1,721,003 research outputs found
The Upsides of Turbulence: Baselining Gossip Learning in Dynamic Settings
No full textIn dynamic settings, fully distributed gossip-based learning schemes have recently gained interest due to their better scalability, robustness, and enhanced privacy protection compared to server-based architectures. However, existing approaches to their performance characterization either assume stable connectivity among nodes or are ad-hoc for specific trace-based mobility patterns. Thus, in dynamic settings, there is currently a poor understanding of the conditions under which gossip-based learning schemes are feasible, and of their main performance tradeoffs. In this work, we start addressing this issue by performing a first baselining of Gossip Learning (GL) on random Time-Varying Graphs (TVG), to get a first-order characterization of their main performance patterns in dynamic settings. The use of random TVG enables a fine-grained and accurate characterization of GL effectiveness as a function of the main system parameters while abstracting from scenariospecific features of patterns of communication and mobility (e.g., induced by road grids or measured mobility traces). Our results suggest that GL schemes are robust to node mobility and comparable in accuracy and convergence speed to Federated Learning architectures, over a wide range of operational conditions. We show that the final model accuracy is robust against data dispersion across nodes as well as against very low rates of exchanges across nodes
Contemporary criminal law and new challenges of globalization: smuggling of migrants
No full textIl contributo analizza le implicazioni, in prospettiva di contrasto transnazionale al fenomeno, della legislazione italiana in materia di contrasto all'immigrazione illegal
ARLCL-Optimizer
No full textARLCL-Optimizer is an application implementing the cooperative localization method ARLCL: Anchor-free Ranging-Likelihood-based Cooperative Localization
A computer vision and control algorithm to follow a human target in a generic environment using a drone
No full textpeer reviewedThis work proposes an innovative technique to solve the problem of tracking and following a generic human target by a drone in a natural, possibly dark scene. The algorithm does not rely on color information but mainly on shape information, using the HOG classifier, and on local brightness information, using the optical flow algorithm. We tried to keep the algorithm as light as possible, envisioning its future application on embedded or mobile devices. After several tests, performed modeling the system as a set of SISO feedback-controlled systems and calculating the Integral Squared Error as quality indicator, we noticed that the final performance, overall satisfactory, degrades as the background complexity and the presence of disturbance sources, such as sharp edges and moving objects that cross the target, increase
Gossip Learning in Edge-Retentive Time-Varying Random Graphs with Node Churn
No full textFully distributed learning schemes based on opportunistic exchanges among nodes, such as Gossip Learning (GL), have recently attracted attention due to their superior scalability, robustness, and enhanced privacy protection. However, their performance has only been characterized in static or application-specific trace-driven mobility scenarios, overlooking the issue of understanding how the structure of the interactions among nodes over time affects the learning process. To address this gap, we propose a new assessment approach for GL in dynamic settings, based on two novel classes of time-varying random graphs, which extend Erdős-Rényi (ER) and Barabási-Albert (BA) random graphs to characterize generic real-world dynamic networks (e.g., social or wireless networks), while accounting for node churn and the rate at which the graph evolves. Evaluating GL on such time-varying graphs allows us to abstract the relationship between the key parameters of GL algorithms, the communication and topology patterns, and the learning performance from factors specific to the experimental contexts, generalizing our findings to a large class of real-world networks. Simulation results show that the sparser the graph, the higher the positive impact edge dynamicity has on GL mean accuracy and convergence time. Surprisingly, we observe that in networks with the same average connectivity degree, regardless of their nodes’ attachment style, a higher edge persistence reduces GL mean accuracy and convergence time, highlighting the value of a varied interaction among nodes. Finally, results show that real-world networks that exhibit preferential attachment can preserve a better GL performance in terms of mean accuracy and convergence time than random networks (i.e., ER-like), even under high node churn and edge dynamicity
FedForce: Network-adaptive Federated Learning for Reinforced Mobility Prediction
