Image processing techniques have been widely used as a non-destructive method to determine the maturity of agriculture products. In the past few decades, numerous fruit maturity grading systems have been proposed and developed. However, there is no system or technique is reported to determine the maturity for Sarawak’s brinjal. Therefore, in this research, a colour image processing-based method is proposed in order to determine the maturity of Sarawak’s brinjal based on the skin colour. Ripe Sarawak’s brinjal has yellow or orange colour skin while unripe Sarawak’s brinjal has green colour skin. The proposed method consists of four main phases which are image acquisition, image pre-processing, features extraction, and classification. CIELAB colour model is used in this proposed method. The RGB value extracted from the image is converted into CIELAB colour space in order to obtain the CIELAB value. The maturity of the Sarawak’s brinjal is determined based on the colour difference between the fruit and the reference colour. In the experiment, a total of 48 Sarawak’s brinjal sample with 24 sample for each grade (ripe and unripe) were prepared. 12 out of 24 samples from each grade were used for thresholding. From the experimental results, a total of 23 Sarawak’s brinjals were correctly classified out of 24 Sarawak’s brinjal sample, accounts for nearly 96% of accuracy.
Identification of microalgae species is of importance due to the uprising of harmful algae blooms affecting both the aquatic habitat and human health. Despite this occurence, microalgae have been identified as a green biomass and alternative source due to its promising bioactive compounds accumulation that play a significant role in many industrial applications. Recently, microalgae species identification has been conducted through DNA analysis and various microscopy techniques such as light, scanning electron, transmission electron, and atomic force -microscopy. The aforementioned procedures have encouraged researchers to consider alternate ways due to limitations such as costly validation, requiring skilled taxonomists, prolonged analysis, and low accuracy. This review highlights the potential innovations in digital microscopy with the incorporation of both hardware and software that can produce a reliable recognition, detection, enumeration, and real-time acquisition of microalgae species. Several steps such as image acquisition, processing, feature extraction, and selection are discussed, for the purpose of generating high image quality by removing unwanted artifacts and noise from the background. These steps of identification of microalgae species is performed by reliable image classification through machine learning as well as deep learning algorithms such as artificial neural networks, support vector machines, and convolutional neural networks. Overall, this review provides comprehensive insights into numerous possibilities of microalgae image identification, image pre-processing, and machine learning techniques to address the challenges in developing a robust digital classification tool for the future.
Microalgae biorefinery is a platform for the conversion of microalgal biomass into a variety of value-added products, such as biofuels, bio-based chemicals, biomaterials, and bioactive substances. Commercialization and industrialization of microalgae biorefinery heavily rely on the capability and efficiency of large-scale cultivation of microalgae. Thus, there is an urgent need for novel technologies that can be used to monitor, automatically control, and precisely predict microalgae production. In light of this, innovative applications of the Internet of things (IoT) technologies in microalgae biorefinery have attracted tremendous research efforts. IoT has potential applications in a microalgae biorefinery for the automatic control of microalgae cultivation, monitoring and manipulation of microalgal cultivation parameters, optimization of microalgae productivity, identification of toxic algae species, screening of target microalgae species, classification of microalgae species, and viability detection of microalgal cells. In this critical review, cutting-edge IoT technologies that could be adopted to microalgae biorefinery in the upstream and downstream processing are described comprehensively. The current advances of the integration of IoT with microalgae biorefinery are presented. What this review discussed includes automation, sensors, lab-on-chip, and machine learning, which are the main constituent elements and advanced technologies of IoT. Specifically, future research directions are discussed with special emphasis on the development of sensors, the application of microfluidic technology, robotized microalgae, high-throughput platforms, deep learning, and other innovative techniques. This review could contribute greatly to the novelty and relevance in the field of IoT-based microalgae biorefinery to develop smarter, safer, cleaner, greener, and economically efficient techniques for exhaustive energy recovery during the biorefinery process.
Continuous automation of conventional industrial operations with smart technology have drawn significant attention. Firstly, the study investigates on optimizing the proportion of industrial biscuit processing waste powder, (B) substituted into BG-11 as a source of cultivation medium for the growth of C. vulgaris. Various percentages of industrial biscuit processing waste powder, (B) were substituted in the inorganic medium to analyse the algal growth and biochemical composition. The use of 40B combination was found to yield highest biomass concentration (4.11 g/L), lipid (260.44 mg/g), protein (263.93 mg/g), and carbohydrate (418.99 mg/g) content compared with all the other culture ratio combination. Secondly, the exploitation of colour acquisition was performed onto C. vulgaris growth phases, and a novel photo-to-biomass concentration estimation was conducted via image processing for three different colour model pixels. Based on linear regression analysis the red, green, blue (RGB) colour model can interpret its colour variance precisely.
Overgrowth of microalgae will result in harmful algae blooms that can affect the aquatic ecosystem and human health. Therefore, the quantitation of chlorophyll pigments can be used as an indicator of algae bloom. However, it is difficult to monitor the geographical and temporal distribution of chlorophyll in the aquatic environment. Accordingly, an innovative and inexpensive method based on the red-green-blue (RGB) image analysis was utilized in this study to estimate the microalgae chlorophyll content. The digital images were acquired using a smartphone camera. The colour index was then evaluated using software and associated with chlorophyll concentration significantly. A regression model, using RGB colour components as independent variables to estimate chlorophyll concentration, was developed and validated. The Green in the RGB index was the most promising way to estimate chlorophyll concentration in microalgae. The result showed that acetone was the best extractant solvent with a high R-squared value among the four extractant solvents. Next, the isolation of useful biomolecules, such as proteins, fatty acids, polysaccharides and antioxidants from the microalgae, has been recognized as an alternative to regulating algae bloom. Microalgae are shown to produce bioactive compounds with a variety of biological activities that can be applied in various industries. This study evaluates the biochemical composition of mixed microalgae species, Desmodesmus sp. and Scenedesmus sp. using the liquid triphasic partitioning (TPP) system. The findings from analytical assays revealed that the biomass consisted of varied concentrations of carbohydrates, protein, and lipids. Phenolic compounds and antioxidant activity were at 60.22 mg/L and 90.69%, respectively.
This study presented a novel methodology to predict microalgae chlorophyll content from colour models using linear regression and artificial neural network. The analysis was performed using SPSS software. Type of extractant solvents and image indexes were used as the input data for the artificial neural network calculation. The findings revealed that the regression model was highly significant, with high R2 of 0.58 and RSME of 3.16, making it a useful tool for predicting the chlorophyll concentration. Simultaneously, artificial neural network model with R2 of 0.66 and low RMSE of 2.36 proved to be more accurate than regression model. The model which fitted to the experimental data indicated that acetone was a suitable extraction solvent. In comparison to the cyan-magenta-yellow-black model in image analysis, the red-greenblue model offered a better correlation. In short, the estimation of chlorophyll concentration using prediction models are rapid, more efficient, and less expensive.