arXiv subjects

Christian Berger

Publications and source records attributed to Christian Berger.

At least 55 records · Page 3Linked to original sources

arXiv2023

ChatGPT as a tool for User Story Quality Evaluation: Trustworthy Out of the Box?

In Agile software development, user stories play a vital role in capturing and conveying end-user needs, prioritizing features, and facilitating communication and collaboration within development teams. However, automated methods for evaluating user stories require training in NLP tools and can be time-consuming to develop and integrate. This study explores using ChatGPT for user story quality evaluation and compares its performance with an existing benchmark. Our study shows that ChatGPT's evaluation aligns well with human evaluation, and we propose a ``best of three'' strategy to improve its output stability. We also discuss the concept of trustworthiness in AI and its implications for non-experts using ChatGPT's unprocessed outputs. Our research contributes to understanding the reliability and applicability of AI in user story evaluation and offers recommendations for future research.

cs.SE↗

arXiv2023

ZEBRA: Z-order Curve-based Event Retrieval Approach to Efficiently Explore Automotive Data

Evaluating the performance of software for automated vehicles is predominantly driven by data collected from the real world. While professional test drivers are supported with technical means to semi-automatically annotate driving maneuvers to allow better event identification, simple data loggers in large vehicle fleets typically lack automatic and detailed event classification and hence, extra effort is needed when post-processing such data. Yet, the data quality from professional test drivers is apparently higher than the one from large fleets where labels are missing, but the non-annotated data set from large vehicle fleets is much more representative for typical, realistic driving scenarios to be handled by automated vehicles. However, while growing the data from large fleets is relatively simple, adding valuable annotations during post-processing has become increasingly expensive. In this paper, we leverage Z-order space-filling curves to systematically reduce data dimensionality while preserving domain-specific data properties, which allows us to explore even large-scale field data sets to spot interesting events orders of magnitude faster than processing time-series data directly. Furthermore, the proposed concept is based on an analytical approach, which preserves explainability for the identified events.

cs.IR↗

arXiv2023

SoK: Scalability Techniques for BFT Consensus

With the advancement of blockchain systems, many recent research works have proposed distributed ledger technology~(DLT) that employs Byzantine fault-tolerant~(BFT) consensus protocols to decide which block to append next to the ledger. Notably, BFT consensus can offer high performance, energy efficiency, and provable correctness properties, and it is thus considered a promising building block for creating highly resilient and performant blockchain infrastructures. Yet, a major ongoing challenge is to make BFT consensus applicable to large-scale environments. A large body of recent work addresses this challenge by developing novel ideas to improve the scalability of BFT consensus, thus opening the path for a new generation of BFT protocols tailored to the needs of blockchain. In this survey, we create a systematization of knowledge about the novel scalability-enhancing techniques that state-of-the-art BFT consensus protocols use. For our comparison, we closely analyze the efforts, assumptions, and trade-offs these protocols make.

cs.DC↗

arXiv2022

The topological Faraday effect cannot be observed in a realistic sample

A striking feature of 3 dimensional (3D) topological insulators (TIs) is the theoretically expected topological magneto-electric (TME) effect, which gives rise to additional terms in Maxwell's laws of electromagnetism with an universal quantized coefficient proportional to half-integer multiples of the fine structure constant $α$. In an ideal scenario one therefore expects also quantized contributions in the magneto-optical response of TIs. We review this premise by taking into account the trivial dielectric background of the TI bulk and potential host substrates, and the often present contribution of itinerant bulk carriers. We show that (i) one obtains a non-universal magneto-optical response whenever there is impedance mismatch between different layers and (ii) that the detectable signals due to the TME rapidly approach vanishingly small values as the impedance mismatch is detuned from zero. We demonstrate that it is methodologically impossible to deduce the existence of a TME exclusively from an optical experiment in the thin film limit of 3D TIs at high magnetic fields.

cond-mat.mes-hall↗

arXiv2022

Simulating BFT Protocol Implementations at Scale

The novel blockchain generation of Byzantine fault-tolerant (BFT) state machine replication (SMR) protocols focuses on scalability and performance to meet requirements of distributed ledger technology (DLT), e.g., decentralization and geographic dispersion. Validating scalability and performance of BFT protocol implementations requires careful evaluation. While experiments with real protocol deployments usually offer the best realism, they are costly and time-consuming. In this paper, we explore simulation of unmodified BFT protocol implementations as as a method for cheap and rapid protocol evaluation: We can accurately forecast the performance of a BFT protocol while experimentally scaling its environment, i.e., by varying the number of nodes or geographic dispersion. Our approach is resource-friendly and preserves application-realism, since existing BFT frameworks can be simply plugged into the simulation engine without requiring code modifications or re-implementation.

