Scholarly Publications - Computer Engineering
Permanent URI for this collectionhttps://hdl.handle.net/11693/115582
Browse
Recent Submissions
Item Open Access Büyük dil modelleriyle kişilik ifadesi(Institute of Electrical and Electronics Engineers Inc., 2025-08-15) Varnalı, Kerem; Sonlu, Sinan; Güdükbay, UğurBu çalışma, Büyük Dil Modellerindeki kişilik ifadesini incelemektedir. Bu amaçla, istenen kişilik özelliklerini ifade eden istemlere yönelik basit ve karmaşık yaklaşımların performansını karşılaştırılmıştır. Ayrıca, belirli bir kişinin adını ve bilgilerini eklemenin sonuçları iyileştirip iyileştirmediğini de incelenmiştir. Genel olarak, daha ayrıntılı istemlerin daha doğru sonuçlar elde ettiğini ancak kişilik faktörleri arasında bir korelasyon ortaya çıkarabileceği gözlemlenmiştir. Ayrıntılı istemler ayrıca daha uzun girdiyle sonuçlanır ve bu da üretken modeli şaşırtabilmektedir. Ayrılmış kişilik faktörlerine odaklanmak, korelasyonlardaki azalma nedeniyle daha iyi sonuçlar vermektedir.Item Open Access Vision-based power line cables and pylons detection for low flying aircraft(Springer, 2025-02-10) Gwizdała, Jakub; Öner, Doruk; Roy, Soumava Kumar; Shah, Mian Akbar; Eberhard, Ad; Egorov, Ivan; Krüsi, Philipp; Yakushev, Grigory; Fua, PascalPower lines are dangerous for low-flying aircraft, especially in low-visibility conditions. Thus, a vision-based system able to analyze the aircraft’s surroundings and to provide the pilots with a “second pair of eyes” can contribute to enhancing their safety. To this end, we develop a deep learning approach to jointly detect power line cables and pylons from images captured at distances of several hundred meters by aircraft-mounted cameras. In doing so, we combine a modern convolutional architecture with transfer learning and a loss function adapted to curvilinear structure delineation. We use a single network for both detection tasks and demonstrate its performance on two benchmarking datasets. We have also integrated it within an onboard system and run it inflight. We show with our experiments that it outperforms the prior distant cable detection method by Stambler et al. (in: International Conference on Robotics and Automation, 2019) on both datasets, while also successfully detecting pylons, given their annotations are available for the data.Item Open Access Patch relevance estimation and multilabel augmentation for weakly supervised histopathology image classification(SPIE - International Society for Optical Engineering, 2025-12-05) Aygüneş, Bulut; Cinbiş, Ramazan Gökberk; Aksoy, SelimPurpose
Weakly supervised learning (WSL) is widely used for histopathological image analysis by modeling images as sets of fixed-size patches and utilizing image-level diagnoses as weak labels. However, in multiclass classification scenarios, patches corresponding to a wide spectrum of diagnostic categories can co-exist in a single image, complicating the learning process. We aim to address label uncertainty in such multiclass settings.Approach
We propose a two-branch architecture and a complementary training strategy to improve patch-based WSL. One branch estimates patch-level class likelihoods, whereas the other predicts per-class patch relevance weights. These outputs are combined into image-level class predictions via a relevance-weighted sum of per-patch class likelihoods. To further improve performance, we introduce a multilabel augmentation strategy that forms new training samples by combining patch sets and labels from pairs of images, resulting in multilabel samples that enrich the training set by increasing the chance of having more patches that are relevant to the augmented label sets.Results
We evaluate our method on two challenging multiclass breast histopathology datasets for region of interest classification. The proposed architecture and training strategy outperform conventional weakly supervised methods, demonstrating improved classification accuracy and robustness, particularly in underrepresented classes.Conclusions
The proposed architecture effectively models the complex relationship between image-level labels and patch-level content in multiclass histopathological image analysis. Combined with the image-level multilabel augmentation strategy, it improves learning under label uncertainty. These contributions hold potential for more accurate and scalable diagnostic support systems in digital pathology.Item Open Access Using mathematical approaches to answer complex biological questions: can exosomal miRnas predict cancer prognosis?