RESUMO

Background: The vocational guidance process in educational institutions faces important challenges in managing trials and errors in diagnoses. Technological tools are identified as an effective solution to address these problems. This research seeks to improve career guidance in educational institutions through the implementation of an expert system. The main objective is to reduce test processing time and achieve greater efficiency in students' self-knowledge regarding their interests, based on the personalities of the Holland Test. Methods: The development of the expert system followed a six-model approach. First, an organisational model was created to assess the scope and feasibility of the project. Next, a task and agent model was developed to investigate the impact and look for improvements. A knowledge model was then developed to analyse the relevant knowledge bases. A communication model was also developed to evaluate the communication interface of the system. Next, a design model was created to provide guidelines for the implementation of the system. Finally, the implementation of the knowledge system was carried out to ensure its correct functioning. Results: The implementation of the expert system has shown significant improvements in the vocational guidance process. It was possible to reduce the time needed to apply the test, thus optimising the psychologist's time and allowing a greater capacity for analysis. In addition, an improvement in the effectiveness of the students' self-knowledge in relation to their vocational interests based on the personalities of the Holland Test was observed. Conclusions: This study contributes to career guidance in educational institutions by introducing an innovative expert system. This technological solution optimizes the career guidance process, benefiting psychologists administering tests and students seeking self-knowledge about their career interests.

Assuntos

RESUMO

The use of herbal medicine to treat various diseases is becoming increasingly important as an alternative therapy. Numerous plants have been traditionally used for different purposes, including antiparasitic in humans and animals. Diseases caused by gastrointestinal parasites in ruminants, especially by the nematode Haemonchus contortus, cause large economic losses to the producers, whether by complications of the diseases or the cost of treatment. The main way of handling nematodiasis is by administering anthelmintic drugs, but their excessive use has the disadvantage of causing drug resistance; therefore, an alternative is the use of herbal medicine for this purpose. Mesquite (Prosopis spp.) has been used in Mexico to treat gastrointestinal diseases attributed to helminths. The present study aimed to characterize the rheological properties of mesquite flour using the SeDeM Expert System to determine its suitability for tablet production by direct compression. Direct compression technology facilitates the tableting process by reducing manufacturing costs. The results of the present study indicate that mesquite flour can be processed by direct compression. The latter could allow the manufacturing of economic tablets to treat infections by H. contortus in ruminants.

Assuntos

RESUMO

En Cuba, el acceso a los servicios farmacéuticos por parte de la población se ve afectado por la no disponibilidad de medicamentos y la lejanía de las farmacias. La falta de información acerca de la existencia de los medicamentos y la cantidad de estos en la red de farmacias cercanas a una ubicación geográfica, aparejados al poco suministro de medicamentos y la calidad de la prestación del servicio, genera descontento e inconformidad en la población. En la presente investigación se realiza un diseño para mejorar la problemática planteada a partir de un sistema basado en reglas como ayuda a la toma de decisiones para la obtención de los medicamentos por parte de la población. Se aplica un estudio de caso mediante el cual es posible sugerir al usuario las 5 farmacias más cercanas donde el paciente puede adquirir los medicamentos sobre las decisiones asumidas.

In Cuba, access to pharmaceutical services by the population is affected by the non-availability of medicines and the remoteness of pharmacies. The lack of information about the existence of medicines and the quantity of these in the network of pharmacies close to a geographical location, coupled with the low supply of medicines and the quality of service provision, generates discontent and nonconformity in the population. In the present investigation, a design is carried out to improve the problem raised from a system based on rules as an aid to decision-making to obtain medicines by the population. A case study is applied through which it is possible to suggest to the user the 5 closest pharmacies where the patient can acquire the medicines on the decisions made.