cs.DC↗

arXiv2022

Automatic Integration of BFT State-Machine Replication into IoT Systems

Byzantine fault tolerance (BFT) can preserve the availability and integrity of IoT systems where single components may suffer from random data corruption or attacks that can expose them to malicious behavior. While state-of-the-art BFT state-machine replication (SMR) libraries are often tailored to fit a standard request-response interaction model with dedicated client-server roles, in our design, we employ an IoT-fit interaction model that assumes a loosly-coupled, event-driven interaction between arbitrarily wired IoT components. In this paper, we explore the possibility of automating and streamlining the complete process of integrating BFT SMR into a component-based IoT execution environment. Our main goal is providing simplicity for the developer: We strive to decouple the specification of a logical application architecture from the difficulty of incorporating BFT replication mechanisms into it. Thus, our contributions address the automated configuration, re-wiring and deployment of IoT components, and their replicas, within a component-based, event-driven IoT platform.

cs.DC↗

arXiv2022

Digital Sovereignty and Software Engineering for the IoT-laden, AI/ML-driven Era

Today's software engineering already needs to deal with challenges originating from the multidisciplinarity that is required to realize IoT products: Many variants consist of sensor/actuator-powered systems that already today use AI/ML systems to better cope with the unstructuredness of their intended operational design domain (ODD), while, at the same time, such systems need to be monitored, diagnosed, maintained, and evolved using cloud-powered dashboards and data analytics pipelines that process, aggregate, and analyze countless data points preferably in real-time. This position paper discusses selected aspects related to Digital Sovereignty from a software engineering's perspective for the IoT-laden, AI/ML-driven era: While we can undeniably expect more and more benefits from such solutions, a specific light shall be shed in particular on challenges and responsibilities at design- and operation-time that, at minimum, prepare for and enable or, even better, preserve and extend digital sovereignty from a software engineering's perspective.

cs.SE↗

arXiv2022

Understanding the Impact of Edge Cases from Occluded Pedestrians for ML Systems

Machine learning (ML)-enabled approaches are considered a substantial support technique of detection and classification of obstacles of traffic participants in self-driving vehicles. Major breakthroughs have been demonstrated the past few years, even covering complete end-to-end data processing chain from sensory inputs through perception and planning to vehicle control of acceleration, breaking and steering. YOLO (you-only-look-once) is a state-of-the-art perception neural network (NN) architecture providing object detection and classification through bounding box estimations on camera images. As the NN is trained on well annotated images, in this paper we study the variations of confidence levels from the NN when tested on hand-crafted occlusion added to a test set. We compare regular pedestrian detection to upper and lower body detection. Our findings show that the two NN using only partial information perform similarly well like the NN for the full body when the full body NN's performance is 0.75 or better. Furthermore and as expected, the network, which is only trained on the lower half body is least prone to disturbances from occlusions of the upper half and vice versa.

cs.CV↗

arXiv2022

Performance Analysis of Out-of-Distribution Detection on Trained Neural Networks

Several areas have been improved with Deep Learning during the past years. Implementing Deep Neural Networks (DNN) for non-safety related applications have shown remarkable achievements over the past years; however, for using DNNs in safety critical applications, we are missing approaches for verifying the robustness of such models. A common challenge for DNNs occurs when exposed to out-of-distribution samples that are outside of the scope of a DNN, but which result in high confidence outputs despite no prior knowledge of such input. In this paper, we analyze three methods that separate between in- and out-of-distribution data, called supervisors, on four well-known DNN architectures. We find that the outlier detection performance improves with the quality of the model. We also analyse the performance of the particular supervisors during the training procedure by applying the supervisor at a predefined interval to investigate its performance as the training proceeds. We observe that understanding the relationship between training results and supervisor performance is crucial to improve the model's robustness and to indicate, what input samples require further measures to improve the robustness of a DNN. In addition, our work paves the road towards an instrument for safety argumentation for safety critical applications. This paper is an extended version of our previous work presented at 2019 SEAA (cf. [1]); here, we elaborate on the used metrics, add an additional supervisor and test them on two additional datasets.

cs.LG↗

arXiv2022

Learning the Pedestrian-Vehicle Interaction for Pedestrian Trajectory Prediction

In this paper, we study the interaction between pedestrians and vehicles and propose a novel neural network structure called the Pedestrian-Vehicle Interaction (PVI) extractor for learning the pedestrian-vehicle interaction. We implement the proposed PVI extractor on both sequential approaches (long short-term memory (LSTM) models) and non-sequential approaches (convolutional models). We use the Waymo Open Dataset that contains real-world urban traffic scenes with both pedestrian and vehicle annotations. For the LSTM-based models, our proposed model is compared with Social-LSTM and Social-GAN, and using our proposed PVI extractor reduces the average displacement error (ADE) and the final displacement error (FDE) by 7.46% and 5.24%, respectively. For the convolutional-based models, our proposed model is compared with Social-STGCNN and Social-IWSTCNN, and using our proposed PVI extractor reduces the ADE and FDE by 2.10% and 1.27%, respectively. The results show that the pedestrian-vehicle interaction influences pedestrian behavior, and the models using the proposed PVI extractor can capture the interaction between pedestrians and vehicles, and thereby outperform the compared methods.