(Taylor and Francis Ltd., 2025-12-31) Missaghi, Olka; Nehri, Leman Nur; Bakhshi, Sepehr; Karaosmanoğlu, Oğuzhan; Sivas, Hülya; Acar, Aybar Can; Banerjee, SreeparnaEpithelial to mesenchymal transition (EMT) has been widely implicated in diverse cellular processes such as development, would healing, as well as in cancer metastasis and therapy resistance. Exosomes are nanosized vesicles that carry cellular products and are known to mediate cell-cell communication. We describe here how a systems biology approach relying on simple experimental data in combination with in silico tools and mathematical modeling can be used to understand complex biological phenomenon such as EMT.Item Embargo High performance graph-parallel accelerator design(Elsevier BV, 2026-01-23) Akyol, Cemil Kaan; Özdal, Muhammet Mustafa; Öztürk, ÖzcanGraph applications are becoming increasingly important with their widespread usage and the amounts of data they deal with. Biological and social web graphs are well-known examples that show the importance of efficiently processing graph analytic applications and problems. Due to limited resources, efficiency and performance are much more critical in embedded systems. We propose an efficient source-to-source-based methodology for graph applications that gives the freedom of not knowing the low-level details of parallelization and distribution by translating any vertex-centric C++ graph application into a pipelined SystemC model. High-Level Synthesis (HLS) tools can synthesize the generated SystemC model to obtain the design of the hardware. To support different types of graph applications, we have implemented features like non-standard application support, active set functionality, asynchronous execution support, conditional pipeline support, non-neighbor data access support, multiple pipeline support, and user-defined data type functionality. Our accelerator development flow can generate better-performing accelerators than OpenCL. Furthermore, it dramatically reduces the design time compared to using HLS tools. Therefore, the proposed methodology can generate fast accelerators with minimal effort using a high-level language description from the user.Item Open Access Abstract: Client security alone fails in federated learning 2D and 3D attack insights(Springer Vieweg, 2025-03-02) Parampottupadam, Santhosh; Floca, Ralf; Bounias, Dimitrios; Hamm, Benjamin; Roy, Saikat; Sav, Sinem; Zenk , Maximilian; Maier-Hein, aus; Palm, C.; Breininger, K.; Deserno, T. M.; Handels, H.; Maier, A.; Maier-Hein, K.; Tolxdorff, T.Federated learning (FL) plays a vital role in boosting both accuracy and privacy in the collaborative medical imaging field. The importance of privacy increases with the diverse security standards across nations and corporations, particularly in healthcare and global FL initiatives. Current research on privacy attacks in federated medical imaging focuses on sophisticated gradient inversion attacks that can reconstruct images from FL communications.Item Unknown A multilevel algorithm for scalable independent task assignment(Elsevier B.V., 2025-10-08) Tabak, Hüseyin Burhan; Tabak, Ertuğrul Kartal; Aykanat, CevdetAssigning a large number of independent tasks to heterogeneous processors is a fundamental problem in modern computing, with applications in many domains such as cloud services, web crawling, and AI training. Exact and matheuristic approaches deliver high-quality assignments but incur superlinear or even exponential runtime costs, making them impractical, especially on large problem instances. Conversely, lightweight heuristics run efficiently at scale but often produce assignments with much lower quality. To address this issue, we present the first multilevel framework for the independent task assignment problem that maintains an end-to-end linear runtime bound of O(KN), where K x N is the size of the expected-time-to-compute matrix, with K and N respectively representing the number of processors and tasks. We propose (i) novel high-quality coarsening metrics that numerically define task characteristics and similarity; (ii) an efficient and effective matching algorithm that incorporates these metrics while maintaining linear time complexity with respect to the input size; (iii) an initial solution scheme that generates base solutions using complementary heuristics, which are disjointly projected back through the uncoarsening levels; (iv) an effective and efficient uncoarsening algorithm that iteratively improves assignment quality with different refinement algorithms. Extensive experimental evaluations involving hundreds of millions of tasks demonstrate that our algorithm achieves significantly higher quality and runs faster than known high-quality heuristics, making it a practical choice for the problem instances at high scale.Item Unknown Hesaplamalı hukukta temel kavramlar(2025-06-30) Küçük, Dilek; Can, FazlıGünümüzde bilgisayar bilimleri ve yapay zekâ alanlarında kayda değer gelişmeler yaşanmakta ve bu gelişmeler de insan hayatının birçok yönünü etkilemektedir. Hiç şüphe yok ki, bu güncel gelişmelerden etkilenen alanlardan en önemlilerinden biri de hukuk sistemleridir. Bu çalışmamızda, hukuk ve bilgisayar bilimleri alanlarının kesişim noktasında bulunan hesaplamalı hukuk konusuna odaklanılmış ve konuyla ilgili literatürde karşılaşılan temel kavramların tanımlarına yer verilmiştir. Söz konusu kavramlar tanıtılırken, uzun yıllardır kullanılan