scholarly journals Hierarchical Tactile Sensation Integration from Prosthetic Fingertips Enables Multi-Texture Surface Recognition

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4324
Author(s):  
Moaed A. Abd ◽  
Rudy Paul ◽  
Aparna Aravelli ◽  
Ou Bai ◽  
Leonel Lagos ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Sliding Contact ◽  
Tactile Sensation ◽  
Support Vector ◽  
Textured Surfaces ◽  
K Nearest Neighbor ◽  
Tactile Sensors ◽  
Time Frequency

Multifunctional flexible tactile sensors could be useful to improve the control of prosthetic hands. To that end, highly stretchable liquid metal tactile sensors (LMS) were designed, manufactured via photolithography, and incorporated into the fingertips of a prosthetic hand. Three novel contributions were made with the LMS. First, individual fingertips were used to distinguish between different speeds of sliding contact with different surfaces. Second, differences in surface textures were reliably detected during sliding contact. Third, the capacity for hierarchical tactile sensor integration was demonstrated by using four LMS signals simultaneously to distinguish between ten complex multi-textured surfaces. Four different machine learning algorithms were compared for their successful classification capabilities: K-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), and neural network (NN). The time-frequency features of the LMSs were extracted to train and test the machine learning algorithms. The NN generally performed the best at the speed and texture detection with a single finger and had a 99.2 ± 0.8% accuracy to distinguish between ten different multi-textured surfaces using four LMSs from four fingers simultaneously. The capability for hierarchical multi-finger tactile sensation integration could be useful to provide a higher level of intelligence for artificial hands.

scholarly journals A Comparative Analysis of Machine Learning Algorithms Modeled from Machine Vision-Based Lettuce Growth Stage Classification in Smart Aquaponics

2020 ◽  
Vol 11 (9) ◽  
pp. 442-449 ◽  
Author(s):  
Sandy C. Lauguico ◽  
◽  
Ronnie S. Concepcion II ◽  
Jonnel D. Alejandrino ◽  
Rogelio Ruzcko Tobias ◽  
...  
Keyword(s):  
Machine Learning ◽  
Comparative Analysis ◽  
Machine Vision ◽  
Nearest Neighbor ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Urban Farming ◽  
K Nearest Neighbor ◽  
Lettuce Growth

The arising problem on food scarcity drives the innovation of urban farming. One of the methods in urban farming is the smart aquaponics. However, for a smart aquaponics to yield crops successfully, it needs intensive monitoring, control, and automation. An efficient way of implementing this is the utilization of vision systems and machine learning algorithms to optimize the capabilities of the farming technique. To realize this, a comparative analysis of three machine learning estimators: Logistic Regression (LR), K-Nearest Neighbor (KNN), and Linear Support Vector Machine (L-SVM) was conducted. This was done by modeling each algorithm from the machine vision-feature extracted images of lettuce which were raised in a smart aquaponics setup. Each of the model was optimized to increase cross and hold-out validations. The results showed that KNN having the tuned hyperparameters of n_neighbors=24, weights='distance', algorithm='auto', leaf_size = 10 was the most effective model for the given dataset, yielding a cross-validation mean accuracy of 87.06% and a classification accuracy of 91.67%.

scholarly journals Identification of Leukemia Subtypes from Microscopic Images Using Convolutional Neural Network

Diagnostics ◽  
2019 ◽  
Vol 9 (3) ◽  
pp. 104 ◽  
Author(s):  
Ahmed ◽  
Yigit ◽  
Isik ◽  
Alpkocak
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Nearest Neighbor ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Data Set ◽  
Leukemia Data

