Skip to content

Commit 3a7b4c4

Browse files
gcerargcerar
committed
deploy: 66ae9af 
1 parent b88822f commit 3a7b4c4

148 files changed

Lines changed: 303 additions & 298 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎00-anomaly-detection/index.html‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
<!doctype html><html lang=en class=no-js><head><meta charset=utf-8><meta http-equiv=X-UA-Compatible content="IE=edge"><meta name=viewport content="width=device-width,initial-scale=1,viewport-fit=cover"><link rel=stylesheet href="/style.min.f29f905470be850fbe5fa8929121ac2e8ac265b98aa89dcf7c19f1e41226fb76.css" integrity="sha256-8p+QVHC+hQ++X6iSkSGsLorCZbmKqJ3PfBnx5BIm+3Y=" crossorigin=anonymous><script defer type=text/javascript src=https://sensorlab.github.io/scripts/app.min.3b4e7d87ccbf185dad88221b3d090e5b5225c1c25fd01c1776cbf4e7a6b614ec.js integrity="sha256-O059h8y/GF2tiCIbPQkOW1IlwcJf0BwXdsv056a2FOw="></script><meta name=google-site-verification content="zl9o8a5lMqKy_2dn2YR6swgC5REHalMWw25PBhJnJSc"><meta name=generator content="Hugo 0.143.1"><meta name=author content="SensorLab"><meta name=description content="Time series anomaly detection is an important and yet unsolved challenge that is relevant for developing, maintaining and monitoring various aspects of smart infrastructures. One of our original contributions to the area consists in the definition of four types of anomalies relevant for monitoring the quality of the wireless links between various smart objects. A second original contribution consists of using time series to image transformations for advancing the state of the art in detection performance.
1+
<!doctype html><html lang=en class=no-js><head><meta charset=utf-8><meta http-equiv=X-UA-Compatible content="IE=edge"><meta name=viewport content="width=device-width,initial-scale=1,viewport-fit=cover"><link rel=stylesheet href="/style.min.cba1219d89e661a624b161c70ede21661d3abdee14045957b20b2f066f38fac1.css" integrity="sha256-y6EhnYnmYaYksWHHDt4hZh06ve4UBFlXsgsvBm84+sE=" crossorigin=anonymous><script defer type=text/javascript src=https://sensorlab.github.io/scripts/app.min.91271064de5be6aaf5625fd549054cf88d2f475f1a3ecc5b9860f8c1fc0a4c76.js integrity="sha256-kScQZN5b5qr1Yl/VSQVM+I0vR18aPsxbmGD4wfwKTHY="></script><meta name=google-site-verification content="zl9o8a5lMqKy_2dn2YR6swgC5REHalMWw25PBhJnJSc"><meta name=generator content="Hugo 0.143.1"><meta name=author content="SensorLab"><meta name=description content="Time series anomaly detection is an important and yet unsolved challenge that is relevant for developing, maintaining and monitoring various aspects of smart infrastructures. One of our original contributions to the area consists in the definition of four types of anomalies relevant for monitoring the quality of the wireless links between various smart objects. A second original contribution consists of using time series to image transformations for advancing the state of the art in detection performance.
22
"><meta name=robots content="index,follow"><link rel=canonical href=https://sensorlab.github.io/00-anomaly-detection/><link rel=alternate hreflang=en href=https://sensorlab.github.io/00-anomaly-detection/><link rel=icon type=image/png href=https://sensorlab.github.io/images/favicon.png><meta property="og:url" content="https://sensorlab.github.io/00-anomaly-detection/"><meta property="og:site_name" content="SensorLab — Jozef Stefan Institute"><meta property="og:title" content="Anomaly detection"><meta property="og:description" content="Time series anomaly detection is an important and yet unsolved challenge that is relevant for developing, maintaining and monitoring various aspects of smart infrastructures. One of our original contributions to the area consists in the definition of four types of anomalies relevant for monitoring the quality of the wireless links between various smart objects. A second original contribution consists of using time series to image transformations for advancing the state of the art in detection performance."><meta property="og:locale" content="en"><meta property="og:type" content="article"><meta name=twitter:card content="summary"><meta name=twitter:title content="Anomaly detection"><meta name=twitter:description content="Time series anomaly detection is an important and yet unsolved challenge that is relevant for developing, maintaining and monitoring various aspects of smart infrastructures. One of our original contributions to the area consists in the definition of four types of anomalies relevant for monitoring the quality of the wireless links between various smart objects. A second original contribution consists of using time series to image transformations for advancing the state of the art in detection performance."><title>Anomaly detection &mdash; SensorLab — Jozef Stefan Institute</title></head><body><header class="navbar navbar-expand-md"><div class=container><a class=navbar-brand href=https://sensorlab.github.io/><img src=https://sensorlab.github.io/images/sensorlab-white.min.svg alt="SensorLab logo" class="d-inline-block align-top me-2" height=42>
33
</a><button class=navbar-toggler type=button data-bs-toggle=collapse data-bs-target=#navbarToggler aria-controls=navbarToggler aria-expanded=false aria-label="Toggle navigation">
44
<span class=navbar-toggler-icon></span></button><nav class="collapse navbar-collapse" id=navbarToggler><ul class="navbar-nav ms-0 ms-md-auto ps-4"><li class=nav-item><a class=nav-link href=https://sensorlab.github.io/projects><span>Projects</span></a></li><li class=nav-item><a class=nav-link href=https://sensorlab.github.io/results><span>Results</span></a></li><li class=nav-item><a class=nav-link href=https://sensorlab.github.io/publications><span>Publications</span></a></li><li class=nav-item><a class=nav-link href=https://sensorlab.github.io/people><span>People</span></a></li><li class=nav-item><a class=nav-link href=https://sensorlab.github.io/opportunities><span>Join Us</span></a></li><li class=nav-item><a class=nav-link href=https://sensorlab.github.io/about><span>About</span></a></li></ul></nav></div></header><main class="flex-fill container post my-4" aria-role=main><aside class=my-4></aside><article class=mt-4><header><h1>Anomaly detection</h1><p><span>Published: <time datetime=0001-01-01T00:00:00Z>Monday, January 1, 1</time></span></p></header><section class=my-4><p>Time series anomaly detection is an important and yet unsolved challenge that is relevant for developing, maintaining and monitoring various aspects of smart infrastructures. One of our original contributions to the area consists in the definition of <a href=https://ieeexplore.ieee.org/document/9264175>four types of anomalies</a> relevant for monitoring the quality of the wireless links between various smart objects. A second original contribution consists of using <a href=https://arxiv.org/abs/2104.00972>time series to image transformations</a> for advancing the state of the art in detection performance.</p></section></article></main><footer class="container d-flex flex-wrap justify-content-between align-items-center py-3 my-4 border-top"><div class="col-md-6 d-flex align-items-center"><a href=https://sensorlab.github.io/ class="mb-3 me-2 mb-md-0 text-body-secondary text-decoration-none lh-1"><img src=https://sensorlab.github.io/images/sensorlab-color.min.svg style=height:2.5rem>

