Search

Your search keyword '"mobile assistant"' showing total 13 results
Start Over Descriptor "mobile assistant"
13 results on '"mobile assistant"'

1. Applying Gamification Principles and Therapeutic Movement Sequences to Design an Interactive Physical Activity Game: Development Study.

Author

Hyungsook Kim, O'Sullivan, David Michael, and Seong Hee Chung

Subjects
*GAMIFICATION, *PHYSICAL activity, *COVID-19 pandemic, *MENTAL depression, *PHYSICAL fitness
Abstract

Background: Depression is a severe illness that has accelerated with the spread of COVID-19 and associated lockdowns. As a result, reported physical activity has substantially decreased, further increasing depressive symptoms. Objective: This study aims to explain the use of gamification principles to develop content for an interactive physical activity game for depression based on clinically proven depression diagnostic criteria. Methods: We discuss related work in this field, the game design framework, the users' depression severity, how we customize the contents accordingly, the gradual progression of the game to match exercise principles, and user flow optimization. Results: We provide a brief description of each of the games developed, including instructions on how to play and design aspects for flow, audio, and visual feedback methods. Exergames (interactive physical activity--based games) stimulate certain physical fitness factors such as improving reaction time, endurance, cardiovascular fitness, and flexibility. In addition, the game difficulty progresses based on various factors, such as the user's performance for successful completion, reaction time, movement speed, and stimulated larger joint range of motions. Cognitive aspects are included, as the user has to memorize particular movement sequences. Conclusions: Mental health issues are linked to behavior and movement; therefore, future physical activity--based interactive games may provide excellent stimulation for inducing user flow, while physical activity can help train various physical fitness factors linked to depression. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

2. Mobile Based Approach for Accident Reporting

Author

Wanumen, Luis, Moreno, Judy, Florez, Hector, Barbosa, Simone Diniz Junqueira, Editorial Board Member, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Kotenko, Igor, Editorial Board Member, Washio, Takashi, Editorial Board Member, Yuan, Junsong, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Botto-Tobar, Miguel, editor, Pizarro, Guillermo, editor, Zúñiga-Prieto, Miguel, editor, D’Armas, Mayra, editor, and Zúñiga Sánchez, Miguel, editor

Published
2019
Full Text
View/download PDF

3. Pemanfaatan Aplikasi Mobile Assistant Untuk Mendeteksi Kerumunan dalam Penerapan New Normal Covid-19

Author

Nova Noor Kamala Sari and Widiatry Widiatry

Subjects
Covid 19, mobile assistant, Extreme Programming, kerumunan, Science, Electronic computers. Computer science, QA75.5-76.95
Abstract

Tatanan kehidupan normal baru (New Normal) pandemi covid 19 dapat memanfaatkan teknologi informasi guna mendukung penerapan pyhsical distancing khususnya dalam mengetahui jumlah orang yang sedang berkumpul pada suatu lokasi secara akurat. Selama ini proses untuk mengetahui jumlah orang dii suatu tempat harus dilakukan dengan penghitungan manual yang tentunya membutuhkan banyak upaya dan juga tenaga yang dibutuhkan.Informasi keberadaan orang dalam suatu tempat saat ini sangat dibutuhkan guna melakukan penekanan terhadap COVID-19, oleh karena itu dibutuhkan sebuah aplikasi mobile yang sifatnya dapat digunakan dimana saja dan juga sangat cocok untuk membantu aktivitas-aktivitas yang memiliki mobilitas tinggi. Aplikasi Mobile Assistant yang dibuat ini berbasis Sistem Operasi Android, dengan memasukkan fungsi pelacakan dari lokasi dengan menggunakan GPS (Global Positioning System) atau dengan metode yang biasa disebut Location Based Services (LBS) untuk menginformasikan keberadaan orang dalam suatu tempat umum yang bisa di setting seperti pasar, perkantoran, rumah sakit, tempat peribadatan, kampus, dan lain-lain. Metode Pengembangan Perangkat lunak menggunakan metode Extreme Programming. Ada empat tahapan yang harus dikerjakan yaitu planning (perencanaan), design (perancangan), coding dan testing. Aplikasi ini dapat menunjang kinerja Pemerintah dalam menjalankan New Normal dan mengetahui jumlah orang dalam kerumunan sehingga physical distancing bisa berjalan secara optimal dan dapat menekan angka laju penyebaran Covid-19.