yerleşmiş kavramlara ek olarak yapay zekâ alanındaki atılımlarla birlikte ortaya çıkan görece yeni kavramlar da dikkate alınmıştır. Herhangi bir araştırma alanı için, alana ait kavramların tanımlanmalarının faydası düşünüldüğünde; bu çalışmamızda yer alan hesaplamalı hukuk kavramlarının özellikle bilişim hukuku literatürüne önemli bir katkı oluşturacağı değerlendirilmektedir.Item Unknown Towards automated detection of inline code comment smells(Association for Computing Machinery, Inc, 2025-12-24) Öztaş, İpek; Torun, Utku Boran; Tüzün, Eray; Babar M.A.; Tosun A.; Wagner S.; Stray V.Background: Code comments are important in software development because they directly influence software maintainability and overall quality. Bad practices of code comments lead to code comment smells, negatively impacting software maintenance. Recent research has been conducted on classifying inline code comment smells, yet automatically detecting these still remains a challenge. Objective: We aim to automatically detect and classify inline code comment smells through machine learning (ML) models and a large language model (LLM) to determine how accurately each smell type can be detected. Method: We enhanced a previously labeled dataset, where comments are labeled according to a determined taxonomy, by augmenting it with additional code segments and their associated comments. GPT-4, a large language model, was used to classify code comment smells on both the original and augmented datasets to evaluate its performance. In parallel, we trained and tested seven different machine learning algorithms on the augmented dataset to compare their classification performance against GPT-4. Results: The performance of models—particularly Random Forest, which achieved an overall accuracy of 69%, along with Gradient Boosting and Logistic Regression, each achieving 66% and 65%, respectively —establishes a solid baseline for future research in this domain. The Random Forest model outperformed all other ML models, by achieving the highest Matthew’s Correlation Coefficient (MCC) score of 0.44. The augmented dataset improved the overall classification accuracy of the GPT-4 model’s predictions from 34% to 55%. Conclusion: This study contributes to software maintainability by exploring the automatic detection and classification of inline code comment smells. We have made our augmented dataset and code artifacts available online, offering a valuable resource for developing automated comment smell detection tools.Item Unknown Beacon reconstruction attack: reconstruction of genomes in genomic data-sharing beacons using summary statistics(Oxford University Press, 2025-05-19) Saleem, Kousar; Çiçek, A. Ercüment; Sav, SinemMotivation Genomic data-sharing beacon protocol, developed by the Global Alliance for Genomics and Health, offers a privacy-preserving mechanism for querying genomic datasets while restricting direct data access. Despite their design, beacons remain vulnerable to privacy attacks. This study introduces a novel privacy vulnerability of the protocol: one can reconstruct large portions of the genomes of all beacon participants by only using the summary statistics reported by the protocol. Results We introduce a novel optimization-based algorithm that leverages beacon responses and SNP correlations for reconstruction. By optimizing for the SNP correlations and allele frequencies, the proposed approach achieves genome reconstruction with a substantially higher F1-score (70%) compared to baseline methods (45%) on beacons generated using individuals from the HapMap and OpenSNP datasets. We show that reconstructed genomes can be used by downstream applications such as in membership inference attacks against other beacons. Our findings reveal that beacons releasing allele frequencies substantially increase the reconstruction risk, underscoring the need for enhanced privacy-preserving mechanisms to protect genomic data.Item Unknown Author correction: systems medicine disease maps: community-driven comprehensive representation of disease mechanisms(Nature Publishing Group, 2018) Mazein, A.; Ostaszewski, M.; Kuperstein, I.; Watterson, S.; Le Novère, N.; Lefaudeux, D.; De Meulder, B.; Pellet, J.; Balaur, I.; Saqi, M.; Nogueira, M. M.; HeFeng, F.; Parton, A.; Lemonnier, N.; Gawron, P.; Gebel, S.; Hainaut, P.; Ollert, M.; Doğrusöz, Uğur; Barillot, E.; Zinovyev, A.; Schneider, R.; Balling, R.; Auffray, C.The development of computational approaches in systems biology has reached a state of maturity that allows their transition to systems medicine. Despite this progress, intuitive visualisation and context-dependent knowledge representation still present a major bottleneck. In this paper, we describe the Disease Maps Project, an effort towards a community-driven computationally readable comprehensive representation of disease mechanisms. We outline the key principles and the framework required for the success of this initiative, including use of best practices, standards