scholarly journals Self-Learning Pipeline for Low-Energy Resource-Constrained Devices

Energies ◽  
2021 ◽  
Vol 14 (20) ◽  
pp. 6636
Author(s):  
Fouad Sakr ◽  
Riccardo Berta ◽  
Joseph Doyle ◽  
Alessandro De De Gloria ◽  
Francesco Bellotti
Keyword(s):  
Embedded System ◽  
Nearest Neighbor ◽  
Energy Resource ◽  
K Nearest Neighbor ◽  
Resource Constrained ◽  
Confidence Measure ◽  
Embedded Devices ◽  
Remote Training ◽  
Iot Devices ◽  
Self Learning

The trend of bringing machine learning (ML) to the Internet of Things (IoT) field devices is becoming ever more relevant, also reducing the overall energy need of the applications. ML models are usually trained in the cloud and then deployed on edge devices. Most IoT devices generate large amounts of unlabeled data, which are expensive and challenging to annotate. This paper introduces the self-learning autonomous edge learning and inferencing pipeline (AEP), deployable in a resource-constrained embedded system, which can be used for unsupervised local training and classification. AEP uses two complementary approaches: pseudo-label generation with a confidence measure using k-means clustering and periodic training of one of the supported classifiers, namely decision tree (DT) and k-nearest neighbor (k-NN), exploiting the pseudo-labels. We tested the proposed system on two IoT datasets. The AEP, running on the STM NUCLEO-H743ZI2 microcontroller, achieves comparable accuracy levels as same-type models trained on actual labels. The paper makes an in-depth performance analysis of the system, particularly addressing the limited memory footprint of embedded devices and the need to support remote training robustness.

scholarly journals Classification of lung condition for early diagnosis of pneumonia and tuberculosis based on embedded system

2021 ◽  
Vol 10 (3) ◽  
pp. 1262-1270
Author(s):  
Rizal Maulana ◽  
Alfatehan Arsya Baharin ◽  
Hurriyatul Fitriyah
Keyword(s):  
Carbon Dioxide ◽  
Embedded System ◽  
Nearest Neighbor ◽  
Image Data ◽  
Early Research ◽  
K Nearest Neighbor ◽  
X Ray ◽  
Lung Condition ◽  
Chest X Ray

The lungs are the main organs in the respiratory system that have a function as a place for exchange of oxygen and carbon dioxide. Due to the importance of lung function, indications of lung disorders must be detected and diagnosed early. Research on the classification of lung conditions generally uses chest x-ray image data. Where a time-consuming procedure is needed to obtain the data. In this research, an embedded system to diagnose lung conditions was designed. The system was made to be easy to use independently and provides real-time examination results. This system uses parameters of body temperature, oxygen saturation, fingernail color and lung volume in classifying lung conditions. There are three conditions that can be classified by the system, that is healthy lungs, pneumonia and tuberculosis. The k-nearest neighbor method was used in the classification process in the designed system. The dataset used was 51 data obtained from the hospital. Each data already has a label in the form of lung condition based on the doctor’s diagnosis. The proposed system has an accuracy of 88.24% in classifying lung conditions.

scholarly journals Irrelevant frame removal for scene analysis using video hyperclique pattern and spectrum analysis

2016 ◽  
Vol 5 (1) ◽  
pp. 1
Author(s):  
Yuchou Chang ◽  
Hong Lin
Keyword(s):  
Semantic Analysis ◽  
Nearest Neighbor ◽  
Video Retrieval ◽  
Video Frame ◽  
K Nearest Neighbor ◽  
Confidence Measure ◽  
Redundant Data ◽  
Support Measure ◽  
Video Frames ◽  
Hyperclique Pattern

<p>Video often include frames that are irrelevant to the scenes for recording. These are mainly due to imperfect shooting, abrupt movements of camera, or unintended switching of scenes. The irrelevant frames should be removed before the semantic analysis of video scene is performed for video retrieval. An unsupervised approach for automatic removal of irrelevant frames is proposed in this paper. A novel log-spectral representation of color video frames based on Fibonacci lattice-quantization has been developed for better description of the global structures of video contents to measure similarity of video frames. Hyperclique pattern analysis, used to detect redundant data in textual analysis, is extended to extract relevant frame clusters in color videos. A new strategy using the k-nearest neighbor algorithm is developed for generating a video frame support measure and an h-confidence measure on this hyperclique pattern based analysis method. Evaluation of the proposed irrelevant video frame removal algorithm reveals promising results for datasets with irrelevant frames.</p>

scholarly journals Pembangunan Perangkat Pendeteksi Jenis Gerakan Raket Bulu Tangkis Dengan Algoritma KNN dan SVM