Published
2021
Full Text
View/download PDF

4. Towards Using an Augmented Reality Mobile Assistant for Improving Driving Skills

Author

Voinea, Gheorghe Daniel, Postelnicu, Cristian, Duguleana, Mihai, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Tian, Feng, editor, Gatzidis, Christos, editor, El Rhalibi, Abdennour, editor, Tang, Wen, editor, and Charles, Fred, editor

Published
2017
Full Text
View/download PDF

5. Medical Assistant Mobile Application for Diabetes Control by Simulating a Compartmental Model.

Author

Hernández-Ordoñez, Martín, Nuño-Maganda, Marco Aurelio, Calles-Arriaga, Carlos Adrián, Rodríguez-León, Abelardo, Ovando-Chacon, Guillermo Efren, Salazar-Hernández, Rolando, Montaño-Rivas, Omar, and Canseco-Cortinas, José Margarito

Subjects
MEDICAL assistants, MOBILE apps, TYPE 2 diabetes, TYPE 1 diabetes, AEROBIC exercises, ARTIFICIAL pancreases
Abstract

Featured Application: Mobile application for iterative simulation of a diabetic model. This paper presents an educational mobile assistant application for type 1 diabetes patients. The proposed application is based on four mathematical models that describe the glucose-insulin-glucagon dynamics using a compartmental model, with additional equations to reproduce aerobic exercise, gastric glucose absorption by the gut, and subcutaneous insulin absorption. The medical assistant was implemented in Java and deployed and validated on several smartphones with Android OS. Multiple daily doses can be simulated to perform intensive insulin therapy. As a result, the proposed application shows the influence of exercise periods, food intakes, and insulin treatments on the glucose concentrations. Four parameter variations are studied, and their corresponding glucose concentration plots are obtained, which show agreement with simulators of the state of the art. The developed application is focused on type-1 diabetes, but this can be extended to consider type-2 diabetes by modifying the current mathematical models. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

6. Medical Assistant Mobile Application for Diabetes Control by Simulating a Compartmental Model

Author

Martín Hernández-Ordoñez, Marco Aurelio Nuño-Maganda, Carlos Adrián Calles-Arriaga, Abelardo Rodríguez-León, Guillermo Efren Ovando-Chacon, Rolando Salazar-Hernández, Omar Montaño-Rivas, and José Margarito Canseco-Cortinas

Subjects
mathematical models, Iterative simulation, compartmental model, diabetes control, mobile assistant, Technology, Engineering (General). Civil engineering (General), TA1-2040, Biology (General), QH301-705.5, Physics, QC1-999, Chemistry, QD1-999
Abstract

This paper presents an educational mobile assistant application for type 1 diabetes patients. The proposed application is based on four mathematical models that describe the glucose-insulin-glucagon dynamics using a compartmental model, with additional equations to reproduce aerobic exercise, gastric glucose absorption by the gut, and subcutaneous insulin absorption. The medical assistant was implemented in Java and deployed and validated on several smartphones with Android OS. Multiple daily doses can be simulated to perform intensive insulin therapy. As a result, the proposed application shows the influence of exercise periods, food intakes, and insulin treatments on the glucose concentrations. Four parameter variations are studied, and their corresponding glucose concentration plots are obtained, which show agreement with simulators of the state of the art. The developed application is focused on type-1 diabetes, but this can be extended to consider type-2 diabetes by modifying the current mathematical models.

Published
2020
Full Text
View/download PDF

7. An Artificial Intelligence Exercise Coaching Mobile App: Development and Randomized Controlled Trial to Verify Its Effectiveness in Posture Correction.