RESUMO

In this study, we develop an artificial intelligence model to predict the vulnerability of broiler production systems (broilers and facilities) to heat conditions using a fuzzy model approach. The model was designed with a multiple-input and a single-output (MISO) approach (input: physical environment and broilers age; output: degree of vulnerability of broilers system). For the validation of the fuzzy model, two approaches were used: (1) records from the scientific literature and (2) meteorological forecasts. First, we validated the model fuzzy with data from the scientific literature; second, we validate the model with data from meteorological forecasts. Both validation approaches were performed in different scenarios of the thermal environment (comfort, discomfort, and discomfort + low heat exchange), broilers' age (21-35 days, 25-39 days, and 28-42 days), and relative cooling efficiency (0% inefficient; and 80% efficient). Then, we applied the model to predict the degree of vulnerability of the broiler system with the help of weather forecasts. The recall and precision of the fuzzy model were high (> 0.9) for the thermal comfort and thermal discomfort + low heat exchange scenarios. In contrast, the fuzzy model was moderate agreement (recall 0.45; precision 0.64) for the thermal discomfort scenario compared to the scientific literature. The application of the model with the weather forecast showed the interaction between the physical and biological systems when submitted to a thermal environment challenge. Regardless of the broilers' age, a high degree of vulnerability was observed in facilities with inefficient cooling system. The fuzzy model developed in this study was efficient to predict the vulnerability of the broiler production system to heat conditions, further, to identify the uncertain conditions associated with broilers' age, relative humidity, and the relative cooling efficiency of the facilities.

Assuntos

RESUMO

Many challenges lie ahead when dealing with COVID-19, not only related to the acceleration of the pandemic, but also to the prediction of personal protective equipment sets consumption to accommodate the explosive demand. Due to this situation of uncertainty, hospital administration encourages the excess stock of these materials, over-stocking products in some hospitals, and provoking shortages in others. The number of available personal protective equipment sets is one of the three main factors that limit the number of patients at a hospital, as well as the number of available beds and the number of professionals per shift. In this scenario, we developed an easy-to-use expert system to predict the demand for personal protective equipment sets in hospitals during the COVID-19 pandemic, which can be updated in real-time for short term planning. For this system, we propose a naive statistical modeling which combines historical data of the consumption of personal protective equipment sets by hospitals, current protocols for their uses and epidemiological data related to the disease, to build predictive models for the demand for personal protective equipment in Brazilian hospitals during the pandemic. We then embed this modeling in the free Safety-Stock system, which provides useful information for the hospital, especially the safety-stock level and the prediction of consumption/demand for each personal protective equipment set over time. Considering our predictions, a hospital may have its needs related to specific personal protective equipment sets estimated, taking into account its historical stock levels and possible scheduled purchases. The tool allows for adopting strategies to control and keep the stock at safety levels to the demand, mitigating the risk of stock-out. As a direct consequence, it also enables the interchange and cooperation between hospitals, aiming to maximize the availability of equipment during the pandemic.

RESUMO

Big construction enterprises, such as electrical power generation dams and mining slopes, demand continuous visual inspections. The sizes of these structures and the necessary level of detail in each mission requires a conflicting set of multi-objective goals, such as performance, quality, and safety. It is challenging for human operators, or simple autonomous path-following drones, to process all this information, and thus, it is common that a mission must be repeated several times until it succeeds. This paper deals with this problem by developing a new cognitive architecture based on a collaborative environment between the unmanned aerial vehicles (UAVs) and other agents focusing on optimizing the data gathering, information processing, and decision-making. The proposed architecture breaks the problem into independent units ranging from sensors and actuators up to high-level intelligence processes. It organizes the structures into data and information; each agent may request an individual behavior from the system. To deal with conflicting behaviors, a supervisory agent analyzes all requests and defines the final planning. This architecture enables real-time decision-making with intelligent social behavior among the agents. Thus, it is possible to process and make decisions about the best way to accomplish the mission. To present the methodology, slope inspection scenarios are shown.

RESUMO

Dengue, Zika, and chikungunya are epidemic diseases transmitted by the Aedes mosquito. These virus infections can be so severe to the point of bringing on mobility and neurological problems, or even death. Expert systems (ES) can be used as tools for the identification of patterns intended to solve problems in the same way as a professional specialist would. This work aimed to develop an ES in the form of an Android application to serve as a supportive tool in the diagnosis of these arboviruses. The goal is to associate the set of symptoms from a patient to a score related to the likelihood of them having these diseases. To make this possible, we implemented a rule-based ES which considers the presence of symptoms itself and the relation between them to associate the case under analysis to others found in the literature. We performed 96 tests (32 for each illness), and our system had a success rate of 96.88%. Resident physicians of a public hospital also analyzed these clinical cases and achieved an average success rate of 72.92%. Comparing the results of the method proposed and errors made by health professionals, we showed an improvement in the effectiveness of clinical diagnoses. Graphical abstract Figure - DZC DIAG Operating Flowchart: the physicians record patients' data and answer a series of questions related to the patient's symptoms; after all the questions, the result is generated by the expert system (score for dengue, Zika, and chikungunya); and it is saved in the same device where the test was done and uploaded online to a FTP.

