scholarly journals GPS-Based Indoor/Outdoor Detection Scheme Using Machine Learning Techniques

2020 ◽  
Vol 10 (2) ◽  
pp. 500
Author(s):  
Van Bui ◽  
Nam Tuan Le ◽  
Thanh Luan Vu ◽  
Van Hoa Nguyen ◽  
Yeong Min Jang

Recent advances in mobile communication require that indoor/outdoor environment information be available for both individual applications and wireless signal transmission in order to improve interference control and serve upper-layer applications. In this paper, we present a scheme to identify the indoor/outdoor environment using GPS signals combined with machine learning classification techniques. Compared to traditional schemes, which are based on received signal strength indicator (RSSI), the proposed scheme promises a robust approach with high accuracy, smooth operation when moving between indoor and outdoor environments, as well as easy implementation and training. The proposed scheme combined information from a certain number of GPS satellites, using the GPS sensor on mobile devices. Then, data are collected, preprocessed, and classified as indoor or outdoor environment using a machine learning model that is optimized for the best performance. The GPS input data were collected in the Kookmin University area and included 850 training samples and 170 test samples. The overall accuracy reached 97%.

2022 ◽  
Author(s):  
Sahan M. Vijithananda ◽  
Mohan L. Jayatilake ◽  
Badra Hewavithana ◽  
Teresa Gonçalves ◽  
Luis M. Rato ◽  
...  

Abstract Background: Diffusion-weighted (DW) imaging is a well-recognized magnetic resonance imaging (MRI) technique that is being routinely used in brain examinations in modern clinical radiology practices. This study focuses on extracting demographic and texture features from MRI Apparent Diffusion Coefficient (ADC) images of human brain tumors, identifying the distribution patterns of each feature and applying Machine Learning (ML) techniques to differentiate malignant from benign brain tumors.Methods: This prospective study was carried out using 1599 labeled MRI brain ADC image slices, 995 malignant, 604 benign from 195 patients who were radiologically diagnosed and histopathologically confirmed as brain tumor patients.The demographics, mean pixel values, skewness, kurtosis, features of Grey Level Co-occurrence Matrix (GLCM), mean, variance, energy, entropy, contrast, homogeneity, correlation, prominence and shade, were extracted from MRI ADC images of each patient.At the feature selection phase, the validity of the extracted features were measured using ANOVA f-test. Then, these features were used as input to several Machine Learning classification algorithms and the respective models were assessed.Results: According to the results of ANOVA f-test feature selection process, two attributes: skewness (3.34) and GLCM homogeneity (3.45) scored the lowest ANOVA f-test scores. Therefore both features were excluded in continuation of the experiment. From the different tested ML algorithms, the Random Forest classifier was chosen to build the final ML model since it presented the highest accuracy. The final model was able to predict malignant and benign neoplasms with an 90.41% accuracy after the hyper parameter tuning process.Conclusion: This study concludes that the above mentioned features (except skewness and GLCM homogeneity) are informative to identify and differentiate malignant from benign brain tumors. Moreover, they enable the development of a high-performance ML model that has the ability to assist in the decision-making steps of brain tumor diagnosis process, prior to attempting invasive diagnostic procedures such as brain biopsies.


2019 ◽  
Vol 141 (12) ◽  
Author(s):  
Conner Sharpe ◽  
Tyler Wiest ◽  
Pingfeng Wang ◽  
Carolyn Conner Seepersad

Abstract Supervised machine learning techniques have proven to be effective tools for engineering design exploration and optimization applications, in which they are especially useful for mapping promising or feasible regions of the design space. The design space mappings can be used to inform early-stage design exploration, provide reliability assessments, and aid convergence in multiobjective or multilevel problems that require collaborative design teams. However, the accuracy of the mappings can vary based on problem factors such as the number of design variables, presence of discrete variables, multimodality of the underlying response function, and amount of training data available. Additionally, there are several useful machine learning algorithms available, and each has its own set of algorithmic hyperparameters that significantly affect accuracy and computational expense. This work elucidates the use of machine learning for engineering design exploration and optimization problems by investigating the performance of popular classification algorithms on a variety of example engineering optimization problems. The results are synthesized into a set of observations to provide engineers with intuition for applying these techniques to their own problems in the future, as well as recommendations based on problem type to aid engineers in algorithm selection and utilization.


