Unification of imprecise data - translation of fuzzy to multi-valued knowledge over Y-axis

Inference systems are a well-defined technology derived from knowledge-based systems. Their main purpose is to model and manage knowledge as well as expert reasoning to insure a relevant decision making while getting close to human induction. Although handled knowledge are usually imperfect, they may be treated using a non classical logic as fuzzy logic or symbolic multi-valued logic. Nonetheless, it is required sometimes to consider both fuzzy and symbolic multi-valued knowledge within the same knowledge-based system. For that, we propose in this paper an approach that is able to standardize fuzzy and symbolic multi-valued knowledge. We intend to convert fuzzy knowledge into symbolic type by projecting them over the Y-axis of their membership functions. Consequently, it becomes feasible working under a symbolic multi-valued context. Our approach provides to the expert more flexibility in modeling their knowledge regardless of their type. A numerical study is provided to illustrate the potential application of the proposed methodology.

Classification of Dental Radiographs Using Deep Learning

Objectives: To retrospectively assess radiographic data and to prospectively classify radiographs (namely, panoramic, bitewing, periapical, and cephalometric images), we compared three deep learning architectures for their classification performance. Methods: Our dataset consisted of 31,288 panoramic, 43,598 periapical, 14,326 bitewing, and 1176 cephalometric radiographs from two centers (Berlin/Germany; Lucknow/India). For a subset of images L (32,381 images), image classifications were available and manually validated by an expert. The remaining subset of images U was iteratively annotated using active learning, with ResNet-34 being trained on L, least confidence informative sampling being performed on U, and the most uncertain image classifications from U being reviewed by a human expert and iteratively used for re-training. We then employed a baseline convolutional neural networks (CNN), a residual network (another ResNet-34, pretrained on ImageNet), and a capsule network (CapsNet) for classification. Early stopping was used to prevent overfitting. Evaluation of the model performances followed stratified k-fold cross-validation. Gradient-weighted Class Activation Mapping (Grad-CAM) was used to provide visualizations of the weighted activations maps. Results: All three models showed high accuracy (>98%) with significantly higher accuracy, F1-score, precision, and sensitivity of ResNet than baseline CNN and CapsNet (p < 0.05). Specificity was not significantly different. ResNet achieved the best performance at small variance and fastest convergence. Misclassification was most common between bitewings and periapicals. For bitewings, model activation was most notable in the inter-arch space for periapicals interdentally, for panoramics on bony structures of maxilla and mandible, and for cephalometrics on the viscerocranium. Conclusions: Regardless of the models, high classification accuracies were achieved. Image features considered for classification were consistent with expert reasoning.

Penerapan Cobit 5 dalam Evaluasi Tata Kelola Teknologi Informasi (Studi Kasus: Dinas Perindustrian dan Perdagangan Provinsi Sumatera Utara)

The Department of Industri and Trade of North Sumatra Province is part of the government in the industrial and trade sector. In carrying out its operational activities, the use of information technology is used to support activities. Some problems that occur are the absence of a system for evaluating information technology governance that is used in a systematic manner. In examining the technology used, it only involves a few expert reasoning skills. The purpose of this study is to determine the extent of management and utilization of information technology in the Department of Industri and Trade of North Sumatra Province and to recommend information technology management policy proposals using COBIT version 5. The process of evaluating governance using COBIT begins with domain selection, primary and secondary data koleksi. , the mapping process, the next step is to process the questionnaire data and calculate the value and level of capability. The results of the application of COBIT 5 can explain the situation in resource optimization which includes planning, pengawasan, and adjustments to the implementation of processes and conditions that have not been met, such as making documentation regarding the management of relationships between business and information technology, making SOPs containing regulating coordination.

Using Framing as a Lens to Understand Context Effects on Expert Reasoning

Biologists frame fluid dynamics problems differently from physicists and engineers, which may have consequences for instruction and learning.

Combining UML Profiles to Design Serious Games Dedicated to Trace Information in Decision Processes

An expert assessment consists of an ordered series of decisions that have to respond to time-evolving information contexts. Improving decisions made in a risk context requires better knowledge of reasoning mechanisms. The authors think that serious games can constitute a rich observatory for reasoning and decisions. However, the design of these games is not trivial and is rarely scalable or reusable. This paper proposes a UML profile library for generically modeling expert reasoning in situations using serious games that involve risks. Two main UML profiles are dedicated to both serious games and gamer decisions traceability modeling. Complementary profiles address risk expert reasoning modeling and data quality modeling. The authors illustrate the approach using the design of a serious game about avalanche risk analysis.