Dwi Rahayu

Bio: Dwi Rahayu is an academic researcher from Sebelas Maret University. The author has contributed to research in topics: Breastfeeding & Population. The author has an hindex of 6, co-authored 74 publications receiving 163 citations. Previous affiliations of Dwi Rahayu include Monash University & Magister.

Learning to be energy-wise: discriminative methods for load disaggregation

Abstract: In this paper we describe an ongoing project which develops an automated residential Demand Response (DR) system that attempts to manage residential loads in accordance with DR signals. In this early stage of the project, we propose an approach for identifying individual appliance consumption from the aggregate load and discuss the effectiveness of load disaggregation techniques when total load data also includes appliances that are unmonitored even during the training phase. We show that simple discriminative methods can directly predict the appliance states (e.g. on, off, standby) and the predicted state can be used to calculate energy consumed by the appliances. We also show that these methods perform substantially better than the generative models of energy consumption that are commonly used. We evaluated the proposed approach using publicly available REDD data set, and our experimental evaluation demonstrates the improvement in accuracy.

Science online learning during the covid-19 pandemic: Difficulties and challenges

Abstract: Students, parents, and teachers in Indonesia get the tremendous effects of the coronavirus (Covid-19 Pandemic) when schools are closed and the rules of Large-Scale Social Restrictions (LSSR) were set to overcome the global pandemic While the government is doing its best to handle the outbreak of the epidemic, teachers respond and strive to provide qualified education for their students during these difficult times Sciences should be learned through minds-on and hands-on, hence teachers must be able to create virtual classroom conditions that help students maintain learning momentum while they cannot interact each other physically This study aimed to identify the difficulties experienced by science teachers during online learning and describe the efforts of science teachers to conduct online learning during the Covid-19 pandemic The research data were obtained through a survey using a semi-structured online questionnaire The respondents were 82 junior high school teachers and 104 biology high school teachers in Indonesia Data analysis used a quantitative descriptive approach The results showed that the majority of science teachers (77 5%) got difficulty in managing online learning This difficulty was identified in three main factors namely technology, students, and teachers Internet access was a technological factor that causes the greatest difficulty (42 4%) in online learning Other difficulties came from the students by 21 5%, including low motivation, time management skills that were not optimal, and the lack of communication devices such as smartphones The third factor, namely teachers, contributed 36 1% of difficulties, especially related to the explanation of concepts and the use of online learning applications Based on these difficulties, 77 4% of teachers made an effort to carry out online learning optimally by presenting the material and providing slide presentation, discussion, as well as learning evaluation A small percentage of teachers (22 6%) used online classes only for task assignments and learning evaluation The efforts of science teachers to manage online learning have not optimized students' varied learning experiences because science can't be learned by reading and discussion only, but also by hands-on activities © Published under licence by IOP Publishing Ltd

SocketWatch: An autonomous appliance monitoring system

Abstract: A significant amount of energy is wasted by electrical appliances when they operate inefficiently either due to anomalies and/or incorrect usage. To address this problem, we present SocketWatch - an autonomous appliance monitoring system. SocketWatch is positioned between a wall socket and an appliance. SocketWatch learns the behavioral model of the appliance by analyzing its active and reactive power consumption patterns. It detects appliance malfunctions by observing any marked deviations from these patterns. SocketWatch is inexpensive and is easy to use: it neither requires any enhancement to the appliances nor to the power sockets nor any communication infrastructure. Moreover, the decentralized approach avoids communication latency and costs, and preserves data privacy. Real world experiments with multiple appliances indicate that SocketWatch can be an effective and inexpensive solution for reducing electricity wastage.

From offline to online learning: Various efforts to secure the learning process during covid-19 outbreaks

Abstract: Coronavirus Disease (Covid) 19 outbreaks occurred in many countries led to the emergence of policy changes in the field of education for the implementation of learning at home in order to avoid the spread of the disease Educational instructors must be responsive to adapt to changes in learning that was originally offline to be online to secure the learning process This study aims to describe the various efforts of lecturers in carrying out online learning during the Covid-19 pandemic The research was in March-April 2020 with 32 respondents (lecturers in the one of Universitas at Surabaya-Indonesia) Rapid survey with Google form by asking the facilities used in the implementation of online learning, the implementation of online learning, and the lecturers' response to online learning Data were analyzed using quantitative-descriptive manner The results showed various lecturers' efforts to secure the learning process during Pandemic Covid-19 Condition They tried to use various platforms and applications to manage online learning, even in Learning Management Systems (LMS) and social media applications The most widely used application was WhatsApp (84 4%) and in LMS was Google classroom (56 3%) In implementing online learning, lecturers had good design in teaching materials, preparation, implementation, evaluation of learning In addition, 72% of lecturers responded positively to online implementation because they had benefited in increased digital literacy The conclusion of this study were most lecturers responded positively by adapting to changes from offline to online learning;online learning has been well implemented © Published under licence by IOP Publishing Ltd

