Data Mining - Concepts and Techniques.

Considerable progress has been made in recent years in the development of dialogue systems that support robust and efficient human–machine interaction using spoken language. Spoken dialogue technology allows various interactive applications to be built and used for practical purposes, and research focuses on issues that aim to increase the system’s communicative competence by including aspects of error correction, cooperation, multimodality, and adaptation in context. This book gives a comprehensive view of state-of-the-art techniques that are used to build spoken dialogue systems. It provides an overview of the basic issues such as system architectures, various dialogue management methods, system evaluation, and also surveys advanced topics concerning extensions of the basic model to more conversational setups. The goal of the book is to provide an introduction to the methods, problems, and solutions that are used in dialogue system development and evaluation. It presents dialogue modelling and system development issues relevant in both academic and industrial environments and also discusses requirements and challenges for advanced interaction management and future research. vi KEywoRDS Spoken dialogue systems, multimodality, evaluation, error-handling, dialogue management, statistical method v MC_Jok nen_FM. ndd Achorn Internat onal 10/10/2009 04:18AM

https://www.morganclaypool.com/doi/suppl/10.2200/S00509ED1V01Y201305HLT023/suppl_file/Dagan_Ch1.pdf

Synthesis Lectures on Human Language Technologies

Watch Me Play: Twitch and the Rise of Game Live Streaming:

Understanding the data and reaching accurate conclusions are of paramount importance in the present era of big data. Machine learning and probability theory methods have been widely used for this purpose in various fields. One critically important yet less explored aspect is capturing and analyzing uncertainties in the data and model. Proper quantification of uncertainty helps to provide valuable information to obtain accurate diagnosis. This paper reviewed related studies conducted in the last 30 years (from 1991 to 2020) in handling uncertainties in medical data using probability theory and machine learning techniques. Medical data is more prone to uncertainty due to the presence of noise in the data. So, it is very important to have clean medical data without any noise to get accurate diagnosis. The sources of noise in the medical data need to be known to address this issue. Based on the medical data obtained by the physician, diagnosis of disease, and treatment plan are prescribed. Hence, the uncertainty is growing in healthcare and there is limited knowledge to address these problems. Our findings indicate that there are few challenges to be addressed in handling the uncertainty in medical raw data and new models. In this work, we have summarized various methods employed to overcome this problem. Nowadays, various novel deep learning techniques have been proposed to deal with such uncertainties and improve the performance in decision making.

/pdf/handling-of-uncertainty-in-medical-data-using-machine-rpi8bge796.pdf

Handling of uncertainty in medical data using machine learning and probability theory techniques: a review of 30 years (1991–2020)

Understanding data and reaching valid conclusions are of paramount importance in the present era of big data. Machine learning and probability theory methods have widespread application for this purpose in different fields. One critically important yet less explored aspect is how data and model uncertainties are captured and analyzed. Proper quantification of uncertainty provides valuable information for optimal decision making. This paper reviewed related studies conducted in the last 30 years (from 1991 to 2020) in handling uncertainties in medical data using probability theory and machine learning techniques. Medical data is more prone to uncertainty due to the presence of noise in the data. So, it is very important to have clean medical data without any noise to get accurate diagnosis. The sources of noise in the medical data need to be known to address this issue. Based on the medical data obtained by the physician, diagnosis of disease, and treatment plan are prescribed. Hence, the uncertainty is growing in healthcare and there is limited knowledge to address these problems. We have little knowledge about the optimal treatment methods as there are many sources of uncertainty in medical science. Our findings indicate that there are few challenges to be addressed in handling the uncertainty in medical raw data and new models. In this work, we have summarized various methods employed to overcome this problem. Nowadays, application of novel deep learning techniques to deal such uncertainties have significantly increased.

Handling of uncertainty in medical data using machine learning and probability theory techniques: A review of 30 years (1991-2020)

In the year 2018, 18.9% of the population in Indonesia mentioned that the main reason for their use of the Internet is social media. One of the social media with an active user of 6.43 million users is Twitter. Based on the surge of information published via Twitter, it is possible that such information may contain the user's opinions on an object, such objects may be events around the community such as a product or service. This makes the company use Twitter as a medium to disseminate information. An example is an Internet Service Provider (ISP) such as Indihome. Through Twitter, users can discuss each other's complaints or satisfaction with Indihome's services. It takes a method of sentiment analysis to understand whether the textual data includes negative opinions or positive opinions. Thus, the authors use the Support Vector Machine (SVM) method in sentiment analysis on the opinions of the Indihome service user on Twitter, with the aim of obtaining a sentiment classification model using SVM, and to know how much accuracy the SVM method generates, which is applied to sentiment analysis, and to see how satisfied the Indihome service users are based on Twitter. After testing with SVM method The result is accuracy 87%, precision 86%, recall 95%, error rate 13%, and F1-score 90%

