Find Academic Supervisors

Christian WilmsView profile

Researcher

• Computer Vision
• Object Recognition
• Image Segmentation
• +6 more

Christian Wilms is a Researcher at the University of Hamburg's Department of Informatics within the Faculty of Mathematics, Informatics and Natural Sciences, where he contributes to the Computer Vision Research Group's cutting-edge work in visual recognition systems. His research focuses on: Object recognition techniques including proposal generation, instance segmentation, and detection Foundation models for segmentation and superpixel-based algorithms Applications in agricultural monitoring, medical imaging, and industrial inspection Multi-modal signal processing for audio-visual perception Analysis of his recent publications reveals a strong emphasis on solving small object detection challenges through semi-supervised learning and attention mechanisms, particularly evident in orchard monitoring applications. His work consistently bridges theoretical advances in segmentation topology with practical implementations in drone-based systems and industrial anomaly detection. As part of the Computer Vision Research Group led by Prof. Simone Frintrop, Wilms contributes to major projects including InteGreatDrones, Crossmodal Learning, and NEUROBOTICS, which explore active perception, object pose estimation, and simultaneous localization in complex environments.

André KelmView profile

Researcher

• Deep Learning for Industrial Innovation
• Domain Adaptation
• Synthetic Data Applications
• +6 more

André Kelm is a PhD candidate in the Computer Vision group at the Department of Informatics , University of Hamburg, affiliated with the Faculty of Mathematics, Informatics and Natural Sciences . His research spans deep learning for industrial innovation, domain adaptation, and synthetic data applications, with interdisciplinary interests in physics, audio, medical, and biological domains. His work focuses on efficient adaptive inference , interpretability in deep learning , and bottom-up/top-down attention mechanisms . Recent publications highlight applications in drone-based port monitoring , dynamic neural network optimization , and multimodal knowledge distillation . Projects he contributes to include InteGreatDrones , Crossmodal Learning (CML) , and NEUROBOTICS . For collaboration, contact him at andre.kelm@uni-hamburg.de.

Chuan-Sheng FooView profile

Researcher

• Deep Learning
• Machine Learning
• Computer Vision
• +4 more

Chuan-Sheng Foo serves as the Deputy Head of the Machine Intelligence Department at the Institute for Infocomm Research (I2R), part of Singapore's Agency for Science, Technology and Research (A*STAR). His research focuses on data-efficient deep learning approaches for applications in healthcare and manufacturing, where large annotated datasets are difficult to obtain due to the need for expert labeling and associated costs. Foo earned his academic credentials from Stanford University with a BS ('08), MS ('12), and PhD ('17) in Computer Science. During his doctoral studies, he collaborated with prominent researchers including Professors Anshul Kundaje, Daphne Koller, Andrew Ng, and Serafim Batzoglou on machine learning applications in biology. Notably, he took a year away from his PhD to develop software for clinically validated genetic tests at Counsyl, where he worked on variant calling and LIMS integration. Foo's research spans multiple AI domains with a consistent focus on developing machine learning methods that require minimal labeled data. His work encompasses semi-supervised learning, generative models (particularly GANs), computer vision, medical imaging, and computational biology. He has made significant contributions across theoretical foundations and practical applications, especially in healthcare contexts where expert annotation is costly. His publication record shows an evolution from foundational machine learning algorithms to increasingly applied research with strong healthcare connections. Early work focused on hyperparameter optimization and RNA structure analysis, while recent publications address computer vision challenges, GAN training improvements, and medical imaging applications. A unifying theme across his career is the development of techniques that maximize performance with limited labeled data. Foo has received numerous prestigious awards throughout his academic journey: Computing Research Association Outstanding Undergraduate Researcher Award (2008) UCSD Data Mining Contest: 1st, 2nd (2006), 3rd (2007), 2nd (2008) Top 200 ranking on the Putnam Mathematics Competition (2005) President's Award for Academic Achievement in the Freshman Year (2006) Best Paper Award at the 16th International Conference on Genome Informatics (2005) A*STAR National Science Scholarship (2002) Bronze medal at the 33rd International Physics Olympiad (2002) As Deputy Head of Department at I2R, Foo leads a research group focused on data-efficient deep learning. His collaborative approach is evident in numerous co-authored publications across multiple domains, particularly in applying machine learning to biological and medical challenges. His work at A*STAR likely involves significant research funding supporting his team's development of practical AI solutions for real-world problems where data annotation presents significant barriers.

