scholarly journals GeSi Nanocrystals Photo-Sensors for Optical Detection of Slippery Road Conditions Combining Two Classification Algorithms

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6395
Author(s):  
Catalin Palade ◽  
Ionel Stavarache ◽  
Toma Stoica ◽  
Magdalena Lidia Ciurea
Keyword(s):  
Traffic Safety ◽  
Nearest Neighbor ◽  
Laser Diodes ◽  
Sensor Data ◽  
Classification Algorithms ◽  
K Nearest Neighbor ◽  
Sio2 Matrix ◽  
Sputtering Deposition ◽  
Ice Coatings ◽  
Working Principle

One of the key elements in assessing traffic safety on the roads is the detection of asphalt conditions. In this paper, we propose an optical sensor based on GeSi nanocrystals embedded in SiO2 matrix that discriminates between different slippery road conditions (wet and icy asphalt and asphalt covered with dirty ice) in respect to dry asphalt. The sensor is fabricated by magnetron sputtering deposition followed by rapid thermal annealing. The photodetector has spectral sensitivity in the 360–1350 nm range and the signal-noise ratio is 102–103. The working principle of sensor setup for detection of road conditions is based on the photoresponse (photocurrent) of the sensor under illumination with the light reflected from the asphalt having different reflection coefficients for dry, wet, icy and dirty ice coatings. For this, the asphalt is illuminated sequentially with 980 and 1064 nm laser diodes. A database of these photocurrents is obtained for the different road conditions. We show that the use of both k-nearest neighbor and artificial neural networks classification algorithms enables a more accurate recognition of the class corresponding to a specific road state than in the case of using only one algorithm. This is achieved by comparing the new output sensor data with previously classified data for each algorithm and then by performing an intersection of the algorithms’ results.

COMPUTER-BASED IDENTIFICATION OF NORMAL AND ALCOHOLIC EEG SIGNALS USING WAVELET PACKETS AND ENERGY MEASURES

2013 ◽  
Vol 13 (03) ◽  
pp. 1350033 ◽  
Author(s):  
OLIVER FAUST ◽  
WENWEI YU ◽  
NAHRIZUL ADIB KADRI
Keyword(s):  
Feature Extraction ◽  
Nearest Neighbor ◽  
Probabilistic Neural Network ◽  
Gaussian Mixture ◽  
Test Method ◽  
Identification System ◽  
Classification Algorithms ◽  
K Nearest Neighbor ◽  
Eeg Signals ◽  
Computer Based

This paper describes a computer-based identification system of normal and alcoholic Electroencephalography (EEG) signals. The identification system was constructed from feature extraction and classification algorithms. The feature extraction was based on wavelet packet decomposition (WPD) and energy measures. Feature fitness was established through the statistical t-test method. The extracted features were used as training and test data for a competitive 10-fold cross-validated analysis of six classification algorithms. This analysis showed that, with an accuracy of 95.8%, the k-nearest neighbor (k-NN) algorithm outperforms naïve Bayes classification (NBC), fuzzy Sugeno classifier (FSC), probabilistic neural network (PNN), Gaussian mixture model (GMM), and decision tree (DT). The 10-fold stratified cross-validation instilled reliability in the result, therefore we are confident when we state that EEG signals can be used to automate both diagnosis and treatment monitoring of alcoholic patients. Such an automatization can lead to cost reduction by relieving medical experts from routine and administrative tasks.

scholarly journals k Nearest Neighbor Search for Location-Dependent Sensor Data in MANETs

IEEE Access ◽  
2015 ◽  
Vol 3 ◽  
pp. 942-954 ◽  
Author(s):  
Yuka Komai ◽  
Yuya Sasaki ◽  
Takahiro Hara ◽  
Shojiro Nishio
Keyword(s):  
Nearest Neighbor ◽  
Nearest Neighbor Search ◽  
Sensor Data ◽  
K Nearest Neighbor ◽  
Neighbor Search ◽  
K Nearest Neighbor Search

scholarly journals Plant disease prediction using classification algorithms

2021 ◽  
Vol 10 (1) ◽  
pp. 257
Author(s):  
Maria Morgan ◽  
Carla Blank ◽  
Raed Seetan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Nearest Neighbor ◽  
Disease Classification ◽  
Future Research ◽  
Support Vector ◽  
Classification Algorithms ◽  
Disease Prediction ◽  
K Nearest Neighbor ◽  
Artificial Neural

