Self-financed
Augmented Reality (AR)Intelligent Go Board Software Autofocus for UVC cameras under Linux OCZ Neural Impulse Actuator - Linux Driver Handwritten Digit Recognition How to bluetooth-enabled your remote car Mobile Robot Toy Cat Simpson's Paradox 
CollaborationsAnalyzing C. elegans GFP images Holistic Pattern Recognition Early-Warning System for Botnets Text Mining in biological research literature (BioMinT) Talks Image Data Analysis in H.sapiens and C.elegans Image analysis and high-content screening Image Data Analysis in H.sapiens and C.elegans Artificial Intelligence Crash Course ScienceDabei 2011 Talk and Video Image Acquisition using Microscopes Image Data Analysis in H.sapiens and C.elegans Open Source Application examples in research and applications Intelligent Biomedical Data Analysis Computer Vision Workshop using OpenCV Computer Vision Crash-Course Open Source Data Mining with WEKA Innovative Applications of Open Source Open Source Data Mining with WEKA/Pentaho Detection and Identification of BotNets Challenges for Machine Learning and Data Mining in Predictive Behavioral Targeting Open Source Data Mining mit WEKA Success Stories in Intelligent Biomedical Data Analysis Artificial Intelligence Basics (09.05.2007) Artificial Intelligence and Image Processing Intelligent Go Board project - Idea Generation Workshop Internship Support Lecture (Winter term 2005) Artificial Intelligence Basics (14.06.2004) Artificial Intelligence in Industrial Applications Artificial Intelligence Methods of Data Analysis (Summer term 2004) Artificial Intelligence Basics (09.12.2003) Functional Programming in LISP (Winter term 2004) Machine Learning and Data Mining (Winter term 2004) Computer Go and Ensembles Functional Programming in LISP (Winter term 2002) Tutor for Prolog and logic-oriented programming (Winter term 1997) Publications Is Intra-tumoral Budding Correlated With Liver Metastasis In Patients With Grade 2 Colorectal Cancer? A Pilot Study The relation between epithelial and stromal area is important for colorectal cancer diagnosis and therapeutic considerations On the Brittleness of Handwritten Digit Recognition Models Automated quantitative analysis of epithelial and stromal area in colorectal cancer: putative application for the prognosis of cancer progression Towards the automated detection and characterization of osteoclasts in microscopic images Automated Detection And Quantification Of Osteoclasts In Culture By A Novel Image Analysis System - A Pilot Study On The Influence Of The Hormone Melatonin On Osteoclast Formation The neonatal IgG Fc-receptor (FcRn) is expressed in the syncytiotrophoblast, fetal endothelial cells and Hofbauer cells of human term placental chorionic villi Epithelium/Stroma Ratio In Colorectal Cancer: Automated Area Detection and Quantitative Analysis Automated Nuclei-based In Silico Discrimination of Murine Osteoclasts and their Precursor Cells A versatile Automated Detection System for Erythrocytes in Human Tissue Sections The neonatal IgG Fc-receptor (FcRn) is expressed in the syncytiotrophoblast, fetal endothelial cells and Hofbauer cells of human term placental chorionic villi Influences of melatonin on murine osteoclast formation in culture - automated detection and quantification by a novel image analysis system Automated detection, quantification and characterization of osteoclasts in cultures using a combined image-processing and machine learning strategy Towards an automated evaluation system of osteoclasts in cultures using a combine Image-processing and machine-learning strategy Towards an Automated Detection of Osteoclasts in Cultures Using a Combined Image-processing and Machine-learning Strategy A novel method for automated quantification of osteoclasts in culture - Advantages, workflow and application Influences on murine osteoclast formation and their automated detection by a novel image analysis software A New Approach for Outlier Detection in Near Real Time Towards a Versatile Automated Cell-Detection System for Science and Diagnostics Automated detection and analysis of fluorescent biomarkers in human placental chorionic tissue Automatic Extraction of Go Game Positions from Still Images: A Multi-Strategical Approach to Constrained Multi-Object Recognition Characterization and quantification of macrophages in colorectal cancer by an automated cell system Automated evaluation of Tumor-Associated Macrophage (TAM) local density in Colorectal Cancer by an Automated Cell Detection System Towards a Versatile Automated Cell-Detection System for Science and Diagnostics