking cessation after diagnosis (p<0.024), LCSS total score (p<0.001), LCSS symptom burden index (p<0.001), fatigue (p<0.001), loss of appetite (p<0.001), dyspnea (p<0.001), pain (p<0.002), and metastatic stage (p<0.01). In multivariate analysis, unemployment (p<0.014), smoking cessation after diagnosis (p<0.013), consumption of analgesic (p<0.002) and the indication of an analgesic radiotherapy (p<0.001) are revealed as independent determinants of QOL. The result of the correlation analyses between total LCSS scores and the total and individual domain SF36 scores was significant (p<0.001); the higher total LCSS score is, the poorer QOL is. Conclusion: A built in support of lung cancer patients would better control the symptoms and promote the QOL of these patients.

Keywords: quality of life, lung cancer, metastasis, symptoms burden

Procedia PDF Downloads 365

Authors: Agnes Siwi Purwaning Tyas, Dewi Cahya Ambarwati

Abstract:

This paper concerns the language learning that develops as a habit formation and a constructive process while exercising an oppressive power to construct the learners. As a locus of discussion, the investigation problematizes the transfer of English language to Indonesian students of junior high school through the use of English textbooks ‘Real Time: An Interactive English Course for Junior High School Students Year VII-IX’. English language has long performed as a global language and it is a demand upon the non-English native speakers to master the language if they desire to become internationally recognized individuals. Generally, English teachers teach the language in accordance with the nature of language learning in which they are trained and expected to teach the language within the culture of the target language. This provides a potential soft cultural penetration of a foreign ideology through language transmission. In the context of Indonesia, learning English as international language is considered dilemmatic. Most English textbooks in Indonesia incorporate cultural elements of the target language which in some extent may challenge the sensitivity towards local cultural values. On the other hand, local teachers demand more English textbooks for junior high school students which can facilitate cultural dissemination of both local and global values and promote learners’ cultural traits of both cultures to avoid misunderstanding and confusion. It also aims to support language learning as bidirectional process instead of instrument of oppression. However, sensitizing and localizing this foreign language is not sufficient to restrain its soft infiltration. In due course, domination persists making the English language as an authoritative language and positioning the locality as ‘the other’. Such critical premise has led to a discursive analysis referring to how the cultural elements of the target language are presented in the textbooks and whether the local characteristics of Indonesia are able to gradually reduce the degree of the foreign oppressive ideology. The three textbooks researched were written by non-Indonesian author edited by two Indonesia editors published by a local commercial publishing company, PT Erlangga. The analytical elaboration examines the cultural characteristics in the forms of names, terminologies, places, objects and imageries –not the linguistic aspect– of both cultural domains; English and Indonesia. Comparisons as well as categorizations were made to identify the cultural traits of each language and scrutinize the contextual analysis. In the analysis, 128 foreign elements and 27 local elements were found in textbook for grade VII, 132 foreign elements and 23 local elements were found in textbook for grade VIII, while 144 foreign elements and 35 local elements were found in grade IX textbook, demonstrating the unequal distribution of both cultures. Even though the ideal pedagogical approach of English learning moves to a different direction by the means of inserting local elements, the learners are continuously imposed to the culture of the target language and forced to internalize the concept of values under the influence of the target language which tend to marginalize their native culture.

Keywords: bidirectional process, English, local culture, oppression

Procedia PDF Downloads 245

Authors: Celine Shi Ying Lee, Jong Jian Lee

Abstract:

Background: Infectious keratitis is one of the leading causes of blindness worldwide. Prompt treatment with effective medication will control the infection early, preventing corneal scarring and visual loss. fluoroquinolones ophthalmic medication is used because of its broad-spectrum properties, potency, good intraocular penetration, and low toxicity. The study aims to evaluate the treatment outcome of corneal ulcers using Levofloxacin 1.5% ophthalmic solution (LVFX) with adjuvant oral ciprofloxacin when indicated and apply this treatment strategy in primary health care as first-line treatment. Methods: Patients with infective corneal ulcer treated in an eye center were recruited. Inclusion criteria includes Corneal infection consistent with bacterial keratitis, single or multiple small corneal ulcers. Treatment regime: LVFX hourly for the first 2 days, 2 hourly from the 3rd day, and 3 hourly on the 5th day of review. Adjuvant oral ciprofloxacin 500mg BD was administered for 5 days if there were multiple corneal ulcers or when the location of the cornea ulcer was central or paracentral. Results: 47 subjects were recruited. There were 16 (34%) males and 31 (66%) females. 40 subjects (85%) were contact lens (CL) related to corneal ulcer, and 7 subjects (15%) were non-contact lens related. 42 subjects (89%) presented with one ulcer, of which 20 of them (48%) needed adjuvant therapy. 5 subjects presented with 2 or 3 ulcers, of which 3 needed adjuvant therapy. A total of 23 subjects (49%) was given adjuvant therapy (oral ciprofloxacin 500mg BD for 5 days).21 of them (91%) were CL related. All subjects recovered fully, and the average duration of treatment was 3.7 days, with 49% of the subjects resolved on the 3rd day, 38% on the 5thday of and 13% on the 7thday. All subjects showed symptoms of relief of pain, light-sensitivity, and redness on the 3rd day with full visual recovery post-treatment. No adverse drug reactions were recorded. Conclusion: Our treatment regime demonstrated good clinical outcome as first-line treatment for corneal ulcers. A corneal ulcer is a common eye condition in Singapore, mainly due to CL wear. Pseudomonas aeruginosa is the most frequent and potentially sight-threatening pathogen involved in CL related corneal ulcer. Coagulase-negative Staphylococci, Staphylococcus aureus, and Streptococcus Pneumoniae were seen in non-CL users. All these bacteria exhibit good sensitivity rates to ciprofloxacin and levofloxacin. It is therefore logical in our study to use LVFX Eyedrops and adjuvant ciprofloxacin oral antibiotics when indicated as first line treatment for most corneal ulcers. Our study of patients, both CL related and non-CL related, have shown good clinical response and full recovery using the above treatment strategy. There was also a full restoration of visual acuity in all the patients. Eye-trained primary Healthcare practitioners can consider adopting this treatment strategy as first line treatment in patients with corneal ulcers. This is relevant during the COVID pandemic, where hospitals are overwhelmed with patients and in regions with limited access to specialist eye care. This strategy would enable early treatment with better clinical outcome.

Keywords: corneal ulcer, levofloxacin hydrate, treatment strategy, ciprofloxacin

Procedia PDF Downloads 154

Authors: Xiaoying Zhang

Abstract:

Forest school – an outdoor educational experience that is undertaken in an outdoor environment with trees – becomes an emerging field of early childhood education recently. In China, the benefits of natural outdoor education to children and young people’s wellness have raised attention. Although different types of outdoor-based activities have been involved in some pre-school of China, few study and practice have been conducted in terms of the notion of forest school. To comprehend the impact of forest school for children and young people, this study aims to systematically review articles on the topic of forest school in preschool education from an ecological perspective, i.e. from individual level (e.g., behavior and mental health) to microsystem level (e.g., the relationship between teachers and children) to ecosystem level. Based on PRISMA framework flow, using the key words of “Forest School” and “Early Childhood Education” for searching in Web-of-science database, a total of 33 articles were identified. Sample participants of 13 studies were not preschool children, five studies were not on forest school theme, and two literature review articles were excluded for further analysis. Finally, 13 articles were eligible for thematic analysis. According to Bronfenbrenner's ecological systems theory, there are some fingdings, on the individual level, current forest school studies are concerned about the children behavioral experience in forest school, how these experience may relate to their achievement or to develop children’s wellbeing/wellness, and how this type of learning experience may enhance children’s self-awareness on risk and safety issues. On the microsystem/mesosystem level, this review indicated that pedagogical development for forest school, risk perception from teachers and parents, social development between peers, and adult’s role in the participation of forest school were concerned, explored and discussed most frequently. On the macrosystem, the conceptualization of forest school is the key theme. Different forms of presentation in various countries with diverse cultures could provide various models of forest school education. However, there was no study investigating forest school on an ecosystem level. As for the potential benefits of physical health and mental wellness that results from forest school, it informs us to reflect the system of preschool education from the ecological perspective for Chinese children. For instance, most Chinese kindergartens ignored the significance of natural outdoor activities for children. Preschool education in China is strongly oriented by primary school system, which means pre-school children are expected to be trained as primary school students to do different subjects, such as math. Hardly any kindergarteners provide the opportunities for children and young people to take risks in a natural environment like forest school does. However, merely copying forest school model for a Chinese preschool education system will be less effective. This review of different level concerns could inform us that the localization the idea of forest school to adapt to a Chinese political, educational and cultural background. More detailed results and profound discussions will be presented in the full paper.

Keywords: early childhood education, ecological system, education development prospects in China, forest school

Procedia PDF Downloads 110

Authors: Dmitriy Babenko, Sergey Yegorov, Ilya Korshukov, Aidana Sultanbekova, Valentina Barkhanskaya, Tatiana Bashirova, Yerzhan Zhunusov, Yevgeniya Li, Viktoriya Parakhina, Svetlana Kolesnichenko, Yeldar Baiken, Aruzhan Pralieva, Zhibek Zhumadilova, Matthew S. Miller, Gonzalo H. Hortelano, Anar Turmuhambetova, Antonella E. Chesca, Irina Kadyrova

Abstract:

Introduction: The rapidly evolving COVID-19 pandemic, along with the re-emergence of pathogens causing acute respiratory infections (ARI), has necessitated the development of novel diagnostic tools to differentiate various causes of ARI. MALDI-MS, due to its wide usage and affordability, has been proposed as a potential instrument for diagnosing SARS-CoV-2 versus non-SARS-CoV-2 ARI. The aim of this study was to investigate the potential of MALDI-MS in conjunction with a machine learning model to accurately distinguish between symptomatic infections caused by SARS-CoV-2 and non-SARS-CoV-2 during both the early and later phases of the pandemic. Furthermore, this study aimed to analyze mass spectrometry (MS) data obtained from nasal swabs of healthy individuals. Methods: We gathered mass spectra from 252 samples, comprising 108 SARS-CoV-2-positive samples obtained in 2020 (Covid 2020), 7 SARS-CoV- 2-positive samples obtained in 2023 (Covid 2023), 71 samples from symptomatic individuals without SARS-CoV-2 (Control non-Covid ARVI), and 66 samples from healthy individuals (Control healthy). All the samples were subjected to RT-PCR testing. For data analysis, we employed the caret R package to train and test seven machine-learning algorithms: C5.0, KNN, NB, RF, SVM-L, SVM-R, and XGBoost. We conducted a training process using a five-fold (outer) nested repeated (five times) ten-fold (inner) cross-validation with a randomized stratified splitting approach. Results: In this study, we utilized the Covid 2020 dataset as a case group and the non-Covid ARVI dataset as a control group to train and test various machine learning (ML) models. Among these models, XGBoost and SVM-R demonstrated the highest performance, with accuracy values of 0.97 [0.93, 0.97] and 0.95 [0.95; 0.97], specificity values of 0.86 [0.71; 0.93] and 0.86 [0.79; 0.87], and sensitivity values of 0.984 [0.984; 1.000] and 1.000 [0.968; 1.000], respectively. When examining the Covid 2023 dataset, the Naive Bayes model achieved the highest classification accuracy of 43%, while XGBoost and SVM-R achieved accuracies of 14%. For the healthy control dataset, the accuracy of the models ranged from 0.27 [0.24; 0.32] for k-nearest neighbors to 0.44 [0.41; 0.45] for the Support Vector Machine with a radial basis function kernel. Conclusion: Therefore, ML models trained on MALDI MS of nasopharyngeal swabs obtained from patients with Covid during the initial phase of the pandemic, as well as symptomatic non-Covid individuals, showed excellent classification performance, which aligns with the results of previous studies. However, when applied to swabs from healthy individuals and a limited sample of patients with Covid in the late phase of the pandemic, ML models exhibited lower classification accuracy.

Keywords: SARS-CoV-2, MALDI-TOF MS, ML models, nasopharyngeal swabs, classification

Procedia PDF Downloads 83

Authors: Ian O'Loughlin

Abstract:

Memory networks aim to integrate some of the recent successes in machine learning with a dynamic memory base that can be updated and deployed in artificial reasoning tasks. These models involve training networks to identify, update, and operate over stored elements in a large memory array in order, for example, to ably perform question and answer tasks parsing real-world and simulated discourses. This family of approaches still faces numerous challenges: the performance of these network models in simulated domains remains considerably better than in open, real-world domains, wide-context cues remain elusive in parsing words and sentences, and even moderately complex sentence structures remain problematic. This innovation, employing an array of stored and updatable ‘memory’ elements over which the system operates as it parses text input and develops responses to questions, is a compelling one for at least two reasons: first, it addresses one of the difficulties that standard machine learning techniques face, by providing a way to store a large bank of facts, offering a way forward for the kinds of long-term reasoning that, for example, recurrent neural networks trained on a corpus have difficulty performing. Second, the addition of a stored long-term memory component in artificial reasoning seems psychologically plausible; human reasoning appears replete with invocations of long-term memory, and the stored but dynamic elements in the arrays of memory networks are deeply reminiscent of the way that human memory is readily and often characterized. However, this apparent psychological plausibility is belied by a recent turn in the study of human memory in cognitive science. In recent years, the very notion that there is a stored element which enables remembering, however dynamic or reconstructive it may be, has come under deep suspicion. In the wake of constructive memory studies, amnesia and impairment studies, and studies of implicit memory—as well as following considerations from the cognitive neuroscience of memory and conceptual analyses from the philosophy of mind and cognitive science—researchers are now rejecting storage and retrieval, even in principle, and instead seeking and developing models of human memory wherein plasticity and dynamics are the rule rather than the exception. In these models, storage is entirely avoided by modeling memory using a recurrent neural network designed to fit a preconceived energy function that attains zero values only for desired memory patterns, so that these patterns are the sole stable equilibrium points in the attractor network. So although the array of long-term memory elements in memory networks seem psychologically appropriate for reasoning systems, they may actually be incurring difficulties that are theoretically analogous to those that older, storage-based models of human memory have demonstrated. The kind of emergent stability found in the attractor network models more closely fits our best understanding of human long-term memory than do the memory network arrays, despite appearances to the contrary.

Keywords: artificial reasoning, human memory, machine learning, neural networks

Procedia PDF Downloads 250

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 22