<p>This paper investigates the capability of six existing classification algorithms (Artificial Neural Network, Naïve Bayes, k-Nearest Neighbor, Support Vector Machine, Decision Tree and Random Forest) in classifying and predicting diseases in soybean and mushroom datasets using datasets with numerical or categorical attributes. While many similar studies have been conducted on datasets of images to predict plant diseases, the main objective of this study is to suggest classification methods that can be used for disease classification and prediction in datasets that contain raw measurements instead of images. A fungus and a plant dataset, which had many differences, were chosen so that the findings in this paper could be applied to future research for disease prediction and classification in a variety of datasets which contain raw measurements. A key difference between the two datasets, other than one being a fungus and one being a plant, is that the mushroom dataset is balanced and only contained two classes while the soybean dataset is imbalanced and contained eighteen classes. All six algorithms performed well on the mushroom dataset, while the Artificial Neural Network and k-Nearest Neighbor algorithms performed best on the soybean dataset. The findings of this paper can be applied to future research on disease classification and prediction in a variety of dataset types such as fungi, plants, humans, and animals.</p>

scholarly journals COMPARATIVE STUDY OF CLASSIFICATION ALGORITHMS: HOLDOUTS AS ACCURACY ESTIMATION

2016 ◽  
Vol 1 (1) ◽  
pp. 13 ◽  
Author(s):  
Debby Erce Sondakh
Keyword(s):  
Decision Tree ◽  
Nearest Neighbor ◽  
Naive Bayes ◽  
Decision Rules ◽  
Naïve Bayes ◽  
Support Vector ◽  
Classification Algorithms ◽  
K Nearest Neighbor ◽  
Accuracy Estimation ◽  
F Measure

Penelitian ini bertujuan untuk mengukur dan membandingkan kinerja lima algoritma klasifikasi teks berbasis pembelajaran mesin, yaitu decision rules, decision tree, k-nearest neighbor (k-NN), naïve Bayes, dan Support Vector Machine (SVM), menggunakan dokumen teks multi-class. Perbandingan dilakukan pada efektifiatas algoritma, yaitu kemampuan untuk mengklasifikasi dokumen pada kategori yang tepat, menggunakan metode holdout atau percentage split. Ukuran efektifitas yang digunakan adalah precision, recall, F-measure, dan akurasi. Hasil eksperimen menunjukkan bahwa untuk algoritma naïve Bayes, semakin besar persentase dokumen pelatihan semakin tinggi akurasi model yang dihasilkan. Akurasi tertinggi naïve Bayes pada persentase 90/10, SVM pada 80/20, dan decision tree pada 70/30. Hasil eksperimen juga menunjukkan, algoritma naïve Bayes memiliki nilai efektifitas tertinggi di antara lima algoritma yang diuji, dan waktu membangun model klasiifikasi yang tercepat, yaitu 0.02 detik. Algoritma decision tree dapat mengklasifikasi dokumen teks dengan nilai akurasi yang lebih tinggi dibanding SVM, namun waktu membangun modelnya lebih lambat. Dalam hal waktu membangun model, k-NN adalah yang tercepat namun nilai akurasinya kurang.

Service complaint identification in hotel social media: A two-step classification approach

2020 ◽  
pp. 002072092092846
Author(s):  
Jiahua Jin ◽  
Lu Lu
Keyword(s):  
Social Media ◽  
Nearest Neighbor ◽  
Support Vector ◽  
Classification Algorithms ◽  
Construction Process ◽  
K Nearest Neighbor ◽  
Classification Approach ◽  
Consumer Complaint ◽  
Training Samples ◽  
Binary Classifiers

