Classification of coffee bean species using image processing, artificial neural network and K nearest neighbors

Drying agricultural product is a post-harvest process that consumes significant energy. It can affect the quality of the product. This paper deals with literature review and field survey of drying methods of coffee beans of Indonesia farmers. The objective is to supply the necessary information on developing continuous solar drier. The results show that intermittent characteristic of sun drying results in a better quality of coffee beans in comparison with constant convective drying. In order to use energy efficiently, the drying process should be divided into several stages. In the first stage when the moist content is high, higher drying air temperature is more effective. After this step, where the moist content is low, lower drying air temperature is better. The field survey of drying coffee beans in Sumatera Utara province reveals that the used drying process is very traditional. It can be divided into two modes and depend on the coffee beans type. The Arabica coffee is firstly fermented and dried to moisture content of 80% using sun drying method, then followed by Green House model of drying up to moisture content about 12%. The latter typically spends 3 days of drying time. On the other hand, The Robusta coffee is dried by exposing to the sun directly without any treatment. After the coffee beans dried follow by peeled process. These findings can be considered to develop a continuous solar drying that suitable for coffee beans drying.

Aim: Coronary illness is one of the main sources of mortality in this current world. A basic test in the field of clinical information assessment is the expectation of cardiovascular infection. The fundamental target of this paper is to work on the exactness of the Data mining algorithms being used to improve heart disease prediction. We will be comparing the novel Random forest with K Nearest Neighbor to find out which of these can give us the best accuracy. Material and Methods: The study used 98 samples with Novel Random Forest and K Nearest Neighbor is executed with varying training and testing splits for predicting the accuracy for heart disease prediction with the 80% of G-power value and data about cardiovascular disease was gathered from numerous web sources, including latest research findings and threshold 0.05%, confidence interval 95% mean and standard deviation. The performance of the accuracy rate of the classifiers is examined using the heart disease dataset.. There was a statistical insignificant difference among Innovative Random Forest and K Nearest Neighbor p = 0.484 (p>0.05). Results and Discussion: The accuracy of predicting heart disease in Novel Random Forest 90.16% and K Nearest Neighbor 67.21% is obtained. Conclusion: Prediction of Heart disease using the innovative Random Forest (RF) technique appears to be a significant improvement over the K Nearest Neighbor (KNN) algorithm in terms of accuracy.

The effects of drum, fluidized bed, and traditional type of coffee roasting technologies on the cup quality and bioactive compounds of Yirgacheffe, Harar, and Sidama variety specialty coffee beans grown in Ethiopia were investigated at light, medium, and dark degree of roast from 150°C to 200°C for 7 to 15 min. No significant differences in cup quality were detected among the roasted coffee varieties disregard of the type of roasters. Varietal difference was found to have significant (p < .05) effect on caffeine content of the coffee beans. A significant reduction in trigonelline and total chlorogenic acids content of the coffee beans was observed during roasting process, with darker roasts attaining the least values. Drum roaster was found to be the best type of coffee roaster for specialty coffee beans at medium degree of roast with the highest cup quality, optimum bioactive compounds content, and minimum acrylamide formation. However, traditional roaster resulted at the least average cup score of 80% among the three coffee samples and the highest acrylamide content of 2.306 mg/L for Yirgacheffe coffee sample at light degree of roast. There are still some bottlenecks that need to be addressed via advancements using novel food processing technologies in order to devise the next generation of coffee processing.

Aim: Prediction of coronary illness utilizing novel Novel k nearest neighbor (KNN) and contrasting its accuracy with decision tree algorithm. Materials and Methods: Two gatherings are proposed for foreseeing the accuracy (%) of coronary illness. To be specific, novel Novel k nearest neighbor and decision tree algorithm. Here we take 20 examples each for assessment and look at. The sample size was calculated using G power with pretest power at 80% and the alpha of 0.05 value. Result: The decision tree gives better accuracy (84.95%) contrasted with the Novel k nearest neighbor accuracy (76.29 %). Along these lines the factual meaning of the decision tree is superior to the novel k nearest neighbor algorithm with significance value of 0.115. Conclusion: From the outcome, it may very well be inferred that the decision tree helps in anticipating the coronary illness with more precision contrasted with the novel k nearest neighbor algorithm.

