PerSummRe

The size of Wikipedia grows exponentially every year, due to which users face the problem of information overload. We purpose a remedy to this problem by developing a recommendation system for Wikipedia articles. The proposed technique automatically generates a personalized synopsis of the article that a user aims to read next. We develop a tool, called PerSummRe, which learns the reading preferences of a user through a vision-based analysis of his/her past reads. We use an ensemble non-invasive eye gaze tracking technique to analyze user’s reading pattern. This tool performs user profiling and generates a recommended personalized summary of yet unread Wikipedia article for a user. Experimental results showcase the efficiency of the recommendation technique.

Evaluation of Diagnostic Performance of Machine Learning Algorithms to Classify the Fetal Heart Rate Baseline from Cardiotocograph

Cardiotocography (CTG) is the widely used cost-effective, non-invasive technique to monitor the fetal heart and mother’s uterine contraction pressure to assess the wellbeing of the fetus. The most important parameters of fetal heart is the baseline upon which the other parameters viz. acceleration, deceleration and variability depend. Accurate classification of the baseline into either normal, bradycardia or tachycardia is thus important to assess the fetal-health. Since visual estimation has its limitations, the authors use various Machine Learning Algorithms to classify the baseline. 110 CTG traces from CTU-UHB dataset, were divided into three subsets using stratified sampling to ensure that the sample is the accurate depiction of the population. The results were analyzed using various statistical methods and compared with the visual estimation by three obstetricians. FURIA provided greatest accuracy of 98.11%. From the analysis of Bland-Altman Plot FURIA was also found to have best agreement with physicians’ estimation.

A new approach to mark termites (Cornitermes cumulans (Kollar) Blattodea: Isoptera) for laboratory bioassays

Behavioral lab bioassays involving termites must be promptly performed to allow intended observations prior to death from dissecation, typical of these soft-bodied insects. To this end, topic markers have been proposed as an alternative to histological stains which, while not always toxic are inevitably lengthy to apply. Among recommended topic markers, gouache is easy to apply, dries out quickly, but it is known affect termites in the long run, being suitable only to short-term bioassays. Its alternative, colored glue, is also easy to apply, but it takes long to dry and it is too dense and heavy, being thus prone to affect termite walking patterns. Here we tested a mix of gouache and colored glue aiming to combine the qualities of both into a suitable topical marker for Cornitermes cumulans termites. Similar patterns of survival presented by marked and unmarked termites ruled out concerns about toxicity of this mixture. Such results were consistent across distinct group densities evidencing that the mixture does not interfere with, nor it is affected by, crowding effects. Because crowding regulates interindividual interactions and these underlie most behaviors, the mixture can be thought to be suitable to behavioral studies. We argue that this 1:2 glue:gouache mixture is an excellent alternative to mark termites for lab bioassays. Being atoxic, cheap, easy to apply, and non-invasive, this mixture may happen to be useful not only for termites but also in bioassaying other similarly soft-bodied insects.

Chemical characterization and effects of volatile oil of Alpinia zerumbet on the quality of collagen deposition and caveolin-1 expression in a muscular fibrosis murine model

This study evaluated the effect of the volatile oil of Alpinia zerumbet (VOAz) on caveolin-1 gene expression and muscular fibrosis. The rats were immobilized to induce fibrosis of the gastrocnemius muscle, and they were treated with VOAz. Collagen quality was assessed by histology and the expression of the caveolin-1 (CAV-1) gene was evaluated using qPCR. Histomorphological analysis indicated a significant reduction in the perimeter, width, and intensity of collagen in the treated groups, thus showing that the oil was effective in regulating the quality of collagen at the three concentrations. The results of expression levels suggested a decrease in the lesioned group and in two treatment groups (0.0115 µg/g and 0.009 µg/g). However, with the lowest concentration (0.0065 µg/g), no significant difference was observed, with levels similar to those found in healthy tissue. Therefore, the results showed that VOAz has the potential to be a non-invasive and low-cost alternative to aid in the treatment of muscular fibrosis.

PerSummRe

The size of Wikipedia grows exponentially every year, due to which users face the problem of information overload. We purpose a remedy to this problem by developing a recommendation system for Wikipedia articles. The proposed technique automatically generates a personalized synopsis of the article that a user aims to read next. We develop a tool, called PerSummRe, which learns the reading preferences of a user through a vision-based analysis of his/her past reads. We use an ensemble non-invasive eye gaze tracking technique to analyze user’s reading pattern. This tool performs user profiling and generates a recommended personalized summary of yet unread Wikipedia article for a user. Experimental results showcase the efficiency of the recommendation technique.

Improving hemoglobin estimation accuracy through standardizing of light-emitting diode power

Nowadays, hemoglobin monitoring is essential during surgeries, blood donations, and dialysis. Which are normally done using invasive methods. To monitor hemoglobin, a non-invasive hemoglobin meter was developed with five fixed light-emitting diode (LED) wavelengths at 670 nm, 770 nm, 810 nm, 850 nm, 950 nm and controlled using an Arduino Uno embedded development board. A photodetector with an on-chip trans-impedance amplifier was utilized to acquire the transmitted signal through the finger using the photoplethysmography (PPG) principle. Before the standardization of LED power, we had tested the designed system on fifteen subjects for the five wavelengths and estimated the hemoglobin with an accuracy of 96.51% and root mean square error (RMSE) of 0.57 gm/dL. To further improve the accuracy, the LED power was standardized and the PPG signal was reacquired on the same subjects. With this, the accuracy improved to 98.29% and also reduced the RMSE to 0.36 gm/dL. The designed system with LED power standardization showed a good agreement with pathology results with the coefficient of determination R²=0.981. Also, Bland–Altman analysis was used to evaluate the designed system and it showed good agreement between the two measurements.