Author

Chae HJ, Kim JB, Park G, O'Sullivan DM, Seo J, and Park JJ

Abstract

Background: Insufficient physical activity due to social distancing and suppressed outdoor activities increases vulnerability to diseases like cardiovascular diseases, sarcopenia, and severe COVID-19. While bodyweight exercises, such as squats, effectively boost physical activity, incorrect postures risk abnormal muscle activation joint strain, leading to ineffective sessions or even injuries. Avoiding incorrect postures is challenging for novices without expert guidance. Existing solutions for remote coaching and computer-assisted posture correction often prove costly or inefficient., Objective: This study aimed to use deep neural networks to develop a personal workout assistant that offers feedback on squat postures using only mobile devices-smartphones and tablets. Deep learning mimicked experts' visual assessments of proper exercise postures. The effectiveness of the mobile app was evaluated by comparing it with exercise videos, a popular at-home workout choice., Methods: Twenty participants were recruited without squat exercise experience and divided into an experimental group (EXP) with 10 individuals aged 21.90 (SD 2.18) years and a mean BMI of 20.75 (SD 2.11) and a control group (CTL) with 10 individuals aged 22.60 (SD 1.95) years and a mean BMI of 18.72 (SD 1.23) using randomized controlled trials. A data set with over 20,000 squat videos annotated by experts was created and a deep learning model was trained using pose estimation and video classification to analyze the workout postures. Subsequently, a mobile workout assistant app, Home Alone Exercise, was developed, and a 2-week interventional study, in which the EXP used the app while the CTL only followed workout videos, showed how the app helps people improve squat exercise., Results: The EXP significantly improved their squat postures evaluated by the app after 2 weeks (Pre: 0.20 vs Mid: 4.20 vs Post: 8.00, P=.001), whereas the CTL (without the app) showed no significant change in squat posture (Pre: 0.70 vs Mid: 1.30 vs Post: 3.80, P=.13). Significant differences were observed in the left (Pre: 75.06 vs Mid: 76.24 vs Post: 63.13, P=.02) and right (Pre: 71.99 vs Mid: 76.68 vs Post: 62.82, P=.03) knee joint angles in the EXP before and after exercise, with no significant effect found for the CTL in the left (Pre: 73.27 vs Mid: 74.05 vs Post: 70.70, P=.68) and right (Pre: 70.82 vs Mid: 74.02 vs Post: 70.23, P=.61) knee joint angles., Conclusions: EXP participants trained with the app experienced faster improvement and learned more nuanced details of the squat exercise. The proposed mobile app, offering cost-effective self-discovery feedback, effectively taught users about squat exercises without expensive in-person trainer sessions., Trial Registration: Clinical Research Information Service KCT0008178 (retrospectively registered); https://cris.nih.go.kr/cris/search/detailSearch.do/24006., (©Han Joo Chae, Ji-Been Kim, Gwanmo Park, David Michael O'Sullivan, Jinwook Seo, Jung-Jun Park. Originally published in the Interactive Journal of Medical Research (https://www.i-jmr.org/), 12.09.2023.)

Published
2023
Full Text
View/download PDF

8. EveryWear, a Human Research and Health Mobile Assistant for Exploration

Author

Marnat, Maurice, Rouquette, Sebastien, Lapeyre, Yann, Fischer, Beate, Afchine, Deihiem, Altenburger, Susanne, Scott, Johnathan, Nicolini, Frank, Nitsch, Alexander, Chaput, Didier, Thuiliez, Emmanuel, and Canton, Remi

Subjects
Health, Security, Exploration, Mobile Assistant, Human Research, Medical Privacy
Published
2022

9. Medical Informatics and Data Analysis.

Author

Nieminen, Pentti and Nieminen, Pentti

Subjects
Medicine, Active Contour Models, GLM, GVF, ICD coding, Iterative simulation, Long-term care (LTC), Monte Carlo, South Korean female, Type I error, age-dependent stretched exponent, biostatistics, bird swarm algorithm, case study, castration-resistant prostate cancer, cervical injury, characteristic life, compartmental model, data analysis, data anonymization, data mining, data presentation, decision support system, deep belief network, deep learning, diabetes control, electronic healthcare, health, health care, heart disease diagnosis, heuristic approach, hierarchical classification, importance-satisfaction (I-S) model, inertial sensors, mathematical models, maximum lifespan, medical informatics, medicine, mobile assistant, modified stretched exponential function, n/a, neck pain, neck surface accelerometer, performance evaluation matrix (PEM), phased long short-term memory, power simulation, prostate cancer, prostate imaging, publications, reporting, retirement threshold, service quality performance matrix (SQPM), skewed data, snake segmentation, software tool, sparse FCM, statistical computing, statistics, surgery scheduling, t-test, vocal distance dose, vocal fatigue, voice of customer (VOC)
Abstract

Summary: During recent years, the use of advanced data analysis methods has increased in clinical and epidemiological research. This book emphasizes the practical aspects of new data analysis methods, and provides insight into new challenges in biostatistics, epidemiology, health sciences, dentistry, and clinical medicine. This book provides a readable text, giving advice on the reporting of new data analytical methods and data presentation. The book consists of 13 articles. Each article is self-contained and may be read independently according to the needs of the reader. The book is essential reading for postgraduate students as well as researchers from medicine and other sciences where statistical data analysis plays a central role.

