IFIP Open Access Digital Library
Not a member yet
22614 research outputs found
Sort by
Remote Revolution: The Impact of Working from Home on Employee Well-Being and Productivity in Germany
No full textPart 2: Digital Transformation and Organizational InnovationInternational audienceDuring the COVID-19 pandemic, 27% of employees in Germany worked from home, leading to significant changes in work practices that impacted both productivity and personal well-being. Early studies on the implications of working from home during COVID-19 predominantly reported positive developments. However, more recent research has increasingly highlighted negative consequences. To contribute to this ongoing academic discussion, we conducted a qualitative study based on semi-structured expert interviews, focusing on employee well-being and productivity. We conducted interviews with representatives from a broad range of companies in the white-collar sector in Germany. Germany is particularly suited for this investigation because it has a relatively high proportion of employees working from home. Our main results include two frameworks illustrating main influencing factors for employee well-being and employee productivity. Moreover, we propose a set of recommendations for working from home regulations. These findings contribute to the academic discourse by enhancing the understanding of factors affecting employee well-being and productivity. Corresponding practical implications include the application of our frameworks and recommendations by organizations to optimize employee health and productivity in working from home settings
MQfilTTr: Strengthening Smart Home Privacy Through MQTT Traffic Manipulation
No full textInternational audienceWe present the software design for an easily extendable architecture that prevents leakage of privacy-relevant data in messages sent from smart home environments to external servers outside of a smart home. Such problems arise since users are mostly unable to control which data leaves the local network unfiltered. We address this situation by a privacy-enforcing hub architecture located at the smart home gateway; our approach enables manipulation of e.g. MQTT messages in order to block or rewrite data before it leaves the smart home. We exemplify our architecture for information dissemination control using MQTT, since it is a well-established and frequently used communication protocol in Internet of Things applications. Our performance analysis demonstrates a comparably low overhead that can easily be tolerated. We also discuss how brown field (e.g. existing) devices can be integrated into such an approach which also highlights our extension of modeling the network protocol’s sender and receiver functions separately facilitating Node-RED; moreover we investigate the danger of circumventing such a hub architecture by exploiting metadata side channels; both these issues have not been sufficiently addressed in previous works, which we extend in this work
Enhancing TRIZ Contradiction Resolution with AI-Driven Contradiction Navigator (AICON)
No full textPart 1: AI-Driven TRIZ and InnovationInternational audienceThis paper presents the AI-driven Contradiction Navigator (AICON), a tool engineered to address the inherent limitations of the traditional TRIZ Contradiction Matrix. By integrating advanced AI technologies, AICON enhances the identification, mapping, and resolution of contradictions with advanced precision and context sensitivity. Central to its architecture is the incorporation of Retrieval-Augmented Generation (RAG) AI, enabling the system to access and utilize diverse knowledge domains dynamically. This capability allows AICON to identify new inventive principles and effectively cover previously unaddressed areas within the TRIZ matrix. The system’s architecture is designed to facilitate AI-driven data enrichment, adaptive contradiction mapping, and tailored solution generation, all within an iterative learning framework that continuously refines its problem-solving efficacy. Preliminary research outcomes highlight AICON’s success in discovering novel inventive principles and expanding the TRIZ matrix’s applicability with contextually relevant solutions. These advancements underline AICON’s potential to improve inventive problem-solving methodologies
Towards a Flexible Accuracy-Oriented Deep Learning Module Inference Latency Prediction Framework for Adaptive Optimization Algorithms
No full textPart 1: Machine LearningInternational audienceWith the rapid development of Deep Learning, more and more applications on the cloud and edge tend to utilize large DNN (Deep Neural Network) models for improved task execution efficiency as well as decision-making quality. Due to memory constraints, models are commonly optimized using compression, pruning, and partitioning algorithms to become deployable onto resource-constrained devices. As the conditions in the computational platform change dynamically, the deployed optimization algorithms should accordingly adapt their solutions. To perform frequent evaluations of these solutions in a timely fashion, RMs (Regression Models) are commonly trained to predict the relevant solution quality metrics, such as the resulted DNN module inference latency, which is the focus of this paper. Existing prediction frameworks specify different RM training workflows, but none of them allow flexible configurations of the input parameters (e.g., batch size, device utilization rate) and of the selected RMs for different modules. In this paper, a deep learning module inference latency prediction framework is proposed, which i) hosts a set of customizable input parameters to train multiple different RMs per DNN module (e.g., convolutional layer) with self-generated datasets, and ii) automatically selects a set of trained RMs leading to the highest possible overall prediction accuracy, while keeping the prediction time/space consumption as low as possible. Furthermore, a new RM, namely MEDN (Multi-task Encoder-Decoder Network), is proposed as an alternative solution. Comprehensive experiment results show that MEDN is fast and lightweight, and capable of achieving the highest overall prediction accuracy and R-squared value. The Time/Space-efficient Auto-selection algorithm also manages to improve the overall accuracy by 2.5% and R-squared by 0.39%, compared to the MEDN single-selection scheme
Empirical Evaluation of Evolutionary Algorithms with Power-Law Ranking Selection
No full textPart 3: Neural and Evolutionary ComputingInternational audienceIt has been proven that non-elitist evolutionary algorithms (EAs) with proper selection mechanisms, including the recently proposed power-law ranking selection, can efficiently escape local optima on a broad class of problems called SparseLocalOpt α,ε, where elitist EAs fail. However, those theoretical upper bounds on the runtime are not tight as they require large populations and a tight balance between mutation rates and selection pressure to keep the algorithms operating near the so-called “error threshold”. This paper empirically clarifies the significance of these theoretical requirements and makes a series of performance comparisons between the non-elitist EA using power-law ranking selection and other EAs on various benchmark problems.Our experimental results show that non-elitist EAs optimise the Funnel problem with deceptive local optimum significantly faster with power-law ranking selection than with tournament selection. Furthermore, power-law selection outperforms UMDA and the (1+1) EA in our experiments on the NK-Landscape and Max k-Sat problems, but yields to the (μ,λ)-selection, tournament selection, and the self-adaptive MOSA-EA. On the unicost set cover problems, the EA with power-law selection shows competitive results
