Cemal GURPINAR

About

I attended the Naval Academy in 2001 and earned my graduate with the eighth place (GPA: 3.56/4.0) as a Naval Officer and Computer Engineer in 2005. Between 2005 and 2010, I worked in the Naval Command Headquarter and aboard several Navy ships. On 2012, I earned my MSc degree in Computer Science from Istanbul Technical University. Then, I was assigned to the Turkish Naval Research Center Command and worked there until 2023. Afterwards, I decided to retire from Turkish Navy in January 2023. In February 2023, I started working as Lead System Engineer at ROKETSAN Inc. Shortly after I started working at ROKETSAN, I received my PhD degree in Computer Science from Istanbul Technical University.

A person's earliest interactions play a crucial role in humans life and have a big impact on their future. The Naval Academy was where I first encountered artificial intelligence, and reading about Alan Turing in particular piqued my curiosity. Due to my interest in Artificial Intelligence, I completed my thesis by designing a map for autonomous tracked vehicles and implementing a shortest path algorithm. The top 10 projects in Naval Academy included this graduation project.

I became interested in computer vision and machine learning during my master's program and started using these concepts with robots. This led me to develop a Humanoid Robot Painter for my master's thesis. This robot had a three-fingered hand, a camera used for recognizing the objects. The robot would first recognize objects and then paint them.

In my PhD study, I researched how to forecast unique children's emotions from videos, such as those with Autism Spectrum Disorder and hearing impairment. I also work on a European project called EMBOA, whose goal is to use artificial intelligence to recognize the emotions of children with autism spectrum disorder (ASD) and to treat ASD children with the help of the humanoid robots Pepper and Kaspar.

In addition to my academic works on artificial intelligence and machine learning, I was the project manager for the Turkish Naval Research Center Command's project on the detection, identification, and classification of surface targets using SAR/ISAR photos collected by unmanned aerial vehicles utilizing machine learning methods. Besides, I worked on the engagement plannig algorithm of ADVENT Combat Management System to build a sensor and weapon matching system based on artificial intelligence.

AI Specialist & ML Engineer & Robotics Enthusiast.

Birthday: 21 Nov 1983
Age: 41
Website: https://cemalgurpinar.github.io/
City: Istanbul, Turkey

Graduated Degree: PhD
Current Degree: PhD
Email: cemalpg@gmail.com
Phone: +90532 406 1773

Skills

JIRA & GIT & JENKINS 85%

Python 90%

Java 85%

C++ 85%

ADA 60%

Fluency in English90%

Machine Learning 93%

Computer Vision 92%

Image Processing 85%

Resume

Summary

12+ years of experience on applying artificial intelligence, machine learning, image processing and computer vision algorithms, especially for emotion recognition and sign language recognition, besides, have a lot of expertise on developing fire control systems and CMS integration of weapons, also, enthusiastic researcher on applying artificial intelligence and machine learning algorithms on command and control systems.

Education

Istanbul Technical University - PhD

2012 - 2023

GPA: 3.81/4.0

Thesis: DA4HI: A Deep Learning Framework for Facial Emotion Recognition in Affective Systems for Children with Hearing Impairments.

Istanbul Technical University - Master of Science

2010 - 2012

GPA: 3.38/4.0

Thesis: Humanoid Robot Painter

Naval Academy

2001 - 2005

GPA: 3.56/4.0 - Place:8/256

Thesis: Map-based Autonomous Tracked Land Vehicle Navigation

Educational Experience

Conference of Chiefs of European Navies 2022

11 - 12 May 2022

Giving a presentation at the conference attended by the Naval Forces Commands of 29 countries on A New Paradigm in Command and Control Systems : Artificial Intelligence.

Istanbul Technical University (ITU) Cognitive Social Robotics (CSR) Laboratory

2012 - Present

I have been a member of a ITU CSR lab since 2012 and we implement projects related to social robotics including Turkish Sign Language recognition and emotion recognition, especially for children.

EMBOA Project (Eurapean Union)

2019 - 2022

Implementing a CNN based automatic emotion recognition algorithm used in KASPAR Robot employed in EMBOA project entitled “Affective loop in Socially Assistive Robotics as an intervention tool for children with autism” .

ROBOREHAB Project (TUBITAK)

2018 - 2020

Implementing an automatic emotion recognition algorithm based on CNN using domain adaptation concept used in PEPPER Robot employed in ROBOREHAB project entitled “ROBOREHAB: Assistive Audiology Rehabilitation Robot” .