cs.CV↗

arXiv2021

Evaluating Blockchain Application Requirements and their Satisfaction in Hyperledger Fabric

Blockchain applications may offer better fault-tolerance, integrity, traceability and transparency compared to centralized solutions. Despite these benefits, few businesses switch to blockchain-based applications. Industries worry that the current blockchain implementations do not meet their requirements, e.g., when it comes to scalability, throughput or latency. Hyperledger Fabric (HLF) is a permissioned blockchain infrastructure that aims to meet enterprise needs and provides a highly modular and well-conceived architecture. In this paper, we survey and analyse requirements of blockchain applications in respect to their underlying infrastructure by focusing mainly on performance and resilience characteristics. Subsequently, we discuss to what extent Fabric's current design allows it to meet these requirements. We further evaluate the performance of Hyperledger Fabric 2.2 simulating different use case scenarios by comparing single with multi ordering service performance and conducting an evaluation with mixed workloads.

cs.DC↗

arXiv2021

Traction Adaptive Motion Planning at the Limits of Handling

In this paper, we address the problem of motion planning and control at the limits of handling, under locally varying traction conditions. We propose a novel solution method where traction variations over the prediction horizon are represented by time-varying tire force constraints, derived from a predictive friction estimate. A constrained finite time optimal control problem is solved in a receding horizon fashion, imposing these time-varying constraints. Furthermore, our method features an integrated sampling augmentation procedure that addresses the problems of infeasibility and sensitivity to local minima that arise at abrupt constraint alterations, e.g., due to sudden friction changes. We validate the proposed algorithm on a Volvo FH16 heavy-duty vehicle, in a range of critical scenarios. Experimental results indicate that traction adaptive motion planning and control improves the vehicle's capacity to avoid accidents, both when adapting to low local traction, by ensuring dynamic feasibility of the planned motion, and when adapting to high local traction, by realizing high traction utilization.

cs.RO↗

arXiv2021

Are we ready for beyond-application high-volume data? The Reeds robot perception benchmark dataset

This paper presents a dataset, called Reeds, for research on robot perception algorithms. The dataset aims to provide demanding benchmark opportunities for algorithms, rather than providing an environment for testing application-specific solutions. A boat was selected as a logging platform in order to provide highly dynamic kinematics. The sensor package includes six high-performance vision sensors, two long-range lidars, radar, as well as GNSS and an IMU. The spatiotemporal resolution of sensors were maximized in order to provide large variations and flexibility in the data, offering evaluation at a large number of different resolution presets based on the resolution found in other datasets. Reeds also provides means of a fair and reproducible comparison of algorithms, by running all evaluations on a common server backend. As the dataset contains massive-scale data, the evaluation principle also serves as a way to avoid moving data unnecessarily. It was also found that naive evaluation of algorithms, where each evaluation is computed sequentially, was not practical as the fetch and decode task of each frame would not scale well. Instead, each frame is only decoded once and then fed to all algorithms in parallel, including for GPU-based algorithms.

cs.CV↗

arXiv2021

A Survey on Resilience in the IoT: Taxonomy, Classification and Discussion of Resilience Mechanisms

Internet-of-Things (IoT) ecosystems tend to grow both in scale and complexity as they consist of a variety of heterogeneous devices, which span over multiple architectural IoT layers (e.g., cloud, edge, sensors). Further, IoT systems increasingly demand the resilient operability of services as they become part of critical infrastructures. This leads to a broad variety of research works that aim to increase the resilience of these systems. In this paper, we create a systematization of knowledge about existing scientific efforts of making IoT systems resilient. In particular, we first discuss the taxonomy and classification of resilience and resilience mechanisms and subsequently survey state-of-the-art resilience mechanisms that have been proposed by research work and are applicable to IoT. As part of the survey, we also discuss questions that focus on the practical aspects of resilience, e.g., which constraints resilience mechanisms impose on developers when designing resilient systems by incorporating a specific mechanism into IoT systems.

