Free alignment classification of dikarya fungi using some machine learning methods

Rohani, Abbas; Mamarabadi, Mojtaba

doi:10.1007/s00521-018-3539-5

Cited by 11 publications

(5 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This process is significant in various fields, such as agriculture, food safety, environmental monitoring, and medical diagnosis. Image processing for fungi classification [6], [13], [17], [21].…”

Section: Fungi Classificationmentioning

confidence: 99%

Application of Ai-Enhanced Image Processing Methods for Educational Applied Physics Experiments

Laukhammer,

Mačerauskas,

Lučun

et al. 2024

ETR

View full text Add to dashboard Cite

This article examines the use of an AI-powered automated image analysis system. The system's purpose is to enhance the workflow of students during applied physics laboratory experiments, helping them analyze images and perform accurate microobject counting. On the software side, the system incorporates machine learning algorithms for visual processing applications using Python and its’ extension libraries – CV2, Tensorflow, Keras, SkLearn etc.. The hardware consists of a camera and microprocessor, which, in conjunction with the image processing software, perform microobject recognition and counting in real-time. The goal is to automate applied physics laboratory experiments in which the counting of microobjects, be it organic or human-made, is usually done manually. During these applied physics laboratory experiments and with the aid of this system, students are exposed to a modern workflow, further preparing them for future work environments, teaching them about process automation, and further increasing their interest in micro-scale related science subjects. Automation using image processing technology combined with automatic data logging from images allows for fast and accurate micro-object counting.

show abstract

Section: Fungi Classificationmentioning

confidence: 99%

Application of Ai-Enhanced Image Processing Methods for Educational Applied Physics Experiments

Laukhammer,

Mačerauskas,

Lučun

et al. 2024

ETR

View full text Add to dashboard Cite

show abstract

“…The SOM algorithm uses a competitive learning method for training and converts nonlinear statistical relationships between input data into simple geometric relationships [37]. In SOM, each neuron of the input layer (x) with a variable associated n-dimensional weight (w ij ) is connected to all Kohonen neurons, and neurons are connected together by a neighborhood function [26,37].…”

Section: Classifier Models 251 Neural Networkmentioning

confidence: 99%

“…Each pattern of training data set is represented in an N-dimensional space of the features during the training phase which is used to classify a new object. The K-nearest neighbor training patterns for each test pattern are determined using the distance function [26,43].…”

Section: K-nearest Neighbor Classifier (Knn) Algorithmmentioning

confidence: 99%

“…Various algorithms such as K-nearest neighbor (KNN), support vector machine (SVM), self-organizing maps (SOM), multilayer perceptron (MLP), radial basis function neural network (RBF), learning vector quantization (LVQ), principal component analysis (PCA), etc., are used for classification. A wide range of research has been done employing these algorithms, such as the classification of rice grains [23] and wheat cultivars [24] using MLP neural network; classification of plant species using SVM [25]; classification of the dikarya fungi using SVM, KNN, and SOM [26]; sorting different parts of saffron with 22 different classifiers (SVM and KNN models) [11]; and classification of saffron and fake samples using PCA and PLS [27].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection and Classification of Saffron Adulterants by Vis-Nir Imaging, Chemical Analysis, and Soft Computing

Alighaleh

Pakdel

Ghooshkhaneh

et al. 2023

Foods

Self Cite

View full text Add to dashboard Cite

Saffron (Crocus sativus L.) is the most expensive spice in the world, known for its unique aroma and coloring in the food industry. Hence, its high price is frequently adulterated. In the current study, a variety of soft computing methods, including classifiers (i.e., RBF, MLP, KNN, SVM, SOM, and LVQ), were employed to classify four samples of fake saffron (dyed citrus blossom, safflower, dyed fibers, and mixed stigma with stamens) and three samples of genuine saffron (dried by different methods). RGB and spectral images (near-infrared and red bands) were captured from prepared samples for analysis. The amount of crocin, safranal, and picrocrocin were measured chemically to compare the images’ analysis results. The comparison results of the classifiers indicated that KNN could classify RGB and NIR images of samples in the training phase with 100% accuracy. However, KNN’s accuracy for different samples in the test phase was between 71.31% and 88.10%. The RBF neural network achieved the highest accuracy in training, test, and total phases. The accuracy of 99.52% and 94.74% was obtained using the features extracted from RGB and spectral images, respectively. So, soft computing models are helpful tools for detecting and classifying fake and genuine saffron based on RGB and spectral images.

show abstract

“…Recently, advancements in deep learning have further enhanced the power and flexibility of molecular representations. Convolutional neural networks (CNNs), recurrent neural networks (RNNs), and graph neural networks (GNNs) have been extensively utilized in diverse applications like drug target interaction prediction [ 14 , 15 , 16 , 17 , 18 ], molecular property prediction [ 19 , 20 , 21 , 22 , 23 ], and genetic biology [ 24 , 25 ]. These methods utilize SMILES (Simplified Molecular Input Line Entry System), a textual representation for chemical structures, as input.…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Comparative Analysis of Deep Learning Based Feature Representations for Molecular Taste Prediction

Song,

Chang,

Tian

et al. 2023

Foods

View full text Add to dashboard Cite

Taste determination in small molecules is critical in food chemistry but traditional experimental methods can be time-consuming. Consequently, computational techniques have emerged as valuable tools for this task. In this study, we explore taste prediction using various molecular feature representations and assess the performance of different machine learning algorithms on a dataset comprising 2601 molecules. The results reveal that GNN-based models outperform other approaches in taste prediction. Moreover, consensus models that combine diverse molecular representations demonstrate improved performance. Among these, the molecular fingerprints + GNN consensus model emerges as the top performer, highlighting the complementary strengths of GNNs and molecular fingerprints. These findings have significant implications for food chemistry research and related fields. By leveraging these computational approaches, taste prediction can be expedited, leading to advancements in understanding the relationship between molecular structure and taste perception in various food components and related compounds.

show abstract

Free alignment classification of dikarya fungi using some machine learning methods

Cited by 11 publications

References 81 publications

Application of Ai-Enhanced Image Processing Methods for Educational Applied Physics Experiments

Application of Ai-Enhanced Image Processing Methods for Educational Applied Physics Experiments

Detection and Classification of Saffron Adulterants by Vis-Nir Imaging, Chemical Analysis, and Soft Computing

A Comprehensive Comparative Analysis of Deep Learning Based Feature Representations for Molecular Taste Prediction

Contact Info

Product

Resources

About