Assuntos

RESUMO

Abstract Introduction: The interest in Expert systems has increased in the medical area. Some of them are employed even for diagnosis. With the variability of transcatheter prostheses, the most appropriate choice can be complex. This scenario reveals an enabling environment for the use of an Expert system. The goal of the study was to develop an Expert system based on artificial intelligence for supporting the transcatheter aortic prosthesis selection. Methods: The system was developed on Expert SINTA. The rules were created according to anatomical parameters indicated by the manufacturing company. Annular aortic diameter, aortic area, aortic perimeter, ascending aorta diameter and Valsalva sinus diameter were considered. After performing system accuracy tests, it was applied in a retrospective cohort of 22 patients with submitted to the CoreValve prosthesis implantation. Then, the system indications were compared to the real heart team decisions. Results: For 10 (45.4%) of the 22 patients there was no concordance between the Expert system and the heart team. In all cases with discordance, the software was right in the indication. Then, the patients were stratified in two groups (same indication vs. divergent indication). The baseline characteristics did not show any significant difference. Mortality, stroke, acute myocardial infarction, atrial fibrillation, atrioventricular block, aortic regurgitation and prosthesis leak did not present differences. Therefore, the maximum aortic gradient in the post-procedure period was higher in the Divergent Indication group (23.9 mmHg vs. 11.9 mmHg, P=0.03), and the mean aortic gradient showed a similar trend. Conclusion: The utilization of the Expert system was accurate, showing good potential in the support of medical decision. Patients with divergent indication presented high post-procedure aortic gradients and, even without clinical repercussion, these parameters, when elevated, can lead to early prosthesis dysfunction and the necessity of reoperation.

Assuntos

RESUMO

This work describes a novel approach based on advanced molecular similarity to predict the sweetness of chemicals. The proposed Quantitative Structure-Taste Relationship (QSTR) model is an expert system developed keeping in mind the five principles defined by the Organization for Economic Co-operation and Development (OECD) for the validation of (Q)SARs. The 649 sweet and non-sweet molecules were described by both conformation-independent extended-connectivity fingerprints (ECFPs) and molecular descriptors. In particular, the molecular similarity in the ECFPs space showed a clear association with molecular taste and it was exploited for model development. Molecules laying in the subspaces where the taste assignation was more difficult were modeled trough a consensus between linear and local approaches (Partial Least Squares-Discriminant Analysis and N-nearest-neighbor classifier). The expert system, which was thoroughly validated through a Monte Carlo procedure and an external set, gave satisfactory results in comparison with the state-of-the-art models. Moreover, the QSTR model can be leveraged into a greater understanding of the relationship between molecular structure and sweetness, and into the design of novel sweeteners.

RESUMO

En este trabajo se presenta un sistema experto (SE) que permite establecer la frecuencia cardiaca máxima en términos de porcentaje de intensidad, la duración de una sesión de entrenamiento y la frecuencia en días por semana. La base del SE es el conocimiento de profesionales en el área de medicina y del deporte, que ayuda a los deportistas con padecimiento de enfermedades o factores de riesgo a tomar mejores decisiones al momento de realizar ejercicio físico. Este sistema se desarrolló en un ambiente web para facilitar la adquisición de los datos por parte de los profesionales, permitiendo así, la incorporación de varios criterios donde la aplicación del algoritmo del SE y de minería de datos proveen a los deportistas resultados con soporte médico. El SE ha sido incorporado a un software que se encarga de monitorizar la frecuencia cardiaca en tiempo real en una disciplina deportiva, donde se evidenció el buen funcionamiento del SE.

This paper presents an expert system (SE) that establishes the maximum heart rate in percentage terms of intensity, duration of a training session and frequency in days per week is presented. The base SE is the knowledge of professionals in the field of medicine and sport that helps athletes suffering from diseases or risk factors make better decisions at the time of exercise. This system was developed in a web environment to facilitate the acquisition of data by professionals, thus allowing the incorporation of several criteria where application of the algorithm SE and mining provide athletes results with medical support. The SE has been incorporated into software that is responsible for monitoring the heart rate in real time in a sport where the proper functioning of the SE was evident.