10. Applying Gamification Principles and Therapeutic Movement Sequences to Design an Interactive Physical Activity Game: Development Study.

Author

Kim H, O'Sullivan DM, and Chung SH

Abstract

Background: Depression is a severe illness that has accelerated with the spread of COVID-19 and associated lockdowns. As a result, reported physical activity has substantially decreased, further increasing depressive symptoms., Objective: This study aims to explain the use of gamification principles to develop content for an interactive physical activity game for depression based on clinically proven depression diagnostic criteria., Methods: We discuss related work in this field, the game design framework, the users' depression severity, how we customize the contents accordingly, the gradual progression of the game to match exercise principles, and user flow optimization., Results: We provide a brief description of each of the games developed, including instructions on how to play and design aspects for flow, audio, and visual feedback methods. Exergames (interactive physical activity-based games) stimulate certain physical fitness factors such as improving reaction time, endurance, cardiovascular fitness, and flexibility. In addition, the game difficulty progresses based on various factors, such as the user's performance for successful completion, reaction time, movement speed, and stimulated larger joint range of motions. Cognitive aspects are included, as the user has to memorize particular movement sequences., Conclusions: Mental health issues are linked to behavior and movement; therefore, future physical activity-based interactive games may provide excellent stimulation for inducing user flow, while physical activity can help train various physical fitness factors linked to depression., (©Hyungsook Kim, David Michael O'Sullivan, Seong Hee Chung. Originally published in JMIR Serious Games (https://games.jmir.org), 16.12.2022.)

Published
2022
Full Text
View/download PDF

11. Medical Assistant Mobile Application for Diabetes Control by Simulating a Compartmental Model

Author

Carlos A. Calles-Arriaga, Guillermo E. Ovando-Chacon, José Margarito Canseco-Cortinas, M. Hernandez-Ordonez, Rolando Salazar-Hernández, Abelardo Rodriguez-Leon, Marco Aurelio Nuño-Maganda, and Omar Montano-Rivas

Subjects
Food intake, Computer science, diabetes control, medicine.medical_treatment, 030209 endocrinology & metabolism, Medical assistant, lcsh:Technology, lcsh:Chemistry, 03 medical and health sciences, 0302 clinical medicine, Diabetes mellitus, medicine, Aerobic exercise, General Materials Science, 030212 general & internal medicine, lcsh:QH301-705.5, Instrumentation, Simulation, Fluid Flow and Transfer Processes, Type 1 diabetes, lcsh:T, mobile assistant, Process Chemistry and Technology, Insulin, Iterative simulation, General Engineering, Insulin treatments, medicine.disease, lcsh:QC1-999, Computer Science Applications, Diabetes control, lcsh:Biology (General), lcsh:QD1-999, lcsh:TA1-2040, lcsh:Engineering (General). Civil engineering (General), mathematical models, compartmental model, lcsh:Physics
Abstract

This paper presents an educational mobile assistant application for type 1 diabetes patients. The proposed application is based on four mathematical models that describe the glucose-insulin-glucagon dynamics using a compartmental model, with additional equations to reproduce aerobic exercise, gastric glucose absorption by the gut, and subcutaneous insulin absorption. The medical assistant was implemented in Java and deployed and validated on several smartphones with Android OS. Multiple daily doses can be simulated to perform intensive insulin therapy. As a result, the proposed application shows the influence of exercise periods, food intakes, and insulin treatments on the glucose concentrations. Four parameter variations are studied, and their corresponding glucose concentration plots are obtained, which show agreement with simulators of the state of the art. The developed application is focused on type-1 diabetes, but this can be extended to consider type-2 diabetes by modifying the current mathematical models.

