arXiv subjects

Kostas Kolomvatsos

Publications and source records attributed to Kostas Kolomvatsos.

At least 19 recordsLinked to original sources

arXiv2026

Label-Free Concept Drift Assessment for Reliable AI in Emerging Wireless Applications

Machine learning models deployed in non-stationary environments degrade silently, since as the input distribution drifts their accuracy decays without an error signal and without labels to reveal it. Sustaining reliable AI therefore requires a concept-drift detector that acts as an external observer of the deployed model, monitoring it using unlabeled operational data alone, so that an MLOps actuator triggers retraining and redeployment only when it is warranted. This paper contributes two concept drift detectors, namely Confidence-Filtered Pseudo-Label Transfer (CFPT) and TabAutoDrift, which combine representation learning with statistical testing to compute an expected utility score that signals whether a deployed model should be retrained, without requiring ground-truth labels after deployment. The detectors are evaluated on two emerging, label-scarce wireless application domains in which post deployment ground truth is effectively unavailable, namely outdoor fingerprinting-based localization and link-anomaly detection. They outperform the classical detectors ADWIN, DDM, and CUSUM, attaining a drift-detection F1-score between 0.88 and 0.94 in the fingerprinting use case and between 0.80 and 1.00 in the link-anomaly use case, up to 0.24 higher than the strongest classical detector. Interpreted as reliability decisions, this precision indicates that the proposed detectors signal retraining more dependably.

cs.NI↗

arXiv2026

A Deep Learning Model for Battery State Prediction towards Intelligent Energy Management

Accurate forecasting of battery health indicators, including remaining capacity and lifetime, is of paramount importance for ensuring the reliability, safety, and operational efficiency of applications such as electric vehicles and large scale energy storage infrastructures. The result of the forecasting can be adopted to build an advanced monitoring mechanism for continuous checking batteries' health status to assist in the efficient real-time management of numerous applications. This research investigates the development and implementation of a Deep Learning (DL) model for the prediction of the future state and performance of industrial electrochemical energy storage systems. To address this challenge, we propose a dedicated computational framework that integrates advanced neural network architectures with large-scale training datasets, enabling precise modeling of batteries degradation dynamics and operational trends. The proposed approach provides a decision support mechanism for the optimal management of batteries facilitating both predictive maintenance and the efficient allocation of energy resources. Our findings highlight the potential of DL-based predictive modeling to significantly contribute to the advancement of sustainable and intelligent energy management systems.

eess.SP↗

arXiv2025

A Representation Learning Approach to Feature Drift Detection in Wireless Networks

AI is foreseen to be a centerpiece in next generation wireless networks enabling enabling ubiquitous communication as well as new services. However, in real deployment, feature distribution changes may degrade the performance of AI models and lead to undesired behaviors. To counter for undetected model degradation, we propose ALERT; a method that can detect feature distribution changes and trigger model re-training that works well on two wireless network use cases: wireless fingerprinting and link anomaly detection. ALERT includes three components: representation learning, statistical testing and utility assessment. We rely on MLP for designing the representation learning component, on Kolmogorov-Smirnov and Population Stability Index tests for designing the statistical testing and a new function for utility assessment. We show the superiority of the proposed method against ten standard drift detection methods available in the literature on two wireless network use cases.

cs.LG↗

arXiv2024

An Ensemble Scheme for Proactive Dominant Data Migration of Pervasive Tasks at the Edge

Nowadays, a significant focus within the research community on the intelligent management of data at the confluence of the Internet of Things (IoT) and Edge Computing (EC) is observed. In this manuscript, we propose a scheme to be implemented by autonomous edge nodes concerning their identifications of the appropriate data to be migrated to particular locations within the infrastructure, thereby facilitating the effective processing of requests. Our objective is to equip nodes with the capability to comprehend the access patterns relating to offloaded data-driven tasks and to predict which data ought to be returned to the original nodes associated with those tasks. It is evident that these tasks depend on the processing of data that is absent from the original hosting nodes, thereby underscoring the essential data assets that necessitate access. To infer these data intervals, we utilize an ensemble approach that integrates a statistically oriented model and a machine learning framework. As a result, we are able to identify the dominant data assets in addition to detecting the density of the requests. A detailed analysis of the suggested method is provided by presenting the related formulations, which is also assessed and compared with models found in the relevant literature.