Este trabalho apresenta um sistema especialista (SE), que estabelece a frequência cardíaca máxima em termos percentuais de intensidade, a duração de uma sessão de treinamento ea freqüência em dias por semana é apresentado. A base de SE é o conhecimento de profissionais no campo da medicina e esporte, que ajuda atletas que sofrem de doenças ou factores de risco a tomar melhores decisões no momento do exercício. Este sistema foi desenvolvido em um ambiente web para facilitar a aquisição de dados por profissionais, permitindo a incorporação de vários critérios, quando a aplicação do algoritmo SE e mineração oferecer aos atletas resultados com apoio médico. A SE foi incorporado no software que é responsável por monitorar o ritmo cardíaco em tempo real em um esporte onde o bom funcionamento da SE foi evidente.

RESUMO

A estenose do canal vertebral lombar (ECL) é uma patologia complexa, com alta incidência entre pessoas acima de 65 anos de idade. No entanto, o diagnóstico correto é, por vezes, difícil de ser confirmado. O uso de modelos de Inteligência Articial (IA) na medicina é, em geral, desconhecida para a maioria da comunidade médica, mas tem sido usada há décadas na assistência em UTI, os métodos de imagem e dispositivos de diagnóstico eletrônico (ECG). Através de uma revisão sistemática da literatura, com foco nos achados clínicos e radiológicos, juntamente com todas as modalidades de tratamento, foi possível identicar o ambiente completo de pacientes LSS, para responder a quatro questões: (a) "Com base no quadro clínico, o paciente tem um, cenário moderado ou grave?"; (b) "Com base nos dados radiológicos, o paciente pode ser classicado com um cenário leve,moderada ou grave?"; (c) "Qual é a probabilidade, com base na anamnese, do paciente ter ECL?"; (d) "Qual é o melhor tratamento a ser oferecido?".þ. Como auxílio de um software usando Sistema Especialista (Expert Sinta), uma linguagem de IA, alocamos todas as variáveis e seus valores para orientar o software responder às quatro perguntas. Foi possível identicar 657 artigos cientícos, no entanto apenas 63 poderia mencionar não apenas as variáveis, mas a sua probabilidade de ocorrência ou teve disponibilidade texto completo. Foi possível classicar a intensidade do quadro clínico e radiológico, criar um índice de probabilidade para LSS e oferecer o melhor tratamento. Recomendamos o uso, sob supervisão médica, em de Neurocirurgia ou clínicas ortopédicas como um conselheiro para os pacientes com ELA.

The lumbar spinal stenosis (LSS) is a complex pathology with high incidence among people above 65 years old. However, the correct diagnose is sometimes difcult to perform. The use of Articial Intelligence (AI) models in medicine is, in general, unfamiliar for the majority of medical community, but has been used for decades in assistance in ICUs, image methods and electronic diagnostic devices (EKG). Through a systematic literature review focused in the clinical and radiological ndings, in addition to all treatmentmodalities, we identied the complete environment of LSS patients, to answer four questions. (a) "Based on the clinical presentation, the patient has a mild, moderate or severe scenario?", (b) "Based on the radiological data, the patient can be classied having a mild, moderate or severe scenario?", (c) "What is the probability, based on the anamneses, the patient has LSS?", and (d) "What is the best treatment to be offered?".With the aid of a software using Expert System (Expert Sinta), a language of AI, we allocate all the variables and their values to orient the software to answer the four questions. It was possible to identify 657 scientic articles, however only 63 could mention not only the variables, but their occurrence probability or had full text availability. It was possible to classify the intensity the clinical and radiological scenario, create a probability index for LSS and offer the best treatment. We recommend the use, under medical supervision, in neurosurgery or orthopedic clinics as an adviser for patients with LSS.

