XAI Empowered Dual Band Wi-Fi Based Indoor Localization via Ensemble Learning

Kakisim, Arzu Gorgulu; Turgut, Zeynep; Atmaca, Tulin

doi:10.1109/nof58724.2023.10302788

Cited by 3 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Soft voting, on the other hand, involves predicting class labels by considering the expected probabilities (p) provided by each classifier. It's important to note that this approach is only advisable if the classifiers are appropriately calibrated [30].…”

Section: Probabilistic Votingmentioning

confidence: 99%

Sentiment analysis of coronavirus data with ensemble and machine learning methods

Başarslan,

Kayaalp

2024

Turkish Journal of Engineering

View full text Add to dashboard Cite

The coronavirus pandemic has distanced people from social life and increased the use of social media. People's emotions can be determined with text data collected from social media applications. This is used in many fields, especially in commerce. This study aims to predict people's sentiments about the pandemic by applying sentiment analysis to Twitter tweets about the pandemic using single machine learning classifiers (Decision Tree-DT, K-Nearest Neighbor-KNN, Logistic Regression-LR, Naïve Bayes-NB, Random Forest-RF) and ensemble learning methods (Majority Voting (MV), Probabilistic Voting (PV), and Stacking (STCK)). After vectorizing the tweets using two predictive methods, Word2Vec (W2V) and Doc2Vec, and two traditional word representation methods, Term Frequency-Inverse Document Frequency (TF-IDF) and Bag of Words (BOW), classification models built using single machine learning classifiers were compared to models built using ensemble learning methods (MV, PV and STCK) by heterogeneously combining single machine classifier algorithms. Accuracy (ACC), F-measure (F), precision (P), and recall (R) were used as performance measures, with training/test separation rates of 70%-30% and 80%-20%, respectively. Among these models, the ACC of ensemble learning models ranged from 89% to 73%, while the ACC of single classifier models ranged from 60% to 80%. Among the ensemble learning methods, STCK with Doc2Vec text representation/embedding method gave the best ACC result of 89%. According to the experimental results, ensemble models built with heterogeneous machine learning classifier algorithms gave better results than single machine learning classifier algorithms.

show abstract

Section: Probabilistic Votingmentioning

confidence: 99%

Sentiment analysis of coronavirus data with ensemble and machine learning methods

Başarslan,

Kayaalp

2024

Turkish Journal of Engineering

View full text Add to dashboard Cite

show abstract

Feature Selection in the Diabetes Dataset with the Marine Predator Algorithm and Classification using Machine Learning Methods

Türk,

Metin,

Lüy

2024

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım Ve Teknoloji

View full text Add to dashboard Cite

Diabetes, which is classified as one of the leading causes of mortality, is a chronic and intricate metabolic disorder defined by disruptions in the metabolism of carbohydrates, fats, and proteins. Type 1 diabetes is categorized alongside Type 2 diabetes, as well as other distinct kinds of diabetes, including gestational diabetes. Complications, both acute and chronic, manifest in individuals with diabetes due to diminished insulin secretion and disruptions in the metabolism of carbohydrates, fats, and proteins. Following the completion of the data preparation step, the diabetes dataset that was collected from Kaggle is then sent to the feature extraction module for analysis. After the optimization process has been completed, the feature selection block will determine which characteristics stand out the most. The selected traits discussed before are sorted into several categories using the categorization module. The findings are compared to those that would have been obtained if the marine predator optimization algorithm (MPOA) technique had not been carried out, specifically regarding metrics like the F1 score, Recall, Accuracy, and Precision. The findings indicate that the LR classification approach achieves an accuracy rate of 77.63% without property selection. However, when the characteristics are selected using the MPOA, the accuracy rate increases to 79.39%.

show abstract

Mobile Robot Positioning with Wireless Fidelity Fingerprinting and Explainable Artificial Intelligence

Abacı,

Seçkin

2024

Sensors

View full text Add to dashboard Cite

Wireless Fidelity (Wi-Fi) based positioning has gained popularity for accurate indoor robot positioning in indoor navigation. In daily life, it is a low-cost solution because Wi-Fi infrastructure is already installed in many indoor areas. In addition, unlike the Global Navigation Satellite System (GNSS), Wi-Fi is more suitable for use indoors because signal blocking, attenuation, and reflection restrictions create a unique pattern in places with many Wi-Fi transmitters, and more precise positioning can be performed than GNSS. This paper proposes a machine learning-based method for Wi-Fi-enabled robot positioning in indoor environments. The contributions of this research include comprehensive 3D position estimation, utilization of existing Wi-Fi infrastructure, and a carefully collected dataset for evaluation. The results indicate that the AdaBoost algorithm attains a notable level of accuracy, utilizing the dBm signal strengths from Wi-Fi access points distributed throughout a four-floor building. The mean average error (MAE) values obtained in three axes with the Adaptive Boosting algorithm are 0.044 on the x-axis, 0.063 on the y-axis, and 0.003 m on the z-axis, respectively. In this study, the importance of various Wi-Fi access points was examined with explainable artificial intelligence methods, and the positioning performances obtained by using data from a smaller number of access points were examined. As a result, even when positioning was conducted with only seven selected Wi-Fi access points, the MAE value was found to be 0.811 for the x-axis, 0.492 for the y-axis, and 0.134 for the Z-axis, respectively.

show abstract

XAI Empowered Dual Band Wi-Fi Based Indoor Localization via Ensemble Learning

Cited by 3 publications

References 15 publications

Sentiment analysis of coronavirus data with ensemble and machine learning methods

Sentiment analysis of coronavirus data with ensemble and machine learning methods

Feature Selection in the Diabetes Dataset with the Marine Predator Algorithm and Classification using Machine Learning Methods

Mobile Robot Positioning with Wireless Fidelity Fingerprinting and Explainable Artificial Intelligence

Contact Info

Product

Resources

About