Identification of the green tea grade level using electronic tongue and pattern recognition

FSKNN: Multi-label text categorization based on fuzzy similarity and k nearest neighbors

Air pollution is a global environmental problem that poses serious threats to human health and quality of life, especially in industrializing and densely populated areas. The use of machine learning techniques in air pollution prediction has become an important tool in air quality management. In this study, PM10 concentrations were estimated using support vector machines (SVM), artificial neural networks (ANN), convolutional neural networks (CNN), random forest (RF), gradient boosting (GB), K ‐nearest neighbor (KNN), linear regression (Lasso), and long short‐term memory (LSTM) models, and the models were examined in detail. The results showed that the SVM model performed best with the lowest error values (mean absolute error [MAE]: 4.747 µg/m 3 and root mean square error [RMSE]: 6.648 µg/m 3 ), whereas the ANN model achieved the highest accuracy level ( R 2 : 0.791). The KNN model showed the weakest performance with the highest error rates (RMSE: 10.07 µg/m 3 ). Among the LSTM models, the model trained with the Adam optimization algorithm exhibited the best performance compared to other LSTM versions. Among the models used in PM10 estimation, SVM, ANN, and CNN highlight the effectiveness of machine learning models for air pollution estimation and constitute an important reference for studies to be conducted in this field. Focusing on Karaman, a medium‐sized industrial city dominated by food‐processing industries, it provides a representative framework for similar medium‐sized industrial cities facing comparable environmental challenges. The research introduces an integrated and transparent machine‐learning approach that combines data preprocessing, outlier correction, normalization, and broad hyperparameter optimization under consistent conditions for eight algorithms. This framework improves the reliability, comparability, and reproducibility of air‐quality prediction.

Medium entropy alloys (MEAs) are a subset of compositionally complex alloys whose mixing entropy lies between R and 1.5 R where R is the universal gas constant. The properties of MEAs largely depend on the phases present in the alloy such as solid solution (SS), solid solution + intermetallic (SS + IM) and amorphous (AM). Hence, the correct prediction of phases can enable the efficient selection of material compositions with anticipated properties. In this paper, three machine learning (ML) algorithms viz. k nearest neighbors (KNNs), artificial neural network (ANN), and random forest (RF) were employed for the ternary phase classification problem. An MEA dataset was constructed by utilizing all reported MEAs till February 2023 to the best of authors’ knowledge. The study implied that the use of only three features (mixing enthalpy, atomic size mismatch, and a strain energy related parameter) were sufficient for the phase prediction in MEAs. Among the three ML algorithms, ANN had the highest macro averaged F1 score (86.7%) and accuracy (87.3%) in predicting the phases in MEAs, while RF has the lowest macro F1 score (84.67%) and accuracy (84.8%). However, for phase prediction between single phase SS and multi-phase SS (binary classification), distance-based algorithm (KNN) was found to be suitable. The prediction performance of ML model over a completely unseen data was assessed in the case study section. The experimentally determined phase details of three new MEA compositions fabricated by powder metallurgy route was also included in the unseen dataset. The SS and AM phases were correctly labeled nine times out of eleven instances by using ANN model. However, the model prediction for SS + IM phase was found to be less reliable (three out of five correct) owing to its relatively poor F1 score.