TSL Project (TUBITAK)

2016 - 2019

Implementing a Turkish Sign Recognition system based on two different approaches including a conventional method involving artificial neural network combined with hidden Markov model and a deep learning based method involving long short-term memory (LSTM) used in ROBOVIE Robot employed in Turhish Sign Language (TSL) project entitled “Robot and Avatar based Interactive Gaming Platform for Hearing Impaired Children (HIC)” .

Professional Experience

ROKETSAN - Lead System Engineer

2023 - Present

Kurtköy, Istanbul, Turkey

Lead in system engineering, development and implementation of MİDLAS (National Vertical Launching System) Launch Control Unit
Lead in development, and implementation of the Evolved Seasparrow Guided Missile (ESSM G/M) Fire Control System for BARBAROS Class Frigates and GABYA Class Frigates
Technical Manager of MİDLAS (National Vertical Launching System) Launch Control Unit - Generate system solution for Combat Management System (CMS) intregration and produce Technical Agreement (TA) document.
Supervise the integration of MIDLAS and HİSAR Guided Missile (G/M) to the Combat Management System (CMS) and successfull launched Controlled Test Missile
Supervise the launch of HISAR G/M from MIDLAS on TCG ISTANBUL

ARMERKOM, NAVY - Senior Lead System Engineer

2012 - 2023

Pendik, Istanbul, Turkey

Consultant membership on behalf of the Turkish Naval Forces Command for Machine Learning and Deep Learning Algorithms within the scope of Identification and Classification of Targets Detected by Radar Project (GÖRÜ) Project.
Lead in development, and implementation of the Evolved Seasparrow Guided Missile (ESSM G/M) Fire Control System for BARBAROS Class Frigates and GABYA Class Frigates
Supervise the integration of MK 41 Vertical Launching System and ESSM Guided Missile (G/M) to the Combat Management System (CMS) and successfull launched missiles
Technical Manager of MİDLAS (National Vertical Launching System) - Generate system solution for Combat Management System (CMS) intregration and produce Technical Agreement (TA) document.
Technical Manager of Surface-to-Surface G/M (ATMACA) Procurement Project - Generate system solution for CMS intregration and produce TA document.
Technical Manager of GÖKDENİZ (National Close-In Weapon System) - Generate system solution for Combat Management System (CMS) intregration and produce TA document.
National Point of Contact for Ship Air Defense Model (SADM) and International ESSM Block 1 Simulator (INTSIM)

NAVAL COMMAND HEAD QUARTER-Infrastructure Management Officer

2008 - 2010

Golcuk, Kocaeli, Turkey

Develope and execute a strategy for disseminating TAFICS (Turkish Armed Forces Integrated Communication System) infrastructure and satellite communication of Navy bases and ships.

NAVAL COMMAND - Signal Officer

2006 - 2008

Golcuk, Kocaeli, Turkey

Report all necessary information to the Executive Officer and work closely with him to achieve and maintain goals.