and protocols. We apply a modular approach to ensure efficient sharing and reuse of resources for projects dedicated to specific diseases. Community-wide use of disease maps will accelerate the conduct of biomedical research and lead to new disease ontologies defined from mechanism-based disease endotypes rather than phenotypes.Item Unknown DECEPTIcON: bridging gaps in in-the-wild deception research(IEEE, 2025-07-22) Biçer, Berat; Durmaz, Bahadır; Aras, Serhat; Dibeklioğlu, HamdiWe present DECEPTIcON, a new large-scale dataset for automatic deception detection. It contains video clips from 100 public figures, mostly politicians, along with manually aligned text transcripts and extracted audio-visual features. Each video is labeled with one of six truth levels from the PolitiFact fact-checking platform, allowing both fine-grained and binary classification tasks. Unlike earlier datasets, DECEPTIcON is designed to study deception in the wild, meaning it includes real-life, unscripted speech from a wide range of people and topics. We test and compare several baseline models for text, audio, and visual input separately, using state of the art pretrained architectures such as MPNet (text), Wav2Vec2 (audio), and VideoMAE (vision). Each model is trained for deception classification using 5-fold subject-independent cross-validation. We report CCR, F1-score, and MAE to evaluate performance. Our results show that text performs best overall, while fusion of multiple inputs leads to small but meaningful improvements. We also analyze the effect of different truth-level grouping strategies and show how attention-based interpretability tools help explain which parts of the input influence model predictions. DECEPTIcON aims to support fair, generalizable, and reproducible research in multimodal deception detection, and the dataset will be made available for research purposes.Item Unknown RNAtranslator: modeling protein-conditional RNA design as sequence-to-sequence natural language translation(Public Library of Science, 2025-10-03) Tabrizi, Sobhan Shukueian; Barazandeh, Sina; Aghdam, Helyasadat Hashemi; Çiçek, A. ErcümentProtein-RNA interactions are essential in gene regulation, splicing, RNA stability, and translation, making RNA a promising therapeutic agent for targeting proteins, including those considered undruggable. However, designing RNA sequences that selectively bind to proteins remains a significant challenge due to the vast sequence space and limitations of current experimental and computational methods. Traditional approaches rely on in vitro selection techniques or computational models that require post-generation optimization, restricting their applicability to well-characterized proteins. We introduce RNAtranslator, a generative language model that formulates protein-conditional RNA design as a sequence-to-sequence natural language translation problem for the first time. By learning a joint representation of RNA and protein interactions from large-scale datasets, RNAtranslator directly generates binding RNA sequences for any given protein target without the need for additional optimization. Our results demonstrate that RNAtranslator produces RNA sequences with natural-like properties, high novelty, and enhanced binding affinity compared to existing methods. This approach enables efficient RNA design for a wide range of proteins and even proteins with no RNA-interaction data available, paving the way for new RNA-based therapeutics and synthetic biology applications.Item Unknown Predicting the risk of death for cryptocurrencies using deep learning(Multidisciplinary Digital Publishing Institute (MDPI), 2025-12-15) Konuk, Doğa Elif; Güvenir, Halil AltayThe rapid rise in the popularity of cryptocurrencies has drawn increasing attention from investors, entrepreneurs, and the public in recent years. However, this rapid growth comes with risk: many coins fail early and become what are known as “dead coins”, defined by a lack of recorded activity for more than a year. This study applies deep learning techniques to estimate the short-term risk of a cryptocurrency’s death. Specifically, three Recurrent Neural Network architectures, Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated Recurrent Unit (GRU), were trained on 18-month time series of daily closing prices and trading volumes using a stratified five-fold cross-validation framework. The models’ predictive performances were compared across input windows ranging from 10 to 180 days. Using the previous 180 days of data as input, GRU achieved the highest point accuracy of 0.7134, whereas BiLSTM exhibited the best performance when evaluated across input sequence lengths varying from 10 to 180 days, reaching an average accuracy of 0.676. These findings show the ability of recurrent architectures to anticipate short-term failure risks in cryptocurrency markets. Theoretically, the study contributes to financial risk modeling by extending time series classification methods