Search

Visual impairment, such as cataract, if not detected and treated early, might lead to blindness. Cataract detection still takes a long time and is quite subjective, depending on ophthalmologist's preference. To expedite cataract screening procedure, an automated cataract detection system should be developed. Fundus image analysis for automatic categorization and grading of cataracts has the potential to reduce the burden of competent ophthalmologists while also assisting cataract patients in learning about their diseases and getting treatment suggestions. The optic disc and blood vessel data play a significant role in the detection and grading of cataracts. Normal, mild, moderate, and severe cataract stages are differentiated based on texture, colour, size, and contrast. Classification and severity rating are carried out using random forest classifier, an ensemble machine-learning method. The accuracy discovered is equivalent to prior study in the literature. This study is expected to help doctors detect cataracts early and prevent cataract-related suffering.

Technology is now playing a critical role in many industries to overcome challenges and get better and optimum results. The farming industry in India significantly affects the country's economy. The agricultural sector continues to employ half of the nation's workforce. The majority of agricultural activities in the nation still use outdated methods, and technical advancement is modest. Effective technology can be applied to this industry to maximize yield and minimize difficulties. Thus, based on the weather, moisture, and season, the machine learning-based farming solution may provide a crop recommendation system that aids farmers in selecting the appropriate crop to sow in their field. This work used six classifiers to recommend best fitted crop depending on soil as well as environmental parameters. It has been observed that the highest accuracy score has been achieved by Naïve Bayes followed by SVM – SVC, decision tree, KNN, SVM – NuSVC, and logistic regression classifier.

In the current work we have used the deep learning based long short-term memory model to predict the strength and peak time of solar cycle 25 by employing the monthly smoothed sunspot number data obtained from WDC-SILSO, Royal Observatory of Belgium, Brussels. We have used the stacked LSTM forecasting model to predict the upcoming cycle 25. From our analysis it has been shown that our proposed model is capable of capturing long term dependencies as well as trend within the data. For cycle 20 and 21 the error difference between predicted as well as observed peak value is 2.3 and 0.7 respectively while the peak prediction error is 1.47% and 0.30%. The RMSE of the model for cycle 20 and 21 is 3.97 and 4.34 respectively. For cycle 22, the AE and RE is 4.6 and 2.16% while the RMSE of the model for this case is 4.50. The predicted peak amplitude of solar cycle 23 and 24 from our proposed model has a relative error of 1.75% and 1.99% respectively from the observed value while the RMSE is 3.4 for cycle 23 and 4.2 for cycle 24. Our projected prediction of cycle 25 using the proposed LSTM model, says that it will be stronger than cycle 24 and weaker than cycle 23. The solar cycle 25 will peak with an amplitude of sunspot number at 171.9 ± 3.4 and will be 47 % stronger than cycle 24. The solar cycle 25 will reach its peak in August 2023 ± 2 months.

Purpose: Patient wait time for every single fraction of every patient treated at our centre for the past year has been presented in this study. The waiting time data were analysed across different treatment sites and modalities. Materials and Methods: Between March 2021 and March 2022, all patients and their corresponding recorded measurements of waiting time were analysed. Times recorded included check-in time (CK), scheduled time to start treatment (SC) and beam-on time for the first beam of therapy (ST). SPSS version 18 was used for statistical calculations, correlations and assessing significance. Results: A total of 181 patients were treated during this duration. The total number of radiotherapy (RT) sessions recorded was 3011. Out of these 3011 sessions, number of times treated by rapid arc (RA), intensity-modulated radiotherapy (IMRT), three-dimensional conformal radiotherapy (3DCRT), stereotactic body radiotherapy (SBRT), stereotactic radiosurgery and stereotactic radiotherapy (SRS/SRT) were 68.18%, 30.19%, 0.167%, 0.565% and 0.19%, respectively. The mean (± standard deviation) times for scheduled time to start treatment (SC) to check-in time (CK), SC to ST (beam-on time for the first beam of treatment), CK to ST and (CK or SC) to ST were −14 ± 48 min, 6 ± 50 min, 19 ± 24 min and −4 ± 31 min, respectively. Conclusion: Patient wait times during RT were presented in this study. This study covered the daily waiting times before RT during modern-day RT treatment sessions. This vast series of consecutive patient data will be a valuable resource for the future planning and management of any modern RT department.