Publications

          @article{GURPINAR2022104572,
                   title = {Contrastive learning based facial action unit detection in children with hearing impairment for a socially assistive robot platform},
                   journal = {Image and Vision Computing},
                   volume = {128},
                   pages = {104572},
                   year = {2022},
                   issn = {0262-8856},
                   doi = {https://doi.org/10.1016/j.imavis.2022.104572},
                   url = {https://www.sciencedirect.com/science/article/pii/S0262885622002013},
                   author = {Cemal Gurpinar and Seyma Takir and Erhan Bicer and Pinar Uluer and Nafiz Arica and Hatice Kose},
                   keywords = {Contrastive learning, Facial action unit detection, Child-robot interaction, Transfer learning, Domain adaptation, Covariate shift},
            }
          @INPROCEEDINGS{9864989,
            author={Biçer, Erhan and Takır, Şeyma and Gürpınar, Cemal and Uluer, Pınar and Köse, Hatice},
            booktitle={2022 30th Signal Processing and Communications Applications Conference (SIU)}, 
            title={Masking and Compression Techniques for Efficient Action Unit Detection of Children for Social Robots}, 
            year={2022},
            volume={},
            number={},
            pages={1-4},
            doi={10.1109/SIU55565.2022.9864989}}
          @INPROCEEDINGS{9864675,
            author={Bozkurt, Muruvvet and Oncel, Firat and Gurpinar, Cemal and Kose, Hatice and Unal, Gozde},
            booktitle={2022 30th Signal Processing and Communications Applications Conference (SIU)}, 
            title={Facial Expressions Detection of Children with Hearing Impairment}, 
            year={2022},
            volume={},
            number={},
            pages={1-4},
            doi={10.1109/SIU55565.2022.9864675}}
          @INPROCEEDINGS{aydin_eleco_2022,
            author={Aydın, Yavuz and Erkmen, Burcu and Gürpınar, Cemal},
            booktitle={2022 13th International Conference on Electrical and Electronics Engineering (ELECO)}, 
            title={Remaining Useful Lifetime (RUL) Prediction of Lithium-Ion Batteries via CWT Based Deep Learning Methods}, 
            year={2022},
            volume={},
            number={},
            pages={1-5},
            keywords={Remaining Useful Lifetime;Continuous Wavelet Transform;Artificial Neural Network;Convolutional Neural Network; Deep Learning},
            url={http://www.eleco.org.tr/ELECO2022/eleco2022_papers/127.pdf}}
          @INPROCEEDINGS{6531542,
            author={Ertuğrul, Bekir Sıtkı and Gurpinar, Cemal and Kivrak, Hasan and Kose, Hatice},
            booktitle={2013 21st Signal Processing and Communications Applications Conference (SIU)}, 
            title={Gesture recognition for humanoid assisted interactive sign language tutoring}, 
            year={2013},
            volume={},
            number={},
            pages={1-4},
            doi={10.1109/SIU.2013.6531542}}
          @Inbook{Kose2015,
            author="Kose, Hatice
            and Akalin, Neziha
            and Yorganci, Rabia
            and Ertugrul, Bekir S.
            and Kivrak, Hasan
            and Kavak, Semih
            and Ozkul, Ahmet
            and Gurpinar, Cemal
            and Uluer, Pinar
            and Ince, G{\"o}khan",
            editor="Mohammed, Samer
            and Moreno, Juan C.
            and Kong, Kyoungchul
            and Amirat, Yacine",
            title="iSign: An Architecture for Humanoid Assisted Sign Language Tutoring",
            Chapter="Intelligent Assistive Robots: Recent Advances in Assistive Robotics for Everyday Activities",
            year="2015",
            publisher="Springer International Publishing",
            address="Cham",
            pages="157--184",
            abstract="This paper investigates the role of interaction and communication kinesics in human-robot interaction. It is based on a project on Sign Language (SL) tutoring through interaction games with humanoid robots. The aim of the study is to design a computational framework, which enables to motivate the children with communication problems (i.e., ASD and hearing impairments) to understand and imitate the signs implemented by the robot using the basic upper torso gestures and sound in a turn-taking manner. This framework consists of modular computational components to endow the robot the capability of perceiving the actions of the children, carrying out a game or storytelling task and tutoring the children in any desired mode, i.e., supervised and semi-supervised. Visual (colored cards), vocal (storytelling, music), touch (using tactile sensors on the robot to communicate), and motion (recognition and implementation of gestures including signs) based cues are proposed to be used for a multimodal communication between the robot, child and therapist/parent. We present an empirical and exploratory study investigating the effect of basic non-verbal gestures consisting of hand movements, body and face gestures expressed by a humanoid robot, and having comprehended the word, the child will give relevant feedback in SL or visually to the robot, according to the context of the game.",
            isbn="978-3-319-12922-8",
            doi="10.1007/978-3-319-12922-8_6",
            url="https://doi.org/10.1007/978-3-319-12922-8_6"
            }
          @Article{G{\"u}rp{\i}nar2020,
            author={G{\"u}rpınar, Cemal
            and Uluer, Pınar
            and Akalın, Neziha
            and K{\"o}se, Hatice},
            title={Sign Recognition System for an Assistive Robot Sign Tutor for Children},
            journal={International Journal of Social Robotics},
            year={2020},
            month={May},
            day={01},
            volume={12},
            number={2},
            pages={355-369},