‎01-link-quality-classification/index.html‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
<!doctype html><html lang=en class=no-js><head><meta charset=utf-8><meta http-equiv=X-UA-Compatible content="IE=edge"><meta name=viewport content="width=device-width,initial-scale=1,viewport-fit=cover"><link rel=stylesheet href="/style.min.f29f905470be850fbe5fa8929121ac2e8ac265b98aa89dcf7c19f1e41226fb76.css" integrity="sha256-8p+QVHC+hQ++X6iSkSGsLorCZbmKqJ3PfBnx5BIm+3Y=" crossorigin=anonymous><script defer type=text/javascript src=https://sensorlab.github.io/scripts/app.min.3b4e7d87ccbf185dad88221b3d090e5b5225c1c25fd01c1776cbf4e7a6b614ec.js integrity="sha256-O059h8y/GF2tiCIbPQkOW1IlwcJf0BwXdsv056a2FOw="></script><meta name=google-site-verification content="zl9o8a5lMqKy_2dn2YR6swgC5REHalMWw25PBhJnJSc"><meta name=generator content="Hugo 0.143.1"><meta name=author content="SensorLab"><meta name=description content="Wireless links are crucial to cost efficiently connecting various components in smart infrastructures. Recently, machine learning techniques proved to be suitable for more accurate estimation and classification. As original contribution to this area, we provide a comprehensive survey on link quality estimators developed from empirical data and then focus on the subset that use ML algorithms. We analyze ML-based Link Quality Estimation (LQE) models from two perspectives using performance data. Firstly, we focus on how they address quality requirements that are important from the perspective of the applications they serve. Secondly, we analyze how they approach the standard design steps commonly used in the ML community.
1+
<!doctype html><html lang=en class=no-js><head><meta charset=utf-8><meta http-equiv=X-UA-Compatible content="IE=edge"><meta name=viewport content="width=device-width,initial-scale=1,viewport-fit=cover"><link rel=stylesheet href="/style.min.cba1219d89e661a624b161c70ede21661d3abdee14045957b20b2f066f38fac1.css" integrity="sha256-y6EhnYnmYaYksWHHDt4hZh06ve4UBFlXsgsvBm84+sE=" crossorigin=anonymous><script defer type=text/javascript src=https://sensorlab.github.io/scripts/app.min.91271064de5be6aaf5625fd549054cf88d2f475f1a3ecc5b9860f8c1fc0a4c76.js integrity="sha256-kScQZN5b5qr1Yl/VSQVM+I0vR18aPsxbmGD4wfwKTHY="></script><meta name=google-site-verification content="zl9o8a5lMqKy_2dn2YR6swgC5REHalMWw25PBhJnJSc"><meta name=generator content="Hugo 0.143.1"><meta name=author content="SensorLab"><meta name=description content="Wireless links are crucial to cost efficiently connecting various components in smart infrastructures. Recently, machine learning techniques proved to be suitable for more accurate estimation and classification. As original contribution to this area, we provide a comprehensive survey on link quality estimators developed from empirical data and then focus on the subset that use ML algorithms. We analyze ML-based Link Quality Estimation (LQE) models from two perspectives using performance data. Firstly, we focus on how they address quality requirements that are important from the perspective of the applications they serve. Secondly, we analyze how they approach the standard design steps commonly used in the ML community.
22
"><meta name=robots content="index,follow"><link rel=canonical href=https://sensorlab.github.io/01-link-quality-classification/><link rel=alternate hreflang=en href=https://sensorlab.github.io/01-link-quality-classification/><link rel=icon type=image/png href=https://sensorlab.github.io/images/favicon.png><meta property="og:url" content="https://sensorlab.github.io/01-link-quality-classification/"><meta property="og:site_name" content="SensorLab — Jozef Stefan Institute"><meta property="og:title" content="Link quality classification"><meta property="og:description" content="Wireless links are crucial to cost efficiently connecting various components in smart infrastructures. Recently, machine learning techniques proved to be suitable for more accurate estimation and classification. As original contribution to this area, we provide a comprehensive survey on link quality estimators developed from empirical data and then focus on the subset that use ML algorithms. We analyze ML-based Link Quality Estimation (LQE) models from two perspectives using performance data. Firstly, we focus on how they address quality requirements that are important from the perspective of the applications they serve. Secondly, we analyze how they approach the standard design steps commonly used in the ML community."