Published
2020
Full Text
View/download PDF

12. Use of NLP Techniques for an Enhanced Mobile Personal Assistant: The Case of Turkish

Author

Gokhan Celikkaya and Gülşen Eryiğit

Subjects
Short Message Service, business.industry, Computer science, mobile assistant, computer.software_genre, Computer Graphics and Computer-Aided Design, NLP, Task (computing), User experience design, Named-entity recognition, question answer system, Artificial Intelligence, Control and Systems Engineering, Web query classification, Phone, Preprocessor, The Internet, Artificial intelligence, natural language processing, business, computer, Natural language processing, Information Systems
Abstract

This article introduces a Turkish mobile assistant application which produces state-of-the art results for the Turkish language by using natural language processing (NLP) techniques. The voice-enabled mobile assistant application allows users to enter queries for nine pre-defined tasks; namely, making calls, sending sms messages and emails, getting directions, querying exchange rates, weather forecast and traffic information, searching on the internet and launching applications on the phone. Users’ queries are processed in a multi-stage approach (viz., NLP, query classification and parameter extraction). Either the requested task is performed or the requested information is displayed as the response of the application. The article presents the architecture of the introduced system, its comparison with some prominent mobile assistants as well as the newly created data resources (viz., two query datasets annotated for classification and parameter extraction, two specific datasets for domain adaptation of named entity recognition and syntactic parsing NLP modules) to be used in further research. The evaluations on the impact of NLP preprocessing layers to the query classification performances reveal that the added value by NLP may range from 0.2 to 10.7 percentage points depending on the preferred machine learning algorithm for the query classification stage. The impact of NLP for the parameter extraction stage is also crucial since the outputs of NLP modules are used systematically by the extraction rules. The overall performance of the introduced approach is measured as 70.8% which is very promising under the fact that the system is trained with very limited-size of annotated data. The technology introduced in this article is basically designed for the case of a mobile assistant but it can also be used for every voice-enabled control system to improve the user experience, such as smart homes or smart televisions.

Published
2017

13. Doğal Dil İşleme Teknikleri Kullanılarak Türkçe Mobil Asistan Yazılımı Geliştirilmesi

Author

Çelikkaya, Gökhan, Eryiğit, Gülşen, Bilgisayar Mühendisliği, Computer Engineering, and Bilgisayar Mühendisliği Ana Bilim Dalı

Subjects
Mobil Asistan, Agglutinative languages, Question Answer, Natural language processing, Konuşma Anlama, Doğal Dil İşleme, Soru Cevap, Mobile Assistant, Speech Understanding, Computer Engineering and Computer Science and Control, Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Siri, Natural Language Processing
Abstract