2021 ◽  
Vol 12 ◽  
Author(s):  
André Geremia Parise ◽  
Gabriela Niemeyer Reissig ◽  
Luis Felipe Basso ◽  
Luiz Gustavo Schultz Senko ◽  
Thiago Francisco de Carvalho Oliveira ◽  
...  

In our study, we investigated some physiological and ecological aspects of the life of Cuscuta racemosa Mart. (Convolvulaceae) plants with the hypothesis that they recognise different hosts at a distance from them, and they change their survival strategy depending on what they detect. We also hypothesised that, as an attempt of prolonging their survival through photosynthesis, the synthesis of chlorophylls (a phenomenon not completely explained in these parasitic plants) would be increased if the plants don’t detect a host. We quantified the pigments related to photosynthesis in different treatments and employed techniques such as electrophysiological time series recording, analyses of the complexity of the obtained signals, and machine learning classification to test our hypotheses. The results demonstrate that the absence of a host increases the amounts of chlorophyll a, chlorophyll b, and β-carotene in these plants, and the content varied depending on the host presented. Besides, the electrical signalling of dodders changes according to the species of host perceived in patterns detectable by machine learning techniques, suggesting that they recognise from a distance different host species. Our results indicate that electrical signalling might underpin important processes such as foraging in plants. Finally, we found evidence for a likely process of attention in the dodders toward the host plants. This is probably to be the first empirical evidence for attention in plants and has important implications on plant cognition studies.


Symmetry ◽  
2020 ◽  
Vol 12 (4) ◽  
pp. 499 ◽  
Author(s):  
Iqbal H. Sarker ◽  
Yoosef B. Abushark ◽  
Asif Irshad Khan

This paper mainly formulates the problem of predicting context-aware smartphone apps usage based on machine learning techniques. In the real world, people use various kinds of smartphone apps differently in different contexts that include both the user-centric context and device-centric context. In the area of artificial intelligence and machine learning, decision tree model is one of the most popular approaches for predicting context-aware smartphone usage. However, real-life smartphone apps usage data may contain higher dimensions of contexts, which may cause several issues such as increases model complexity, may arise over-fitting problem, and consequently decreases the prediction accuracy of the context-aware model. In order to address these issues, in this paper, we present an effective principal component analysis (PCA) based context-aware smartphone apps prediction model, “ContextPCA” using decision tree machine learning classification technique. PCA is an unsupervised machine learning technique that can be used to separate symmetric and asymmetric components, and has been adopted in our “ContextPCA” model, in order to reduce the context dimensions of the original data set. The experimental results on smartphone apps usage datasets show that “ContextPCA” model effectively predicts context-aware smartphone apps in terms of precision, recall, f-score and ROC values in various test cases.


2016 ◽  
Vol 2016 ◽  
pp. 1-21 ◽  
Author(s):  
Taimur Bakhshi ◽  
Bogdan Ghita

Traffic classification utilizing flow measurement enables operators to perform essential network management. Flow accounting methods such as NetFlow are, however, considered inadequate for classification requiring additional packet-level information, host behaviour analysis, and specialized hardware limiting their practical adoption. This paper aims to overcome these challenges by proposing two-phased machine learning classification mechanism with NetFlow as input. The individual flow classes are derived per application throughk-means and are further used to train a C5.0 decision tree classifier. As part of validation, the initial unsupervised phase used flow records of fifteen popular Internet applications that were collected and independently subjected tok-means clustering to determine unique flow classes generated per application. The derived flow classes were afterwards used to train and test a supervised C5.0 based decision tree. The resulting classifier reported an average accuracy of 92.37% on approximately 3.4 million test cases increasing to 96.67% with adaptive boosting. The classifier specificity factor which accounted for differentiating content specific from supplementary flows ranged between 98.37% and 99.57%. Furthermore, the computational performance and accuracy of the proposed methodology in comparison with similar machine learning techniques lead us to recommend its extension to other applications in achieving highly granular real-time traffic classification.


