Change Point Detection (CPD) is a critical task in time series analysis, aiming to identify moments when the underlying data-generating process shifts. Traditional CPD methods often rely on unsupervised techniques, which lack adaptability to task-specific definitions of change and cannot benefit from user knowledge. To address these limitations, we propose MuRAL-CPD, a novel semi-supervised method that integrates active learning into a multiresolution CPD algorithm. MuRALCPD leverages a wavelet-based multiresolution decomposition to detect changes across multiple temporal scales and incorporates user feedback to iteratively optimize key hyperparameters. This interaction enables the model to align its notion of change with that of the user, improving both accuracy and interpretability. Our experimental results on several real-world datasets show the effectiveness of MuRAL-CPD against state-of-the-art methods, particularly in scenarios where minimal supervision is available.

Most Federated Learning (FL) approaches assume a single global model is updated locally by clients and aggregated at the server. However, the single-model assumption is often too restrictive, especially in scenarios involving a large amount of different users, where adaptation to different domains and personalization are necessary to improve model performance. In this paper, we propose ClusterSSFDA, the first FL framework to leverage clustering for addressing domain shifts in Semi-Supervised Federated Learning (SSFL), where clients collect data without supervision. In particular, ClusterSSFDA clusters clients based on their models' agreement, and updates multiple models at the server, each tailored to a cluster of similar clients. ClusterSSFDA significantly improves adaptation in SSFL, striking a balance between a single global model, which may be suboptimal in the presence of domain shift among the clients, and fully personalized models, which would be trained on too small datasets. Our experiments on real-world scenarios with multiple levels of domain shift demonstrate that ClusterSSFDA outperforms existing methods, achieving superior performance in challenging SSFL settings.

Semi-Supervised Federated Learning (SSFL) aims to improve a pretrained model using unlabeled data from clients. Traditional SSFL solutions relying on pseudo-labels or autoencoders often struggle in the presence of domain shift, i.e. a difference in data distributions between the server and the clients. In this paper we present SemiFDA, the first solution to effectively handle domain shift in SSFL. After training an initial classifier on the server's labeled data, we establish an unsupervised learning process at clients to train feature extractors based on encoders. This process adopts a custom unsupervised loss function that promotes the clients' encoders to align their feature distributions with those extracted by the encoder at server. The updated encoders are then aggregated at the server using Federated Aver-aging and sent back for the next iteration, while the classification head remains frozen to preserve the benefits of aligning features locally. Furthermore, we design an experimental framework to mimic various levels of domain shift and test SSFL methods in real-world scenarios, including HAR and Digit Classification. Our results also demonstrate the detrimental effects of domain shift in SSFL and show that SemiFDA outperforms other solutions under these challenging conditions.

We present Augmented Grad-CAM, a general framework to provide a high-resolution visual explanation of CNN outputs. Our idea is to take advantage of image augmentation to aggregate multiple low-resolution heat-maps - in our experiments Grad-CAMs - computed from augmented copies of the same input image. We generate the high-resolution heat-map through super-resolution, and we formulate a general optimization problem based on Total Variation regularization. This problem is entirely solved on the GPU at inference time, together with image augmentation. Augmented Grad-CAM outperforms Grad-CAM in weakly supervised localization on Imagenet dataset, and provides more detailed heat-maps. Moreover, Augmented Grad-CAM turns to be particularly useful in monitoring the production of silicon wafers, where CNNs are employed to classify defective patterns on the wafer surface to detect harmful faults in the production line.

As it was mostly developed in a non-academic context, the literature on the blockchain often lacks of mathematical rigour. Therefore, fundamental computational problems of this new technology such as consensus, Byzantine fault tolerance and self-stabilization can not be fully looked into. In this work we use the principles of distributed computing to introduce a topological structure with the purpose of facilitating the study of the blockchain. Our model exploits classical topological tools used in the context of distributed systems to describe the evolution of a blockchain. Different assumptions on the input assignments, number of generated blocks and latency of the system are considered in our analysis. Furthermore, we define a probabilistic structure to enrich our model and to add also a predictive capability.

We present a prototype wearable device able to perform online and long-term monitoring of ECG signals, and detect anomalous heartbeats such as arrhythmias. Our solution is based on user-specific dictionaries which characterizes the morphology of normal heartbeats and are learned every time the device is positioned. Anomalies are detected via an optimized sparse coding procedure, which assesses the conformance of each heartbeat to the user-specific dictionary. The dictionaries are adapted during online monitoring, to track heart rate variations occurring during everyday activities. Perhaps surprisingly, dictionary adaptation can be successfully performed by transformations that are user-independent and learned from large datasets of ECG signals.