Tez (Yüksek Lisans) -- İstanbul Teknik Üniversitesi, Fen Bilimleri Enstitüsü, 2015, Thesis (M.Sc.) -- İstanbul Technical University, Instıtute of Science and Technology, 2015, Günümüzde tüketiciler hem istedikleri işlemleri yerine getirmek hem de ihtiyaç duydukları bilgi ve içeriğe erişmek için mobil cihazlarıyla basit ve kolay etkileşim kurmanın yollarını aramaktadırlar. Bu doğrultuda mobil cihazlarla sesli olarak etkileşim kurmaya imkan sağlayan kişisel asistan uygulamaları gittikçe popüler hale gelmektedir. Özellikle Apple'ın SIRI uygulamasının yaygınlaşmasından sonra, çeşitli firmalar benzer ürünler geliştirmişlerdir. Fakat çıkan ürünler çoğunlukla İngilizceyi ve Amerika Birleşik Devletleri, İngiltere gibi İngilizce konuşulan ülkelerde kullanılabilen servisleri desteklemektedirler. Türkçe için, 2015 yılı Nisan ayındaki güncelleme ile Türkçe desteği kazanan SIRI haricinde gelişmiş doğal dil işleme yöntemleri kullanan, birçok servisi esnek bir yapıda destekleyen, kullanıcının isteğini doğru anlama açısından başarımı yüksek bir mobil kişisel asistan uygulaması henüz geliştirilememiştir. Bu tezin amacı gelişmiş doğal dil işleme yöntemlerinin bu uygulamalar üzerindeki etkisini göstermek ve akıllı telefon ve tabletler üzerinde Türkçe doğal dil girdisi ile çalışacak yüksek başarımlı bir kişisel asistan uygulaması geliştirmektir. Bir sanal asistan, içerisinde yapay zekanın hemen her tür bileşenini bulunduran bir uygulamadır. Bunlar arasında, ses tanıma, ses üretimi, algılanan sesin anlamsal olarak işlenmesine yönelik doğal dil işleme (DDİ) yöntemleri ve hatta 3 boyutlu hologramların kullanımı ile sistemin bir insanı taklit etmesi (görüntü tanıma, görüntü oluşturma vb.) sayılabilir. Mobil sanal asistanlar ise şimdilik sadece kullanıcı ile ses üzerinden iletişim kuran ve sistemden beklenen istekleri yerine getirip sorgulara sesli cevap döndüren uygulamalardır. Bu tez kapsamında geliştirilen uygulama, sesli yanıt döndürme özelliği bulunmayan bir mobil sanal asistan uygulamasıdır. Son 15 yıl içerisinde, Türkçe için başarılı sayılabilecek ses tanıma, ses üretimi, doğal dil işleme bileşenleri geliştirilmiştir ve bu konudaki araştırmalar halen aktif olarak devam etmektedir. Ancak bu ayrı bileşenler henüz başarılı üst düzey uygulamalarda bir araya getirilebilmiş değillerdir. Bu tez çerçevesinde, Türkçe için geliştirilen bu çalışmaların (sesi metine dönüştürme, sözcük çözümleyicileri, cümle çözümleyicileri, varlık ismi saptayıcıları, metin normalleştiricileri vb..) öncelikle "kişisel asistan uygulamaları" konusuna yönelik alan adaptasyonları yapılmış ve sonrasında bileşenler ürüne yönelik ortak bir çatı altında birleştirilmiştir. Yapılan ön incelemelerde, Türkçe için az sayıdaki mevcut sanal asistan uygulamasının, temel olarak kural tabanlı veya basit doğal dil işleme bileşenlerine sahip oldukları veya bu bileşenleri hiç içermeyip sadece görselleştirmeye yöneldikleri görülmüştür. Bu nedenle, dili anlama ve istenilen işlemleri yerine getirme konusundaki başarımlarının oldukça düşük olduğu gözlemlenmektedir. Son yıllarda Türkçe DDİ üzerine geliştirilen yeni yöntemlerin bu uygulamalar için bir araya getirilmesi ile çok daha yüksek başarımlı kişisel mobil asistan uygulamaları oluşturulabileceği tarafımızdan öngörülmüştür. Bu çalışma ile geliştirilen uygulamanın bu alanda öncü bir rol oynaması hedeflenmektedir. Tez kapsamında geliştirilen uygulamanın aşağıdaki işlemler ve servisler ile ilgili sesli komutları anlayıp yerine getirmektedir. Sms gönderimi (Gökhan'a yarın akşam gelemeyeceğimi mesaj at), E-posta gönderimi (Gökhan'a yarın akşam gelemeyeceğimi mail at), Numarayı veya kayıtlı kişiyi arama (Gökhan'ı ara), Telefonda yüklü olan uygulamaları çalıştırma (Facebook'u başlat), İnternet üzerinden arama başlatma (İstanbul'u Google'da ara), Hava durumu bilgisini alma (Bugün hava nasıl olacak?), Harita servisi (Beşiktaş'a nasıl giderim?), Döviz çevirme işlemleri (10 dolar kaç lira), Trafik bilgisini alma (Şu an İstanbul'da trafik nasıl?). Geliştirilen sistem 2 kısımdan oluşmaktadır. Mobil uygulama, sesi yazıya dönüştürme, sunucuya istek gönderme ve gelen yanıtı gösterme veya gerçekleştirme görevlerinden sorumludur. Sunucu, yazılı olarak gelen isteği DDİ araçlarını kullanarak anlamak ve gerekiyorsa 3. parti diğer servislerden bilgi toplayarak yanıt döndürmekten sorumludur. Gelen sorgu sunucu tarafında işlenmeden önce olası dil bilgisi hatalarını azaltmak için metin normalleştiriciden geçirilir. Ardından DDİ araçlarının sonuçlarının da kullanıldığı kural ve istatistiksel yöntemlerin birleşiminden oluşan melez bir yapı ile sorgunun hangi servis ile ilgili olduğu anlaşılır. Geliştirilen melez model, test verimiz üzerinde %98.30 başarı göstermiştir. Ardından belirlenen servis için anlamlı olan parametreler çıkartılır ve gerekli olan servisler için 3. parti kaynaklardan bilgi çekilerek yanıt döndürülür. Tüm sistemin başarısı ortalama %70.79 olarak belirlenmiştir., Since the interaction with mobile devices increased enormously in recent years, user friendly interfaces facilitating human-machine interaction became very important. Since natural language is the most natural way of communication for humans, mobile assistant applications became very popular. Especially after SIRI gained popularity, several companies developed similar applications and released to the application markets. Nevertheless most of these applications supports English and provide services mostly for English-speaking countries. Unfortunately, the challenges caused by the typological differences of some natural languages also appears in mobile applications and the generated systems which are mostly on English, could not be adapted easily to other languages such as Turkish. In the current