Hotel social media provides access to dissatisfied customers and their experiences with services. However, due to massive topics and posts in social media, and the sparse distribution of complaint-related posts and, manually identifying complaints is inefficient and time-consuming. In this study, we propose a supervised learning method including training samples enlargement and classifier construction. We first identified reliable complaint and noncomplaint samples from the unlabeled dataset by using small labeled samples as training samples. Combining the labeled samples and enlarged samples, classification algorithms support vector machine and k-nearest neighbor were then adopted to build binary classifiers during the classifier construction process. Experimental results indicate the proposed method can identify complaints from social media efficiently, especially when the amount of labeled training samples is small. This study provides an efficient approach for hotel companies to distinguish a certain kind of consumer complaint information from large number of unrelated information in hotel social media.

scholarly journals APPLYING THE CLASSIFICATION ALGORITHM FOR THE SYSTEM RECOMMENDATIONS BUY SELL IN FOREX TRADING

2020 ◽  
Vol 10 (2) ◽  
pp. 152-158
Author(s):  
Iswanto ◽  
Yuliana Melita Pranoto ◽  
Reddy Alexandro Harianto
Keyword(s):  
Time Series ◽  
Recommendation System ◽  
Nearest Neighbor ◽  
Classification Algorithm ◽  
Classification Algorithms ◽  
K Nearest Neighbor

Abstract- Having a sophisticated application, even though often experience problems in deciding BUY - SELL in trading forex trading. This is due to the often time series predictions, in the high variable experiencing high values ​​as well as low variables, for that it is needed a recommendation system to overcome this problem. The application of classification algorithms to the recommendation system in support of BUY-SELL decisions is one appropriate alternative to overcome this. K-Nearest Neighbor (K-NN) algorithm was chosen because the K-NN method is an algorithm that can be used in building a recommendation system that can classify data based on the closest distance. This system is designed to assist traders in making BUY-SELL decisions, based on predictive data. The results of the recommendation system from the ten trials predicted by Arima are recommended. When compared to the price in the field the target profit is 7% per week from ten experiments if the average profit has exceeded the target

scholarly journals Performance Research on Medical Data Classification using Traditional and Soft Computing Techniques

2019 ◽  
Vol 8 (2S3) ◽  
pp. 990-995
Keyword(s):  
Data Mining ◽  
Soft Computing ◽  
Nearest Neighbor ◽  
Classification Performance ◽  
Medical Data ◽  
Support Vector ◽  
Classification Algorithms ◽  
K Nearest Neighbor ◽  
Classification Techniques ◽  
Soft Computing Techniques

The world today has made giant leaps in the field of Medicine. There is tremendous amount of researches being carried out in this field leading to new discoveries that is making a heavy impact on the mankind. Data being generated in this field is increasing enormously. A need has arisen to analyze these data in order to find out the meaningful and relevant hidden patterns. These patterns can be used for clinical diagnosis. Data mining is an efficient approach in discovering these patterns. Among the many data mining techniques that exists, this paper aims at analyzing the medical data using various Classification techniques. The classification techniques used in this study include k-Nearest neighbor (kNN), Decision Tree, Naive Bayes which are hard computing algorithms, whereas the soft computing algorithms used in this study include Support Vector Machine (SVM), Artificial Neural Networks (ANN) and Fuzzy k-Means clustering. We have applied these algorithms to three kinds of datasets that are Breast Cancer Wisconsin, Haberman Data and Contraceptive Method Choice dataset. Our results show that soft computing based classification algorithms better classifications than the traditional classification algorithms in terms of various classification performance measures

Classification Algorithms for Determining Handwritten Digit

2016 ◽  
Vol 12 (1) ◽  
pp. 96-102 ◽  
Author(s):  
Hayder AL-Behadili
Keyword(s):  
Machine Learning ◽  
Nearest Neighbor ◽  
Paper Analysis ◽  
Classification Algorithms ◽  
Learning Approaches ◽  
K Nearest Neighbor ◽  
Data Intensive ◽  
Knowledge Based ◽  
Computer Scientists ◽  
Mathematical Techniques