Teknika ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 113-120
Author(s):  
Raymond Chandra Putra
Keyword(s):  
Support Vector Machine ◽  
Internet Of Things ◽  
Embedded System ◽  
Web Service ◽  
Nearest Neighbor ◽  
Support Vector ◽  
K Nearest Neighbor

Internet of Things (IoT) dapat diaplikasikan untuk banyak bidang, salah satunya pada latihan olahraga bulu tangkis. Pada olahraga bulu tangkis, terutama bagi pemain pemula mengalami kesulitan untuk mengetahui apakah gerakan yang dilakukan sudah benar atau belum. Pada penelitian ini, dibangun sebuah embedded system yang dipasang pada raket yang berfungsi mengambil data gerakan pukulan. Data pukulan ini dikirim ke sebuah perangkat lunak yang dapat mendeteksi jenis gerakan raket bulu tangkis. Embedded system terdiri dari Arduino dan sensor accelerometer dan gyroscope. Data pukulan disimpan ke dalam basis data melalui web service. Perangkat lunak dibangun dengan memanfaatkan prinsip pembelajaran mesin terarah yaitu klasifikasi. Algoritma klasifikasi yang digunakan adalah algoritma k-Nearest Neighbor dan membandingkan hasilnya dengan algoritma lain yaitu Support Vector Machine. Pengujian dilakukan dengan mengumpulkan data latih yang digunakan oleh algoritma klasifikasi untuk memprediksi gerakan. Kinerja dari kedua algoritma klasifikasi diukur dan dibandingkan. Dari hasil pengujian, maka disimpulkan bahwa algoritma Support Vector Machine menghasilkan kinerja yang lebih baik dari k-Nearest Neighbor dalam mendeteksi gerakan raket. Selain itu kinerja algoritma Support Vector Machine yang lebih baik tersebut dihasilkan dengan data latih yang lebih sedikit dibandingkan k-Nearest Neighbor.

Estimating the Posterior Probabilities Using the K-Nearest Neighbor Rule

2005 ◽  
Vol 17 (3) ◽  
pp. 731-740 ◽  
Author(s):  
Amir F. Atiya
Keyword(s):  
Posterior Probability ◽  
Nearest Neighbor ◽  
Nearest Neighbors ◽  
Posterior Probabilities ◽  
Classification Problems ◽  
K Nearest Neighbor ◽  
Confidence Measure ◽  
K Nearest Neighbors ◽  
Nearest Neighbor Rule ◽  
Likelihood Approach

In many pattern classification problems, an estimate of the posterior probabilities (rather than only a classification) is required. This is usually the case when some confidence measure in the classification is needed. In this article, we propose a new posterior probability estimator. The proposed estimator considers the K-nearest neighbors. It attaches a weight to each neighbor that contributes in an additive fashion to the posterior probability estimate. The weights corresponding to the K-nearest-neighbors (which add to 1) are estimated from the data using a maximum likelihood approach. Simulation studies confirm the effectiveness of the proposed estimator.

Machine Learning Verdict of EEG Signals in Brain Computer Interface

2018 ◽  
pp. 429-441
Author(s):  
M. Jeyanthi ◽  
C. Velayutham
Keyword(s):  
Nearest Neighbor ◽  
Technology Development ◽  
Vital Role ◽  
Svm Classifier ◽  
K Nearest Neighbor ◽  
Data Mining Technique ◽  
Data Set ◽  
Eeg Data ◽  
Irrelevant Attributes

In Science and Technology Development BCI plays a vital role in the field of Research. Classification is a data mining technique used to predict group membership for data instances. Analyses of BCI data are challenging because feature extraction and classification of these data are more difficult as compared with those applied to raw data. In this paper, We extracted features using statistical Haralick features from the raw EEG data . Then the features are Normalized, Binning is used to improve the accuracy of the predictive models by reducing noise and eliminate some irrelevant attributes and then the classification is performed using different classification techniques such as Naïve Bayes, k-nearest neighbor classifier, SVM classifier using BCI dataset. Finally we propose the SVM classification algorithm for the BCI data set.

PENENTUAN DAERAH PRIORITAS PELAYANAN AKTA KELAHIRAN DENGAN METODE K-NN DAN K-MEANS

2020 ◽  
Vol 17 (1) ◽  
pp. 319-328
Author(s):  
Ade Muchlis Maulana Anwar ◽  
Prihastuti Harsani ◽  
Aries Maesya
Keyword(s):  
Nearest Neighbor ◽  
Information Gain ◽  
Birth Certificate ◽  
Population Data ◽  
Community Services ◽  
Birth Certificates ◽  
Similar Data ◽  
K Nearest Neighbor ◽  
Civil Registration ◽  
The Family

