Classification of commercial grade lumber requires a visual inspection of the milled board to determine if the board meets attributes of the various grades of lumber. The lower the number of anomalies, such as knots, the higher the grade of the piece. Knot wood and clear wood radiate and absorb heat at different rates, thereby allowing for the development of a computerized thermal recognition system to detect knot anomalies. This dissertation investigated the use of high power (6 kW) quartz infrared halogen lamp heaters, and high power radio frequency (35 kW) to treat the piece to be inspected. The thermal response was obtained by an infrared image (512 by 480 pixels). Twelve species of wood were investigated. For this dissertation, a computerized thermal recognition system was developed using the optimal derived images to produce a technique to detect anomalies in images. The thermal recognition system to identify anomalies used a soft computing architecture for edge detection in this noisy environment. The principle of soft computing techniques is to arrive at a near-best solution with imprecise, incomplete, and marginal information by adopting a coherent strategy. This methodology recognizes that an optimum solution cannot be obtained but that a near or best-available solution may be just as workable when dealing with real systems. The technology described here evolves an object such that it becomes a replica of the object visualized and constantly compares the view and the image until it is fully-grown. In this research, this approach is referred to as "seedlet technology". Seedlet technology uses soft computational techniques to detect anomalies in images. The seedlet system consists of a discrete cosine transform (DCT) filter, a neural network, a seedlet, and a genetic algorithm. The DCT filter forms a preprocessing module to reduce noise on the image. The neural network provides information about the anomaly in which rules for the seedlet can be developed. In addition, the neural network forms an intelligent selective low-pass filter of the image. The seedlet then grows according to derived rules and by using information provided by the neural network. The seedlets remove noise on the image, and identify the approximate location of anomalies on the image. The genetic algorithm then manipulates parameters of the seedlets to optimize the location of the anomaly. At this point, the location of the anomaly has been determined. This technique was successfully applied for locating knot anomalies in wood.

Στα πλαίσια της βελτίωσης της εκπαιδευτικής διαδικασίας εστιάζοντας την προσοχή στο επιστημονικό αντικείμενο της τεχνητής νοημοσύνης, σχεδιάζονται και υλοποιούνται στα πλαίσια αυτής της διπλωματικής εργασίας ένα σύνολο από εκπαιδευτικές εφαρμογές ιστού. Πιο συγκεκριμένα, το αντικείμενο της διπλωματικής εργασίας είναι η δημιουργία και ένταξη ενός μαθησιακού υλικού με τη μορφή ασκήσεων εξάσκησης και ασκήσεων αξιολόγησης. Οι ασκήσεις εξάσκησης έχουν ως στόχο την εξοικείωση του φοιτητή με τις έννοιες της τεχνητής νοημοσύνης και διαβαθμίζονται με βάση τη βοήθεια που προσφέρουν για τη λύση του προβλήματος, ενώ οι ασκήσεις αξιολόγησης στοχεύουν στην βαθμολόγηση του επιπέδου γνώσης ενός φοιτητή. Οι ασκήσεις έχουν εγκατασταθεί σ’ ένα e-learning λογισμικό που ονομάζεται Ευφυές Σύστημα Διδασκαλίας Τεχνητής Νοημοσύνης το οποίο αποτελεί ένα σύστημα που περιέχει θέματα τεχνητής νοημοσύνης. Είναι ένα σύστημα που έχει ως στόχο να βοηθήσει το φοιτητή στη μελέτη του μαθήματος της τεχνητής νοημοσύνης Το υπόλοιπο της εργασίας ακολουθεί την παρακάτω δομή: Στο κεφάλαιο 2 γίνεται εισαγωγή στην εξ’ αποστάσεως εκπαίδευση, στο κεφάλαιο 3 παρουσιάζονται τα συστήματα E-learning, στη συνέχεια παρουσιάζονται τα Συστήματα Διαχείρισης Περιεχομένου, στο κεφάλαιο 4 γίνεται περιγραφή του σχεδιασμού διεπαφών, στη συνέχεια στο κεφάλαιο 5 περιγράφονται οι τεχνολογίες που χρησιμοποιήθηκαν καθώς επίσης και όλες οι ασκήσεις που υλοποιήθηκαν και τέλος το κεφάλαιο 6 ολοκληρώνει την εργασία με τα συμπεράσματα. / The work is based on creating exercises for search algorithms on intelligent system for teaching.