Generating high-resolution daily soil moisture by using spatial downscaling techniques: a comparison of six machine learning algorithms

Mainly, the holy Quran is the holy book for all Muslims. Reading the holy Quran is a special reading with rules. Reading the Holy Quran is called recitation. One of the Muslim essential activities is reading or listening to the Holy Quran. In this paper, a machine learning approach for recognizing the reader of the holy Quran (reciter) is proposed. The proposed system contains basic traditional phases for a recognition system, including data acquisition, pre-processing, feature extraction, and classification. A dataset is created for ten well-known reciters. The reciters are the prayer leaders in the holy mosques in Mecca and Madinah. The audio dataset set is analyzed using the Mel Frequency Cepstral Coefficients (MFCC). Both the K nearest neighbor (KNN) classifier, and the artificial neural network (ANN) classifier are applied for classification purpose. The pitch is used as features which are utilized to train the ANN and the KNN for classification. Two chapters from the Holy Quran are selected in this paper for system validation. Excellent accuracy is achieved. Using the ANN, the proposed system gives 97.62% accuracy for chapter 18 and 96.7% accuracy for chapter 36. On the other hand, the proposed system gives 97.03% accuracy for chapter 18 and 96.08% accuracy for chapter 36 by using the KNN.

One of the most destructive natural hazard is an earthquake. Both the built environment and significant lives are lost. Due to presence of subduction zone and continuous continent to continent collision, major earthquakes in India are concentrated along the seismo-tectonically active Himalayan arc. Seismicity along the Alpine Himalayan Belt varies in well-defined patterns which are based on different parameters such as distance from tectonic source, presence of other historic earthquakes, intersections of tectonic features (in numbers), river length, presence of water body, meandering of rivers, soil conditions. An earthquake catalogue consisting of 540 earthquakes from year 1552 to 2020 is prepared for the consideration of data set. 117 tectonic features are considered for the study. For extracting feature a buffer of radius 25 km is considered along each earthquake of the catalogue. Four features namely distance from nearest tectonic feature, magnitude of earthquake, number of earthquakes within the buffer zone and presence of rivers (length) is extracted. A combination of these features allows identifying patterns based on training and classification of the entire data set. This paper is an attempt to compare four classification algorithms namely Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), K nearest neighbors (KNN) and Artificial Neural Networks (ANN) and present an integrated predictive model for identifying seismically susceptible zones (SSZ) around the Kangra Region. The seismicity in the study area is divided into two classes: class A and Class B based on the magnitude of earthquakes and are called as training data set for the classification algorithms. The training data set provides a basis for classifying a set of data into class A and Class B based on the extracted features. After classification the study area is the classified into two classes: Class A: Significant seismically susceptible area, Class B: less Susceptible zone. A comparative analysis is done in terms of accuracy of classifying an earthquake into the correct class as per training data set. Of the four classification methodologies, ANN showed the best performance by reducing the error in misclassifying the epicenters from either class. The errors accuracy of classifying an earthquake in the correct group were found to be 24.74%, 6.45%, 7.78%, 2.9% for LDA, SVM, KNN and ANN respectively.