• Natural Language Processing
• Machine Learning
• Unsupervised Learning
• +4 more

Taylor Berg-Kirkpatrick is an Associate Professor in the Department of Computer Science and Engineering at the University of California, San Diego. He directs the BergLab research group, which focuses on developing machine learning methods for analyzing human language and artifacts, including historical documents, music, and multimodal data. His work bridges natural language processing, computational linguistics, and creative AI applications. Research Interests: Berg-Kirkpatrick's research spans unsupervised learning for language understanding, structured prediction models, and computational analysis of human artifacts. The BergLab specializes in: Deciphering historical documents and languages using computer vision and NLP Developing generative models for music and audio synthesis Creating novel methods for low-resource and unsupervised machine learning Cross-modal analysis between text, audio, and visual data Recent Publication Trends: His 15 most recent publications (2023-2024) demonstrate three key research vectors: advanced music generation using diffusion models and symbolic representations; computational analysis of historical artifacts including cuneiform tablets and early modern books; and foundational NLP work on model architectures, decoding methods, and multimodal systems. The work shows consistent innovation in generative AI, historical document processing, and efficient machine learning techniques. Awards and Honors: NSF CAREER Award for 'Modeling Language Evolution via Deep Probabilistic Factorization' (2022) Advising and Funding: Berg-Kirkpatrick has advised over 10 PhD students to completion on topics spanning NLP, music generation, and historical document analysis. His research is supported by the NSF CAREER grant and focuses on developing unsupervised methods for language evolution modeling. The BergLab maintains several open-source projects including Klavier (piano transcription), Ocular (historical document recognition), and Puck (high-speed parser). Lab Direction: The BergLab at UCSD develops computational methods for analyzing diverse human artifacts through interdisciplinary collaborations with historians, musicians, and archaeologists. Current projects include computational bibliography of early modern books, decipherment of historical ciphers, and generative models for symbolic music.

• Predictive Brain
• Naturalistic Cognitive Neuroscience
• Neural Representational Dynamics
• +4 more

Ingmar Engbert Jacob De Vries is a Tenure-Track Assistant Professor at the University of Trento, affiliated with the Centre for Mind/Brain Sciences (CIMeC) and the Department of Physics. He also works as a Visiting Researcher at the Donders Centre for Cognitive Neuroimaging (DCCN) at Radboud University, The Netherlands. His research focuses on predictive brain mechanisms and naturalistic cognitive neuroscience using MEG, EEG, and eye-tracking. PhD in Cognitive Neuroscience (2019), Vrije Universiteit Amsterdam Bachelor and Master in Human Movement Sciences (2009-2014), Vrije Universiteit Amsterdam His research explores how the brain anticipates future states to enable adaptive behavior. Key areas include predictive brain , naturalistic cognitive neuroscience , and neural representational dynamics . Methodologically, he specializes in MEG , EEG , and eye-tracking to analyze neural signals during naturalistic (audio)-visual stimuli processing. His work also investigates VR-EEG applications for future studies. Scientific awards include the 2024 CAOs Abstract Prize, 2022 MSCA Postdoctoral Fellowship, and 2020 MSCA Seal of Excellence. He has supervised multiple MSc thesis students and co-supervised a PhD project. His publications focus on predictive neural representations, dynamic representational similarity analysis (RSA), and neural oscillations in visual working memory. Collaborations include #EEGmanylabs, #EEGmanypipelines, and #EEGmanyanalyst replication projects.

Nuria OliverView profile

Researcher

• Computational Models of Human Behavior
• Human-Computer Interaction
• Intelligent User Interfaces
• +12 more

Nuria Oliver, PhD is a pioneering computer scientist and ACM Fellow , recognized as the first female Spanish computer scientist to achieve both ACM Distinguished Scientist and IEEE Fellow status. Current affiliations include Microsoft Research and former roles at MIT Media Lab. First female Spanish ACM Fellow IEEE Fellow Academia Europaea member Her research spans human behavior modeling , intelligent user interfaces , and mobile computing , with notable work in: Wearable context-aware systems (DyPERS, HealthGear) Music-adaptive exercise platforms (MPTrain, TripleBeat) Social network analysis (information propagation, community link modeling) Computer vision interfaces (LAFTER facial expression recognition) Scientific achievements include: 41 patents 15+ years of continuous multimodal systems research Recognized for LAFTER system (2000 paper) She actively promotes technology accessibility through: Media collaborations Technical/non-technical keynotes STEM outreach for girls