state, there is no application for Turkish that uses advanced natural language processing (NLP) solutions, supports many services in a flexible structure and has a high success rate on understanding users' request except SIRI which started to support Turkish language after IOS 8.3 update in April 2015. Even though SIRI began to support Turkish, its success rate and supported service count is very low compared to its English version. The goal of this thesis is to illustrate the impact of using natural language solutions on mobile assistant applications and develop a new application that will support Turkish natural language input with high success rate. The application developed performs operations on mobile device (e.g. calling someone) and retrieve and show information (e.g. weather forecast information). A virtual assistant is an application that contains almost all components of artificial intelligence. Voice recognition, voice generation, natural language processing components to understand the voice semantically, and even usage of 3 dimensional holograms to simulate humans (image recognition or generation) can be considered in this aspect. Mobile assistants are applications that interacts with user over voice processing and understands user's intention and accomplish his/her request. In the last 15 years successful voice recognition, voice generation and natural language processing components have been developed for Turkish. The researches in these fields are still continuing actively. However the components have not been integrated in a high level application. Within this thesis, domain adaptation is applied to these researches (speech to text, morphological analysis, dependency parser, named entity recognizer, text normalizer) in personal mobile assistant domain and combined in an application. It is observed that Turkish mobile assistant applications which there is only few, developed in a rule based approach and does not use or uses very basic natural language processing components. Therefore, their success rate on understanding and executing user's query is very low. For example for a query such as "Ankara'da hava bugün nasıl? (How is the weather today in Ankara)", such applications return the weather forecast of the current location (e.g. "Istanbul") instead of the requested location ("Ankara"). Implementing Turkish NLP researches to the software would increase the success of these applications. This work is the first academic study focusing on the language related problem of a Turkish Mobile Assistant and shows the state-of-the art in this field. It is expected that the application and study in this thesis will become a pioneer in its field of practice. The application developed is able to understand and fulfill voice queries on following domains. Sending message (Gökhan'a yarın akşam gelemeyeceğimi mesaj at) (Send message to Gökhan that I will not come tomorrow evening), Sending e-mail (Gökhan'a yarın akşam gelemeyeceğimi mail at) (Send email to Gökhan that I will not come tomorrow evening), Calling a number or contact (Gökhan'ı ara) (Call Gökhan), Launching applications on the device (Facebook'u başlat) (Launch Facebook), Search something on the Internet (İstanbul'u Google'da ara) (Search Istanbul on Google), Retrieve weather information (Bugün hava nasıl olacak?) (How will be the weather today), Map Direction Google Maps (Beşiktaş'a nasıl giderim?) (How can I go to Besiktas), Currency exchange (10 dolar kaç lira) (How many liras is 10 dollars), Traffic information (Şu an İstanbul'da trafik nasıl?) (How is traffic in Istanbul). Developed system consists of 2 modules which interacts with each other using defined JSON protocol. Mobile application is responsible for 1. capturing the spoken request, 2. converting it to written text 3. transferring the user requests to the server side and 4. displaying and/or performing the requested operation according to the result received from the server. Server service is responsible for processing the user's query and understand its true intention. It also collects information from third party web services if needed, and finally, compiles the results and sends it back to the client. Google's speech recognition API for Android is used in mobile application in order to capture the user spoken queries and convert them into written messages. The speech recognizer returns more than one text suggestions for a given entry and each suggestion has its own confidence level. If any of the produced suggestions has more than this threshold value, it is the assumed to be the correct suggestion. Otherwise, the application presents a list of text suggestions to the user in. After this stage, the selected query text is sent to the server along with the user's context, which includes the user id, current location and time. The returned answer from the server is then either executed on the phone or displayed to the user. On the server-side incoming user query is first processed with NLP tools, and then the query is mapped to one of the supported operations through a hybrid approach of rule-based and statistical classification. Different algorithms have been tested in statistical classification step and best result is obtained with support vector machine (SVM) algorithm with 95.80% classification accuracy. Total classification success of the hybrid approach is measured as %98.30. After this stage, the required parameters for each operation are extracted from the query using the assigned analysis by the automatic natural language processing modules. Whole system success is measured as 70.79%., Yüksek Lisans, M.Sc.

Published
2015

Catalog

Books, media, physical & digital resources
See catalog results