scholarly journals PEMETAAN RISET TENTANG DETEKSI TOPIK PADA TWITTER DENGAN TEKNIK SYSTEMATIC LITERATURE REVIEW

2021 ◽  
Vol 5 (1) ◽  
pp. 55-62
Author(s):  
Dwi Suchisty ◽  
Widodo ◽  
Bambang Prasetya Adhi
Keyword(s):  
Neural Network ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Recurrent Neural Network ◽  
Digital Library ◽  
Deep Neural Network ◽  
Research Question ◽  
Search String

Sebuah dokumen atau tulisan pastinya mengandung suatu informasi penting di dalamnya. Peringkasan dokumen membuat penemuan informasi-informasi tersebut menjadi lebih mudah karena mempersingkat kalimat dengan cara menghilangkan kata atau kalimat yang tidak penting. Peringkasan dokumen saat ini sudah banyak dilakukan dengan cara yang otomatis menggunakan metode-metode yang dikembangkan dari model neural netowork. Penelitian ini bertujuan untuk mengetahui sejauh mana perkembangan metode neural network dalam meringkas dokumen dilakukan dengan cara menganalisis literatur atau penelitian menggunakan teknik systematic literature review. Pengumpulan literatur dilakukan dengan cara melakukan pencarian pada beberapa digital library dengan memasukkan search string yang telah dibuat berdasarkan research question dengan batas publikasi antara tahun 2014-2018. Hasil dari penelitian ini menunjukkan bahwa dari 1266 literatur yang diperoleh 39 diantaranya layak untuk dianalisa. Berdasarkan dari 39 literatur tersebut diketahui bahwa metode neural network yang digunakan untuk meringkas dokumen adalah sebanyak 28 metode. Metode yang paling sering digunakan adalah metode Recurrent Neural Network (RNN) dan metode terbaik yang ditemukan untuk melakukan peringkasan adalah Deep Neural Network (DNN) dengan persentase ketepatan mencapai 62%.

scholarly journals Systematic Literature Review pada Analisis Prediktif dengan IoT: Tren Riset, Metode, dan Arsitektur

2020 ◽  
Vol 3 (1) ◽  
pp. 43-53
Author(s):  
Fahrur Rozi
Keyword(s):  
Neural Network ◽  
Data Analysis ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Smart Home ◽  
Research Question ◽  
Support Vector ◽  
Research Fields ◽  
Vector Machines ◽  
Artificial Neural Network Ann

Nowadays IoT researches on intelligent service systems is becoming a trend. IoT produces a variety of data from sensors or smart phones. Data generated from IoT can be more useful and can be followed up if data analysis is carried out. Predictive analytic with IoT is part of data analysis that aims to predict something solution. This analysis utilization produces innovative applications in various fields with diverse predictive analytic methods or techniques. This study uses Systematic Literature Review (SLR) to understand about research trends, methods and architecture used in predictive analytic with IoT. So the first step is to determine the research question (RQ) and then search is carried out on several literature published in popular journal databases namely IEEE Xplore, Scopus and ACM from 2015 - 2019. As a result of a review of thirty (30) selected articles, there are several research fields which are trends, namely Transportation, Agriculture, Health, Industry, Smart Home, and Environment. The most studied fields are agriculture. Predictive analytic with IoT use varied method according to the conditions of data used. There are five most widely used methods, namely Bayesian Network (BN), Artificial Neural Network (ANN), Recurrent Neural Networks (RNN), Neural Network (NN), and Support Vector Machines (SVM). Some studies also propose architectures that use predictive analytic with IoT.

A Systematic Literature Review of Cutting Tool Wear Monitoring in Turning by Using Artificial Intelligence Techniques

Machines ◽  
2021 ◽  
Vol 9 (12) ◽  
pp. 351
Author(s):  
Lorenzo Colantonio ◽  
Lucas Equeter ◽  
Pierre Dehombreux ◽  
François Ducobu
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Research Question ◽  
Support Vector ◽  
Self Organizing Map ◽  
Holistic View ◽  
Benchmark Database ◽  
Depth Analysis

