Microalgae identification: Future of image processing and digital algorithm

Chong, Jun Wei Roy; Khoo, Kuan Shiong; Chew, Kit Wayne; Vo, Dai‐Viet N.; Banat, Fawzi; Munawaroh, Heli Siti Halimatul; Show, Pau Loke

doi:10.1016/j.biortech.2022.128418

Cited by 22 publications

(6 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By integrating morphological and genetic data in a user-friendly and accessible platform, this method can revolutionize the way microalgae are identified, enhancing data accuracy, and facilitating further research in diverse fields such as ecology, biotechnology, and environmental monitoring. Our concept agreed with the study of Chong et al ( 2023 ), which is focused on the integration of image processing and machine learning to improve microalgae species identification. Specifically, advanced image processing techniques, including deep learning algorithms, are advocated to enhance the accuracy and efficiency of the identification process.…”

Section: Discussionsupporting

confidence: 90%

Applying an internal transcribed spacer as a single molecular marker to differentiate between Tetraselmis and Chlorella species

Fathy,

Techen,

Elsayed

et al. 2023

Front. Microbiol.

View full text Add to dashboard Cite

In the realm of applied phycology, algal physiology, and biochemistry publications, the absence of proper identification and documentation of microalgae is a common concern. This poses a significant challenge for non-specialists who struggle to identify numerous eukaryotic microalgae. However, a promising solution lies in employing an appropriate DNA barcoding technique and establishing comprehensive databases of reference sequences. To address this issue, we conducted a study focusing on the molecular characterization and strain identification of Tetraselmis and Chlorella species, utilizing the internal transcribed spacer (ITS) barcode approach. By analyzing the full nuclear ITS region through the Sanger sequencing approach, we obtained ITS barcodes that were subsequently compared with other ITS sequences of various Tetraselmis and Chlorella species. To ensure the reliability of our identification procedure, we conducted a meticulous comparison of the DNA alignment, constructed a phylogenetic tree, and determined the percentage of identical nucleotides. The findings of our study reveal the significant value of the ITS genomic region as a tool for distinguishing and identifying morphologically similar chlorophyta. Moreover, our results demonstrate that both the ITS1 and ITS2 regions are capable of effectively discriminating isolates from one another; however, ITS2 is preferred due to its greater intraspecific variation. These results underscore the indispensability of employing ITS barcoding in microalgae identification, highlighting the limitations of relying solely on morphological characterization.

show abstract

Section: Discussionsupporting

confidence: 90%

Applying an internal transcribed spacer as a single molecular marker to differentiate between Tetraselmis and Chlorella species

Fathy,

Techen,

Elsayed

et al. 2023

Front. Microbiol.

View full text Add to dashboard Cite

show abstract

“…ML applications can optimize strain selection by predicting beneficial traits and selecting the strains with optimal bioplastic‐producing capabilities 58, 128. This results in more efficient strain selection and contributes to production optimization 129. In addition, ML can help predict microalgae growth, allowing for improved production forecasting and resource optimization.…”

Section: Applying Artificial Intelligence To Algae Cultivation and Al...mentioning

confidence: 99%

Towards a Sustainable Circular Economy: Algae‐Based Bioplastics and the Role of Internet‐of‐Things and Machine Learning

Bin Abu Sofian,

Lim,

Manickam

et al. 2023

ChemBioEng Reviews

View full text Add to dashboard Cite

The growing potential of sustainable materials such as polyhydroxyalkanoates (PHAs), polylactic acid (PLA), alginate, carrageenan, and ulvan for bioplastics production presents an opportunity to promote a sustainable circular economy. This review investigates their properties, applications, and challenges. Bioplastics derived from algae offer an environmentally friendly alternative to petroleum‐based plastics, a shift of paramount importance to society due to the escalating environmental concerns associated with traditional plastics. The role of the internet‐of‐things (IoT) and machine learning in refining these bioplastics' production and development processes is emphasized. IoT monitors cultivation conditions, data collection, and process control for more sustainable production. Machine learning can enhance algae cultivation, increasing the supply of raw materials for algal bioplastics and improving their efficiency and output. The study results indicate the promise of algae‐based bioplastics, IoT, and machine learning in fostering a more environmentally sustainable future. By harnessing these advanced technologies, optimization of bioplastic production is possible, potentially revolutionizing the materials industry and addressing existing challenges toward achieving a sustainable circular economy.

show abstract

“…Reducing the size of dataset can be advantageous in scenario where the number of features in the dataset is equal to or greater than the number of samples. Excessive and unknowingly large dataset can often lead to overfitting, where the model becomes too specific to the training data and performs poorly on the validation dataset [ 45 ]. Feature selection techniques such as principal component analysis (PCA), linear discriminant analysis (LDA), and multidimensional scaling are applied for correlation analysis, mutual information, and identifying relevant features while removing irrelevant or redundant features to improve model’s efficiency and interpretability [ 43 ].…”

Section: Ai Key Strategies Into Extraction and Quantification Processmentioning

confidence: 99%

“…DL is a subset of ML that implements deep neural algorithms such as ANN and convolutional neural networks (CNNs), have the ability to solve non-linear problems and automatically extract relevant features from spectral data or digital images. On the contrary, ML models often rely on manual feature engineering, where domain experts manually select and design features to be fed into the learning algorithms [ 45 ]. Based on Shishodia et al [ 73 ], they stressed that ANN model was successful in modeling complex non-linear input-output relationships in some extremely interdisciplinary field.…”

Section: Digitalised Perspectives On the Quantification Of Organic Pi...mentioning

confidence: 99%

Bridging artificial intelligence and fucoxanthin for the recovery and quantification from microalgae

Chong

Tang

Leong³

et al. 2023

Bioengineered

Self Cite

View full text Add to dashboard Cite

Fucoxanthin is a carotenoid that possesses various beneficial medicinal properties for human well-being. However, the current extraction technologies and quantification techniques are still lacking in terms of cost validation, high energy consumption, long extraction time, and low yield production. To date, artificial intelligence (AI) models can assist and improvise the bottleneck of fucoxanthin extraction and quantification process by establishing new technologies and processes which involve big data, digitalization, and automation for efficiency fucoxanthin production. This review highlights the application of AI models such as artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS), capable of learning patterns and relationships from large datasets, capturing non-linearity, and predicting optimal conditions that significantly impact the fucoxanthin extraction yield. On top of that, combining metaheuristic algorithm such as genetic algorithm (GA) can further improve the parameter space and discovery of optimal conditions of ANN and ANFIS models, which results in high R 2 accuracy ranging from 98.28% to 99.60% after optimization. Besides, AI models such as support vector machine (SVM), convolutional neural networks (CNNs), and ANN have been leveraged for the quantification of fucoxanthin, either computer vision based on color space of images or regression analysis based on statistical data. The findings are reliable when modeling for the concentration of pigments with high R 2 accuracy ranging from 66.0% − 99.2%. This review paper has reviewed the feasibility and potential of AI for the extraction and quantification purposes, which can reduce the cost, accelerate the fucoxanthin yields, and development of fucoxanthin-based products.

show abstract

Microalgae identification: Future of image processing and digital algorithm

Cited by 22 publications

References 97 publications

Applying an internal transcribed spacer as a single molecular marker to differentiate between Tetraselmis and Chlorella species

Applying an internal transcribed spacer as a single molecular marker to differentiate between Tetraselmis and Chlorella species

Towards a Sustainable Circular Economy: Algae‐Based Bioplastics and the Role of Internet‐of‐Things and Machine Learning

Bridging artificial intelligence and fucoxanthin for the recovery and quantification from microalgae

Contact Info

Product

Resources

About