Sarcasm Detection on Indonesian Twitter Feeds

Abstract: In social media, some people use positive words to express negative opinion on a topic which is known as sarcasm. The existence of sarcasm becomes special because it is hard to be detected using simple sentiment analysis technique. Research on sarcasm detection in Indonesia is still very limited. Therefore, this research proposes a technique in detecting sarcasm in Indonesian Twitter feeds particularly on several critical issues such as politics, public figure and tourism. Our proposed technique uses two feature extraction methods namely interjection and punctuation. These methods are later used in two different weighting and classification algorithms. The empirical results demonstrate that combination of feature extraction methods, tf-idf, k-Nearest Neighbor yields the best performance in detecting sarcasm.

Education at a Glance

Abstract: A detailed review of the education sector in Australia as in the data provided by the 2006 edition of the OECD's annual publication, 'Education at a Glance' is presented. While the data has shown that in almost all OECD countries educational attainment levels are on the rise, with countries showing impressive gains in university qualifications, it also reveals that a large of share of young people still do not complete secondary school, which remains a baseline for successful entry into the labour market.

国际生命条形码计划—DNA Barcoding

Abstract: 中国拥有数目庞大、种类繁多的动植物,也有很多珍贵、濒危生物,这些更是异常宝贵的科学资源。DNA条形码技术的出现可以更好的帮助鉴别这些物种,了解其分支来源,甚至可以预知其进化方向。笔者简述了DNA条形码的技术原理与操作步骤及这项技术的产生与发展情况;简要列出了DNA条形码发展过程中的重要进步与研究相对集中的物种;概述了DNA条形码的应用途径及目前DNA条形码研究中存在的主要问题、矛盾、研究思路与发展方向,并对其发展前景做出展望。

NILMTK: an open source toolkit for non-intrusive load monitoring

Abstract: Non-intrusive load monitoring, or energy disaggregation, aims to separate household energy consumption data collected from a single point of measurement into appliance-level consumption data. In recent years, the field has rapidly expanded due to increased interest as national deployments of smart meters have begun in many countries. However, empirically comparing disaggregation algorithms is currently virtually impossible. This is due to the different data sets used, the lack of reference implementations of these algorithms and the variety of accuracy metrics employed. To address this challenge, we present the Non-intrusive Load Monitoring Toolkit (NILMTK); an open source toolkit designed specifically to enable the comparison of energy disaggregation algorithms in a reproducible manner. This work is the first research to compare multiple disaggregation approaches across multiple publicly available data sets. Our toolkit includes parsers for a range of existing data sets, a collection of preprocessing algorithms, a set of statistics for describing data sets, two reference benchmark disaggregation algorithms and a suite of accuracy metrics. We demonstrate the range of reproducible analyses which are made possible by our toolkit, including the analysis of six publicly available data sets and the evaluation of both benchmark disaggregation algorithms across such data sets.

Toward Non-Intrusive Load Monitoring via Multi-Label Classification

Abstract: Demand-side management technology is a key element of the proposed smart grid, which will help utilities make more efficient use of their generation assets by reducing consumers’ energy demand during peak load periods. However, although some modern appliances can respond to price signals from the utility companies, there is a vast stock of older appliances that cannot. For such appliances, utilities must infer what appliances are operating in a home, given only the power signals on the main feeder to the home (i.e., the home’s power consumption must be disaggregated into individual appliances). We report on an in-depth investigation of multi-label classification algorithms for disaggregating appliances in a power signal. A systematic review of this research topic shows that this class of algorithms has received little attention in the literature, even though it is arguably a more natural fit to the disaggregation problem than the traditional single-label classifiers used to date. We examine a multi-label meta-classification framework (RA ${k}$ EL), and a bespoke multi-label classification algorithm (ML ${k}$ NN), employing both time-domain and wavelet-domain feature sets. We test these classifiers on two real houses from the Reference Energy Disaggregation Dataset. We found that the multilabel algorithms are effective and competitive with published results on the datasets.