exemplified through receptor for advanced glycated end-products (RAGE) quantification in placental chorionic villi Quantifying Phenotypic Variation in Isogenic Caenorhabditis elegans Expressing Phsp-16 On the Detection and Identification of Botnets Automated cell-detection technologies for science and diagnostics Automated cell-detection technologies for science and diagnostics On the Brittleness of Handwritten Digit Recognition Models Towards Automating Malware Classification and Characterization An Approximation of the String Subsequence Kernel for Practical SVM Classification and Redundancy Clustering Present and Future of Spam Improving the Effectiveness of Mailings by Building a Response Model for Inactive Customers An Evaluation of Naive Bayes Variants in Content-Based Learning for Spam Filtering Evaluation of Term Utility Functions for Very Short Multi-Document Summaries BioMinT: the Research Assistant for Biological Text Mining GPSDB: a new database for synonyms expansion of gene and protein names An Evaluation of Naive Bayes Variants in Content-Based Learning for Spam Filtering Lambda Pruning - An Approximation of the String Subsequence Kernel Digits - A Dataset for Handwritten Digit Recognition A Close Look at Current Approaches in Spam Filtering Ranking for Medical Annotation: Investigating Performance, Local Search and Homonymy Recognition Combining Bayesian and Rule Score Learning: Automated Tuning for SpamAssassin Evaluating Protein Name Recognition: An Automatic Approach Recognizing Domain and Species from MEDLINE Proteomics Publications Towards a Theoretical Framework for Ensemble Classification Towards Understanding Stacking The Intelligent Go Board project Exploring the Parameter State Space of Stacking Meta-Learning for Stacked Classification How to Make Stacking Better and Faster While Also Taking Care of an Unknown Weakness Offline Evaluation of Term Utility Functions An Evaluation of Grading Classifiers Hybrid Decision Tree Learners with Alternative Leaf Classifiers: An Empirical Study Entertainment Robots - Myth Or Reality CoIL Challenge 2000 - Submitted Solution A Mobile Robot Toy Cat Controlled by Vision And Motivation
Mobile Robot Toy Cat
2001/10/01
In 1998/1999, we built a mobile robot toy cat based on the EyeBot-board and LEGO. While it was much fun and sometimes enlightening, ultimately we were sorely disappointed with the State-of-the-Art and now take only a cursory interest in this field.
A short story to illustrate shortcomings of robotics technology: I had the pleasure to be one of the many spectators of RoboCup '99 in Stockholm which featured a Sony legged-robot league and can therefore fully confirm that they resemble cats much more than dogs. Take the following scene: the robot struggles to walk towards the ball, eventually reaches it, lifts his paw, kicks the ball successfully into the goal - however, unfortunately it was the wrong goal, even though the goal colors were blue vs. yellow with an orange ball in front of a dark green background, despite carefully controlled lighting conditions and even black hoods for the human players who had to rearrange the robots about twice per minute since they kept bumping into each other and into the boundaries. It was still most impressing that some of the robots "died" in such a convincing, life-like way, showing erratic and spastic random movement before they froze and crashed completely.
This convinced me that Robotics has still some decades to go before it gets interesting for me again. Of course this might happen sooner than expected... but still, the most successful applications of robotics are those where the task to be achieved was re-engineered - consider e.g. a dishwashing machine.
2011/11/25
Invited by Ao.Univ.-Prof.Dipl.-Ing. Dr. Isabella Ellinger from the Institute for Medical Pathology and Allergy research of the Medical University of Vienna, we held an Artificial Intelligence Crash course. Contents: Definition, history, recent successes, outlook.
2005/12/31
Research, design and development of a SpamAssassin-based spam filter system (sampling methodology, training methodology, evaluation), initially seven test users, prepared for institute-wide deployment; involved in many locally and EU-funded research projects.
2001/05/21
Seewald A.K.: Entertainment Robots - Myth Or Reality. In Proceedings of the 14th International FLAIRS Conference (FLAIRS-2001), AAAI Press, Menlo Park, California.
1999/10/01
A.K. Seewald (1999): A Mobile Robot Toy Cat Controlled by Vision And Motivation. Diploma Thesis, Vienna University of Technology, 1999.