to cryptocurrency failure prediction. Practically, it provides investors and analysts with a data-driven early-warning tool to manage portfolio risk and reduce potential losses.Item Unknown 3D Stylization via Large Reconstruction Model(Association for Computing Machinery, Inc, 2025-07-27) Öztas, İpek; Ceylan, Duygu; Dündar, Ayşegül; Spencer S.N.With the growing success of text or image guided 3D generators, users demand more control over the generation process, appearance stylization being one of them. Given a reference image, this requires adapting the appearance of a generated 3D asset to reflect the visual style of the reference while maintaining visual consistency from multiple viewpoints. To tackle this problem, we draw inspiration from the success of 2D stylization methods that leverage the attention mechanisms in large image generation models to capture and transfer visual style. In particular, we probe if large reconstruction models, commonly used in the context of 3D generation, has a similar capability. We discover that the certain attention blocks in these models capture the appearance specific features. By injecting features from a visual style image to such blocks, we develop a simple yet effective 3D appearance stylization method. Our method does not require training or test time optimization. Through both quantitative and qualitative evaluations, we demonstrate that our approach achieves superior results in terms of 3D appearance stylization, significantly improving efficiency while maintaining high-quality visual outcomes. Code and models are available via our project website: https://github.com/ipekoztas/3D-Stylization-LRM.Item Unknown Automated code review in practice(Institute of Electrical and Electronics Engineers (IEEE), 2025-08-20) Cihan, Umut; Haratian, Vahid; İçöz, Arda; Gül, Mert Kaan; Devran, Ömercan; Bayendur, Emircan Furkan; Uçar, Baykal Mehmet; Tüzün, ErayContext: Code review is a widespread practice among practitioners to improve software quality and transfer knowledge. It is often perceived as time-consuming due to the need for manual effort and potential delays in the development process. Several AI-assisted code review tools (Qodo, GitHub Copilot, Coderabbit, etc.) provide automated code reviews using large language models (LLMs). The overall effects of such tools in the industry setting are yet to be examined. Objective: This study examines the impact of LLM-based automated code review tools in an industry setting. Method: The study was conducted within an industrial software development environment that adopted an AI-assisted code review tool (based on open-source Qodo PR Agent). 238 practitioners across ten projects had access to the tool. We focused our analysis on three projects, which included 4,335 pull requests, 1,568 of which underwent automated reviews. Our data collection comprised three sources: (1) a quantitative analysis of pull request data, including comment labels indicating whether developers acted on the automated comments, (2) surveys sent to developers regarding their experience with the reviews on individual pull requests, and (3) a broader survey of 22 practitioners capturing their general opinions on automated code reviews. Results: 73.8% of automated code review comments were labeled as resolved. However, the overall average pull request closure duration increased from five hours 52 minutes to eight hours 20 minutes, with varying trends observed across different projects. According to survey responses, most practitioners observed a minor improvement in code quality as a result of automated code reviews. Conclusion: The LLM-based automated code review tool proved useful in software development, enhancing bug detection, increasing awareness of code quality, and promoting best practices. However, it also led to longer pull request closure times and introduced drawbacks such as faulty reviews, unnecessary corrections, and irrelevant comments. Based on these findings, we discussed how practitioners can more effectively utilize automated code review technologies.Item Unknown Reference-based 3D-aware image editing with triplanes(IEEE, 2025-08-13) Bilecen, Bahri Batuhan; Yalın, Yiğit; Yu, Ning; Dündar, AyşegülGenerative Adversarial Networks (GANs) have emerged as powerful tools for high-quality image generation and real image editing by manipulating their latent spaces. Recent advancements in GANs include 3D-aware models such as EG3D, which feature efficient triplane-based architectures capable of reconstructing 3D geometry from single images. However, limited attention has been given to providing an integrated framework for 3D-aware, high-quality, reference-based image editing. This study addresses this gap by exploring and demonstrating the effectiveness of the triplane space for advanced reference-based edits. Our novel approach integrates encoding, automatic localization, spatial disentanglement of triplane features, and fusion learning to achieve the desired