To evaluate the performance of a support vector machine algorithm that automatically and objectively identifies corneal patterns based on a combination of 22 parameters obtained from Pentacam measurements and to compare this method with other known keratoconus (KC) classification methods. Pentacam data from 860 eyes were included in the study and divided into 5 groups: 454 KC, 67 forme fruste (FF), 28 astigmatic, 117 after refractive surgery (PR), and 194 normal eyes (N). Twenty-two parameters were used for classification using a support vector machine algorithm developed in Weka, a machine-learning computer software. The cross-validation accuracy for 3 different classification tasks (KC vs. N, FF vs. N and all 5 groups) was calculated and compared with other known classification methods. The accuracy achieved in the KC versus N discrimination task was 98.9%, with 99.1% sensitivity and 98.5% specificity for KC detection. The accuracy in the FF versus N task was 93.1%, with 79.1% sensitivity and 97.9% specificity for the FF discrimination. Finally, for the 5-groups classification, the accuracy was 88.8%, with a weighted average sensitivity of 89.0% and specificity of 95.2%. Despite using the strictest definition for FF KC, the present study obtained comparable or better results than the single-parameter methods and indices reported in the literature. In some cases, direct comparisons with the literature were not possible because of differences in the compositions and definitions of the study groups, especially the FF KC.
Purpose: To validate a recently developed program for automatic and objective keratoconus detection (Keratoconus Assistant [KA]) by applying it to a new population and comparing it with other methods described in the literature. Methods: KA uses machine learning and 25 Pentacam-derived parameters to classify eyes into subgroups, such as keratoconus, keratoconus suspect, postrefractive surgery, and normal eyes. To validate this program, it was applied to 131 eyes diagnosed separately by experienced corneal specialists from 2 different centers (Fondation Rothschild, Paris, and Antwerp University Hospital [UZA]). The agreement of the KA classification with 7 other indices from the literature was assessed using interrater reliability and confusion matrices. The agreement of the 2 clinical classifications was also assessed. Results: For keratoconus, KA agreed in 92.6% of cases with the clinical diagnosis by UZA and in 98.0% of cases with the diagnosis by Rothschild. In keratoconus suspect and forme fruste detection, KA agreed in 65.2% (UZA) and 100% (Rothschild) of cases with the clinical assessments. This corresponds with a moderate agreement with a clinical assessment (κ = 0.594 and κ = 0.563 for Rothschild and UZA, respectively). The agreement with the other classification methods ranged from moderate (κ = 0.432; Score) to low (κ = 0.158; KISA%). Both clinical assessments agreed substantially (κ = 0.759) with each other. Conclusions: KA is effective at detecting early keratoconus and agrees with trained clinical judgment. As keratoconus detection depends on the method used, we recommend using multiple methods side by side.
29 September 2019 in Journal of Raman Spectroscopy
IPTV services are the fastest growing television services in the world today. This is a bandwidth intensive service, requiring low latency and tight control of jitter. To guarantee the quality of service required, service providers opt to multicast all TV channels at all times to everywhere. However, a significant number of channels are rarely watched, so this method is provably resource- and energy-inefficient. In this paper, we argue that the expected increase in quantity and quality of TV channels will become a serious issue, both in terms of bandwidth and energy costs. To overcome this problem, we propose a dynamic scheme that pre-joins only a selection of TV channels. This scheme was evaluated by means of trace-driven simulations using a large dataset from a commercial nationwide IPTV service. The dataset comprises 255 thousand users, 150 TV channels, and covers a 6-month period. We show that by using our scheme IPTV service providers can save a considerable amount of bandwidth while affecting only a very small number of TV channel switching requests. To understand how these bandwidth savings are translated in energy savings, we developed a power consumption model for network equipment based on real measurements. The main conclusions are that while today the bandwidth savings will have reduced impact in energy consumption in the core network, with the introduction of very high definition channels this impact will become significant, justifying the use of resource-efficient distribution schemes such as the one proposed.
High voltage bushing failures are one of the main causes that affect reliability and availability of high voltage transformers and reactors. Not only reliability and availability are affected, but also failures in these components could produce fires, damages in nearby equipment and injuries to people working in the proximity. It was shown that performing periodic diagnosis or implementing continuous monitoring help to avoid terminal failures. In order to expand knowledge regarding how high voltage bushings age and how the signs of ageing could be detected, the results of the analysis of six high voltage bushings removed preventively from service are presented in this work. These bushings had been operating for between twenty and thirty-three years before being removed. Three of them were pulled out preventively because diagnoses performed over them showed risk of failure. The analysis includes test of dissipation factor (tan δ) and capacitance, tip-up, frequency domain spectroscopy performed during their life in service and lab tests conducted when they were out of services: dissipation factor and capacitance, frequency domain spectroscopy, tip-up, dissipation factor at nominal voltage, partial discharges, DGA and oil analysis performed in laboratory. At the end of the lab test each bushing was disassembled, and a detailed visual inspection was carried out. Oil samples were taken to carry out physical and chemical analysis. Tests results, both field historical and in laboratory, life time in service, visual inspection and oil sample analysis results are presented correlated with the aim of evaluating failure mechanisms that were present, and analyzing which diagnosis tests have shown to be the most suitable to detect their condition.