Application of fuzzy logic for the evaluation of livestock slaughtering

A lógica fuzzy admite infinitos valores lógicos intermediários entre o falso e o verdadeiro. Com esse princípio, foi elaborado neste trabalho um sistema baseado em regras fuzzy, que indicam o índice de massa corporal de animais ruminantes com objetivo de obter o melhor momento para o abate. O sistema fuzzy desenvolvido teve como entradas as variáveis massa e altura, e a saída um novo índice de massa corporal, denominado Índice de Massa Corporal Fuzzy (IMC Fuzzy), que poderá servir como um sistema de detecção do momento de abate de bovinos, comparando-os entre si através das variáveis linguísticas )Muito BaixaM, ,BaixaB, ,MédiaM, ,AltaA e Muito AltaM. Para a demonstração e aplicação da utilização deste sistema fuzzy, foi feita uma análise de 147 vacas da raça Nelore, determinando os valores do IMC Fuzzy para cada animal e indicando a situação de massa corpórea de todo o rebanho. A validação realizada do sistema foi baseado em uma análise estatística, utilizando o coeficiente de correlação de Pearson 0,923, representando alta correlação positiva e indicando que o método proposto está adequado. Desta forma, o presente método possibilita a avaliação do rebanho, comparando cada animal do rebanho com seus pares do grupo, fornecendo desta forma um método quantitativo de tomada de decisão para o pecuarista. Também é possível concluir que o presente trabalho estabeleceu um método computacional baseado na lógica fuzzy capaz de imitar parte do raciocínio humano e interpretar o índice de massa corporal de qualquer tipo de espécie bovina e em qualquer região do País.

Influence of professional experience on detection and treatment decision of occlusal caries lesions in primary teeth

To evaluate the influence of examiner's clinical experience on detection and treatment decision of caries lesions in primary molars. Design Three experienced dentists (Group A) and three undergraduate students (Group B) used the International Caries Detection and Assessment System (ICDAS) criteria and bitewing radiographs (BW) to perform examinations twice in 77 primary molars that presented a sound or carious occlusal surface. For the treatment decision (TD), the examiners attributed scores, analyzing the teeth in conjunction with the radiographs. The presence and the depth of lesion were validated histologically, and reproducibility was evaluated. The sensitivity, specificity, accuracy, and area under the ROC curve values were calculated for ICDAS and BW. The associations between ICDAS, BW, and TD were analyzed by means of contingency tables. Results Interexaminer agreement for ICDAS, BW, and TD were excellent for Group B and moderate for Group A. The two groups presented similar and satisfactory performance for caries lesion detection using ICDAS and BW. In the treatment decision, Group A was shown to have a less invasive approach than Group B. Conclusion The examiner's experience was not determinant for the clinical and radiographic detection of occlusal lesions in primary teeth but influenced the treatment decision of initial lesions.

Automatic method to classify images based on multiscale fractal descriptors and paraconsistent logic

In this study is presented an automatic method to classify images from fractal descriptors as decision rules, such as multiscale fractal dimension and lacunarity. The proposed methodology was divided in three steps: quantification of the regions of interest with fractal dimension and lacunarity, techniques under a multiscale approach; definition of reference patterns, which are the limits of each studied group; and, classification of each group, considering the combination of the reference patterns with signals maximization (an approach commonly considered in paraconsistent logic). The proposed method was used to classify histological prostatic images, aiming the diagnostic of prostate cancer. The accuracy levels were important, overcoming those obtained with Support Vector Machine (SVM) and Bestfirst Decicion Tree (BFTree) classifiers. The proposed approach allows recognize and classify patterns, offering the advantage of giving comprehensive results to the specialists.