In turning operations, the wear of cutting tools is inevitable. As workpieces produced with worn tools may fail to meet specifications, the machining industries focus on replacement policies that mitigate the risk of losses due to scrap. Several strategies, from empiric laws to more advanced statistical models, have been proposed in the literature. More recently, many monitoring systems based on Artificial Intelligence (AI) techniques have been developed. Due to the scope of different artificial intelligence approaches, having a holistic view of the state of the art on this subject is complex, in part due to a lack of recent comprehensive reviews. This literature review therefore presents 20 years of literature on this subject obtained following a Systematic Literature Review (SLR) methodology. This SLR aims to answer the following research question: “How is the AI used in the framework of monitoring/predicting the condition of tools in stable turning condition?” To answer this research question, the “Scopus” database was consulted in order to gather relevant publications published between 1 January 2000 and 1 January 2021. The systematic approach yielded 8426 articles among which 102 correspond to the inclusion and exclusion criteria which limit the application of AI to stable turning operation and online prediction. A bibliometric analysis performed on these articles highlighted the growing interest of this subject in the recent years. A more in-depth analysis of the articles is also presented, mainly focusing on six AI techniques that are highly represented in the literature: Artificial Neural Network (ANN), fuzzy logic, Support Vector Machine (SVM), Self-Organizing Map (SOM), Hidden Markov Model (HMM), and Convolutional Neural Network (CNN). For each technique, the trends in the inputs, pre-processing techniques, and outputs of the AI are presented. The trends highlight the early and continuous importance of ANN, and the emerging interest of CNN for tool condition monitoring. The lack of common benchmark database for evaluating models performance does not allow clear comparisons of technique performance.

Requirements Engineering for Software Systems: A Systematic Literature Review

2021 ◽  
Vol 12 (7) ◽  
pp. 339-349
Author(s):  
A. A. Kodubets ◽  
◽  
I. L. Artemieva ◽  
Keyword(s):  
Literature Review ◽  
Requirements Engineering ◽  
Language Processing ◽  
Systematic Literature Review ◽  
Large Scale ◽  
Development Process ◽  
Research Question ◽  
Software Systems ◽  
Software System ◽  
Requirements Development

This article contains a systematic literature review of requirements engineering for software systems. The literature published within last 5 years was included into the review. A research question was defined as requirements development process of large scale software system (with thousands of requirements) and an interaction problem during this process (communication, coordination and control). The problem is caused by the fact that large-scale software system requirements process is a cross-disciplinary task and it involves multiple parties — stakeholders, domain experts, and suppliers with own goals and constrains, and thus, the interaction between them seriously slows down the overall requirements development process than writing the requirements specification itself. The research papers were classified by several research directions: Natural Language Processing for Requirements Engineering (NLP4RE), Requirement Prioritization, Requirements Traceability, Quality of Software Requirements, Non-functional Requirements and Requirements Elicitation. Motivation and intensity of each direction was described. Each direction was structured and represented with the key references. A contribution of each research direction into the research question was analyzed and summarized including potential further steps. It was identified that some researchers had met a part of the described problem in different forms during their researches. At the end, other researches were described additionally in a short overview. To approach the research question further potential direction was described.

Collaboration among public organizations: a systematic literature review on determinants of interinstitutional performance

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Lorenzo Costumato
Keyword(s):  
Literature Review ◽  
Performance Management ◽  
Systematic Literature Review ◽  
Public Management ◽  
Research Question ◽  
Collaborative Governance ◽  
Content Type ◽  
Systematic Overview ◽  
Interinstitutional Collaboration ◽  
Performance Determinants

PurposeThe concept of collaboration has received increased attention from scholars in public management, as it has been seen as a viable solution to address “wicked” problems. Solving such problems may require a horizontal collaboration within the same governmental jurisdiction or, vertically, between different levels of government. Despite broad interest from the field of public management, the dynamics of public interinstitutional collaboration have received little attention within the literature. This paper aims to provide a systematic overview of the most significant academic contributions on the topic, highlighting the features of this collaborative context and identifying determinants those can foster its performance.Design/methodology/approachIn total, two main literature streams have occasionally dealt with public interinstitutional collaboration and related performance management: the “collaborative governance” stream and “public network performance”. Through a systematic literature review (SLR), this paper answers the following research question: what has been done and what is missing in order to assess performance in the context of public interinstitutional collaboration?FindingsThe findings of this study suggest that the most relevant papers are those dealing with public interagency collaboration, as this form of collaboration presents several similarities with public interinstitutional circumstances. Furthermore, the authors provide an analysis of the main determinants of public interinstitutional performance, which highlight the effects of trust, power sharing, leadership style, management strategies and formalization on the achievement of efficient and effective collaboration between public entities.Originality/valueBy drawing on two autonomous literature streams, this paper describes the main features of public interinstitutional collaboration. It contributes to the field by offering a systematic overview of how specific performance determinants, which are widely recognized as relevant for collaboration in general, work in the specificity of public–public contexts.