cs.DC↗

arXiv2021

Making Reads in BFT State Machine Replication Fast, Linearizable, and Live

Practical Byzantine Fault Tolerance (PBFT) is a seminal state machine replication protocol that achieves a performance comparable to non-replicated systems in realistic environments. A reason for such high performance is the set of optimizations introduced in the protocol. One of these optimizations is read-only requests, a particular type of client request which avoids running the three-step agreement protocol and allows replicas to respond directly, thus reducing the latency of reads from five to two communication steps. Given PBFT's broad influence, its design and optimizations influenced many BFT protocols and systems that followed, e.g., BFT-SMaRt. We show, for the first time, that the read-only request optimization introduced in PBFT more than 20 years ago can violate its liveness. Notably, the problem affects not only the optimized read-only operations but also standard, totally-ordered operations. We show this weakness by presenting an attack in which a malicious leader blocks correct clients and present two solutions for patching the protocol, making read-only operations fast and correct. The two solutions were implemented on BFT-SMaRt and evaluated in different scenarios, showing their effectiveness in preventing the identified attack.

cs.DC↗

arXiv2021

A Structured Analysis of the Video Degradation Effects on the Performance of a Machine Learning-enabled Pedestrian Detector

ML-enabled software systems have been incorporated in many public demonstrations for automated driving (AD) systems. Such solutions have also been considered as a crucial approach to aim at SAE Level 5 systems, where the passengers in such vehicles do not have to interact with the system at all anymore. Already in 2016, Nvidia demonstrated a complete end-to-end approach for training the complete software stack covering perception, planning and decision making, and the actual vehicle control. While such approaches show the great potential of such ML-enabled systems, there have also been demonstrations where already changes to single pixels in a video frame can potentially lead to completely different decisions with dangerous consequences. In this paper, a structured analysis has been conducted to explore video degradation effects on the performance of an ML-enabled pedestrian detector. Firstly, a baseline of applying YOLO to 1,026 frames with pedestrian annotations in the KITTI Vision Benchmark Suite has been established. Next, video degradation candidates for each of these frames were generated using the leading video codecs libx264, libx265, Nvidia HEVC, and AV1: 52 frames for the various compression presets for color and gray-scale frames resulting in 104 degradation candidates per original KITTI frame and 426,816 images in total. YOLO was applied to each image to compute the intersection-over-union (IoU) metric to compare the performance with the original baseline. While aggressively lossy compression settings result in significant performance drops as expected, it was also observed that some configurations actually result in slightly better IoU results compared to the baseline. The findings show that carefully chosen lossy video configurations preserve a decent performance of particular ML-enabled systems while allowing for substantial savings when storing or transmitting data.

cs.CV↗

arXiv2021

Social-IWSTCNN: A Social Interaction-Weighted Spatio-Temporal Convolutional Neural Network for Pedestrian Trajectory Prediction in Urban Traffic Scenarios

Pedestrian trajectory prediction in urban scenarios is essential for automated driving. This task is challenging because the behavior of pedestrians is influenced by both their own history paths and the interactions with others. Previous research modeled these interactions with pooling mechanisms or aggregating with hand-crafted attention weights. In this paper, we present the Social Interaction-Weighted Spatio-Temporal Convolutional Neural Network (Social-IWSTCNN), which includes both the spatial and the temporal features. We propose a novel design, namely the Social Interaction Extractor, to learn the spatial and social interaction features of pedestrians. Most previous works used ETH and UCY datasets which include five scenes but do not cover urban traffic scenarios extensively for training and evaluation. In this paper, we use the recently released large-scale Waymo Open Dataset in urban traffic scenarios, which includes 374 urban training scenes and 76 urban testing scenes to analyze the performance of our proposed algorithm in comparison to the state-of-the-art (SOTA) models. The results show that our algorithm outperforms SOTA algorithms such as Social-LSTM, Social-GAN, and Social-STGCNN on both Average Displacement Error (ADE) and Final Displacement Error (FDE). Furthermore, our Social-IWSTCNN is 54.8 times faster in data pre-processing speed, and 4.7 times faster in total test speed than the current best SOTA algorithm Social-STGCNN.

cs.CV↗

arXiv2021

Performance Analysis of Out-of-Distribution Detection on Various Trained Neural Networks

Several areas have been improved with Deep Learning during the past years. For non-safety related products adoption of AI and ML is not an issue, whereas in safety critical applications, robustness of such approaches is still an issue. A common challenge for Deep Neural Networks (DNN) occur when exposed to out-of-distribution samples that are previously unseen, where DNNs can yield high confidence predictions despite no prior knowledge of the input. In this paper we analyse two supervisors on two well-known DNNs with varied setups of training and find that the outlier detection performance improves with the quality of the training procedure. We analyse the performance of the supervisor after each epoch during the training cycle, to investigate supervisor performance as the accuracy converges. Understanding the relationship between training results and supervisor performance is valuable to improve robustness of the model and indicates where more work has to be done to create generalized models for safety critical applications.

cs.LG↗