Successful ECG monitoring algorithms often rely on learned models to describe the heartbeats morphology. Unfortunately, when the heart rate increases the heartbeats get transformed, and a model that can properly describe the heartbeats of a specific user in resting conditions might not be appropriate for monitoring the same user during everyday activities. We model heartbeats by dictionaries yielding sparse representations and propose a novel domain-adaptation solution which transforms user-specific dictionaries according to the heart rate. In particular, we learn suitable linear transformations from a large dataset containing ECG tracings, and we show that these transformations can successfully adapt dictionaries when the heart rate changes. Remarkably, the same transformations can be used for multiple users and different sensing apparatus. We investigate the implications of our findings in ECG monitoring by wearable devices, and present an efficient implementation of an anomaly-detection algorithm leveraging such transformations.

In this paper we address the Wireless Sensor Networks localization problem in a realistic scenario with outliers and structured missing data (i.e. non-random). Our approach couples SMACOF, which handles incomplete data, with IRLS, which is resilient to outliers. In addition, we provide a new insight on how the initialization method — which is crucial to ensure fold-free solutions — should be adapted to the pattern of missing measures. Experiments shows that the proposed method compares favorably with the state-of-the-art.

Fault attacks are among the most effective techniquesto break real implementations of cryptographic algorithms. They usually require some kind of knowledge bythe attacker on the effect of the faults on the target device, which in practice turns to be a poorly reliable informationtypically affected by uncertainty. This paper is devoted toaddress this problem by softening the a-priori knowledge on the injection technique needed by the attacker in the contextof Differential Fault Analysis (DFA). We conceive an originalsolution, named J-DFA, based on translating the stage ofdifferential cryptanalysis of DFA attacks into terms of fittingmultiple models to data corrupted by outliers. Specifically, wetailor J-Linkage algorithm [9] to the fault analysis. In order toshow the effectiveness of J-DFA and its benefits in practicalscenarios, we applied the technique under different attackconditions.

In this paper, we consider the problem of RSS-fingerprinting localization in wireless sensor networks. In particular, inspired by the recent advances in sparse approximation and compressive sensing theory, we propose a localization scheme based on the dictionary design of block-sparse signals. We show via numerical simulations and real experiments that the proposed technique outperforms traditional fingerprinting methods.

This paper proposes a robust method to solve the absolute rotation estimation problem, which arises in global registration of 3D point sets and in structure-from-motion. A novel cost function is formulated which inherently copes with outliers. In particular, the proposed algorithm handles both outlier and missing relative rotations, by casting the problem as a "low-rank & sparse" matrix decomposition. As a side effect, this solution can be seen as a valid and cost-effective detector of inconsistent pair wise rotations. Computational efficiency and numerical accuracy, are demonstrated by simulated and real experiments.

In this paper we propose a method to encode/decode multiview textures and associated depth maps together in a single bitstream. Encoded bits of depth maps have been merged into that of associated textures in an innovative way with very minimal loss in PSNR of textures, 0.1-0.2 dB for high delay and 0.2-1 dB for low delay applications. Benchmarking results in terms of compression efficiency and quality on HD sequences have been reported to explore the viability of using this technique for Free-view point Video (FVV) or 3DV use cases.

After the extensive effort dedicated by both Academia and Industry in the area of peer-to-peer (P2P) streaming by looking at models and network algorithms to achieve optimal load distribution, recent works are moving forward to enhance the overall P2P systems efficiency by focusing on specific video codecs and packetization techniques at application layer. The purpose to integrate different technologies with the aim to design full streaming solutions requires a joint efforts from the market and EU projects community. Many engineering issues have been brought out in terms of compatibility and integration that need to be addressed. In this paper we focused on a bottleneck discovered during the packetization step between the Scalable Video Coding (SVC) streaming module (during content creation) and the P2P engine before delivering the packets over the network. We compared the a priori fixed packet size solution adopted in P2P-Next project with a codec aware approach, gaining performance in terms of network overhead. We performed experiments with various sequences aiming at overall P2P streaming efficiency and measured the bandwidth cost under various conditions. Since we focused on the application layer, our statistics analysis can be helpful in designing P2P streaming solutions dealing with any network type.

In this paper we present a novel methodology that can be used to design efficient hardware structures for a certain class of combinatorial functions. The methodology is primarily intended to achieve low-power synthesis of non-linear one-to-one functions on ASIC technology libraries and fits well for the synthesis of small cryptographic substitution box (Sbox) functional components; the latter are found in most secret key cryptographic algorithms, and usually represent their most relevant part in terms of required computational power. We also describe an extension that allows us to apply the method to general vectorial Boolean functions.

Cryptographic applications in embedded systems for smart-cards require low-latency, low-complexity and low power dedicated hardware. In this work the GBB algorithm for finite field multiplication is optimised by recoding and the related digit-serial VLSI multiplier architecture is designed and evaluated.