><meta property="og:locale" content="en"><meta property="og:type" content="article"><meta name=twitter:card content="summary"><meta name=twitter:title content="Link quality classification"><meta name=twitter:description content="Wireless links are crucial to cost efficiently connecting various components in smart infrastructures. Recently, machine learning techniques proved to be suitable for more accurate estimation and classification. As original contribution to this area, we provide a comprehensive survey on link quality estimators developed from empirical data and then focus on the subset that use ML algorithms. We analyze ML-based Link Quality Estimation (LQE) models from two perspectives using performance data. Firstly, we focus on how they address quality requirements that are important from the perspective of the applications they serve. Secondly, we analyze how they approach the standard design steps commonly used in the ML community."><title>Link quality classification &mdash; SensorLab — Jozef Stefan Institute</title></head><body><header class="navbar navbar-expand-md"><div class=container><a class=navbar-brand href=https://sensorlab.github.io/><img src=https://sensorlab.github.io/images/sensorlab-white.min.svg alt="SensorLab logo" class="d-inline-block align-top me-2" height=42>
33
</a><button class=navbar-toggler type=button data-bs-toggle=collapse data-bs-target=#navbarToggler aria-controls=navbarToggler aria-expanded=false aria-label="Toggle navigation">
44
<span class=navbar-toggler-icon></span></button><nav class="collapse navbar-collapse" id=navbarToggler><ul class="navbar-nav ms-0 ms-md-auto ps-4"><li class=nav-item><a class=nav-link href=https://sensorlab.github.io/projects><span>Projects</span></a></li><li class=nav-item><a class=nav-link href=https://sensorlab.github.io/results><span>Results</span></a></li><li class=nav-item><a class=nav-link href=https://sensorlab.github.io/publications><span>Publications</span></a></li><li class=nav-item><a class=nav-link href=https://sensorlab.github.io/people><span>People</span></a></li><li class=nav-item><a class=nav-link href=https://sensorlab.github.io/opportunities><span>Join Us</span></a></li><li class=nav-item><a class=nav-link href=https://sensorlab.github.io/about><span>About</span></a></li></ul></nav></div></header><main class="flex-fill container post my-4" aria-role=main><aside class=my-4></aside><article class=mt-4><header><h1>Link quality classification</h1><p><span>Published: <time datetime=0001-01-01T00:00:00Z>Monday, January 1, 1</time></span></p></header><section class=my-4><p>Wireless links are crucial to cost efficiently connecting various components in smart infrastructures. Recently, machine learning techniques proved to be suitable for more accurate estimation and classification. As original contribution to this area, we provide a comprehensive <a href="https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9333616">survey</a> on link quality estimators developed from empirical data and then focus on the subset that use ML algorithms. We analyze ML-based Link Quality Estimation (LQE) models from two perspectives using performance data. Firstly, we focus on how they address quality requirements that are important from the perspective of the applications they serve. Secondly, we analyze how they approach the standard design steps commonly used in the ML community.</p></section></article></main><footer class="container d-flex flex-wrap justify-content-between align-items-center py-3 my-4 border-top"><div class="col-md-6 d-flex align-items-center"><a href=https://sensorlab.github.io/ class="mb-3 me-2 mb-md-0 text-body-secondary text-decoration-none lh-1"><img src=https://sensorlab.github.io/images/sensorlab-color.min.svg style=height:2.5rem>

0 commit comments

Comments
 (0)