Population Data is individual data or aggregate data that is structured as a result of Population Registration and Civil Registration activities. Birth Certificate is a Civil Registration Deed as a result of recording the birth event of a baby whose birth is reported to be registered on the Family Card and given a Population Identification Number (NIK) as a basis for obtaining other community services. From the total number of integrated birth certificate reporting for the 2018 Population Administration Information System (SIAK) totaling 570,637 there were 503,946 reported late and only 66,691 were reported publicly. Clustering is a method used to classify data that is similar to others in one group or similar data to other groups. K-Nearest Neighbor is a method for classifying objects based on learning data that is the closest distance to the test data. k-means is a method used to divide a number of objects into groups based on existing categories by looking at the midpoint. In data mining preprocesses, data is cleaned by filling in the blank data with the most dominating data, and selecting attributes using the information gain method. Based on the k-nearest neighbor method to predict delays in reporting and the k-means method to classify priority areas of service with 10,000 birth certificate data on birth certificates in 2019 that have good enough performance to produce predictions with an accuracy of 74.00% and with K = 2 on k-means produces a index davies bouldin of 1,179.

Optimizing Error Rate in Intrusion Detection System Using Artificial Neural Network Algorithm

2018 ◽  
Vol 6 (9) ◽  
pp. 152
Author(s):  
S. Vijaya Rani ◽  
G. N. K. Suresh Babu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Intrusion Detection ◽  
Error Rate ◽  
Learning Process ◽  
Nearest Neighbor ◽  
Detection System ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Artificial Neural

The illegal hackers  penetrate the servers and networks of corporate and financial institutions to gain money and extract vital information. The hacking varies from one computing system to many system. They gain access by sending malicious packets in the network through virus, worms, Trojan horses etc. The hackers scan a network through various tools and collect information of network and host. Hence it is very much essential to detect the attacks as they enter into a network. The methods  available for intrusion detection are Naive Bayes, Decision tree, Support Vector Machine, K-Nearest Neighbor, Artificial Neural Networks. A neural network consists of processing units in complex manner and able to store information and make it functional for use. It acts like human brain and takes knowledge from the environment through training and learning process. Many algorithms are available for learning process This work carry out research on analysis of malicious packets and predicting the error rate in detection of injured packets through artificial neural network algorithms.

Perancangan Aplikasi Prediksi Kelulusan Tepat Waktu Bagi Mahasiswa Baru Dengan Teknik Data Mining (Studi Kasus: Data Akademik Mahasiswa STMIK Dipanegara Makassar)

2015 ◽  
Vol 1 (4) ◽  
pp. 270
Author(s):  
Muhammad Syukri Mustafa ◽  
I. Wayan Simpen
Keyword(s):  
Data Mining ◽  
Nearest Neighbor ◽  
Test Results ◽  
K Nearest Neighbor ◽  
Accuracy Rate ◽  
Sample Data ◽  
New Students ◽  
K Nearest Neighbor Algorithm ◽  
Using Data ◽  
Existing Data

Penelitian ini dimaksudkan untuk melakukan prediksi terhadap kemungkian mahasiswa baru dapat menyelesaikan studi tepat waktu dengan menggunakan analisis data mining untuk menggali tumpukan histori data dengan menggunakan algoritma K-Nearest Neighbor (KNN). Aplikasi yang dihasilkan pada penelitian ini akan menggunakan berbagai atribut yang klasifikasikan dalam suatu data mining antara lain nilai ujian nasional (UN), asal sekolah/ daerah, jenis kelamin, pekerjaan dan penghasilan orang tua, jumlah bersaudara, dan lain-lain sehingga dengan menerapkan analysis KNN dapat dilakukan suatu prediksi berdasarkan kedekatan histori data yang ada dengan data yang baru, apakah mahasiswa tersebut berpeluang untuk menyelesaikan studi tepat waktu atau tidak. Dari hasil pengujian dengan menerapkan algoritma KNN dan menggunakan data sampel alumni tahun wisuda 2004 s.d. 2010 untuk kasus lama dan data alumni tahun wisuda 2011 untuk kasus baru diperoleh tingkat akurasi sebesar 83,36%.This research is intended to predict the possibility of new students time to complete studies using data mining analysis to explore the history stack data using K-Nearest Neighbor algorithm (KNN). Applications generated in this study will use a variety of attributes in a data mining classified among other Ujian Nasional scores (UN), the origin of the school / area, gender, occupation and income of parents, number of siblings, and others that by applying the analysis KNN can do a prediction based on historical proximity of existing data with new data, whether the student is likely to complete the study on time or not. From the test results by applying the KNN algorithm and uses sample data alumnus graduation year 2004 s.d 2010 for the case of a long and alumni data graduation year 2011 for new cases obtained accuracy rate of 83.36%.

Sign in / Sign up

Export Citation Format

Share Document