Assuntos

RESUMO

Realizar un buen diagnóstico es vital para el éxito en el tratamiento de una enfermedad, por ello, las herramientas que apoyan el proceso de diagnóstico son de gran interés. Particularmente, los especialistas en inmunología no cuentan con herramientas que apoyen el diagnóstico de enfermedades autoinmunes específicas de órgano. Esto hace que en dicho proceso los especialistas deban acudir a su experiencia y al conocimiento formalizado de esta área de la medicina. Pero cuando dicho conocimiento no está a la mano o simplemente no se cuenta con la experiencia, el diagnóstico presenta complicaciones que seguramente repercutirán en la salud del paciente. Desde las TI se han realizado diferentes intentos por colaborar en la tarea de diagnóstico, generalmente con la construcción de Sistemas Expertos que modelan el conocimiento de los especialistas ante circunstancias determinadas. Este trabajo plantea la creación de un prototipo de Sistema Experto para el Diagnóstico de Enfermedades Autoinmunes específicas de órgano SEDEA, el cual integra el conocimiento clínico con el modelo descriptivo ofrecido por Internist, a través de una ontología que permite manejar los diferentes conceptos por medio de reglas declaradas en el motor de inferencia de JESS, ofreciendo además interfaces que permiten ingresar y procesar datos con facilidad.

To make a good diagnosis is vital to the successful in the treatment of a disease. Therefore, tools that contribute to more accurate diagnosis are of great interest. Particularly, immunology specialists do not have tools to support the organ-specific autoimmune diseases diagnosis process. This makes that during this process, specialists must resort to their experience and to the formalized knowledge of this medicine area. But when the knowledge is not at hand or simply no one has the experience, the diagnosis presents complications which will surely impact on the patient’s health. Different efforts to collaborate in diagnostic task has been made from the IT field; generally in the building of Experts Systems that model the specialist knowledge to certain conditions. This paper proposes the creation of an Expert System prototype for the Diagnostic of organ-specific Autoimmune diseases SEDEA, which not only integrates the clinical knowledge with the Internist descriptive model through an ontology that allows to handle the different concepts using rules declared in the JESS inference engine, but alsomoffers interfaces toeasilyinsert and process data.

Assuntos

RESUMO

Introduction Based on the increasing usability of technology in healthcare, this paper discusses the use of an expert system (ES) to identify the sensory profile of patients starting Occupational Therapy, allowing the professional to make assertive decisions in establishing priorities in the therapeutic plan.Objective To develop a decision support system from the Infant/Toddler Sensory Profile.Method Structuring of an ES based on Infant/Toddler Sensory Profile, from terms translation into Portuguese, identification of variables and domain values involved, and construction of production rules.Results Twelve variables were registered for the construction of the ES, 6 of these were treated as goal-variables, 20 rules being built.Conclusion This ES is an important support to the occupational therapist in the decision-making process of treatment plans, determining priorities and respecting the sensory profile of each child. In addition, it must be noted that there is no equivalent system.

Introdução Com a crescente usabilidade da tecnologia na área da saúde, este artigo aborda a utilização de um sistema especialista (SE) para identificar o perfil sensorial de pacientes a iniciarem o tratamento de Terapia Ocupacional, permitindo ao profissional tomar decisões assertivas no estabelecimento de prioridades no plano terapêutico.Objetivo Construir um sistema de apoio à decisão a partir do Infant/Toddler Sensory Profile.Método Estruturação de um SE baseado no Infant/Toddler Sensory Profile, a partir da tradução para o português dos termos contidos neste instrumento, identificação das variáveis e valores de domínio envolvidos; e a construção das respectivas regras de produção.Resultados Para a construção do SE foram cadastradas 12 variáveis, destas 6 foram tratadas como variáveis-objetivo, sendo construídas 20 regras.Conclusão O SE construído constitui apoio importante ao terapeuta ocupacional no processo de tomada de decisão sobre o plano terapêutico, determinando as prioridades e respeitando o perfil sensorial de cada criança. Além disso, é preciso salientar que não há um sistema equivalente.

RESUMO

Cloacal temperature (CT) of broiler chickens is an important parameter to classify its comfort status; therefore its prediction can be used as decision support to turn on acclimatization systems. The aim of this research was to develop and validate a system using the fuzzy set theory for CT prediction of broiler chickens. The fuzzy system was developed based on three input variables: air temperature (T), relative humidity (RH) and air velocity (V). The output variable was the CT. The fuzzy inference system was performed via Mamdani's method which consisted in 48 rules. The defuzzification was done using center of gravity method. The fuzzy system was developed using MAPLE® 8. Experimental results, used for validation, showed that the average standard deviation between simulated and measured values of CT was 0.13°C. The proposed fuzzy system was found to satisfactorily predict CT based on climatic variables. Thus, it could be used as a decision support system on broiler chicken growth.

