Search

This work modifies the architecture of conventional CNN with the integration of Multi-resolution Analysis (MRA) in a CNN framework for Diabetic Retinopathy (DR) diagnosis and grading. Here, the HF sub-bands are subjected to optimized activations and are directly fed to the fully connected layers, as it encompasses edge features. Unlike FD-Relu, the proposed function preserves significant negative coefficients, compared to the S-Relu, the proposed third-order S-Relu is optimized such that it sustains the activations in the range suitable for the wavelet coefficients. The coefficients of higher-order terms of the proposed 3rd-order S-Relu are optimized with PSO, fitting the maximum energy of the wavelet sub-bands to ensure High Frequency (HF) edge preservation. The authors re-architecture 3 different CNNs published in the Retinal Image analysis field, with spatial and wavelet inputs with optimized activations. The highest accuracy of 96% is attained with the AlexNet re-architecture, with 35,126 fundus images secured from the Kaggle dataset. As we can infer the proposed re-architecture wavelet CNN outperformed the multiscale shallow CNNs, multiscale attention net, and stacked CNNs with a 6.6, 0.3, 0.7 per cent increase in accuracy. The entire implementation of the wavelet CNN is made available under source code.

Background: Ureteropelvic junction obstruction (UPJO) is the most common cause of antenatal hydronephrosis. Although majority of them improve with time, none of the existing diagnostic modalities can accurately predict which hydronephrotic kidney is at the risk of progressive renal damage and will benefit from early surgery. Postural variations in the anteroposterior pelvic diameter (APPD) of the hydronephrotic kidney in children during follow-up postnatal ultrasonography (USG) reflect the intrapelvic tension, which might help in predicting the need of surgery amongst these patients. Materials and Methods: We designed this prospective observational study in all unilateral UPJO patients on postural variation in the APPD of renal pelvis on ultrasonography. The mean age of all patients were 2.15 years (0-5 years) and managed at our institute at All India Institute of Medical Sciences, Bhubaneswar. The study duration was from July 2019 to May 2021. The management of these patients was done as per the standard institutional protocol and there was no deviation due to inclusion in this study. We documented the variations in postural APPD both amongst the conservatively managed group and the surgically managed group of patients. Linear correlation between two continuous variables was explored using Pearson’s correlation (if the data were normally distributed) and Spearman’s correlation (for non-normally distributed data). Results: We found a higher prone APPD than supine APPD in all these patients indicating the obstruction at ureteropelvic junction. However, in the surgical group, there was less variation in the postural APPD compared to the conservative group, and when there was no variation in the postural APPD, the need of surgery was 100%. The limitation of our study was the small sample size (n = 36). A study involving a larger population or involving multiple institutions may further add significance to our findings. Conclusion: We found less postural variation in APPD on USG to be more likely associated with severe UPJO requiring early surgery. This may indicate a non-compliant renal pelvis. However, it was statistically not significant.

One new species and three new records of Tomocerus have been reported for the first time from India. The new species Tomocerus sikkimensis sp. nov. discovered from Gangtok, Sikkim (India) has been illustrated and described here. The new species differs from others in dental spine number, arrangement and mucro teeth number. Tomocerus (Ocreatomurus) qinae Yu, Yan & Liu, 2016, Tomocerus (Tomocerus) minor (Lubbock, 1862) and Tomocerus (Ocreatomurus) paraspinulus Gong, Qin & Yu, 2018 are the first time reported from the Indian states Arunachal Pradesh and West Bengal respectively. A key to the Indian species of Tomocerus has also been provided.

Six Collembola species from five families and two orders are for the first time recorded from India. All the described new records are mainly from two states, West Bengal and Arunachal Pradesh and collected from the surveys conducted in the Eastern Himalayan Region. Sphyrotheca multifasciata (Reuter, 1881) (Sminthuridae), Sminthurinus bimaculatus Axelson, 1902 (Katiannidae), Dicranocentrus nepalensis Mari Mutt & Bhattacharjee, 1980 (Orchesellidae), Isotomurus plumosus Bagnall, 1940 (Isotomidae), Isotomurus pseudopalustris Carapelli, Frati, Fanciulli & Dallai, 2001, (Isotomidae), Willowsia jacobsoni (Börner, 1913) (Entomobryidae), are the Collembola species whose occurrence is first time observed in India. As a result of the present work Collembola fauna of India reached up to 348 species. Material examined, a brief description and microscopic images of the new records are provided in the present study.

Abstract With the tremendous increase in the number of vehicles, the dense traffic created can lead to accidents and fatalities. In a traffic system, the costs for accidents are immeasurable. Numerous studies have been carried out to predict the cost of fatal accidents but have provided the actual values. Therefore, in this study, a monkey-based modular neural system (MbMNS) is developed to identify accident cost. The accident cases and cost data were collected and preprocessed to remove the noise, and the required features were extracted using the spider monkey function. Based on the extracted features, the accidents and the costs were identified. For rail engineering, this will support evaluating the number of railroad crossing accidents with different time intervals. The impact of every accident was also measured with different cost analysis constraints, including insurance, medical, and legal and administrative costs. Therefore, the present study contributes to the field by collecting and organizing the present railroad level crossing accident data from crossing inventory dashboards. Then, the introduction of a novel MbMNS for the cost analysis is the primary contribution of this study to further enrich the railroad level crossing protection system. The third contribution is the tuning of the prediction layer of a modular neural network to the desired level to achieve the highest predictive exactness score. Hence, the designed MbMNS was tested in the Python environment, and the results were validated with regard to recall, accuracy, F-measure, precision, and error values; a comparative analysis was also conducted to confirm the improvement. The novel MbMNS recorded high accuracy of 96.29% for accident and cost analysis, which is better than that reported for other traditional methods.

Global warming is causing industrial development to increase greenhouse gas emissions, impact power provider economies, and potentially pose a solution through renewable energy. In order to solve these issues, the research offers a dual strategic auction difficulty for renewable energy market clear prices (MCPs) to maximize supplier and buyer revenues while mitigating rival unpredictability and renewable vacillation power supply sources. The study uses scenario reduction techniques, including Beta and Weibull distribution of probability, forward-reduction technique, and underestimation and overestimation of the cost function to manage uncertainties in renewable energy. The Gravitation Search algorithm and a hybrid approach ordered weighted average distance (OWAD) combined, with Topsis operational gravitational search algorithm TOGSA (OWAD-TOGSA), are used to solve the multi-objective issue. The study evaluates the performance of IEEE standard 30-bus and 57-bus test systems and an Indian 75-bus operational system to solve a problem involving wind and sun energy in spite of its volatility. The proposed bidding approach is feasible and could increase revenue by nearly 10 %, potentially improving efficiency for electric energy-producing utilities and consumers, and its findings will be beneficial for similar research using optimization techniques.