Peter KieferView profile

Lecturer

• Eye tracking
• Spatial decision making
• Human-computer interaction
• +6 more

Peter Kiefer is a Lecturer at ETH Zurich's Department of Civil, Environmental and Geomatic Engineering, specifically within the Institute for Cartography and Geoinformation. He leads the geoGAZElab research group since 2011 and has established himself as a prominent researcher in eye tracking applications for spatial decision-making. His work bridges geography, computer science, and human factors with a focus on creating cognition-aware systems. Dr. Kiefer's research spans multiple domains with a consistent focus on how eye tracking technology can enhance spatial decision situations. His primary interests include gaze-based interaction with maps, location-based services, mobile interfaces, and aviation applications. He has pioneered work in intention recognition from gaze patterns, gaze-adaptive interfaces, and the application of eye tracking in outdoor environments. His research aims to make information systems cognition-aware by inferring users' cognitive states and adapting interfaces accordingly. Analyzing his recent publications reveals strong trends toward practical applications of eye tracking in real-world scenarios, particularly in aviation safety and spatial decision-making. His work increasingly integrates machine learning with gaze data to create intelligent systems that can predict user needs and adapt interfaces dynamically. The research shows a clear progression from theoretical foundations to applied solutions in domains like weather visualization for pilots, 3D sketch mapping, and unobtrusive interaction techniques. Dr. Kiefer has been actively involved in numerous research projects as Principal Investigator or key contributor, including IGAMaps (Swiss National Science Foundation), PEGGASUS (EU Horizon 2020), EFDISA (Federal Office of Civil Aviation), and FRS 2 (National Research Foundation Singapore). These projects demonstrate his ability to secure competitive funding and lead interdisciplinary research teams across international boundaries. As an educator, Dr. Kiefer teaches Mobile GIS and Location-Based Services for Geomatics Master students, GIS I for Environmental Engineers, and contributes to courses on Mobile GIS, Human-Computer Interaction in GIS, and GIS III. He also participates in continuing education programs including the Certificate of Advanced Studies on Spatial Information Systems and the Master of Advanced Studies on Mobility of the Future. His teaching is deeply integrated with his research, particularly through the geoGAZElab where students gain hands-on experience with cutting-edge eye tracking technologies. The geoGAZElab under Dr. Kiefer's leadership serves as a hub for innovative research at the intersection of geography, computer science, and cognitive science. The lab has developed specialized tools and methodologies for outdoor eye tracking, gaze-based map interaction, and aviation interface design. The lab's work has significant implications for improving spatial decision-making across multiple domains including transportation, urban planning, and emergency response.

• Educational Technology
• Digital Games
• Computer Graphics and Simulations
• +3 more