Leukemia is a fatal cancer and has two main types: Acute and chronic. Each type has two more subtypes: Lymphoid and myeloid. Hence, in total, there are four subtypes of leukemia. This study proposes a new approach for diagnosis of all subtypes of leukemia from microscopic blood cell images using convolutional neural networks (CNN), which requires a large training data set. Therefore, we also investigated the effects of data augmentation for an increasing number of training samples synthetically. We used two publicly available leukemia data sources: ALL-IDB and ASH Image Bank. Next, we applied seven different image transformation techniques as data augmentation. We designed a CNN architecture capable of recognizing all subtypes of leukemia. Besides, we also explored other well-known machine learning algorithms such as naive Bayes, support vector machine, k-nearest neighbor, and decision tree. To evaluate our approach, we set up a set of experiments and used 5-fold cross-validation. The results we obtained from experiments showed that our CNN model performance has 88.25% and 81.74% accuracy, in leukemia versus healthy and multiclass classification of all subtypes, respectively. Finally, we also showed that the CNN model has a better performance than other wellknown machine learning algorithms.

scholarly journals Execution Assessment of Machine Learning Algorithms for Spam Profile Detection on Instagram

2021 ◽  
Vol 10 (3) ◽  
pp. 1889-1894
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Random Forest ◽  
Nearest Neighbor ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Learning Tools ◽  
Learning Models ◽  
K Nearest Neighbor

Witheverypassingsecondsocialnetworkcommunityisgrowingrapidly,becauseofthat,attackershaveshownkeeninterestinthesekindsofplatformsandwanttodistributemischievouscontentsontheseplatforms.Withthefocus on introducing new set of characteristics and features forcounteractivemeasures,agreatdealofstudieshasresearchedthe possibility of lessening the malicious activities on social medianetworks. This research was to highlight features for identifyingspammers on Instagram and additional features were presentedto improve the performance of different machine learning algorithms. Performance of different machine learning algorithmsnamely, Multilayer Perceptron (MLP), Random Forest (RF), K-Nearest Neighbor (KNN) and Support Vector Machine (SVM)were evaluated on machine learning tools named, RapidMinerand WEKA. The results from this research tells us that RandomForest (RF) outperformed all other selected machine learningalgorithmsonbothselectedmachinelearningtools.OverallRandom Forest (RF) provided best results on RapidMiner. Theseresultsareusefulfortheresearcherswhoarekeentobuildmachine learning models to find out the spamming activities onsocialnetworkcommunities.

scholarly journals A Perspective View of Cotton Leaf Image Classification Using Machine Learning Algorithms Using WEKA

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Bhagya M. Patil ◽  
Vishwanath Burkpalli
Keyword(s):  
Machine Learning ◽  
Nearest Neighbor ◽  
Learning Algorithms ◽  
Texture Features ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Cotton Leaf ◽  
K Nearest Neighbor ◽  
Color Features ◽  
Leaf Image

Cotton is one of the major crops in India, where 23% of cotton gets exported to other countries. The cotton yield depends on crop growth, and it gets affected by diseases. In this paper, cotton disease classification is performed using different machine learning algorithms. For this research, the cotton leaf image database was used to segment the images from the natural background using modified factorization-based active contour method. First, the color and texture features are extracted from segmented images. Later, it has to be fed to the machine learning algorithms such as multilayer perceptron, support vector machine, Naïve Bayes, Random Forest, AdaBoost, and K-nearest neighbor. Four color features and eight texture features were extracted, and experimentation was done using three cases: (1) only color features, (2) only texture features, and (3) both color and texture features. The performance of classifiers was better when color features are extracted compared to texture feature extraction. The color features are enough to classify the healthy and unhealthy cotton leaf images. The performance of the classifiers was evaluated using performance parameters such as precision, recall, F-measure, and Matthews correlation coefficient. The accuracies of classifiers such as support vector machine, Naïve Bayes, Random Forest, AdaBoost, and K-nearest neighbor are 93.38%, 90.91%, 95.86%, 92.56%, and 94.21%, respectively, whereas that of the multilayer perceptron classifier is 96.69%.

scholarly journals Estimating Bus Cross-Sectional Flow Based on Machine Learning Algorithm Combined with Wi-Fi Probe Technology