京都大学 / 新制・課程博士 / 博士(工学) / 甲第23173号 / 工博第4817号 / 新制||工||1753(附属図書館) / 京都大学大学院工学研究科都市社会工学専攻 / (主査)教授 堀 智晴, 教授 田中 茂信, 教授 角 哲也 / 学位規則第4条第1項該当 / Doctor of Philosophy (Engineering) / Kyoto University / DFAM

Product visual inspection is still performed manually or semi automatically in most industries from simple ceramic tile grading to complicated automotive body panel paint defect and surface quality inspection. Moreover, specular surfaces present additional challenges to conventional vision systems due to specular reflections, which may mask the true location of objects and lead to incorrect measurements. Some sophisticated optical inspection methods have already been developed for high precision surface defect inspection in recent years. Unfortunately, most of them are highly computational. Systems built on those methods are either inapplicable or costly to achieve real-time inspection. This thesis describes an integrated low-cost intelligent system developed to automatically capture and extract regular defects of the ceramic tiles with uniformly colored specular coatings. The proposed system is implemented on a group of smart cameras using its on-board processing ability to achieve real-time inspection. The results of this study will be used to facilitate the design of a robust, low-cost, closed-loop inspection system for a class of products with smooth specular coatings. The experimental results on real test panels demonstrate the effectiveness and robustness of proposed system.

Eichstätt-Ingolstadt, Univ., Diss., 2007

For intelligent systems, the ability to adapt a sensor's sensing capabilities offers promise for reducing numbers, weight, and volume of sensors required. This basic idea is in line with a recent assertion by the well-known roboticist Rodney Brooks, that versatile robots could be used to perform various tasks instead of requiring a large number of specialized robots.In the current work, we consider the concept of a "smart" sensor which could dynamically adapt itself to replace multiple static sensors--within the application area of ingestible smart pills, where small sensors might be required to detect problems such as bleeding or tumours.\\ Simulations were used to evaluate some basic strategies for how to adapt the sensor and their effectiveness was compared; as well, a hardware prototype using LEDs to indicate system switching was prepared.

No description available.

O crescente aumento na demanda de energia elétrica nacional, associada às alterações regulamentares do setor, em que o tempo que um equipamento permanece indisponível para o sistema, aguardando manutenção significa perda de receita para as companhias de energia, motivou a busca por diagnósticos precisos e utilização de técnicas não invasivas que possam ser aplicadas em transformadores em serviço. Assim, o foco desta pesquisa foi o desenvolvimento de uma arquitetura de sistema inteligente baseado em Redes Neurais Artificiais, que a partir de características extraídas de sinais de emissão acústicas provenientes de sensores distribuídos espacialmente no tanque de transformadores de potência, possa identificar internamente o local de ocorrência das descargas parciais e fornecer as distâncias estimadas entre os sensores e o ponto dessa descarga, e com essas distâncias, utilizando técnicas numéricas de triangulação, o sistema fornece também a coordenada espacial da falha auxiliando no diagnostico de defeito do transformador e no processo de tomada de decisões. / The increasing in the demand for national electrical energy coupled with alterations in the regulation of the sector, where the time which a piece of the electrical system equipment stays out of service means loss of income for the electrical companies, has motivated the search for correct diagnostics and usage of non-invasive technics that can be used in tranformers which are in operation. Therefore, the aim of this research was to develop the design of an intelligent system based on Artificial Neural Nets, which through the characteristics extracted from the acoustic emission signals coming from the sensors spatially distributed in the power transformer tank can identify internally the place of the occourrence of the partial discharges and provide the estimate distances between the sensors and the discharges point, so with these distances using triangle technical analysis the system will also provide the spatial coordinate of the flaw for diagnosing the problem with the transformer and help the process of decision making.

The human cognitive biases that result in anthropomorphism, the moral confusion surrounding the status of robots, and wider societal concerns related to the deployment of artificial intelligence at scale all motivate the study of robot transparency --- the design of robots such that they may be fully understood by humans. Based on the hypothesis that robot transparency leads to better (in the sense of more accurate) mental models of robots, I investigate how humans perceive and understand a robot when they encounter it, both in online video and direct physical encounter. I also use Amazon Mechanical Turk as a platform to facilitate online experiments with larger population samples. To improve transparency I use a visual real-time transparency tool providing a graphical representation of the internal processing and state of a robot. I also describe and deploy a vocalisation algorithm for transparency. Finally, I modify the form of the robot with a simple bee-like cover, to investigate the effect of appearance on transparency. I find that the addition of a visual or vocalised representation of the internal processing and state of a robot significantly improves the ability of a naive observer to form an accurate model of a robot's capabilities, intentions and purpose. This is a significant result across a diverse, international population sample and provides a robust result about humans in general, rather than one geographic, ethnic or socio-economic group in particular. However, all the experiments were unable to achieve a Mental Model Accuracy (MMA) of more than 59%, indicating that despite improved transparency of the internal state and processing, naive observers' models remain inaccurate, and there is scope for further work. A vocalising, or 'talking', robot greatly increases the confidence of naive observers to report that they understand a robot's behaviour when observed on video. Perhaps we might be more easily deceived by talking robots than silent ones. A zoomorphic robot is perceived as more intelligent and more likeable than a very similar mechanomorphic robot, even when the robots exhibit almost identical behaviour. A zoomorphic form may attract closer visual attention, and whilst this results in an improved MMA, it also diverts attention away from transparency measures, reducing their efficacy to further increase MMA. The trivial embellishment of a robot to alter its form has significant effects on our understanding and attitude towards it. Based on the concerns that motivate this work, together with the results of the robot transparency experiments, I argue that we have a moral responsibility to make robots transparent, so as to reveal their true machine nature. I recommend the inclusion of transparency as a fundamental design consideration for intelligent systems, particularly for autonomous robots. This research also includes the design and development of the 'Instinct' reactive planner, developed as a controller for a mobile robot of my own design. Instinct provides facilities to generate a real-time 'transparency feed'--- a real-time trace of internal processing and state. Instinct also controls agents within a simulation environment, the 'Instinct Robot World'. Finally, I show how two instances of Instinct can be used to achieve a second order control architecture.