Veljko Aleksić is an Associate Professor at the Department of Information Technology, Faculty of Technical Sciences in Čačak, University of Kragujevac, Serbia. With over 15 years of academic experience, he specializes in Educational Technology, focusing on the intersection of digital games, computer graphics, and teaching methodologies. His work bridges theoretical educational frameworks with practical technological applications, making significant contributions to both national and international educational technology communities. Awarded the "Dr Milivoje Urošević" foundation award as the best graduate student, Aleksić earned his Bachelor's degree in Teacher of Technics and Informatics from the Technical Faculty in Čačak with an average grade of 9.59. He continued his academic journey with a Master's degree from the University of Kragujevac (average grade: 10.00) and completed his Doctoral studies at the University of Novi Sad, Faculty of Sciences, with a dissertation titled "Relation between digital gameplay and multiple intelligences profile of higher grade elementary school students." Professor Aleksić's research spans multiple interconnected domains within educational technology. His primary focus lies in investigating how digital games can enhance learning experiences, particularly examining the relationship between gameplay preferences and multiple intelligences profiles of students. This work has led to significant contributions in understanding how different learning styles interact with digital educational tools. His expertise extends to computer graphics and simulations, where he explores innovative approaches to visual learning and virtual environments. Additionally, he has made substantial contributions to teaching methodology, particularly in technics and informatics education, developing frameworks that integrate modern technologies into traditional educational settings. His work on neuroscience connections demonstrates his interdisciplinary approach to understanding educational processes. A review of Professor Aleksić's recent publications reveals a clear trajectory toward increasingly sophisticated applications of technology in education. His work has evolved from foundational studies on digital game-based learning to more complex investigations involving artificial intelligence, virtual reality, and cross-cultural educational comparisons. Recent publications demonstrate a growing emphasis on practical applications of educational technology, with several studies focusing on implementing these technologies in real-world educational settings across Serbia and internationally. His comparative studies between Serbian and Greek educational contexts highlight his expanding international research collaborations and the global relevance of his work. The thematic progression shows increasing sophistication in research methodology and broader educational impact. While specific major scientific awards aren't prominently listed in his profile, Professor Aleksić's extensive involvement as a reviewer for the National Accreditation and Quality Review Body in Higher Education and his participation in numerous international conference program committees represent significant professional recognition. His leadership roles in various educational projects funded by the Ministry of Education, Science and Technological Development of Serbia further demonstrate the value placed on his expertise by national educational authorities. His membership in the IEEE Computer Society Technical Committee on Learning Technology underscores his standing in the international educational technology community. Professor Aleksić has supervised numerous educational initiatives and projects, including "Osnaživanje kompetencija studenata - master profesora tehnike i informatike za preduzetničko obrazovanje i podršku profesionalnom razvoju učenika (MPTIPoPr)" and "Digitalna transformacija predmeta obrazovna tehnologija (DTPOT)" funded by the Ministry of Education. He has served as head of study programs including IAS Tehnika i informatika and MAS Predmetna nastava at the Faculty of Technical Sciences in Čačak. His extensive work with the Institute for Education Quality and Evaluation, and the Institute for the Advancement of Education demonstrates his significant contribution to national educational standards development. His involvement in international projects like ALLVET shows his commitment to European educational cooperation. As an active member of the IEEE Computer Society Technical Committee on Learning Technology and participant in numerous international research collaborations, Professor Aleksić contributes to cutting-edge educational technology development. His work with the Computer Science Laboratory at the Faculty of Technical Sciences in Čačak has fostered an environment for innovative research in educational technology, particularly in the areas of digital games development and computer graphics applications for learning. His leadership in organizing the Technics and Informatics in Education (TIE) conference series has created important platforms for scholarly exchange in the region.

Catherine DominguèsView profile

Researcher

• Natural Language Processing
• Cartography
• Data Mining
• +3 more

Catherine Dominguès is a senior researcher at the French National Mapping Agency (IGN) specializing in Natural Language Processing for Cartography within the MEIG (Mediation and Enrichment of Geographic Information) research team. Her work bridges computational linguistics and geographic information science, focusing on the intersection of language analysis and spatial data representation. Education : Habilitation à diriger des recherches (HDR) in Natural Language Processing (2020), PhD in Computer Science (2001), DEA in Theoretical Foundations of Computer Systems (1989) Research Interests center on places and placenames , expressive variations in toponym spelling , location-based information retrieval , and sensitive cartography . Her methodology combines data mining , fuzzy spatial reasoning , and geovisualization techniques. Key publication trends show her work connects NLP for map analysis , mountain rescue support systems , and narrative-based mapping . She contributes to heterogeneous data integration and fuzzy logic applications in geographic contexts. Supervision : Co-supervised Dong Chuanming (PhD) and previously supervised Firas Bessadok (PhD) Projects : Core member of the CHOUCAS project (2017-2022) integrating heterogeneous data for mountain rescue, and involved in MATRICIEL (2016-2017) mapping migrant perceptions