cs.DC↗

arXiv2023

BundleMoCap: Efficient, Robust and Smooth Motion Capture from Sparse Multiview Videos

Capturing smooth motions from videos using markerless techniques typically involves complex processes such as temporal constraints, multiple stages with data-driven regression and optimization, and bundle solving over temporal windows. These processes can be inefficient and require tuning multiple objectives across stages. In contrast, BundleMoCap introduces a novel and efficient approach to this problem. It solves the motion capture task in a single stage, eliminating the need for temporal smoothness objectives while still delivering smooth motions. BundleMoCap outperforms the state-of-the-art without increasing complexity. The key concept behind BundleMoCap is manifold interpolation between latent keyframes. By relying on a local manifold smoothness assumption, we can efficiently solve a bundle of frames using a single code. Additionally, the method can be implemented as a sliding window optimization and requires only the first frame to be properly initialized, reducing the overall computational burden. BundleMoCap's strength lies in its ability to achieve high-quality motion capture results with simplicity and efficiency. More details can be found at https://moverseai.github.io/bundle/.

cs.CV↗

arXiv2023

Noise-in, Bias-out: Balanced and Real-time MoCap Solving

Real-time optical Motion Capture (MoCap) systems have not benefited from the advances in modern data-driven modeling. In this work we apply machine learning to solve noisy unstructured marker estimates in real-time and deliver robust marker-based MoCap even when using sparse affordable sensors. To achieve this we focus on a number of challenges related to model training, namely the sourcing of training data and their long-tailed distribution. Leveraging representation learning we design a technique for imbalanced regression that requires no additional data or labels and improves the performance of our model in rare and challenging poses. By relying on a unified representation, we show that training such a model is not bound to high-end MoCap training data acquisition, and exploit the advances in marker-less MoCap to acquire the necessary data. Finally, we take a step towards richer and affordable MoCap by adapting a body model-based inverse kinematics solution to account for measurement and inference uncertainty, further improving performance and robustness. Project page: https://moverseai.github.io/noise-tail

cs.CV↗

arXiv2023

A Pervasive Framework for Human Detection and Tracking

The advent of the Edge Computing (EC) leads to a huge ecosystem where numerous nodes can interact with data collection devices located close to end users. Human detection and tracking can be realized at edge nodes that perform the surveillance of an area under consideration through the assistance of a set of sensors (e.g., cameras). Our target is to incorporate the discussed functionalities to embedded devices present at the edge keeping their size limited while increasing their processing capabilities. In this paper, we propose two models for human detection accompanied by algorithms for tracing the corresponding trajectories. We provide the description of the proposed models and extend them to meet the challenges of the problem. Our evaluation aims at identifying models' accuracy while presenting their requirements to have them executed in embedded devices.

cs.CV↗

arXiv2022

A Proactive Uncertainty driven Model for Tasks Offloading

The ever-increasing demands of end-users on the Internet of Things (IoT), often cause great congestion in the nodes that serve their requests. Therefore, the problem of node overloading arises. In this article we attempt to solve the problem of heavy traffic in a node, by proposing a mechanism that keeps the node from overloading, regardless of the load entering in it, and which takes into consideration both the priority and the task demand. More specifically, we introduce a proactive, self-healing mechanism that utilizes fuzzy systems, in combination to a non-parametric statistic method. Through our approach, we manage to ensure the uninterrupted service of high demand or priority tasks, regardless of the load the node may receive, based on a proactive approach. Also, we ensure the fastest possible result delivery to the requestors, through the high priority and high demand sensitive mechanism. A series of experimental scenarios are used to evaluate the performance of the suggested model, while we present the relevant numerical results.