Introduction: This study aimed to quantify the difference in setup margin in cone beam computed tomography (CBCT) setup imaging, utilising the van Herk formula for two different image registration methods. Two alternative techniques of registration, bony landmark (BL) matching and soft tissue matching (ST) for head and neck cancer patients, were investigated. Methods: This study included 30 head and neck cancer patients who received a simultaneous integrated boost of 54–60–66 Gy in 30 fractions, using volumetric modulated arc treatment. A total of 867 CBCT images were acquired during patient setup and further analysed for setup margin calculation. A region of interest was described using a clip box between the reference and CBCT image to calculate the patient’s positional inaccuracy in three translational directions, X, Y and Z, where X was mediolateral, Y was the cranial-caudal, and Z was the anterior-posterior direction in the patient-based coordinate system, respectively. The shifts were captured by altering the BL and ST matching, and the setup margin was calculated using the van Herk formula (=2·5Σ + 0·7σ where Σ was the systematic and σ was the random error). Results: The difference between bony and ST matching in most cases was observed to be 1·4 mm in all translational directions at a 95% confidence interval and Conclusion: Two distinct registration approaches for head-neck patient setup did not yield any significant difference in the setup margin calculation. A suitable approach for CBCT and reference CT registration technique was required for the setup margin calculation. Confusion in selecting the correct image registration procedure can result in incorrect treatment execution. The compatibility of the two registration approaches was established in this study. Image fusion was neutralised before the second match (ST) to avoid hysteresis. For setup verification using CBCT for the head and neck region, both bone and ST registration were compatible for setup verification.

PurposeIn order to reduce avoidably lengthy duration required to test highly reliable products under usage stress, accelerated life test sampling plans (ALTSPs) are employed. This paper aims to build a decision model for obtaining optimal sampling plan under accelerated life test setting using Type-I hybrid censoring scheme for products covered under warranty.Design/methodology/approachThe primary decision model proposed in this paper determines ALTSP by minimizing the relevant costs involved. To arrive at the decision model, the Fisher information matrix for Type-I hybrid censoring scheme under accelerated life test setting is derived. The optimal solution is attained by utilizing appropriate techniques following a nonlinear constrained optimization approach. As a special case, ALTSP for Type-I censoring is obtained using the same approach. ALTSP under Type-I hybrid censoring using the variance minimization approach is also derived.FindingsOn comparing the optimal results obtained using the above mentioned approaches, it is found that the cost minimization approach does better in reducing the total cost incurred. Results also show that the proposed ALTSP model under cost function setting has considerably lower expected testing time. Interesting findings from the sensitivity analysis conducted using a newly introduced failure dataset pertaining to locomotive controls are highlighted.Originality/valueThe research introduces a model to design optimum ALTSP for Type-I hybrid censoring scheme. The practical viability of the model makes it valuable for real-life situations. The practical application of the proposed model is exemplified using a real-life case.

PurposeThis article considers Inverse Gaussian distribution as the basic lifetime model for the test units. The unknown model parameters are estimated using the method of moments, the method of maximum likelihood and Bayesian methods. As part of maximum likelihood analysis, this article employs an expectation-maximization algorithm to simplify numerical computation. Subsequently, Bayesian estimates are obtained using the Metropolis–Hastings algorithm. This article then presents the design of optimal censoring schemes using a design criterion that deals with the precision of a particular system lifetime quantile. The optimal censoring schemes are obtained after taking into account budget constraints.Design/methodology/approachThis article first presents classical and Bayesian statistical inference for Progressive Type-I Interval censored data. Subsequently, this article considers the design of optimal Progressive Type-I Interval censoring schemes after incorporating budget constraints.FindingsA real dataset is analyzed to demonstrate the methods developed in this article. The adequacy of the lifetime model is ensured using a simulation-based goodness-of-fit test. Furthermore, the performance of various estimators is studied using a detailed simulation experiment. It is observed that the maximum likelihood estimator relatively outperforms the method of moment estimator. Furthermore, the posterior median fares better among Bayesian estimators even in the absence of any subjective information. Furthermore, it is observed that the budget constraints have real implications on the optimal design of censoring schemes.Originality/valueThe proposed methodology may be used for analyzing any Progressive Type-I Interval Censored data for any lifetime model. The methodology adopted to obtain the optimal censoring schemes may be particularly useful for reliability engineers in real-life applications.