Data-intensive science is a critical science paradigm that interferes with all other sciences. Data mining (DM) is a powerful and useful technology with wide potential users focusing on important meaningful patterns and discovers a new knowledge from a collected dataset. Any predictive task in DM uses some attribute to classify an unknown class. Classification algorithms are a class of prominent mathematical techniques in DM. Constructing a model is the core aspect of such algorithms. However, their performance highly depends on the algorithm behavior upon manipulating data. Focusing on binarazaition as an approach for preprocessing, this paper analysis and evaluates different classification algorithms when construct a model based on accuracy in the classification task. The Mixed National Institute of Standards and Technology (MNIST) handwritten digits dataset provided by Yann LeCun has been used in evaluation. The paper focuses on machine learning approaches for handwritten digits detection. Machine learning establishes classification methods, such as K-Nearest Neighbor(KNN), Decision Tree (DT), and Neural Networks (NN). Results showed that the knowledge-based method, i.e. NN algorithm, is more accurate in determining the digits as it reduces the error rate. The implication of this evaluation is providing essential insights for computer scientists and practitioners for choosing the suitable DM technique that fit with their data.

scholarly journals SARM: Salah Activities Recognition Model Based on Smartphone

Electronics ◽  
2019 ◽  
Vol 8 (8) ◽  
pp. 881
Author(s):  
Nafees Ahmad ◽  
Lansheng Han ◽  
Khalid Iqbal ◽  
Rashid Ahmad ◽  
Muhammad Adil Abid ◽  
...  
Keyword(s):  
Nearest Neighbor ◽  
Major Effect ◽  
Sensor Data ◽  
Data Sets ◽  
Mobile Sensor ◽  
K Nearest Neighbor ◽  
Recognition Model ◽  
Average Accuracy ◽  
Smartphone Sensors ◽  
Model Features

Alzheimer’s is a chronic neurodegenerative disease that frequently occurs in many people today. It has a major effect on the routine activities of affected people. Previous advancement in smartphone sensors technology enables us to help people suffering from Alzheimer’s. For people in the Muslim community, where it is mandatory to offer prayers five times a day, it may mean that they are struggling in their daily life prayers due to Alzheimer’s or lack of concentration. To deal with such a problem, automated mobile sensor-based activity recognition applications can be supportive to design accurate and precise solutions with an objective to direct the Namazi (worshipper). In this paper, a Salah activities recognition model (SARM) using a mobile sensor is proposed with the aim to recognize specific activities, such as Al-Qayam (standing), Ruku (standing to bowing), and Sujud (standing to prostration). This model entails the collection of data, selection and placement of sensor, data preprocessing, segmentation, feature extraction, and classification. The proposed model will provide a stepping edge to develop an application for observing prayer. For these activities’ recognition, data sets were collected from ten subjects, and six different features sets were used to get improved results. Extensive experiments were performed to test and validate the model features to train random forest (RF), K-nearest neighbor (KNN), naive Bayes (NB), and decision tree (DT). The predicted average accuracy of RF, KNN, NB, and DT was 97%, 94%, 71.6%, and 95% respectively.

scholarly journals Feature Analysis of Smart Shoe Sensors for Classification of Gait Patterns

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6253
Author(s):  
Unang Sunarya ◽  
Yuli Sun Hariyani ◽  
Taeheum Cho ◽  
Jongryun Roh ◽  
Joonho Hyeong ◽  
...  
Keyword(s):  
Nearest Neighbor ◽  
Pressure Sensors ◽  
Machine Learning Algorithms ◽  
Sensor Data ◽  
Human Gait ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Gait Patterns ◽  
Gait Classification

Gait analysis is commonly used to detect foot disorders and abnormalities such as supination, pronation, unstable left foot and unstable right foot. Early detection of these abnormalities could help us to correct the walking posture and avoid getting injuries. This paper presents extensive feature analyses on smart shoes sensor data, including pressure sensors, accelerometer and gyroscope signals, to obtain the optimum combination of the sensors for gait classification, which is crucial to implement a power-efficient mobile smart shoes system. In addition, we investigated the optimal length of data segmentation based on the gait cycle parameters, reduction of the feature dimensions and feature selection for the classification of the gait patterns. Benchmark tests among several machine learning algorithms were conducted using random forest, k-nearest neighbor (KNN), logistic regression and support vector machine (SVM) algorithms for the classification task. Our experiments demonstrated the combination of accelerometer and gyroscope sensor features with SVM achieved the best performance with 89.36% accuracy, 89.76% precision and 88.44% recall. This research suggests a new state-of-the-art gait classification approach, specifically on detecting human gait abnormalities.

Sign in / Sign up

Export Citation Format

Share Document