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 844
Author(s):  
Ting-Zhao Chen ◽  
Yan-Yan Chen ◽  
Jian-Hui Lai
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Transport Systems ◽  
Support Vector ◽  
Surveillance Video ◽  
K Nearest Neighbor ◽  
Cross Sectional ◽  
Passenger Flow

With expansion of city scale, the issue of public transport systems will become prominent. For single-swipe buses, the traditional method of obtaining section passenger flow is to rely on surveillance video identification or manual investigation. This paper adopts a new method: collecting wireless signals from mobile terminals inside and outside the bus by installing six Wi-Fi probes in the bus, and use machine learning algorithms to estimate passenger flow of the bus. Five features of signals were selected, and then the three machine learning algorithms of Random Forest, K-Nearest Neighbor, and Support Vector Machines were used to learn the data laws of signal features. Because the signal strength was affected by the complexity of the environment, a strain function was proposed, which varied with the degree of congestion in the bus. Finally, the error between the average of estimation result and the manual survey was 0.1338. Therefore, the method proposed is suitable for the passenger flow identification of single-swiping buses in small and medium-sized cities, which improves the operational efficiency of buses and reduces the waiting pressure of passengers during the morning and evening rush hours in the future.

scholarly journals Leveraging Machine Learning Algorithms For Zero-Day Ransomware Attack

2019 ◽  
Vol 8 (6) ◽  
pp. 4104-4107
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Nearest Neighbor ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Supervised Learning Algorithms ◽  
Microsoft Windows

Current global huge cyber protection attacks resulting from Infected Encryption ransomware structures over all international locations and businesses with millions of greenbacks lost in paying compulsion abundance. This type of malware encrypts consumer files, extracts consumer files, and charges higher ransoms to be paid for decryption of keys. An attacker could use different types of ransomware approach to steal a victim's files. Some of ransomware attacks like Scareware, Mobile ransomware, WannaCry, CryptoLocker, Zero-Day ransomware attack etc. A zero-day vulnerability is a software program security flaw this is regarded to the software seller however doesn’t have patch in vicinity to restore a flaw. Despite the fact that machine learning algorithms are already used to find encryption Ransomware. This is based on the analysis of a large number of PE file data Samples (benign software and ransomware utility) makes use of supervised machine learning algorithms for ascertain Zero-day attacks. This work was done on a Microsoft Windows operating system (the most attacked os through encryption ransomware) and estimated it. We have used four Supervised learning Algorithms, Random Forest Classifier , K-Nearest Neighbor, Support Vector Machine and Logistic Regression. Tests using machine learning algorithms evaluate almost null false positives with a 99.5% accuracy with a random forest algorithm.

scholarly journals Computational Predictions for Protein Sequences of COVID-19 Virus via Machine Learning Algorithms

2020 ◽  
Author(s):  
Walaa Alkady ◽  
Muhammad Zanaty ◽  
Heba M. Afify
Keyword(s):  
Machine Learning ◽  
Amino Acids ◽  
Learning Algorithms ◽  
Protein Sequences ◽  
Data Preprocessing ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Code Number ◽  
Proposed Model

Abstract The coronavirus infection is increasingly evolving to be an international epidemic in 27 countries as a serious respiratory disease. Therefore, the computational biology carrying this virus that correlated with the human population is urgently needed. In this paper, the classification of the human protein sequences of COVID-19 according to the country is applied by machine learning algorithms. The proposed model is based on the distinguishing of 9238 sequences by three stages including data preprocessing, data labeling, and classification. In the first stage, the function of data preprocessing converts the amino acids of COVID-19 protein sequences to eight groups of numbers based on volume and dipole of the amino acids. In the second stage, there are two methods for data labeling of 27 countries from 0 to 26. The first method is based on the selection of one number for each country according to the code number of countries while the second method is based on binary elements only for each country. The classification algorithms are executed to discover different COVID-19 protein sequences according to their countries. The findings are concluded that the accuracy of 100% performed by country based binary labeling method with Linear Regression (LR) or K-Nearest Neighbor (KNN) or Support Vector Machine (SVM) classifiers. Further, it found that the USA with large data records in infection rate has more priority for correct classification compared to other countries with a low data rate. The unbalanced data for COVID-19 protein sequences is considered a major issue, especially the available data in USA represented 76% from a total of 9238 sequences. As a consequence, this proposed model will help as a diagnostic bioinformatics tool for the COVID-19 protein sequences among different countries.

