Search

This research paper investigates the use of Deep learning and Auto-encoders (DAE) for the automated detection of cardiac arrest in human beings. We propose a new method for automated detection that utilizes auto encoders, a type of deep learning model, to detect abnormalities in the cardiovascular system. To achieve this, a dataset of cardiovascular heart disease was used to train and evaluate an auto encoder model. We confirm the efficacy of the proposed approach by evaluating its performance on a dataset of cardiac arrest patients. The results indicate that the proposed technique can accurately detect cardiac arrest in human beings yielding a high degree of accuracy rate of 93%. This study highlights the potential of using DAE for automated detection of cardiac arrest and provides a promising direction for further research in the field. Results from the model show that it is possible to accurately detect cardiac arrest in humans. The performance evaluation metrics are f-measure, accuracy, precision and recall. The proposed DAEalgorithm is compared with other existing approaches are ANN, BPNN, SVM, DT, XG Boost, RF, DNN and SAE.

The present study reports the first incidence of intersex in Cobia, Rachycentron canadum maintained at sea cages in the Gulf of Mannar, India. During the 10 year study period (2010–2019), at total of 815 broodstock (386 wild captured and 429 captive raised) were maintained under captivity in sea cages in the Gulf of Mannar, India for the purpose of seed production. Of which, 318 male and 252 female broods’ gonads were examined post-mortem following a natural death. Only one male fish was found with a visible gonadal anomaly. Microscopic analysis of gonad revealed the presence of both the characteristic female and male tissues in testes of a single specimen (testis-ova). Only the abnormal nodular portion contained primary oocytes, whereas the central testicular tissue contained spermatocytes and spermatids in the seminiferous lobules. This is the first reported intersex of cobia from the Gulf of Mannar, India. It could be interpreted as low-level rare incidence of natural aberration.

Wireless Sensor Networks (WSNs) are critical in numerous applications due to their ability to sense and transmit data. However, energy limitations of sensor nodes, powered by finite batteries, significantly impact network longevity. Traditional routing methods involving multi-hop transmissions and cluster formation can result in substantial energy consumption, particularly by Cluster Heads (CHs) involved in data aggregation and transmission. This research addresses the problem by optimizing energy-efficient routing using a Deep Belief Network (DBN) with Long Short-Term Memory (LSTM) for routing and CH selection. A mobile sink moving in a linear path minimizes energy consumption by reducing cluster formation and promoting single-hop transmissions. The proposed method utilizes LSTM-based CH selection to ensure that nodes with the highest residual energy are chosen, enhancing network lifetime. Experimental results demonstrate that the proposed method reduces energy consumption by up to 25% compared to circular path sink movement and multi-hop data transmission, resulting in a 40% increase in network lifetime. Performance was evaluated on a 100-node network with varying sink velocities, achieving an energy efficiency of 15% over traditional models. [ABSTRACT FROM AUTHOR]

Two primary methods for treating ventral hernias are laparoscopic and open surgery. Shorter hospital stays and less discomfort following surgery are two advantages of laparoscopic surgery. Studies have also shown that laparoscopic surgery has fewer complications than open surgery. The aim of this study was to compare the outcomes, complications, length of stay, discomfort following surgery, and return to work between laparoscopic and open ventral hernia repairs. Methods This was a prospective observational study with 50 patients over the age of 18 that was carried out at the Government Medical College in Vellore between 2020 and 2022. Purposive sampling was used to choose 25 patients for each group. On postoperative days 1, 3, and 5, the visual analog scale was used to calculate the amount of pain following surgery. On postoperative days 3, 5, 7, and 4, the Eura HS quality of life scale was calculated. Results of the surgery were noted in terms of the emergence of a seroma, wound, or mesh infection. Patients were monitored for up to a year following surgery, starting one and two weeks later. Pearson's chi squared test and Fischer's exact test were used for statistical analysis. Results The majority of the groups started oral intake within 6 hours, with no difference in the time required to start oral fluids. Infections from wounds occurred 72% of the time in the traditional group and none at all in the laparoscopic group. Hospital stay was substantially shorter in the laparoscopic group (2.4 ± 0.5 days) than in the traditional group (7.32 ± 1.07 days) (p < 0.001). While 76% of patients in the laparoscopic group returned to normal activity in less than 14 days, all patients in the traditional group-all but one-took more than that amount of time. There was a statistically significant difference (p < 0.001). Suture removal occurred 7.84 ± 0.69 days earlier in the laparoscopic group than in the traditional group (p < 0.001). Conclusion Compared to open hernia repair, LVHR (Laparoscopic Ventral Hernia Repair) has several advantages, including shorter recovery times, shorter hospital stays, and an earlier return to regular activity with fewer problems. [ABSTRACT FROM AUTHOR]