            abstract={This paper presents a sign recognition system for a sign tutoring assistive humanoid robot. In this study, a specially designed 5-fingered robot platform with expressive face (Robovie R3) is used for interaction and communication with deaf or hard of hearing children using signs and visual cues. The robot is able to recognize and generate accurately a selected set of signs from Turkish sign language using various hand, arm and head gestures as relevant feedback. This paper focuses on the sign recognition system of the robot to recognize the human participant's signing during the interaction. The system is based on two different approaches including a conventional method involving artificial neural network combined with hidden Markov model and a deep learning based method involving long short-term memory. The system is tested both on offline and real-time settings within an interaction game scenario with deaf or hard of hearing children. During the study, besides testing the sign recognition system, participants' subjective evaluations and impressions were also collected and examined. The robot is perceived as likable and intelligent by the children, based on the questionnaires; and the proposed sign recognition system enables robust real-time interaction and communication of the assistive robot with children in sign language.},
            issn={1875-4805},
            doi={10.1007/s12369-019-00609-9},
            url={https://doi.org/10.1007/s12369-019-00609-9}
            }
          @ARTICLE{Uluer2017-nv,
            title    = "Interactive Games with an Assistive Robotic System for
                        {Hearing-Impaired} Children",
            author   = "Uluer, Pinar and Akalin, Neziha and Gurpinar, Cemal and Kose,
                        Hatice",
            abstract = "This paper presents an assistive robotic system, which can
                        recognize and express sign language words from a predefined set,
                        within interactive games to communicate with and teach
                        hearing-impaired children sign language. The robotic system uses
                        audio, visual and tactile feedback for interaction with the
                        children and the teacher/researcher.",
            journal  = "Stud Health Technol Inform",
            volume   =  242,
            pages    = "298--305",
            year     =  2017,
            address  = "Netherlands",
            keywords = "Human-robot interaction; games and gamification; sign language;
                        sign recognition",
            language = "en"
          }
          @InProceedings{10.1007/978-3-030-68790-8_4,
            author="Baglayici, Engin
            and Gurpinar, Cemal
            and Uluer, Pinar
            and Kose, Hatice",
            editor="Del Bimbo, Alberto
            and Cucchiara, Rita
            and Sclaroff, Stan
            and Farinella, Giovanni Maria
            and Mei, Tao
            and Bertini, Marco
            and Escalante, Hugo Jair
            and Vezzani, Roberto",
            title="A New Facial Expression Processing System for an Affectively Aware Robot",
            booktitle="Pattern Recognition. ICPR International Workshops and Challenges",
            year="2021",
            publisher="Springer International Publishing",
            address="Cham",
            pages="36--51",
            abstract="This paper introduces an emotion recognition system for an affectively aware hospital robot for children, and a data labeling and processing tool called LabelFace for facial expression recognition (FER) to be employed within the presented system. The tool provides an interface for automatic/manual labeling and visual information processing for emotion and facial action unit (AU) recognition with the assistant models based on deep learning. The tool is developed primarily to support the affective intelligence of a socially assistive robot for supporting the healthcare of children with hearing impairments. In the proposed approach, multi-label AU detection models are used for this purpose. To the best of our knowledge, the proposed children AU detector model is the first model which targets 5- to 9- year old children. The model is trained with well-known posed-datasets and tested with a real-world non-posed dataset collected from hearing-impaired children. Our tool LabelFace is compared to a widely-used facial expression tool in terms of data processing and data labeling capabilities for benchmarking, and performs better with its AU detector models for children on both posed-data and non-posed data testing.",
            isbn="978-3-030-68790-8"
            }
            @INPROCEEDINGS{6213403,
              author={Gurpinar, Cemal and Alasag, Tolga and Kose, Hatice},
              booktitle={2012 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO)}, 
              title={Humanoid robot painter assisted by a human}, 
              year={2012},
              volume={},
              number={},
              pages={79-82},
              doi={10.1109/ARSO.2012.6213403}}
            @INPROCEEDINGS{akalininsansi,
              booktitle={2015 2th T{\"u}rkiye Robotbilim Konferansı (ToRK)},
              title={Insansı Robot Etkilesimli Isaret Dili Oyunlarında Isaret Tanıma},
              author={Akalın, Neziha and Uluer, Pınar and {\"O}zden, Yakup and G{\"u}rpınar, Cemal and K{\"o}se, Hatice},
              year={2015},
              volume={},
              number={},
              pages={1-3}
            }
            @MastersThesis{gurpinar2012human,
              author={G{\"u}rpınar, Cemal},
              title={Human assisted humanoid robot painter},
              school={Istanbul Technical University},
              organization = {Faculty of Computer and Informatics Engineering},
              year={2012},
              type = {Master of Science Thesis}
            }
            @phdthesis{gurpinar2023da4hi,
              author={G{\"u}rpınar, Cemal},
              title={DA4HI: A deep learning framework for facial emotion recognition in affective systems for children with hearing impairments.},
              school={Istanbul Technical University},
              organization = {Faculty of Computer and Informatics Engineering},
              year={2023},
              type = {PhD Thesis}
            }

Contact

Location:

Tuzla, İstanbul, Turkey

Email:

cemalpg@gmail.com

Call:

+90 532 406 1773