scholarly journals A Machine Learning Framework to Predict Nutrient Content in Valencia-Orange Leaf Hyperspectral Measurements

2020 ◽  
Vol 12 (6) ◽  
pp. 906 ◽  
Author(s):  
Lucas Prado Osco ◽  
Ana Paula Marques Ramos ◽  
Mayara Maezano Faita Pinheiro ◽  
Érika Akemi Saito Moriya ◽  
Nilton Nobuhiro Imai ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Nutrient Content ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Surface Reflectance ◽  
K Nearest Neighbor ◽  
First Derivative ◽  
Derivative Spectra ◽  
Valencia Orange

This paper presents a framework based on machine learning algorithms to predict nutrient content in leaf hyperspectral measurements. This is the first approach to evaluate macro- and micronutrient content with both machine learning and reflectance/first-derivative data. For this, citrus-leaves collected at a Valencia-orange orchard were used. Their spectral data was measured with a Fieldspec ASD FieldSpec® HandHeld 2 spectroradiometer and the surface reflectance and first-derivative spectra from the spectral range of 380 to 1020 nm (640 spectral bands) was evaluated. A total of 320 spectral signatures were collected, and the leaf-nutrient content (N, P, K, Mg, S, Cu, Fe, Mn, and Zn) was associated with them. For this, 204,800 (320 × 640) combinations were used. The following machine learning algorithms were used in this framework: k-Nearest Neighbor (kNN), Lasso Regression, Ridge Regression, Support Vector Machine (SVM), Artificial Neural Network (ANN), Decision Tree (DT), and Random Forest (RF). The training methods were assessed based on Cross-Validation and Leave-One-Out. The Relief-F metric of the algorithms’ prediction was used to determine the most contributive wavelength or spectral region associated with each nutrient. This approach was able to return, with high predictions (R2), nutrients like N (0.912), Mg (0.832), Cu (0.861), Mn (0.898), and Zn (0.855), and, to a lesser extent, P (0.771), K (0.763), and S (0.727). These accuracies were obtained with different algorithms, but RF was the most suitable to model most of them. The results indicate that, for the Valencia-orange leaves, surface reflectance data is more suitable to predict macronutrients, while first-derivative spectra is better linked to micronutrients. A final contribution of this study is the identification of the wavelengths responsible for contributing to these predictions.

scholarly journals The Role of Machine Learning Algorithms for Diagnosing Diseases

2021 ◽  
Vol 2 (01) ◽  
pp. 10-19
Author(s):  
Ibrahim Ibrahim ◽  
Adnan Abdulazeez
Keyword(s):  
Machine Learning ◽  
Nearest Neighbor ◽  
Learning Algorithms ◽  
Medical Diagnostics ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Medical Database ◽  
K Nearest Neighbor ◽  
Medical Sector

Nowadays, machine learning algorithms have become very important in the medical sector, especially for diagnosing disease from the medical database. Many companies using these techniques for the early prediction of diseases and enhance medical diagnostics. The motivation of this paper is to give an overview of the machine learning algorithms that are applied for the identification and prediction of many diseases such as Naïve Bayes, logistic regression, support vector machine, K-nearest neighbor, K-means clustering, decision tree, and random forest. In this work, many previous studies were reviewed that used machine learning algorithms for detecting various diseases in the medical area in the last three years. A comparison is provided concerning these algorithms, assessment processes, and the obtained results. Finally, a discussion of the previous works is presented.

Sign in / Sign up

Export Citation Format

Share Document