A temperatura cloacal (TC) de frangos de corte é um importante parâmetro para classificar a sua condição de conforto, portanto, a sua predição pode ser usada no suporte à decisão de acionamento de sistemas de climatização. Objetivou-se com a presente pesquisa desenvolver e validar um sistema, utilizando a teoria dos conjuntos fuzzy para predição da TC de frangos de corte. O sistema fuzzy foi desenvolvido com base em três variáveis de entrada: temperatura do ar (T), umidade relativa (UR) e velocidade do ar (V), tendo, como variável de saída, a TC. A inferência fuzzy foi realizada por meio do método tipo Mamdani, que consistiu na elaboração de 48 regras e a defuzzificação por meio do método do Centro de Gravidade. O sistema fuzzy foi desenvolvido no ambiente computacional MAPLE® 8. Resultados experimentais, usados para a validação, mostraram que o desvio padrão médio entre os valores simulados e medidos de TC foi de 0,13°C. O sistema fuzzy proposto prediz satisfatoriamente a TC com base nas variáveis climáticas, podendo ser utilizado como suporte à decisão em sistemas de criação de frangos de corte.

RESUMO

Cloacal temperature (CT) of broiler chickens is an important parameter to classify its comfort status; therefore its prediction can be used as decision support to turn on acclimatization systems. The aim of this research was to develop and validate a system using the fuzzy set theory for CT prediction of broiler chickens. The fuzzy system was developed based on three input variables: air temperature (T), relative humidity (RH) and air velocity (V). The output variable was the CT. The fuzzy inference system was performed via Mamdani's method which consisted in 48 rules. The defuzzification was done using center of gravity method. The fuzzy system was developed using MAPLE® 8. Experimental results, used for validation, showed that the average standard deviation between simulated and measured values of CT was 0.13°C. The proposed fuzzy system was found to satisfactorily predict CT based on climatic variables. Thus, it could be used as a decision support system on broiler chicken growth.

A temperatura cloacal (TC) de frangos de corte é um importante parâmetro para classificar a sua condição de conforto, portanto, a sua predição pode ser usada no suporte à decisão de acionamento de sistemas de climatização. Objetivou-se com a presente pesquisa desenvolver e validar um sistema, utilizando a teoria dos conjuntos fuzzy para predição da TC de frangos de corte. O sistema fuzzy foi desenvolvido com base em três variáveis de entrada: temperatura do ar (T), umidade relativa (UR) e velocidade do ar (V), tendo, como variável de saída, a TC. A inferência fuzzy foi realizada por meio do método tipo Mamdani, que consistiu na elaboração de 48 regras e a defuzzificação por meio do método do Centro de Gravidade. O sistema fuzzy foi desenvolvido no ambiente computacional MAPLE® 8. Resultados experimentais, usados para a validação, mostraram que o desvio padrão médio entre os valores simulados e medidos de TC foi de 0,13°C. O sistema fuzzy proposto prediz satisfatoriamente a TC com base nas variáveis climáticas, podendo ser utilizado como suporte à decisão em sistemas de criação de frangos de corte.

RESUMO

Cloacal temperature (CT) of broiler chickens is an important parameter to classify its comfort status; therefore its prediction can be used as decision support to turn on acclimatization systems. The aim of this research was to develop and validate a system using the fuzzy set theory for CT prediction of broiler chickens. The fuzzy system was developed based on three input variables: air temperature (T), relative humidity (RH) and air velocity (V). The output variable was the CT. The fuzzy inference system was performed via Mamdani's method which consisted in 48 rules. The defuzzification was done using center of gravity method. The fuzzy system was developed using MAPLE® 8. Experimental results, used for validation, showed that the average standard deviation between simulated and measured values of CT was 0.13°C. The proposed fuzzy system was found to satisfactorily predict CT based on climatic variables. Thus, it could be used as a decision support system on broiler chicken growth.

A temperatura cloacal (TC) de frangos de corte é um importante parâmetro para classificar a sua condição de conforto, portanto, a sua predição pode ser usada no suporte à decisão de acionamento de sistemas de climatização. Objetivou-se com a presente pesquisa desenvolver e validar um sistema, utilizando a teoria dos conjuntos fuzzy para predição da TC de frangos de corte. O sistema fuzzy foi desenvolvido com base em três variáveis de entrada: temperatura do ar (T), umidade relativa (UR) e velocidade do ar (V), tendo, como variável de saída, a TC. A inferência fuzzy foi realizada por meio do método tipo Mamdani, que consistiu na elaboração de 48 regras e a defuzzificação por meio do método do Centro de Gravidade. O sistema fuzzy foi desenvolvido no ambiente computacional MAPLE® 8. Resultados experimentais, usados para a validação, mostraram que o desvio padrão médio entre os valores simulados e medidos de TC foi de 0,13°C. O sistema fuzzy proposto prediz satisfatoriamente a TC com base nas variáveis climáticas, podendo ser utilizado como suporte à decisão em sistemas de criação de frangos de corte.