Accurate calculation of set-up margin is a prerequisite to arrive at the most optimal clinical to planning target volume margin. The aim of this study was to evaluate the compatibility of different on-board and in-room stereoscopic imaging modalities by calculating the set-up margins (SM) in stereotactic body radiotherapy technique accounting and unaccounting for rotational positional errors (PE). Further, we calculated separate SMs one based on residual positional errors and another based on residual + intrafraction positional errors from the imaging data obtained in a dual imaging environment. A total of 22 lung cancer patients were included in this study. For primary image guidance, four-dimensional cone beam computed tomography (4-D CBCT) was used and stereoscopic ExacTrac was used as the auxiliary imaging. Following table position correction (TPC) based on the initial 4-D CBCT, another 4-D CBCT (post-TPC) and a pair of stereoscopic ExacTrac images were obtained. Further, during the treatment delivery, a series of ExacTrac images were acquired to identify the intrafraction PE. If a, b and c were the observed translational shifts in lateral (x-axis), longitudinal (y-axis) and vertical direction (z-axis) and α, β and γ were the rotational shifts in radians about the same axes, respectively, then the resultant translational vectors (A, B and C) were calculated on the basis of translational and rotational values. Set-up margins were calculated using residual errors post-TPC only and also using intrafraction positional errors in addition to the residual errors. Residual and residual + intrafraction SM were calculated from a dataset of 82 CBCTs and 189 ExacTrac imaging sessions. CBCT-based mean ± SD shifts in translational and rotational directions were 0.3 ± 1.8 mm, 0.1 ± 1.8 mm, − 0.4 ± 1.6 mm, 0.1 ± 0.4°, 0.0 ± 1.0° and 0.3 ± 0.7°, respectively, and for ExacTrac − 0.1 ± 1.8 mm, 0.2 ± 2.4 mm, − 0.6 ± 1.8 mm, 0.1 ± 1.2°, − 0.2 ± 1.3° and − 0.1 ± 0.6°, respectively. Residual SM without considering the rotational correction in x, y and z directions were 5.0 mm, 4.5 mm and 4.4 mm; rotation-corrected SM were 4.4 mm, 4.0 mm and 5.5 mm, respectively. Residual plus intrafraction SM were 5.5 mm, 6.6 mm and 6.2 mm without considering the rotational corrections, whereas they were 5.0 mm, 6.3 mm and 6.2 mm with rotational errors accounted for. Accurate calculation of set-up margin is required to find the clinical to planning target volume margin. Primary and auxiliary imaging margins fall in the range of 4.0 to 5.5 mm and 5.0 to 7.0 mm, respectively, indicating a higher SM for X-ray-based planar imaging techniques over three-dimensional cone beam images. This study established the degree of mutual compatibility between two different kinds of widely used set-up imaging modalities, on-board CBCT and in-room stereoscopic imaging ExacTrac. It also describes the technique to calculate the residual and residual plus intrafraction SM and its variation in a dual imaging environment accounting for rotational PE in stereotactic body radiotherapy of lung.

In the current investigation we have studied the distribution as well as the asymmetry of solar X-ray flares during the period 1976–2017 which corresponds to solar cycle 21, 22, 23 and the almost complete solar cycle 24. The study of the N–S distribution of soft X-ray flares during solar cycles 21, 22, 23 and 24 reveals that the 10°–20° latitude band produced maximum number of soft X-ray flares and is found to be southern hemisphere dominated during all the considered cycles. The soft X-ray flares events above 40° latitude is very rare. Most of the solar X-ray flare activities are observed to be concentrated in the 8°–30° latitude band. A time-latitude plot has been plotted to graphically represent the soft X-ray flare distribution at various latitudes over the course of solar cycle. Our analysis also reveals that solar cycles 21, 22 and 23 are southern hemisphere dominated and the corresponding probability value is statistically significant. The soft X-ray solar flare activity during solar cycle 24 is also found to be southern hemisphere dominated, similar to cycles 21, 22 and 23. Using cross-correlation analysis, we have found that the smoothed curves of the number of soft X-ray flares in northern hemisphere are ahead of the southern hemisphere by 10 months, 2 months, 8 months and 4 months during solar cycles 21, 22, 23 and 24 respectively. Also, for total time span (1976–2017), the smoothed curve of the frequency of soft X-ray flares in northern hemisphere is ahead of a similar curve from the southern hemisphere by 7 months.