Predicting toxic action mechanisms of phenols using AdaBoost Learner

&amp;lt;p&amp;gt;Satellite based rainfall estimates (SBRE) are used as an alternative to gauge rainfall in hydrological studies particularly for basins with data issues. However, these data products exhibit errors which cannot be always corrected by bias correction methods such as Ratio Bias Correction (RBC). Data fusion or data merging can be a potentially good approach in merging various SBREs to obtain a fused dataset, which can benefit from all the data sources and may minimise the error in rainfall estimates. Data merging methods which are commonly applied in meteorology and hydrology are: Arithmetic merging method (AMM), Inverse error squared weighting (IESW) and Error variance (EV). Among these methods EV is popular, which merges bias corrected SBREs using the minimisation of variance principle.&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;In this research we propose using K Nearest Neighbour (KNN) as a data merging method. KNN has a particular advantage as it does not depend upon any specific statistical model to merge data and presents a great flexibility as the value of K (the number of neighbours to be chosen) can be varied to suit the purpose (for example, choosing different K values for different seasons). In this research it is proposed to compute the distances of bias corrected SBREs of the training data from the gauge data and to assign the SBRE with the minimum distance as the class C where C = 1, 2, 3,&amp;amp;#8230;, number of SBREs. In validation each data point consisting of a value of each SBRE may be compared with the data points from the training set and the class of the data point(s) closest to this data point is assigned as the class of the validation data point.&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;The KNN approach as a data merging method was applied to the Indus basin in Pakistan. Three satellite rainfall products CMORPH, PERSIANN CDR and TRMM 3B42 with 0.25&amp;amp;#176; x 0.25&amp;amp;#176; spatial and daily temporal resolution were used. Based on the climatic and physiographic features the Indus basin was divided into four zones. Rainfall products were compared at daily, weekly, fortnightly, monthly and seasonally whereas spatial scales were gauge location, zonal scales and basin scale. The RBC method was used to correct the bias. The KNN method with K=1, 3 and 5 was used and compared with other merging methods namely AMM, IESW and EV. The results were compared in two seasons i.e. non-wet and wet season. AMM and EV methods performed similarly whereas IESW performed poorly at zonal scales. KNN merging method outperformed all other merging methods and gave lowest error across the basin. The daily normalised root mean square error at the Indus basin scale was reduced to 0.3, 0.45 and 0.45 respectively with KNN, AMM and EV whereas this error was 0.8, 0.65 and 0.53 respectively in CMORPH, PERSIANN CDR and TRMM datasets. The KNN merged product gave lowest error at daily scale in calibration and validation period which justifies that merging with KNN improves rainfall estimates in sparsely gauged basins.&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;&amp;amp;#160;&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;&amp;lt;strong&amp;gt;Key words:&amp;lt;/strong&amp;gt; Merging, data fusion, K nearest neighbour, KNN, error variance, Indus.&amp;lt;/p&amp;gt;

The present study reports a physicochemical comparison of shade-grown and sun-grown coffee beans, under unripe, rip and roasted-ripe conditions, using electrical conductivity measurements, electron paramagnetic resonance (EPR), infrared spectroscopy (FTIR), and high performance liquid chromatography (HPLC). Moreover, the assessed physicochemical parameters were compared with organoleptic evaluations based on the Coffee Quality Institute protocol. The values found for electrical conductivity, leached potassium, and stable free radicals were respectively 29%, 31%, and 350% higher for shade-grown coffee beans, whereas polyphenol oxidase enzymatic activity was 23% lower. By contrast, FTIR and HPLC measurements identified higher chlorogenic acid and lipid contents in sun-grown coffee beans. Importantly, the sensorial grade attributed to roasted-ripe grains was 12% higher for sun-grown coffee. Our findings suggest that shade-grown coffee beans have undergone microorganismal activity and undesired fermentation during cultivation, which resulted in lower coffee quality. A correlation between a set of selected physicochemical properties and organoleptic properties was robustly established and could be used in the development of future coffee bean quality control protocols.

Today, the amount of biological data types obtained are increasing every day. Among these data types are micro arrays that play an important role in cancer diagnosis. The data analysis that are carried out through traditional approaches have proven unsuccessful in delivering efficient results on data types where data complexity is high and where sampling is low. For this reason, using a hybrid algorithm by merging the effective features of two distinct algorithms will yield effective results. In this study, a classification process was performed firstly by dimension reduction on micro array data that were obtained from the tissues from patients with a tumor in their central nervous system and then by using an artificial neural network algorithm that was optimized through Fire Fly Algorithm (FF), a hybrid approach. The data obtained were compared to K Nearest Neighbors (KNN), Support Vector Machine (SVM) and Artificial Neural Networks (ANN) classification algorithms, which are frequently used in the literature. Also, the results were compared to the findings that were obtained from artificial neural networks, which are reinforced by Genetic Algorithm (GA), another hybrid approach. Then the results were shared. The performance results obtained show that hybrid approaches present a highly precise and more efficient classification process but they show a slower performance than basic classification algorithms.