RESUMO

Production losses due to lack of precision in detecting estrus in dairy cows are well known and reported in milk production countries. Nowadays automatic estrus detection has become possible as a result of technical progress in continuously monitoring dairy cows using fuzzy pertinence functions. Dairy cow estrus is usually visually detected; however, solely use of visual detection is considered inefficient. Many studies have been carried out to develop an effective model to interpret the occurrence of estrus and detect estrus; however, most models present too many false-positive alerts and because of this they are sometimes considered unreliable. The objective of this research was to construct a system based on fuzzy inference functions evaluated with a receiver-operating characteristic curve, capable of efficiently detect estrus in dairy cows. For the input data the system combined previous estrus cases information and prostaglandin application with the data of cow activities. The system outputs were organized in three categories: 'in estrus', 'maybe in estrus" and 'not in estrus'. The system validation was carried out in a commercial dairy farm using a herd of 350 lactating cows. The performance of the test was measured by calculating its sensitivity towards the right estrus detection; and its specificity towards the precision of the detection. Within a six months period of tests, over 25 thousands cases of estrus were analyzed from a database of the commercial farm. The sensitivity found was 84.2%, indicating that the system can detect estrus efficiently and it may improve automatic estrus detection.

Perdas na produção leiteiras devido às falhas de detecção do estro são bem conhecidas e relatadas em vários paises. Atualmente a automação na detecção do estro, tem sido possível, devido aos avanços tecnológicos na contínua monitoração de vacas leiteiras e utilização de modelos fuzzy. O estro em vacas de leite é normalmente detectado visualmente, um método considerado ineficiente. Alguns estudos têm sido desenvolvidos com o intuito de se obter modelos efetivos para interpretar a ocorrência e detecção do estro, contudo, muitos modelos apresentam alertas falsos positivos, sendo muitas vezes considerados falhos. Construiu-se um sistema baseado nas funções de inferência fuzzy capaz de detectar eficientemente o estro de vacas de leite, avaliando seu desempenho com curvas ROC (Receiver-Operating Characteristic). Os dados de entrada do sistema combinaram informações de casos prévios de estro, aplicações de prostaglandina com dados das atividades das vacas. As saídas do sistema foram organizadas em três categorias: "em estro", "talvez em estro" e "sem estro". A validação do sistema foi realizada em uma granja leiteira comercial utilizando um rebanho de 350 vacas em lactação. O desempenho do teste foi avaliado calculando a sensibilidade na detecção correta de estro; e sua especificidade através da precisão da detecção. O teste teve uma duração de seis meses, sendo analisados mais de 25 mil casos de estro da base de dados da granja. A sensibilidade obtida foi de 84,2%, indicando que o sistema pode detectar eficientemente o estro melhorando a detecção automática em vacas leiteiras.

RESUMO

Production losses due to lack of precision in detecting estrus in dairy cows are well known and reported in milk production countries. Nowadays automatic estrus detection has become possible as a result of technical progress in continuously monitoring dairy cows using fuzzy pertinence functions. Dairy cow estrus is usually visually detected; however, solely use of visual detection is considered inefficient. Many studies have been carried out to develop an effective model to interpret the occurrence of estrus and detect estrus; however, most models present too many false-positive alerts and because of this they are sometimes considered unreliable. The objective of this research was to construct a system based on fuzzy inference functions evaluated with a receiver-operating characteristic curve, capable of efficiently detect estrus in dairy cows. For the input data the system combined previous estrus cases information and prostaglandin application with the data of cow activities. The system outputs were organized in three categories: 'in estrus', 'maybe in estrus" and 'not in estrus'. The system validation was carried out in a commercial dairy farm using a herd of 350 lactating cows. The performance of the test was measured by calculating its sensitivity towards the right estrus detection; and its specificity towards the precision of the detection. Within a six months period of tests, over 25 thousands cases of estrus were analyzed from a database of the commercial farm. The sensitivity found was 84.2%, indicating that the system can detect estrus efficiently and it may improve automatic estrus detection.