scholarly journals Mining e-cigarette adverse events in social media using Bi-LSTM recurrent neural network with word embedding representation

2017 ◽  
Vol 25 (1) ◽  
pp. 72-80 ◽  
Author(s):  
Jiaheng Xie ◽  
Xiao Liu ◽  
Daniel Dajun Zeng
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Adverse Events ◽  
Recurrent Neural Network ◽  
Deep Neural Network ◽  
Word Embedding ◽  
Named Entity ◽  
Text Input ◽  
Safety Surveillance ◽  
F Measure

Abstract Objective Recent years have seen increased worldwide popularity of e-cigarette use. However, the risks of e-cigarettes are underexamined. Most e-cigarette adverse event studies have achieved low detection rates due to limited subject sample sizes in the experiments and surveys. Social media provides a large data repository of consumers’ e-cigarette feedback and experiences, which are useful for e-cigarette safety surveillance. However, it is difficult to automatically interpret the informal and nontechnical consumer vocabulary about e-cigarettes in social media. This issue hinders the use of social media content for e-cigarette safety surveillance. Recent developments in deep neural network methods have shown promise for named entity extraction from noisy text. Motivated by these observations, we aimed to design a deep neural network approach to extract e-cigarette safety information in social media. Methods Our deep neural language model utilizes word embedding as the representation of text input and recognizes named entity types with the state-of-the-art Bidirectional Long Short-Term Memory (Bi-LSTM) Recurrent Neural Network. Results Our Bi-LSTM model achieved the best performance compared to 3 baseline models, with a precision of 94.10%, a recall of 91.80%, and an F-measure of 92.94%. We identified 1591 unique adverse events and 9930 unique e-cigarette components (ie, chemicals, flavors, and devices) from our research testbed. Conclusion Although the conditional random field baseline model had slightly better precision than our approach, our Bi-LSTM model achieved much higher recall, resulting in the best F-measure. Our method can be generalized to extract medical concepts from social media for other medical applications.

scholarly journals A Systematic Literature Review of Multi-Criteria Analysis Model Methods on Sustainability Weighting for Ethanol Plant

2021 ◽  
Vol 16 ◽  
pp. 1-13
Author(s):  
Norfazilah Binti Abdul Halim ◽  
Aliff Radzuan Bin Mohamad Radzi ◽  
Nor Zalina Binti Kasim ◽  
Faiz Bin Mohd Turan
Keyword(s):  
Literature Review ◽  
Systematic Literature Review ◽  
Industrial Development ◽  
Social Impact ◽  
Research Question ◽  
The Body ◽  
Analysis Model ◽  
Sustainability Evaluation ◽  
Ethanol Plant ◽  
Multi Criteria Analysis

The sustainability weighting is crucial as it is practically implemented into sustainability evaluation, especially in industrial development. Sustainability is about the interconnection between three aspects of sustainability impact such as economic impact, environmental impact, and social impact. Multi-Criteria Analysis (MCA) model play important roles to measure the weighting for each impact according to the scenario and criteria selected based on scientific rules and robust statistical methods. However, there were insufficient studies on the existing literature sustainability weighting model from MCA method for the ethanol plant. Hence, the present paper demonstrates a systematic literature review of MCA model methods on sustainability weighting for the ethanol plant. There are two steps involved in systematic literature reviews: formulation of the research question and systematic searching strategies consisting of identification, screening, eligibility, quality appraisal, data abstraction and analysis. The review is based on leading databases; Scopus – ScienceDirect, Springer, Taylor and Francis, and one supporting database – Google Scholar. From the review, the preferable MCA weighting model for sustainability evaluation of ethanol plants is ‘integrated Analytical Hierarchy Process (AHP)’ rather than ‘standalone AHP’. The paper offered a significant contribution to the body of knowledge and sustainability evaluation purposes.

scholarly journals Identification of Key Component of E-marketplace to Enhance Service Quality in the Market

2020 ◽  
Vol 8 (5) ◽  
pp. 4087-4092
Keyword(s):  
Quality Of Service ◽  
Literature Review ◽  
Service Quality ◽  
Systematic Literature Review ◽  
Data Extraction ◽  
Improve Quality ◽  
Exclusion Criteria ◽  
Online Chat ◽  
Search String

