Rough fuzzy MLP: knowledge encoding and classification

A scheme of knowledge encoding in a fuzzy multilayer perceptron (MLP) using rough set-theoretic concepts is described. Crude domain knowledge is extracted from the data set in the form of rules. The syntax of these rules automatically determines the appropriate number of hidden nodes while the dependency factors are used in the initial weight encoding. The network is then refined during training. Results on classification of speech and synthetic data demonstrate the superiority of the system over the fuzzy and conventional versions of the MLP (involving no initial knowledge)     

Tele-rheumatology: telephone follow up and cyberclinic

This paper reviews here the main practical applications of telemedicine with particular reference to telephone care by health professionals to patients. A pilot project of out-patient telephone follow-up service for continuity of ambulatory rheumatology patients is described and recommendations are provided for those keen to develop such a service. In a later section newer technologies such as the potential practical applications of the internet and e-mail are described with the setting up of a cyber project for rheumatology and osteoporosis patients. It is noted that despite enthusiasm and development of such new projects, conventional clinicians need further longer term observation to grasp the advantages and pitfalls before more widespread use of telemedicine becomes commonplace.     

Some novel classifiers designed using prototypes extracted by a newscheme based on self-organizing feature map

We propose two new comprehensive schemes for designing prototype-based classifiers. The scheme addresses all major issues (number of prototypes, generation of prototypes, and utilization of the prototypes) involved in the design of a prototype-based classifier. First we use Kohonen's self-organizing feature map (SOFM) algorithm to produce a minimum number (equal to the number of classes) of initial prototypes. Then we use a dynamic prototype generation and tuning algorithm (DYNAGEN) involving merging, splitting, deleting, and retraining of the prototypes to generate an adequate number of useful prototypes. These prototypes are used to design a "1 nearest multiple prototype (1-NMP)" classifier. Though the classifier performs quite well, it cannot reasonably deal with large variation of variance among the data from different classes. To overcome this deficiency we design a "1 most similar prototype (1-MSP)" classifier. We use the prototypes generated by the SOFM-based DYNAGEN algorithm and associate with each of them a zone of influence. A norm (Euclidean)-induced similarity measure is used for this. The prototypes and their zones of influence are fine-tuned by minimizing an error function. Both classifiers are trained and tested using several data sets, and a consistent improvement in performance of the latter over the former has been observed. We also compared our classifiers with some benchmark results available in the literature.     

An evaporated multilayer thin film RC notch filter

The fabrication and characteristics of multilayer film C-R-NC filters are discussed. The results of experimental study are found to be in good agreement with the theory. The circuit is suitable for fabrication in hybrid integrated circuit technology as it yields better performance than equivalent R-C-NR structures in certain active configurations.     

Some life history parameters and production of Daphnia carinata (king) grown in different culturing media

Estimates of the abundance and production of Daphnia carinata in six mass culture experiments revealed higher values in the cow dung medium compared with other manures tested. Average production ranged from 1.2 to 223 mg m⁻³ wk⁻¹ and average biomass of the population from 1.3 to 194 mg m⁻³ wk⁻¹. The P/B coefficient was highest in the mohua (Madhuca indica) oil cake (1.15) and lowest in the poultry manure (0.77). Daphnia started reproducing at the age of 6–9 days in different culture media. Longevity was higher in the field ( 36 days) than in the laboratory. The total numbers of offspring per female was closely correlated with the mean number of eggs per female in her life span. The intrinsic rate (r) and the finite rate (e') of population of growth of Daphnia were markedly higher in the field than in the laboratory.     

Effect of Cryogenic Pre-Treatment on Breakage Characteristics of Rocks

Improvement of energy efficiency in comminution of rocks using various pretreatment methods is being explored worldwide. This paper presents experimental data on breakage characteristics of granite and sandstone using cryogenic pre-treatment. The samples were treated with varying duration of immersion in liquid nitrogen. Combined pretreatment using oven heating followed by quenching in liquid nitrogen were also explored. The results indicate that using cryogenic pretreatment uniaxial tensile strength of granite can be decreased by more than 40% while in uniaxial compressive strength about 28% reduction is possible. For sandstone as much as 33% reduction in uniaxial compressive strength was observed.

     

Plasma insulin and growth hormone during antarctic residence

A 50-year-old female developed a swelling in the epigastrium which later ruptured to form a sinus. A diagnosis of primary cutaneous cryptococcosis was made with the help of histopathology and microbiological studies. Treatment with amphotericin-B and 5-flucytosine gave a good therapeutic response and the sinus healed within 2 months.