Design and Implementation of Risk Control Model Based on Deep Ensemble Learning Algorithm
No full textPart 1: Machine LearningInternational audienceThis paper aims to explore the concept of “depth” through the selection of various ensemble methods and proposes a practical deep ensemble learning method. In this study, we propose a nested ensemble learning method. First, we employ the stacking framework for selective ensemble learning. Next, we integrate the stacked ensemble with bagging and boosting techniques to create a comprehensive stacked ensemble. We utilized both domestic and foreign online loan data to build the model and test its ability to generalize. The experimental results demonstrate that the nested ensemble proposed in this paper outperforms models such as logistic regression and support vector machines, showing exceptional generalization ability
Training Artificial Immune Networks as Standalone Generative Models for Realistic Data Synthesis
No full textPart 3: Neural and Evolutionary ComputingInternational audienceIn recent years, generative modelling has become a significant area of computer science research and artificial intelligence. This has been primarily due to the fact that generative models are useful in addressing the class imbalance problem inherent in some datasets. By generating synthetic data samples for underrepresented classes with a decent amount of variation through random noise, classification models could be trained more efficiently. The popularity of generative models was also increased by the prospect of being able to generate previously non-existent samples of images, audio and video for other creative tasks not related to addressing the class imbalance in datasets. This paper presents exploratory research to train an artificial immune network as a standalone generative model (called a generative adversarial artificial immune network, or GAAINet) using purely immunological computation concepts, such as antibody affinity, clonal selection and hypermutation. Experimental results show that the resulting generator artificial immune network could generate human-recognisable synthetic handwritten digits without any prior knowledge of the MNIST handwritten digits dataset
Divide-and-Conquer Strategy for Large-Scale Dynamic Bayesian Network Structure Learning
No full textPart 1: Machine LearningInternational audienceDynamic Bayesian Networks (DBNs), renowned for their interpretability, have become increasingly vital in representing complex stochastic processes in various domains such as gene expression analysis, healthcare, and traffic prediction. Structure learning of DBNs from data is a challenging endeavor, particularly for datasets with thousands of variables. Most current algorithms for DBN structure learning are adaptations from those used in static Bayesian Networks (BNs), and are typically focused on smaller-scale problems. In order to solve large-scale problems while taking full advantage of existing algorithms, this paper introduces a novel divide-and-conquer strategy, originally developed for static BNs, and adapts it for large-scale DBN structure learning. Additionally, we leverage the prior knowledge of 2 Time-sliced BNs (2-TBNs), a special class of DBNs, to enhance the performance of this strategy. Our approach significantly improves the scalability and accuracy of 2-TBN structure learning. Designed experiments demonstrate the effectiveness of our method, showing substantial improvements over existing algorithms in both computational efficiency and structure learning accuracy. In problem instances with more than 1,000 variables, our proposed approach on average improves two accuracy metrics by 74.45% and 110.94%, respectively, while reducing runtime by an average of 93.65%. Moreover, in problem instances with more than 10,000 variables, our proposed approach successfully completed the task in a matter of hours, whereas the baseline algorithm failed to produce a reasonable result within a one-day runtime limit
From Concept to Prototype: Developing and Testing GAAINet for Industrial IoT Intrusion Detection
No full textPart 5: Business Intelligence and Risk ControlInternational audienceIntrusion detection is a growing area of concern in Industrial Internet of Things (IIoT) systems. This is largely due to the fact that IIoT systems are typically used to augment the operation of Critical Information Infrastructures, the compromise of which could result in severe consequences for industries or even nations. In addition, IIoT is a relatively new technological development which introduces new vulnerabilities. Machine learning methods are increasingly being applied to IIoT intrusion detection. However, the data imbalance prevalent in IIoT intrusion detection datasets can limit the performance of intrusion detection algorithms due to the significantly smaller amount of attack samples. As such, generative models have been applied to address the data imbalance problem by modelling distributions of intrusion detection datasets in order to generate synthetic attack samples. Current work presents the implementation of a Generative Adversarial Artificial Immune Network (GAAINet) as an approach for addressing data imbalance IIoT intrusion detection. Experimental results show that GAAINet could generate synthetic attack samples for the WUSTL-IIoT-2021 dataset. The resulting balanced dataset was used to train an Artificial Immune Network classifier, which achieved a detection accuracy of 99.13% for binary classification and 98.87% for multi-class classification
Intuitiveness and Trustworthiness of AI-Powered Interfaces for Neurological Diagnosis - Preliminary Results
No full textPart 4: PostersInternational audienceThe work presented in this article is part of a broader research initiative whose focus revolves around the integration of Artificial Intelligence (AI) in diagnosing Mild Cognitive Impairment (MCI), in particular, investigating the reliability and stability of eXplainable AI (XAI) predictions concerning markers of MCI and Alzheimer’s Disease. In order to foster neurologists’ understanding, confidence and trust in the AI system results, the initial Machine Learning (ML) based analysis pipeline has been now extended to incorporate a graphical user interface (GUI) that would provide “neurologist-centred” explanations. In this article, the focus is on a preliminary study that involved neurology professionals to assess their understanding and confidence in AI-generated diagnoses presented through three alternative plots implemented in the system GUI