In tongue diagnosis, colour information of tongue body has kept valuable information regarding the state of disease and its correlation with the internal organs. Qualitatively, practitioners may have difficulty in their judgement due to the instable lighting condition and naked eye's ability to capture the exact colour distribution on the tongue especially the tongue with multicolour substance. To overcome this ambiguity, this paper presents a two-stage tongue's multicolour classification based on a support vector machine (SVM) whose support vectors are reduced by our proposed k-means clustering identifiers and red colour range for precise tongue colour diagnosis. In the first stage, k-means clustering is used to cluster a tongue image into four clusters of image background (black), deep red region, red/light red region, and transitional region. In the second-stage classification, red/light red tongue images are further classified into red tongue or light red tongue based on the red colour range derived in our work. Overall, true rate classification accuracy of the proposed two-stage classification to diagnose red, light red, and deep red tongue colours is 94%. The number of support vectors in SVM is improved by 41.2%, and the execution time for one image is recorded as 48 seconds.
In computerized tongue diagnostic system, tongue body color has been one of the essential features that contain rich information for diagnosing disease. However, tongue body color measurement can be influenced by the tongue coating color and other ineffective features such as significant coatings, shadows, teeth mark and crackles. This paper presents a fast processing segmentation algorithm using Hue, Saturation and Value (HSV) color space transformation to segment and remove these ineffective features aiming to have an accurate color measurement for online diagnosis. The newly devised Brightness Conformable Multiplier (BCM) has been proposed to automatically adjust the threshold brightness based on three conditions of lower perioral area’s brightness, ; when is smaller than its standard deviation, is greater than its standard deviation and otherwise. Besides, the Modified Sequential Algorithm (MSA) has been proposed to offer fast processing algorithm of 1.445 seconds and better segmentation. The successful segmentation rate was recorded as 90%. Furthermore, color measurement is carried out on the segmented samples and the analysis showed that the dispersion range of tongue body color measurement is small. This indicates a convincing result as the color boundary among light red, red and deep red tongue has been determined precisely.
This paper investigated the performance of Malaysian power plants from the year 2015 to 2017 using Malmquist Total Factor Productivity (TFP) index, which is based on Data Envelopment Analysis (DEA). This approach offers substantial advantages as compared to other existing methods as it can measure productivity changes over time for a variety of inputs and outputs. Moreover, it comprises two primary components: the technical efficiency change and the technological change indexes that provide clearer insight into the factors that are responsible for shifts in total factor productivity. This study uses a single input, installed generation capacity (MW), and two outputs, average thermal efficiency (%) and average equivalent availability factor (%). These output-input data included ten main power plants: TNB Natural Gas, SESB Natural Gas, SESB Diesel, SEB Natural Gas, SEB Coal, SEB Diesel, IPP Semenanjung Natural Gas, IPP Semenanjung Coal, IPP Sabah Natural Gas, and IPP Sabah Diesel. The results have two significant implications for fossil fuel power plants in Malaysia. First, technological change was the primary factor in boosting the TFP performance of the fossil fuel power plants in Malaysia. Meanwhile, the decline in TFP performance in Malaysian fossil fuel power plants may be attributed, in part, to a lack of innovation in technical components as the results found that the average technical efficiency changes in 2015 – 2016 were at 146% and then dropped significantly to 2% in 2016 – 2017. Second, the average scale efficiency changes rose dramatically from -53% to 3% providing a significant contribution to the improvement of technical efficiency changes. The fossil fuel power plants become efficient as the power plants’ size increases. This indicates that the size of a power plant positively impacts the performance of the TFP.
Tongue inspection is a complementary diagnosis method that widely used in Traditional Chinese Medicine (TCM) by inspecting the tongue body constitution to decide the physiological and pathological functions of the human body. Since tongue manifestation is done by practitioner’s observation using naked eye, many limitations can affect the diagnosis result including environment condition and experiences of the practitioner. Lately, tongue diagnosis has been widely studied in order to solve these limitations via digital system. However, most of recent digital system are bulky and not equipped with intelligent diagnosis system that can finally predict the health status of the patient. In this research, digital tongue diagnosis system that uses intelligent diagnosis consisted of image segmentation analysis, tongue coating recognition analysis, and tongue color classification has been embedded on Raspberry Pi. Tongue segmentation implements Hue, Saturation and Value (HSV) color space with Brightness Conformable Multiplier (BCM) for adaptive brightness filtering to recognized tongue body accurately while eliminating perioral area. Tongue Coating Recognition uses threshold method to detect tongue coating and eliminate the unwanted features including shadow. Tongue color classification uses hybrid method consisted of k-means clustering and Support Vector Machine (SVM) to classify between red, light red and deep red tongue and further gave diagnosis based on color. This experiment concluded that it is feasible to embed the algorithm on Raspberry Pi to promote system portability while attaining similar accuracy for future telemedicine.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.