Opinions from others play a significant part to take our own decision, The people’s opinions, attitudes and emotions are a computational study toward an entity is called as Sentiment Analysis (SA) or Opinion Mining (OM). In today's world, everything like business, organization and even individuals wants to know opinion from public or customers about their presentation, products and about their services which will give clear idea about their product, portfolio in the market and if these services is not up to the mark how their services they improve, so that their business will perform better. To give output as positive, negative or neutral and find the difference of a specified user text or data from the dataset is the main task of the sentiment or opinion analysis. The opinions, sentiments and subjectivity of text are computational treatment in text mining with Sentiment Analysis (SA). With the help of sentiment analysis this paper describe the machine learning classification techniques for hotel reviews for which dataset obtained from Trip advisor hotel reviews website. System got 99.07 % accuracy for MAXENT Classifier with Train size and Test size 80% and 20% respectively.


Author(s):  
Seyma Kiziltas Koc ◽  
Mustafa Yeniad

Technologies which are used in the healthcare industry are changing rapidly because the technology is evolving to improve people's lifestyles constantly. For instance, different technological devices are used for the diagnosis and treatment of diseases. It has been revealed that diagnosis of disease can be made by computer systems with developing technology.Machine learning algorithms are frequently used tools because of their high performance in the field of health as well as many field. The aim of this study is to investigate different machine learning classification algorithms that can be used in the diagnosis of diabetes and to make comparative analyzes according to the metrics in the literature. In the study, seven classification algorithms were used in the literature. These algorithms are Logistic Regression, K-Nearest Neighbor, Multilayer Perceptron, Random Forest, Decision Trees, Support Vector Machine and Naive Bayes. Firstly, classification performance of algorithms are compared. These comparisons are based on accuracy, sensitivity, precision, and F1-score. The results obtained showed that support vector machine algorithm had the highest accuracy with 78.65%.


Author(s):  
Anupam Sen

Machine Learning (ML) techniques play an important role in the medical field. Early diagnosis is required to improve the treatment of carcinoma. During this analysis Breast Cancer Coimbra dataset (BCCD) with ten predictors are analyzed to classify carcinoma. In this paper method for feature selection and Machine learning algorithms are applied to the dataset from the UCI repository. WEKA (“Waikato Environment for Knowledge Analysis”) tool is used for machine learning techniques. In this paper Principal Component Analysis (PCA) is used for feature extraction. Different Machine Learning classification algorithms are applied through WEKA such as Glmnet, Gbm, ada Boosting, Adabag Boosting, C50, Cforest, DcSVM, fnn, Ksvm, Node Harvest compares the accuracy and also compare values such as Kappa statistic, Mean Absolute Error (MAE), Root Mean Square Error (RMSE). Here the 10-fold cross validation method is used for training, testing and validation purposes.


Author(s):  
Ahmad Abdulla ◽  
George Baryannis ◽  
Ibrahim Badi

Supplier selection is an important part of supply chain management (SCM) for any organisation to achieve their objectives. The problem has attracted great interest from academics and practitioners. The selection process starts with determining the most important criteria out of a wide range. Many academic researchers apply multi-criteria decision-making (MCDM) techniques for supplier selection. However, the complexity of such approaches may increase significantly, especially when considering a large number of suppliers and selection criteria. This paper proposes an integrated approach combining machine learning classification with the Analytic Hierarchy Process (AHP) to select and evaluate the most suitable supplier. A Decision Tree (DT) classifier is used to select the most important criteria, instead of applying AHP on the complete set of criteria. The applicability of the approach is demonstrated using data from Libyan companies. Results show that decision trees can successfully lead to a most important subset of selection criteria, which would lead to a less complex application of AHP.


Diabetes Mellitus is considered one of the chronic diseases of humankind which causes an increase in blood sugar. Many complications are reported if DM remains untreated and unidentified. Identification of this disease requires a lot of physical and mental trauma and effort which involves visiting a doctor, blood and urine test at the diagnostic center which consumes more time. Difficulties can be over crossed using the trending technology of Machine learning. The idea of the model is to prognosticate the occurrence of a diabetic with high accuracy. Therefore, two machine learning classification algorithms namely Fine Decision Tree and Support Vector Machine are used in this experiment to detect diabetes at an early stage. Therefore two machine learning classification algorithms namely Fine Decision Tree and Support Vector Machine are used in this experiment to detect diabetes at an early stage.


Sign in / Sign up

Export Citation Format

Share Document