cs.NI↗

arXiv2022

Monitoring and Proactive Management of QoS Levels in Pervasive Applications

The advent of Edge Computing (EC) as a promising paradigm that provides multiple computation and analytics capabilities close to data sources opens new pathways for novel applications. Nonetheless, the limited computational capabilities of EC nodes and the expectation of ensuring high levels of QoS during tasks execution impose strict requirements for innovative management approaches. Motivated by the need of maintaining a minimum level of QoS during EC nodes functioning, we elaborate a distributed and intelligent decision-making approach for tasks scheduling. Our aim is to enhance the behavior of EC nodes making them capable of securing high QoS levels. We propose that nodes continuously monitor QoS levels and systematically evaluate the probability of violating them to proactively decide some tasks to be offloaded to peer nodes or Cloud. We present, describe and evaluate the proposed scheme through multiple experimental scenarios revealing its performance and the benefits of the envisioned monitoring mechanism when serving processing requests in very dynamic environments like the EC.

cs.DC↗

arXiv2021

Local Learning at the Network Edge for Efficient & Secure Real-Time Predictive Analytics

The ability to perform computation on devices, such as smartphones, cars, or other nodes present at the Internet of Things leads to constraints regarding bandwidth, storage, and energy, as most of these devices are mobile and operate on batteries. Using their computational power to perform locally machine learning and analytics tasks can enable accurate and real-time predictions at the network edge. A trained machine learning model requires high accuracy towards the prediction outcome, as wrong decisions can lead to negative consequences on the efficient conclusion of applications. Most of the data sensed in these devices are contextual and personal requiring privacy-preserving without their distribution over the network. When working with these privacy-preserving data, not only the protection is important but, also, the model needs the ability to adapt to regular occurring concept drifts and data distribution changes to guarantee a high accuracy of the prediction outcome. We address the importance of personalization and generalization in edge devices to adapt to data distribution updates over continuously evolving environments. The methodology we propose relies on the principles of Federated Learning and Optimal Stopping Theory extended with a personalization component. The privacy-efficient and quality-awareness of personalization and generalization is the overarching aim of this work.

cs.DC↗

arXiv2021

A Proactive Management Scheme for Data Synopses at the Edge

The combination of the infrastructure provided by the Internet of Things (IoT) with numerous processing nodes present at the Edge Computing (EC) ecosystem opens up new pathways to support intelligent applications. Such applications can be provided upon humongous volumes of data collected by IoT devices being transferred to the edge nodes through the network. Various processing activities can be performed on the discussed data and multiple collaborative opportunities between EC nodes can facilitate the execution of the desired tasks. In order to support an effective interaction between edge nodes, the knowledge about the geographically distributed data should be shared. Obviously, the migration of large amounts of data will harm the stability of the network stability and its performance. In this paper, we recommend the exchange of data synopses than real data between EC nodes to provide them with the necessary knowledge about peer nodes owning similar data. This knowledge can be valuable when considering decisions such as data/service migration and tasks offloading. We describe an continuous reasoning model that builds a temporal similarity map of the available datasets to get nodes understanding the evolution of data in their peers. We support the proposed decision making mechanism through an intelligent similarity extraction scheme based on an unsupervised machine learning model, and, at the same time, combine it with a statistical measure that represents the trend of the so-called discrepancy quantum. Our model can reveal the differences in the exchanged synopses and provide a datasets similarity map which becomes the appropriate knowledge base to support the desired processing activities. We present the problem under consideration and suggest a solution for that, while, at the same time, we reveal its advantages and disadvantages through a large number of experiments.

cs.LG↗

arXiv2021

A Soft Method for Outliers Detection at the Edge of the Network

The combination of the Internet of Things and the Edge Computing gives many opportunities to support innovative applications close to end users. Numerous devices present in both infrastructures can collect data upon which various processing activities can be performed. However, the quality of the outcomes may be jeopardized by the presence of outliers. In this paper, we argue on a novel model for outliers detection by elaborating on a `soft' approach. Our mechanism is built upon the concepts of candidate and confirmed outliers. Any data object that deviates from the population is confirmed as an outlier only after the study of its sequence of magnitude values as new data are incorporated into our decision making model. We adopt the combination of a sliding with a landmark window model when a candidate outlier is detected to expand the sequence of data objects taken into consideration. The proposed model is fast and efficient as exposed by our experimental evaluation while a comparative assessment reveals its pros and cons.

