Blind colour separation of H&E stained histological images by linearly transforming the colour space

Blind source separation methods aim to split information into the original sources. In histology, each dye component attempts to specifically characterize different microscopic structures. In the case of the hematoxylin–eosin stain, universally used for routine examination, quantitative analysis may often require the inspection of different morphological signatures related mainly to nuclei patterns, but also to stroma distribution. Stain separation is usually a preprocessing operation that is transversal to different applications. This paper presents a novel colour separation method that finds the hematoxylin and eosin clusters by projecting the whole space to a folded surface connecting the distributions of a series of planes that divide the cloud of H&E tones. The proposed method produces density maps closer to those obtained with the colour mixing matrices set by an expert, when comparing with the density maps obtained using nonnegative matrix factorization (NMF), independent component analysis (ICA) and a state‐of‐the‐art method. The method has outperformed three baseline methods, NMF, Macenko and ICA, in about 8%, 12% and 52% for the eosin component, whereas this was about 4%, 8% and 26% for the hematoxylin component.     

ORDERING FUZZY SETS BY CONSENSUS CONCEPT AND FUZZY RELATION EQUATIONS

A general class of consensus measures of fuzzy sets is introduced in this paper. It is shown that, while the consensus measures are valuations but neither isotone nor antitone with respect to the lattice structure induced by the pointwise maximum and minimum operations to the set of all the fuzzy sets on a nonempty crisp set, they are antitone valuations with respect to the lattice structure induced by the generalized sharpening relation to a quotient set of the set of fuzzy sets. It is also shown that the solutions of a finite fuzzy relation equation that have the maximum consensus measure can be characterized through the join operation of the latter lattice in terms of the maximum solution and some of the minimal solutions of the equation.     

Planning tool requirements for flexible manufacturing: an analytical approach

The problem of tool and fixture resources dimensioning is considered and examined for a productive environment with flexible features. With reference to previous studies, different tool management strategies are pointed out and commented upon; a further control policy based on workpiece batching is suggested and tested. In the second section of the paper, an analytical interpretation of the question in hand is presented and discussed; the effectiveness of the procedure itself is tested by comparing analytical data with results derived from the detailed simulation of a real tool management area. Results are shown in the last section     

ARTIFICIAL INTELLIGENCE GOES MOBILE

New mobile computing technologies require new paradigms for infrastructure and interaction with mobile and networked devices. For building smart mobile companions for new intelligent services, a number of challenges have to be addressed. We argue that artificial intelligence is a key to a new generation of mobile systems. In this introduction to AI in mobile systems, we present some of the challenges and solutions in this exciting field of research.     

Fatty acid profile of milk from goats fed diets with different levels of conserved and fresh forages

Aim of the study was to evaluate the effect of different proportions of hay and fresh grass in goats’ diet on milk fatty acid profile. Nine Camosciata goats were fed a fixed amount of concentrate (30% of total diet) and different percentages (40% vs 30%, 50% vs 20% and 60% vs 10%) of hay and fresh grass, respectively. Diminishing amounts of fresh grass percentages in the diet led to significant increases of lauric, myristic and palmitic acids (P ≤ 0.001) and to significant decreases of C18:1 t6‐11, rumenic and α‐linolenic acids (P ≤ 0.001) in milk, thus determining a worsening of the health value of milk fat.     

AN EXPERT SYSTEM FOR ACADEMIC COUNSELING

In recent years, high enrollment has greatly increased the counseling loads of academic advisors at American colleges and universities. Expert systems can assist academic counselors by solving a relatively easy class of problems which deal with the most encountered cases. In this paper, a prototype expert system, CLASS COUNSELOR, is presented. CLASS COUNSELOR recommends a set of courses after an interactive session with the student. It handles the upper division courses of the undergraduate program in the Department of Electrical Engineering, University of Florida. The program runs on IBM-AT personal computers and compatibles.     

Advanced spinning disk‐TIRF microscopy for faster imaging of the cell interior and the plasma membrane

Understanding the cellular processes that occur between the cytosol and the plasma membrane is an important task for biological research. Till now, however, it was not possible to combine fast and high‐resolution imaging of both the isolated plasma membrane and the surrounding intracellular volume. Here, we demonstrate the combination of fast high‐resolution spinning disk (SD) and total internal reflection fluorescence (TIRF) microscopy for specific imaging of the plasma membrane. A customised SD‐TIRF microscope was used with specific design of the light paths that allowed, for the first time, live SD‐TIRF experiments at high acquisition rates. A series of experiments is shown to demonstrate the feasibility and performance of our setup.     

A NOTE: EFFECTS OF LOGARITHMIC TRANSFORMATIONS OF NONLINEAR GOALS IN THE GOAL PROGRAMMING PROBLEM

This note points out that in the context of goal programming the linearization of nonlinear goals by logarithmic transformations, as it is usually done in the field of mechanical engineering applications, is not in general a valid method and can lead to wrong results.     

DESIGNING COMPLEX SYSTEMS WITHIN DISTRIBUTED ARCHITECTURES: AN INTELLIGENT TUTORING SYSTEMS PERSPECTIVE

The goal of this work is to introduce the basic concepts of distributed artificial intelligence as new methodologies to conceive and realize complex intelligent systems. We focused our attention on the design of intelligent tutoring systems, and using a distributed framework, we reached a fine control on the communicability process, one of the key issues in the realization of intelligent tutoring systems. A prototype is presented as an open information system in which classical modules, such as the domain expertise module and the tutor, are seen as populations of intelligent actors that share their fragmentary knowledge and organize their tasks in a concurrent universe in order to accomplish a common goal, the teaching session. The system has been written in a concurrent object-oriented language, realized on top of the Common Lisp Object System.     

Stochastic approximation and realization of Hankel matrices

Dynamic systems are considered whose outputs can be represented either by a deterministic series of the input variables or by a stochastic series of brownian motion processes. Approximate representations of such series are proposed. The representations are based on the Hankel matrix representation of the series. First, it is shown that any Hankel matrix, belonging to suitable classes, can be approximated in the deterministic and stochastic sense by finite rank Hankel matrices. Then, a method is proposed to design bilinear realizations of finite rank Hankel matrices, effective in the deterministic and stochastic sense.