Perdas na produção leiteiras devido às falhas de detecção do estro são bem conhecidas e relatadas em vários paises. Atualmente a automação na detecção do estro, tem sido possível, devido aos avanços tecnológicos na contínua monitoração de vacas leiteiras e utilização de modelos fuzzy. O estro em vacas de leite é normalmente detectado visualmente, um método considerado ineficiente. Alguns estudos têm sido desenvolvidos com o intuito de se obter modelos efetivos para interpretar a ocorrência e detecção do estro, contudo, muitos modelos apresentam alertas falsos positivos, sendo muitas vezes considerados falhos. Construiu-se um sistema baseado nas funções de inferência fuzzy capaz de detectar eficientemente o estro de vacas de leite, avaliando seu desempenho com curvas ROC (Receiver-Operating Characteristic). Os dados de entrada do sistema combinaram informações de casos prévios de estro, aplicações de prostaglandina com dados das atividades das vacas. As saídas do sistema foram organizadas em três categorias: "em estro", "talvez em estro" e "sem estro". A validação do sistema foi realizada em uma granja leiteira comercial utilizando um rebanho de 350 vacas em lactação. O desempenho do teste foi avaliado calculando a sensibilidade na detecção correta de estro; e sua especificidade através da precisão da detecção. O teste teve uma duração de seis meses, sendo analisados mais de 25 mil casos de estro da base de dados da granja. A sensibilidade obtida foi de 84,2%, indicando que o sistema pode detectar eficientemente o estro melhorando a detecção automática em vacas leiteiras.

RESUMO

Resumen La identificación de bacilos gramnegativos no fermentadores de la glucosa (BGNNF) es una tarea compleja y laboriosa que exige la participación de expertos. Para facilitar la toma de decisiones se desarrolló y puso a prueba un Sistema Experto (SE) con una base de conocimientos construida aplicando el algoritmo C4.5 modificado, capaz de inducir un árbol de decisión (reglas primarias) para un conjunto de géneros, y la diferenciación entre éstos (reglas complementarias) para la identificación de géneros específicos. La incertidumbre del sistema es tratada mediante el esquema de factores de certeza. En este trabajo se sometió a prueba el SE con una selección de cultivos de BGNNF de diferente origen, identificados y preservados en el Centro Venezolano de Colecciones de Microorganismos (CVCM): géneros Achromobacter, Acinetobacter, Alcaligenes, Brevundimonas, Burkholderia, Chryseobacterium, Comamonas, Delftia, Moraxella, Myroides, Ochrobactrum, Oligella, Pseudomonas, Shewanella, Sphingobacterium y Stenotrophomonas. Mediante la aplicación de 11 pruebas (características primarias) se obtuvo una aproximación entre varios de los géneros posibles. Las pruebas complementarias sugeridas (entre 1 y 9), permitieron una mayor aproximación al género posible. Los resultados muestran una coincidencia del 95.8% con los reportados por el CVCM. En base a estos resultados se estudia la ampliación de la base conocimiento para la identificación de especies de BGNNF, y de otros grupos de bacterias.

Abstract The identification of glucose non fermentative gram-negative bacilli (NFGNB) is a complex and laborious task. In order to facilitate genera identification an Expert System (ES) was developed applying a modified C4.5 algorithm able to induce a decision tree (primary rules) for a set of genera, and the differentiation between these (complementary rules) for the identification of specific genera- The uncertainty of the system is treated by means of a certainty factors scheme. In this work the ES was put on approval using a selection of cultures of NFGNB of different origin, identified and preserved in the Venezuelan Center for Microbial Collections (CVCM): genera Achromobacter, Acinetobacter, Alcaligenes, Brevundimonas, Burkholderia, Chryseobacterium, Comamonas, Delftia, Moraxella, Myroides, Ochrobactrum, Oligella, Pseudomonas, Shewanella, Sphingobacterium y Stenotrophomonas. By means of the application of 11 tests (primary characteristics) an approach between several of possible genera was obtained, The suggested complementary testes (between 1 to 9) allowed great approach to the possible generas.-.The results show a coincidence of the 95.8% with the reported ones by the CVCM. An extent of the ES for the identification of other genera is under study.