cs.DC↗

arXiv2020

On the Road from Edge Computing to the Edge Mesh

Nowadays, we are witnessing the advent of the Internet of Things (EC) with numerous devices performing interactions between them or with end users. The huge number of devices leads to huge volumes of collected data that demand the appropriate processing. The 'legacy' approach is to rely on Cloud where increased computational resources can be adopted to realize any processing. However, even if the communication with the Cloud back end lasts for some seconds there are cases where problems in the network or the need for supporting real time applications require a reduced latency in the provision of responses/outcomes. Edge Computing (EC) comes into the scene as the 'solver' of the latency problem (and not only). Any processing can be performed close to data sources, i.e., at EC nodes having direct connection with IoT devices. Hence, an ecosystem of processing nodes can be present at the edge of the network giving the opportunity to apply novel services upon the collected data. Various challenges should be met before we talk about a fully automated ecosystem where EC nodes can cooperate or understand the status of them and the environment to be capable of efficiently serving end users or applications. In this paper, we perform a survey of the relevant research activities targeting to support the vision of Edge Mesh (EM), i.e., a 'cover' of intelligence upon the EC infrastructure. We present all the parts of the EC/EM framework starting from the necessary hardware and discussing research outcomes in every aspect of EC nodes functioning. We present technologies and theories adopted for data, tasks and resource management while discussing how (deep) machine learning and optimization techniques are adopted to solve various problems. Our aim is to provide a starting point for novel research to conclude efficient services/applications opening up the path to realize the future EC form.

cs.DC↗

arXiv2020

A Fuzzy Logic Controller for Tasks Scheduling Using Unreliable Cloud Resources

The Cloud infrastructure offers to end users a broad set of heterogenous computational resources using the pay-as-you-go model. These virtualized resources can be provisioned using different pricing models like the unreliable model where resources are provided at a fraction of the cost but with no guarantee for an uninterrupted processing. However, the enormous gamut of opportunities comes with a great caveat as resource management and scheduling decisions are increasingly complicated. Moreover, the presented uncertainty in optimally selecting resources has also a negatively impact on the quality of solutions delivered by scheduling algorithms. In this paper, we present a dynamic scheduling algorithm (i.e., the Uncertainty-Driven Scheduling - UDS algorithm) for the management of scientific workflows in Cloud. Our model minimizes both the makespan and the monetary cost by dynamically selecting reliable or unreliable virtualized resources. For covering the uncertainty in decision making, we adopt a Fuzzy Logic Controller (FLC) to derive the pricing model of the resources that will host every task. We evaluate the performance of the proposed algorithm using real workflow applications being tested under the assumption of different probabilities regarding the revocation of unreliable resources. Numerical results depict the performance of the proposed approach and a comparative assessment reveals the position of the paper in the relevant literature.

cs.DC↗

arXiv2020

A Probabilistic Approach for Data Management in Pervasive Computing Applications

Current advances in Pervasive Computing (PC) involve the adoption of the huge infrastructures of the Internet of Things (IoT) and the Edge Computing (EC). Both, IoT and EC, can support innovative applications around end users to facilitate their activities. Such applications are built upon the collected data and the appropriate processing demanded in the form of requests. To limit the latency, instead of relying on Cloud for data storage and processing, the research community provides a number of models for data management at the EC. Requests, usually defined in the form of tasks or queries, demand the processing of specific data. A model for pre-processing the data preparing them and detecting their statistics before requests arrive is necessary. In this paper, we propose a promising and easy to implement scheme for selecting the appropriate host of the incoming data based on a probabilistic approach. Our aim is to store similar data in the same distributed datasets to have, beforehand, knowledge on their statistics while keeping their solidity at high levels. As solidity, we consider the limited statistical deviation of data, thus, we can support the storage of highly correlated data in the same dataset. Additionally, we propose an aggregation mechanism for outliers detection applied just after the arrival of data. Outliers are transferred to Cloud for further processing. When data are accepted to be locally stored, we propose a model for selecting the appropriate datasets where they will be replicated for building a fault tolerant system. We analytically describe our model and evaluate it through extensive simulations presenting its pros and cons.

