Movements of Diplodus sargus (Sparidae) within a Portuguese coastal Marine Protected Area: Are they really protected?

Mark-recapture tagging and acoustic telemetry were used to study the movements of Diplodus sargus within the Pessegueiro Island no-take Marine Protected Area (MPA), (Portugal) and assess its size adequacy for this species' protection against fishing activities. Therefore, 894 Diplodus sargus were captured and marked with conventional plastic t-bar tags. At the same time, 19 D. sargus were tagged with acoustic transmitters and monitored by 20 automatic acoustic receivers inside the no-take MPA for 60 days. Recapture rate of conventionally tagged specimens was 3.47%, most occurring during subsequent marking campaigns. One individual however was recaptured by recreational fishermen near Faro (ca. 250 km from the tagging location) 6 months after release. Furthermore, three specimens were recaptured in October 2013 near releasing site, one year after being tagged. Regarding acoustic telemetry, 18 specimens were detected by the receivers during most of the study period. To analyse no-take MPA use, the study site was divided into five areas reflecting habitat characteristics, three of which were frequently used by the tagged fish: Exterior, Interior Protected and Interior Exposed areas. Information on no-take protected area use was also analysed according to diel and tidal patterns. Preferred passageways and permanence areas were identified and high site fidelity was confirmed. The interaction between tide and time of day influenced space use patterns, with higher and more variable movements during daytime and neap tides. This no-take MPA proved to be an important refuge and feeding area for this species, encompassing most of the home ranges of tagged specimens. Therefore, it is likely that this no-take MPA is of adequate size to protect D. sargus against fishing activities, thus contributing to its sustainable management in the region.

Improving Bangla ocr output through correction algorithms

Bangla OCR (Optical Character Recognition) is a long deserving software for Bengali community all over the world. Numerous e efforts suggest that due to the inherent complex nature of Bangla alphabet and its word formation process development of high fidelity OCR producing a reasonably acceptable output still remains a challenge. One possible way of improvement is by using post processing of OCR’s output; algorithms such as Edit Distance and the use of n-grams statistical information have been used to rectify misspelled words in language processing. This work presents the first known approach to use these algorithms to replace misrecognized words produced by Bangla OCR. The assessment is made on a set of fifty documents written in Bangla script and uses a dictionary of 541,167 words. The proposed correction model can correct several words lowering the recognition error rate by 2.87% and 3.18% for the character based n- gram and edit distance algorithms respectively. The developed system suggests a list of 5 (five) alternatives for a misspelled word. It is found that in 33.82% cases, the correct word is the topmost suggestion of 5 words list for n-gram algorithm while using Edit distance algorithm the first word in the suggestion properly matches 36.31% of the cases. This work will ignite rooms of thoughts for possible improvements in character recognition endeavour.