Submitted by MIRIAM REGINA BORDINHON null (mrbfai@gmail.com) on 2017-03-22T18:37:51Z No. of bitstreams: 1 SISTEMA INTELIGENTE FUZZY PARA A CLASSIFICAÇÃO DOS FATORES DE RISCO À SAÚDE-versão final.pdf: 1868286 bytes, checksum: 940f29e8fd8b50bf8ac1da768e53ae79 (MD5) / Approved for entry into archive by Luiz Galeffi (luizgaleffi@gmail.com) on 2017-03-23T13:57:21Z (GMT) No. of bitstreams: 1 bordinhon_mr_dr_ilha.pdf: 1868286 bytes, checksum: 940f29e8fd8b50bf8ac1da768e53ae79 (MD5) / Made available in DSpace on 2017-03-23T13:57:21Z (GMT). No. of bitstreams: 1 bordinhon_mr_dr_ilha.pdf: 1868286 bytes, checksum: 940f29e8fd8b50bf8ac1da768e53ae79 (MD5) Previous issue date: 2017-03-10 / Nesta pesquisa, é abordado o desenvolvimento de um sistema inteligente visando à classificação (análise) dos fatores de risco à saúde numa visão amplamente adotada pelo Núcleo de Apoio à Saúde da Família (NASF). Trata-se de um recurso alternativo importante para a referida entidade, assim como para uso em outros núcleos similares. A base de dados no NASF é composta por informações procedentes de 376 pacientes alocados em setores numa divisão feita por bairros. Estes pacientes são assistidos, semanalmente, com atividades físicas e realização de exames de saúde. Os dados clínicos são armazenados numa base de dados configurada no MySQL 6.3. O sistema, baseado na teoria da lógica fuzzy, emprega uma métrica de inferência, um controlador fuzzy, de acordo com a concepção do dispositivo de defuzzificação proposto por Mamdani. Nesta pesquisa, é avaliado o desempenho do controlador lógico fuzzy, no qual é possível verificar as classificações de cada indicador como o índice de massa corporal, razão cintura/quadril, pressão arterial, níveis glicêmicos, síndrome metabólica, frequência cardíaca de repouso, colesterol total, LDL-C, HDL-C, triglicerídeos, circunferência abdominal, os quais compõem os principais parâmetros à análise. O sistema para o servidor é realizado usando a linguagem de programação C-sharp e do aplicativo web em Cordova. Em resumo, verifica-se que o programa do NASF pode ser melhor acompanhado pelos profissionais da área, que puderam obter uma visão do estado da saúde de cada paciente e, assim, direcionarem as atividades físicas adequadas para cada um dos participantes, além disso, o paciente terá à disposição, via smartphone, as principais informações sobre perfil da sua saúde permitindo a adoção de recursos com vistas à mitigação dos riscos à saúde dos pacientes. / This research addresses the development of an intelligent system focusing on the classification (analysis) of health risk factors through a point of view widely used by NASF (Family Health Support Group). It is an important alternative resource for this entity, as well as for the use of many others similar health support groups. NASF database is formed by information of more than 376 patients divided into sectors through a division made by neighborhoods. These patients are observed weekly, with physical activities and health exams. Clinical data is stored in a MySQL 6.3 defined database. The system, based on fuzzy logic theory, works with metric inference, a fuzzy controller according to the defuzzification process proposed by Mamdani. This research evaluated fuzzy logic controller performance, in which is possible to verify the classification of each indicator such as body mass index, waist/hip ratio, blood pressure, glicemic levels, metabolic syndrome, rest cardiac frequency, total cholesterol, LDL-C, HDL-C, triglycerides, abdomen circumference, which are the main parameters for analysis. The system development for the server was developed by using C-sharp and web Cordova. In short, it was possible to check that NASF program can have a better follow up by health professionals and obtain the patient status and, thus, direct adequate physical activity for each participant, furthermore, the patient will have his health profile by smartphone which allows resources to be used considering the mitigation of the risk for the patient’s health.