cs.DC↗

arXiv2020

An Intelligent Edge-Centric Queries Allocation Scheme based on Ensemble Models

The combination of Internet of Things (IoT) and Edge Computing (EC) can assist in the delivery of novel applications that will facilitate end users activities. Data collected by numerous devices present in the IoT infrastructure can be hosted into a set of EC nodes becoming the subject of processing tasks for the provision of analytics. Analytics are derived as the result of various queries defined by end users or applications. Such queries can be executed in the available EC nodes to limit the latency in the provision of responses. In this paper, we propose a meta-ensemble learning scheme that supports the decision making for the allocation of queries to the appropriate EC nodes. Our learning model decides over queries' and nodes' characteristics. We provide the description of a matching process between queries and nodes after concluding the contextual information for each envisioned characteristic adopted in our meta-ensemble scheme. We rely on widely known ensemble models, combine them and offer an additional processing layer to increase the performance. The aim is to result a subset of EC nodes that will host each incoming query. Apart from the description of the proposed model, we report on its evaluation and the corresponding results. Through a large set of experiments and a numerical analysis, we aim at revealing the pros and cons of the proposed scheme.

cs.DB↗

arXiv2020

Data Synopses Management based on a Deep Learning Model

Pervasive computing involves the placement of processing services close to end users to support intelligent applications. With the advent of the Internet of Things (IoT) and the Edge Computing (EC), one can find room for placing services at various points in the interconnection of the aforementioned infrastructures. Of significant importance is the processing of the collected data. Such a processing can be realized upon the EC nodes that exhibit increased computational capabilities compared to IoT devices. An ecosystem of intelligent nodes is created at the EC giving the opportunity to support cooperative models. Nodes become the hosts of geo-distributed datasets formulated by the IoT devices reports. Upon the datasets, a number of queries/tasks can be executed. Queries/tasks can be offloaded for performance reasons. However, an offloading action should be carefully designed being always aligned with the data present to the hosting node. In this paper, we present a model to support the cooperative aspect in the EC infrastructure. We argue on the delivery of data synopses to EC nodes making them capable to take offloading decisions fully aligned with data present at peers. Nodes exchange data synopses to inform their peers. We propose a scheme that detects the appropriate time to distribute synopses trying to avoid the network overloading especially when synopses are frequently extracted due to the high rates at which IoT devices report data to EC nodes. Our approach involves a Deep Learning model for learning the distribution of calculated synopses and estimate future trends. Upon these trends, we are able to find the appropriate time to deliver synopses to peer nodes. We provide the description of the proposed mechanism and evaluate it based on real datasets. An extensive experimentation upon various scenarios reveals the pros and cons of the approach by giving numerical results.

cs.DC↗

arXiv2020

Proactive Tasks Management based on a Deep Learning Model

Pervasive computing applications deal with intelligence surrounding users that can facilitate their activities. This intelligence is provided in the form of software components incorporated in embedded systems or devices in close distance with end users.One example infrastructure that can host intelligent pervasive services is the Edge Computing (EC) infrastructure. EC nodes can execute a number of tasks for data collected by devices present in the Internet of Things (IoT) infrastructure. In this paper, we propose an intelligent, proactive tasks management model based on the demand. Demand depicts the number of users or applications interested in using the available tasks in EC nodes, thus, characterizing their popularity. We rely on a Deep Machine Learning (DML) model and more specifically on a Long Short Term Memory (LSTM) network to learn the distribution of demand indicators for each task and estimate the future interest. This information is combined with historical observations and support a decision making scheme to conclude which tasks will be offloaded due to limited interest on them. We have to notice that in our decision making, we also take into consideration the load that every task may add to the processing node where it will be allocated. The description of our model is accompanied by a large set of experimental simulations for evaluating the proposed mechanism. We provide numerical results and reveal that the proposed scheme is capable of deciding on the fly while concluding the most efficient allocation.

cs.NI↗