No full textFederated Learning (FL) has become popular in the field of mobility and trajectory prediction due to its privacy-preserving and scalability capabilities. Deploying FL over resource-constrained devices and varying network conditions is challenging for achieving a good tradeoff among prediction performance, computational load, and communication volume. On the other hand, the design of FL’s distributed neural architectures is complex, time-consuming, and dependent on experts’ prior knowledge. To tackle the above limitations, we propose the network-adaptive FEDerated learning for reinFORCEd mobility prediction (FedForce) system. FedForce employs reinforcement learning to design a transformer neural network whose architecture jointly optimizes the prediction accuracy, training time, and transmission time based on the mobility dataset’s unique features, the client’s computing capacity, and the available network throughput. FedForce outperforms several state-of-theart trajectory predictors and achieves an average displacement error of 0.20m on the ETH+UCY dataset and an accuracy of 76% on the Orange dataset (-0.02m and 10% higher than the bestperforming baseline, respectively), while cutting the FL training and transmission time by half. FedForce can save up to 80% of computational resources and 96% of communication overheads with a negligible accuracy decrease
ARES: Adaptive Resource-Aware Split Learning for Internet of Things
Full text linkDistributed training of Machine Learning models in edge Internet of Things (IoT) environments is challenging because of three main points. First, resource-constrained devices have large training times and limited energy budget. Second, resource heterogeneity of IoT devices slows down the training of the global model due to the presence of slower devices (stragglers). Finally, varying operational conditions, such as network bandwidth, and computing resources, significantly affect training time and energy consumption. Recent studies have proposed Split Learning (SL) for distributed model training with limited resources but its efficient implementation on the resource-constrained and decentralized heterogeneous IoT devices remains minimally explored. We propose Adaptive REsource-aware Splitlearning (ARES), a scheme for efficient model training in IoT systems. ARES accelerates local training in resource-constrained devices and minimizes the effect of stragglers on the training through device-targeted split points while accounting for time-varying network throughput and computing resources. ARES takes into account application constraints to mitigate training optimization tradeoffs in terms of energy consumption and training time. We evaluate ARES prototype on a real testbed comprising heterogeneous IoT devices running a widely-adopted deep neural network and dataset. Results show that ARES accelerates model training on IoT devices by up to 48% and minimizes the energy consumption by up to 61.4% compared to Federated Learning (FL) and classic SL, without sacrificing the model convergence and accurac
DFL: Dynamic Federated Split Learning in Heterogeneous IoT
Full text linkFederated Learning (FL) in edge Internet of Things (IoT) environments is challenging due to the heterogeneous nature of the learning environment, mainly embodied in two aspects. Firstly, the statistically heterogeneous data, usually non-independent identically distributed (non-IID), from geographically distributed clients can deteriorate the FL training accuracy. Secondly, the heterogeneous computing and communication resources in IoT devices often result in unstable training processes that slow down the training of a global model and affect energy consumption. Most existing solutions address only the unilateral side of the heterogeneity issue but neglect the joint problem of resources and data heterogeneity for the resource-constrained IoT. In this article, we propose Dynamic Federated split Learning (DFL) to address the joint problem of data and resource heterogeneity for distributed training in IoT. DFL enhances training efficiency in heterogeneous dynamic IoT through resource-aware split computing of deep neural networks and dynamic clustering of training participants based on the similarity of their sub-model layers. We evaluate DFL on a real testbed comprising heterogeneous IoT devices using two widely-adopted datasets, in various non-IID settings. Results show that DFL improves training performance in terms of training time by up to 48%, accuracy by up to 32%, and energy consumption by up to 62.8% compared to classic FL and Federated Split Learning in scenarios with both data and resource heterogeneity
SecureAoX: A Location Verification System
No full textThe Constant Tone Extension that enables Angle of Arrival direction finding in Bluetooth Low Energy is not protected. Therefore, an attacker might be able to manipulate or forge locations. SecureAoX uses basic cryptographic functions and the contradictions between the Angle of Arrival measured on the anchor points and the Angle of Departure measured on the asset tag to verify location claims and detect manipulated and forged locations. A Monte Carlo simulation used to evaluate the performance of the detection algorithm shows that the approach is efficient in detecting attacks and real-world Angle of Arrival accuracy measurements show that the approach is feasible in real-world scenarios. In conclusion, SecureAoX can detect forged and manipulated positions that are further away from the attacked positions than the uncertainty of the used Positioning System
- …