/pdf/analisis-sentimen-terhadap-layanan-indihome-berdasarkan-2rwsceqbsz.pdf

Analisis Sentimen Terhadap Layanan Indihome Berdasarkan Twitter Dengan Metode Klasifikasi Support Vector Machine (SVM)

Human-Centered Design Method is a method of approach in the development and design of a system that focuses on the user according to aspects of the needs and habits of the user. Difficulty in accessing information on the website becomes a problem faced by the user and in terms of visual website can not be responsive when accessed via mobile. The initial stage carried out in this method is observation which aims to find and to better understand the problems faced by users to conduct testing to find out whether the solutions provided can be understood and easily used by the user. Website testing is done by giving tasks to the user to interact on the website prototype, as the final result of success in the aspect of ease and comfort of the user using the website. After testing the user directly the test results are obtained, ie the user already feels quite understanding and easy when using the website that was created. The responsive mobile feature created also makes users feel helped when using a website on a smartphone.

/pdf/perancangan-user-interface-design-dan-user-experience-mobile-42wsaboqb9.pdf

Perancangan User Interface Design dan User Experience Mobile Responsive Pada Website Perusahaan

In this paper, a new technique of agglomerative hierarchical clustering (AHC), which is known as SLG (single linkage dissimilarity increment distribution, global cumulative score standard), can work well in analyzing students' activity in online learning as evidenced by obtaining the highest score in testing the validity index of cophenetic correlation coefficient (CPCC) ie 0.9237, 0.9015, 0.9967, 0.8853, 0.9875 of the five datasets compared with conventional agglomerative hierarchical clustering methods.

A new agglomerative hierarchical clustering to model student activity in online learning

Sales transaction data histories can be used to predict the possibility of sales transaction that will occur in the future. These characteristics are in accordance with forecasting using time series method where this method uses previous data as tools to predict transaction value that will appear in the present time. Company X that runs its business by sell their product through distributors has sales data that is not optimally utilized. The average number of sales per year ranges from 5000 transactions which is not use to forecast transactions hereafter. Transaction data is stored in the company database so that data mining technology can be applied to support company X transaction data collection from previous year. The data is processed in applications where the results of forecasting are compared with real data in 2018 to see the accuracy of the forecasting results. The graphic that shown in application has pattern which can use for forecasting. From the forecasting method used, it can be seen that the forecasting results show data that came out did not produce data that matched the real data where the highest level of accuracy was 99.68% and the lowest accuracy was still above 50%.

http://journal.portalgaruda.org/index.php/EECSI/article/download/2028/1471

Data Mining Implementation to Predict Sales Using Time Series Method

Seleksi Paskibraka dilakukan pada setiap tahun dengan tujuan mencari putra putri terbaik yang nantinya akan ditugaskan pada upacara peringatan kemerdekaan Indonesia untuk mengibarkan duplikat bendera pusaka. Pada beberapa wilayah, seleksi Paskibraka masih menggunakan perhitungan dengan excel atau perhitungan manual lainnya dalam menentukan keputusan. Perhitungan manual ini tentunya membutuhkan waktu yang lebih lama dan hasil yang dapat kurang akurat. Oleh karena itu, dibuatlah aplikasi sistem pendukung keputusan dengan menggunakan metode Weighted Product(WP) dan Simple Additive Weighting (SAW) yang dapat memberikan nilai akhir penilaian seleksi sesuai dengan kriteria dan bobot yang telah ditetapkan. Hasil dari kedua metode ini nantinya akan dibandingkan agar didapatkan hasil yang terbaik. Hasil dari aplikasi ini berupa perangkingan peserta berdasarkan kecamatannya. Kata Kunci: Sistem Pendukung Keputusan; Paskibraka; Seleksi; Simple Additive Weighting; Weighted Product.

/pdf/perbandingan-metode-weighted-product-wp-dan-simple-additive-3khacl7pwm.pdf

Agung Triayudi

Papers

Analisis Sentimen Terhadap Layanan Indihome Berdasarkan Twitter Dengan Metode Klasifikasi Support Vector Machine (SVM)

Perancangan User Interface Design dan User Experience Mobile Responsive Pada Website Perusahaan

A new agglomerative hierarchical clustering to model student activity in online learning

Data Mining Implementation to Predict Sales Using Time Series Method

Perbandingan Metode Weighted Product (WP) dan Simple Additive Weighting (SAW) terhadap Sistem Pendukung Keputusan Rekomendasi Calon Paskibraka