• Computer Science
• Artificial Intelligence
• Machine Learning
• +9 more

Prof. Dr. Hayri Sever is a full-time faculty member at Çankaya University, Department of Computer Engineering, since 2018. He previously held professorship roles at Hacettepe University (1997-2018), University of Massachusetts Amherst (2000-2002), and Başkent University (2003-2007). His academic journey includes a PhD in Computer Science from the University of Louisiana at Lafayette (1995), a Master's from the University of Maine (1991), and a BSc in Computer Engineering from Hacettepe University (1987). Education: PhD (1995), Computer Science, University of Louisiana at Lafayette MS (1991), Computer Science, University of Maine BSc (1987), Computer Engineering, Hacettepe University Prof. Sever's research spans Artificial Intelligence, Data Mining, Natural Language Processing, Cybersecurity, and Machine Learning . His recent work focuses on applications in violence detection in videos, sentiment analysis, blockchain security, medical decision support systems, and Turkish language processing. He has supervised over 40 graduate students in topics ranging from deep learning to blockchain and IoT security. His 15 most recent publications (2019-2024) highlight expertise in deep learning for video analysis , blockchain reputation systems , 3D CNN applications , and sentiment analysis in Turkish/Arabic . Collaborations include institutions like Hacettepe University, University of Massachusetts, and international projects funded by TÜBİTAK, UNESCO, and the UN. He has led projects such as "KGYS: Smart Support Software Development" and "DiCoMa: Disaster Control Management" , with roles as researcher, coordinator, and advisor. Professional memberships include IEEE (2005-), ACM (2002-), and Tübitak (2005-).

• Data Science
• Data Mining
• Machine Learning
• +5 more

Howard J. Hamilton is a Professor at the Department of Computer Science, Faculty of Science, University of Regina. His research spans Data Mining, Machine Learning, and Human-Computer Interaction. University of Regina Department of Computer Science Faculty of Science Research Interests: Hamilton focuses on Data Science , Machine Learning , Speech Recognition , and Augmented Reality applications in healthcare. His recent work includes the My Daily Routine (MDR) system using HoloLens for dementia care and blockchain-based IoT security mechanisms. Scientific Contributions: He has co-authored 15 recent papers on topics spanning Time Series Forecasting , GANs for Game Design , and Smart Grid Security . His work has been presented at top venues like IEEE ICC, ICAART, and IEEE VR. Awards: Recipient of the Best Paper Award at INTENSIVE'12 and Second Place Best Paper at FLAIRS'99. Student Training: As a supervisor, he has mentored over 30 graduate students and project assistants in Computer Science and related fields, including Ph.D. candidates in Multi-Agent Systems and AI for Cooperative Games .

Florian HuberView profile

Professor

• Data Science
• Machine Learning
• Visual Analytics
• +4 more

Prof. Dr. Florian Huber serves as Professor of Data Science and Visual Analytics at the Department of Media, Faculty of Media, Hochschule Düsseldorf University of Applied Sciences (HSD), a position held since September 2021. He is additionally affiliated with the Center for Digitalization and Digitality (ZDD), where he bridges data science methodologies with real-world applications in scientific and cultural domains through machine learning and visualization techniques. His academic foundation includes: Diploma in Physics, University of Leipzig PhD in Biological Physics, University of Leipzig (2012), thesis: "Emergent structure formation of the actin cytoskeleton" Prior to HSD, he worked as a postdoctoral researcher at AMOLF (Amsterdam) and TU Delft, founded the sustainable sweets company KÄNDI, and served as Data Scientist at the Netherlands eScience Center (2018-2021). Huber's research focuses on developing data science algorithms for comparative analysis of complex datasets, combining machine learning with domain expertise to enable meaningful comparisons through latent space transformations. Key areas include mass spectrometry-based metabolomics (chemical identification/similarity prediction), natural language processing (e.g., lyrical evolution analysis), and audio data science, with emphasis on interpretable and reproducible computational approaches for biology, medicine, and cultural studies. Analysis of his 2023-2025 publications reveals dominant themes in mass spectrometry data science (tools like matchms, MS2Query, Mass2SMILES) and NLP applications in musicology. His work increasingly integrates deep learning for cross-domain similarity prediction while creating educational resources, reflecting a trend toward versatile open-source solutions for interdisciplinary data challenges. Huber actively contributes to open science through GitHub repositories and reproducible pipelines, suggesting collaborative funding models centered on software sustainability. His teaching includes the "Data Science" module (MMI 05.35) with practical components for engineering programs, offered in German or English. He leads initiatives within HSD's Center for Digitalization and Digitality, fostering collaborations between data scientists and domain experts. Current projects involve interdisciplinary teams tackling metabolomics, cultural analytics, and educational tool development using Python-based open-source ecosystems, with future work likely expanding into new application domains while advancing methodological rigor.