Business began with a physical store, which is the place for customer and seller in doing the product transaction. In this era, e-marketplace is proliferating to collect various tenants with various products to join in one same company to give the best service for customers, but every company must strategically compete with each other to survive in the market. The purpose of this study is to find the key components in e-marketplace to enhance service quality in the market, so businesses in this field can focus to develop the services based on the identified components. This study uses systematic literature review to collect all data from various databases; derived from keywords search, search string, inclusion and exclusion criteria, and data extraction. Thirty-eight selected studies that have been identified from data extraction will be evaluated further in this research by mapping them into demographic in trends. Based on the analysis, this research discovers six key components in e-marketplace which are Buyer, Partner, Infrastructure, Content, Online Chat, and Product Prices that can improve quality of service in the market.

scholarly journals Machine learning for modeling the progression of Alzheimer disease dementia using clinical data: a systematic literature review

JAMIA Open ◽  
2021 ◽  
Vol 4 (3) ◽  
Author(s):  
Sayantan Kumar ◽  
Inez Oh ◽  
Suzanne Schindler ◽  
Albert M Lai ◽  
Philip R O Payne ◽  
...  
Keyword(s):  
Machine Learning ◽  
Alzheimer Disease ◽  
Literature Review ◽  
Clinical Data ◽  
Systematic Literature Review ◽  
Digital Library ◽  
Model Risk ◽  
Computing Machinery ◽  
Data Tables ◽  
The Impact

Abstract Objective Alzheimer disease (AD) is the most common cause of dementia, a syndrome characterized by cognitive impairment severe enough to interfere with activities of daily life. We aimed to conduct a systematic literature review (SLR) of studies that applied machine learning (ML) methods to clinical data derived from electronic health records in order to model risk for progression of AD dementia. Materials and Methods We searched for articles published between January 1, 2010, and May 31, 2020, in PubMed, Scopus, ScienceDirect, IEEE Explore Digital Library, Association for Computing Machinery Digital Library, and arXiv. We used predefined criteria to select relevant articles and summarized them according to key components of ML analysis such as data characteristics, computational algorithms, and research focus. Results There has been a considerable rise over the past 5 years in the number of research papers using ML-based analysis for AD dementia modeling. We reviewed 64 relevant articles in our SLR. The results suggest that majority of existing research has focused on predicting progression of AD dementia using publicly available datasets containing both neuroimaging and clinical data (neurobehavioral status exam scores, patient demographics, neuroimaging data, and laboratory test values). Discussion Identifying individuals at risk for progression of AD dementia could potentially help to personalize disease management to plan future care. Clinical data consisting of both structured data tables and clinical notes can be effectively used in ML-based approaches to model risk for AD dementia progression. Data sharing and reproducibility of results can enhance the impact, adaptation, and generalizability of this research.

scholarly journals A Scheme with Acoustic Emission Hit Removal for the Remaining Useful Life Prediction of Concrete Structures

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7761
Author(s):  
Tuan-Khai Nguyen ◽  
Zahoor Ahmad ◽  
Jong-Myon Kim
Keyword(s):  
Neural Network ◽  
Acoustic Emission ◽  
Recurrent Neural Network ◽  
Life Prediction ◽  
Deep Neural Network ◽  
Remaining Useful Life ◽  
Support Vector ◽  
Health Indicator ◽  
Removal Process ◽  
Useful Life

In this study, a scheme of remaining useful lifetime (RUL) prognosis from raw acoustic emission (AE) data is presented to predict the concrete structure’s failure before its occurrence, thus possibly prolong its service life and minimizing the risk of accidental damage. The deterioration process is portrayed by the health indicator (HI), which is automatically constructed from raw AE data with a deep neural network pretrained and fine-tuned by a stacked autoencoder deep neural network (SAE-DNN). For the deep neural network structure to perform a more accurate construction of health indicator lines, a hit removal process with a one-class support vector machine (OC-SVM), which has not been investigated in previous studies, is proposed to extract only the hits which matter the most to the portrait of deterioration. The new set of hits is then harnessed as the training labels for the deep neural network. After the completion of the health indicator line construction, health indicators are forwarded to a long short-term memory recurrent neural network (LSTM-RNN) for the training and validation of the remaining useful life prediction, as this structure is capable of capturing the long-term dependencies, even with a limited set of data. Our prediction result shows a significant improvement in comparison with a similar scheme but without the hit removal process and other methods, such as the gated recurrent unit recurrent neural network (GRU-RNN) and the simple recurrent neural network.

Sign in / Sign up

Export Citation Format

Share Document