edits. We demonstrate how our approach excels across diverse domains, including human faces, 360-degree heads, animal faces, partially stylized edits like cartoon faces, full-body clothing edits, and edits on class-agnostic samples. Our method shows state-of-the-art performance over relevant latent direction, text, and image-guided 2D and 3D-aware diffusion and GAN methods, both qualitatively and quantitatively.Item Unknown Evaluating the quality of benchmark datasets for low-resource languages: a case study on Turkish(Association for Computational Linguistics, 2025-04-26) Cengiz, Ayse Aysu; Sever, Ahmet; Umutlu, Elif Ecem; Erdem, Naime Seyma; Aytan, Burak; Tufan, Busra; Topraksoy, Abdullah; Darici, Esra; Toraman, CagriThe reliance on translated or adapted datasets from English or multilingual resources introduces challenges regarding linguistic and cultural suitability. This study addresses the need for robust and culturally appropriate benchmarks by evaluating the quality of 17 commonly used Turkish benchmark datasets. Using a comprehensive framework that assesses six criteria, both human and LLM-judge annotators provide detailed evaluations to identify dataset strengths and shortcomings. Our results reveal that 70% of the benchmark datasets fail to meet our heuristic quality standards. The correctness of the usage of technical terms is the strongest criterion, but 85% of the criteria are not satisfied in the examined datasets. Although LLM judges demonstrate potential, they are less effective than human annotators, particularly in understanding cultural common sense knowledge and interpreting fluent, unambiguous text. GPT-4o has stronger labeling capabilities for grammatical and technical tasks, while Llama3.3-70B excels at correctness and cultural knowledge evaluation. Our findings emphasize the urgent need for more rigorous quality control in creating and adapting datasets for low-resource languages.Item Unknown Effects of embodiment and personality in LLM-Based conversational agents(Institute of Electrical and Electronics Engineers, 2025-03-28) Sonlu, Sinan; Bendiksen, Bennie; Durupinar, Funda; Güdükbay, UğurThis work investigates the effects of personality expression and embodiment in conversational agents. We extend a personality-driven conversational agent framework by integrating LLM-based conversation support to provide information about contemporary scientific topics. We describe a user study built on this system to evaluate two opposing personality styles using three models: a dialogue-only model that conveys personality verbally, an animated human model that expresses personality only through dialogue, and an animated human model expressing personality through dialogue and expressive animations. The users perceive all models positively regarding personality and learning outcomes; however, models with high personality traits are perceived as more engaging than those with low personality traits. We provide an analysis of personality perception, learning, and user experience.Item Unknown Opac: An optimization-augmented control framework for single and coordinated multi-arm robotic manipulation(Institute of Electrical and Electronics Engineers Inc., 2025) Özcan, M.; Öğüz, Salih Özgür; Laugier, C.; Renzaglia, A.Robotic manipulation demands precise control over both contact forces and motion trajectories. While force control is essential for achieving compliant interaction and high-frequency adaptation, it is limited to operations in close proximity to the manipulated object and often fails to maintain stable orientation during extended motion sequences. Conversely, optimization-based motion planning excels in generating collision-free trajectories over the robot's configuration space but struggles with dynamic interactions where contact forces play a crucial role. To address these limitations, we propose a multi-modal control framework that combines force control and optimization-augmented motion planning to tackle complex robotic manipulation tasks in a sequential manner, enabling seamless switching between control modes based on task requirements. Our approach decomposes complex tasks into subtasks, each dynamically assigned to one of three control modes: Pure optimization for global motion planning, pure force control for precise interaction, or hybrid control for tasks requiring simultaneous trajectory tracking and force regulation. This framework is particularly advantageous for bimanual and multi-arm manipulation, where synchronous motion and coordination among arms are essential while considering both the manipulated object and environmental constraints. We demonstrate the versatility of our method through a range of long-horizon manipulation tasks, including single-arm, bimanual, and multi-arm applications, highlighting its ability to handle both free-space motion and contact-rich manipulation with robustness and precision. More information is available at https://sites.google.com/view/komo-force/home.