Decomposition aided attention-based recurrent neural networks for multistep ahead time-series forecasting of renewable power generation.

Renewable energy plays an increasingly important role in our future. As fossil fuels become more difficult to extract and effectively process, renewables offer a solution to the ever-increasing energy demands of the world. However, the shift toward renewable energy is not without challenges. While fossil fuels offer a more reliable means of energy storage that can be converted into usable energy, renewables are more dependent on external factors used for generation. Efficient storage of renewables is more difficult often relying on batteries that have a limited number of charge cycles. A robust and efficient system for forecasting power generation from renewable sources can help alleviate some of the difficulties associated with the transition toward renewable energy. Therefore, this study proposes an attention-based recurrent neural network approach for forecasting power generated from renewable sources. To help networks make more accurate forecasts, decomposition techniques utilized applied the time series, and a modified metaheuristic is introduced to optimized hyperparameter values of the utilized networks. This approach has been tested on two real-world renewable energy datasets covering both solar and wind farms. The models generated by the introduced metaheuristics were compared with those produced by other state-of-the-art optimizers in terms of standard regression metrics and statistical analysis. Finally, the best-performing model was interpreted using SHapley Additive exPlanations.

A Correlation Study of the Colorectal Cancer Statistics and Economic Indicators in Selected Balkan Countries.

Colorectal cancer (CRC) is one of the most commonly diagnosed malignant neoplasms. The aim of the study was to evaluate and correlate most important epidemiological and economic indicators of CRC in 11 selected Balkan countries. The number of new CRC cases was 56,960, and the highest 5-year CRC prevalence was in Slovenia, Croatia, and Greece. Age-standardized CRC incidence rates were highest in Slovenia, Serbia, and Croatia, and age-standardized mortality rates were highest in Croatia, Serbia, and Bulgaria. Current Health Expenditure as % of Gross Domestic Product was the highest in Bosnia and Herzegovina and Serbia. The GDP per capita levels have shown positive correlation with the CRC incidence rate and prevalence. Absolute numbers of new and death-related CRC cases and 5-year prevalence in absolute numbers have shown strong positive correlation with GDP in million current US$. It has been shown that various economic indicators can be linked to the rate of incidence and prevalence of the CRC patients in the selected Balkan countries. Therefore, economic factors can influence the epidemiology of CRC, and heavy CRC burden in the Balkan region may be one of the indexes of the economic development.

Approach to frequency estimation in self-mixing interferometry: multiple signal classification.

Based on the nature of self-mixing signals, we propose the use of the multiple signal classification (MUSIC) algorithm in place of the fast Fourier transform (FFT) for processing signals obtained from self-mixing interferometry (SMI). We apply this algorithm to two representative SMI measurement techniques: range finding and velocimetry. Applying MUSIC to SMI range finding, we find its signal-to-noise ratio performance to be significantly better than that of the FFT, allowing for more robust, longer-range measurement systems. We further demonstrate that MUSIC enables a fundamental change in how SMI Doppler velocity measurement is approached, letting one discard the complex fitting procedure and allowing for a real-time frequency estimation process.

Perineal endometriosis in episiotomy scar with anal sphincter involvement: report of two cases and review of the literature.

Perineal endometriosis with anal sphincter involvement is a rare occurrence with only nine cases reported so far. Two such cases are presented, and the literature is reviewed. In presented cases, diagnosis was suspected at clinical exam. Anal manometry was performed in both cases and endoanal ultrasound in one case. Wide surgical excision of endometriotic mass together with part of external anal sphincter was carried out in both cases. The procedure was followed by anal sphincter reconstruction in an "overlapping" fashion in the first and "apposition" technique in the second case. Histopathologic tests confirmed endometriosis. The recovery was uneventful in both cases with excellent functional results. Two years after the operation, patients are asymptomatic and fully continent. According to the literature and our own experience, wide excision of endometrioma with primary sphincteroplasty seems to be the best chance of cure with satisfactory functional results and should be recommended.