Giacomo TarroniView profile

Lecturer

• Medical Image Analysis
• Machine Learning
• Artificial Intelligence
• +9 more

Dr. Giacomo Tarroni is a Lecturer in Artificial Intelligence at City St George's, University of London, where he is a member of the CitAI Research Centre within the Department of Computer Science. He has previously held research positions at Imperial College London (as a Research Fellow and Marie Skłodowska-Curie Fellow), University of Padova, and University of Bologna. His educational background includes a PhD in Medical Image Analysis from the University of Bologna (2009-2012), an M.S. in Electronic Engineering from the University of Bologna (2005-2008), and a B.S. in Electronic Engineering from the University of Bologna (2002-2005). During his PhD, he collaborated with the University of Chicago. Dr. Tarroni's research focuses on medical image analysis, with particular emphasis on unsupervised anomaly detection , self-supervised image classification/segmentation , and federated learning for medical applications. His work spans cardiovascular, brain, and fetal imaging, with significant contributions in cardiac MRI analysis. His research bridges computer vision and healthcare, developing AI solutions that address practical clinical challenges while respecting data privacy constraints through techniques like federated learning. His publication record demonstrates consistent high-impact contributions to medical imaging conferences (MICCAI, ISBI) and journals (IEEE Transactions on Medical Imaging, Medical Image Analysis). Recent work shows increasing focus on foundational AI techniques like diffusion models and self-supervised learning applied to medical imaging challenges. Fellow of Advance Higher Education (HEA), 2021 Marie Skłodowska-Curie Fellowship from the European Commission for the JUNO project (Principal Investigator) Board member of the UK Chapter of Marie Curie Alumni Association (MCAA-UK) since 2018 Associate Editor for IEEE ISBI 2019 conference Dr. Tarroni has secured significant research funding, generating over 183k€ through his Marie Skłodowska-Curie Fellowship. He has collaborated with major medical image analysis projects including SmartHeart (EPSRC, 5M£), iFind (Wellcome Trust and EPSRC, 10M£), and CHIRON (EU Artemis-JU, 18M€). As an active reviewer, he contributes to leading journals including IEEE Transactions on Medical Imaging and Medical Image Analysis, as well as top conferences like MICCAI and IEEE ISBI. His laboratory work centers around developing robust AI methods for medical imaging that can operate effectively with limited or distributed data sources.

Salman AvestimehrView profile

Professor

• Information Theory
• Federated Machine Learning
• Decentralized Learning
• +3 more

Salman Avestimehr is a Dean’s Professor at the University of Southern California (USC) in the Viterbi School of Engineering, jointly affiliated with the Electrical and Computer Engineering and Computer Science Departments. He is the co-founder and CEO of FedML, an open-source framework for federated learning, and serves as director of both the USC-Amazon Center on Secure & Trusted ML and the vITAL Research Lab. His research focuses on information theory, decentralized machine learning, and secure/privacy-preserving computing. His recent research explores federated learning for healthcare applications, uncertainty estimation in LLMs, multimodal distillation for heterogeneous systems, and secure aggregation techniques. The vITAL Lab under his leadership has produced numerous publications in 2024-2025 across top conferences like ICLR, CVPR, PETS, and NAACL. Notable achievements include the Andrea Goldsmith Young Scholars Award received by his lab member Batu. His work spans practical frameworks (FedML), theoretical advances (coded computing), and interdisciplinary applications (LANTERN for biomedical prediction, CryptoMamba for cryptocurrency modeling).

Ahmet Onur DurahimView profile

Lecturer

• Artificial Intelligence
• Big Data Analytics
• Social Network Analysis
• +4 more

Ahmet Onur Durahim is a Lecturer at Boğaziçi University , specializing in Artificial Intelligence, Big Data Analytics, and Cybersecurity. With a PhD in Computer Science and Engineering from Sabancı University, his research focuses on social media analysis, cryptographic protocols, and network security. Education: Sakarya Anadolu Lisesi (High School) Boğaziçi University: B.S. in Industrial Engineering and Construction Engineering (Double Major) Boğaziçi University: M.S. in Civil Engineering Sabancı University: PhD in Computer Science and Engineering Durahim's research spans AI applications in social media, big data processing, and security protocols for wireless networks. His work includes sentiment analysis on Twitter, spam detection frameworks, and cryptographic authentication systems. Recent publications highlight his contributions to cryptocurrency interest identification, music emotion classification, and spam review detection. His methodological focus includes semi-supervised learning and imbalanced data handling.