Indoor Positioning System using Regression-based Fingerprint Method

Abstract

Indoor Positioning System has opportunity to be used in different business platform. Based on past research, optimized localization method for Bluetooth Low Energy (BLE) to predict position of person or object with high accuracy has not been found yet. Most recent research that have solve Received Signal Strength (RSS) inconsistent value is using fingerprint method. This paper proposed a deep regression machine learning using convolutional neural network (CNN) with regression-based fingerprint model to estimate real position. The model used 5 nearest fingerprints as reference RSS values with their location (x or y) label as inputs to produce output of single value position (x or y), then repeat the process to produce second value of position to create complete coordinate of estimated position. To evaluate the proposed model, a comparison between training data with validation data using Root Mean Squared Error (RMSE) is used. The comparisons are with Multilayer Perceptron model and with the weighted sum method as benchmark. The experiment Gave results of mean distance and 90th percentile distance between proposed model with the benchmark. CNN model achieved accuracies of lower than 330cm at 90th percentile with mean distance lower than 185cm. Weighted sum model achieved accuracies lower than 360cm at 90th percentile with mean distance higher than 185cm, and MLP is in between them. The result demonstrates that the proposed method outperformed the benchmark methods.

Indoor Positioning System Based on Wi-Fi and Bluetooth Low Energy

“…The authors developed a fuzzy matching algorithm by using a particle swarm optimization. In [13], the authors analyzed the effect of the beacon's location while considering the effect of the grid size and the location of the reference points (RPs). Using a K-means algorithm, the authors in [14] proposed an efficient method for fingerprintbased positioning of multi-story buildings.…”

The Transformation of MDMC Social Piety in Forming Public Spaces in the Middle of the Covid-19 Pandemic in Indonesia

“…Permasalahan penelitian terdahulu, kurang mampu dalam mengelaborasi dampak perubahan kualitatif dari gerakan volunter Muhammadiyah Disaster Management Center. Ghozali and Putra (2019); Surahman (2020) hanya mengkaji tentang Peran Muhammadiyah Disaster Management Center Dalam Mitigasi Bencana, namun pada saat yang sama justru menghilangkan dua permasalahan terpenting yaitu dampak perubahan sosial yang terjadi pasca benca, dan pembentukan ruang publik demokratik dari proses transformasi sosial. Dengan demikian, perlu dikaji dengan melakukan studi eksploratif yang lebih dalam dengan menggunakan perspektif sinkronik tentang transformasi kesalehan sosial volunter Muhammadiyah Disaster Management Center dalam merekonstruksi ruang publik di tengah pandemi Covid-19 di Indonensia secara komprehensif.…”

FedLoc: Federated Learning Framework for Data-Driven Cooperative Localization and Location Data Processing

“…Various works on using deep learning models and RSS measurements for indoor fingerprinting have been published in recent years, for instance [114], [115], [116], [117], [118] based on DNN, CNN, LSTM. Although these works are originally centralized algorithms, they can be implemented in a distributed manner under our FedLoc framework.…”

“…Before leaving this subsection, let us give a concrete example to shed more light on both the latency and the positioning accuracy of KNN and CNN model. In [114], a real office room is considered and a CNN model is applied to predict some unknown 2-dimensional positions y. The selected CNN architecture consists of 3 convolution layers and each convolution layer has 5 kernels, followed by two fully connected layers with 10 neurons in each layer.…”

“…The selected CNN architecture consists of 3 convolution layers and each convolution layer has 5 kernels, followed by two fully connected layers with 10 neurons in each layer. For more details, interested readers can refer to the original paper [114]. In the test phase, a number of 260 data samples (of 24-dimensional) are fed into CNN.…”