Post Hoc Explainability for Time Series Classification Toward a signal processing perspective

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Tensegrity structures are spatial, reticulated, and lightweight structures that are composed of struts and cables. Stability is provided by a self-stress state between tensioned and compressed members obtained by prestress. Although the form finding of ten ...

The usual explanation of the efficacy of wavelet-based methods hinges on the sparsity of many real-world objects in the wavelet domain. Yet, standard wavelet-shrinkage techniques for sparse reconstruction are not competitive in practice, one reason being t ...

Chatter is a harmful self-excited vibration that commonly occurs during milling processes. Data -driven chatter detection and prediction is critical to achieve high surface quality and process efficiency. Most existing chatter detection approaches are base ...

Resting-state fMRI has proven to entail subject-specific signatures that can serve as a fingerprint to identify individuals. Conventional methods are based on building a connectivity matrix based on correlation between the average time course of pairs of b ...

The latest standard "New Dual" power module has been developed for both silicon and silicon-carbide devices to meet the increasing demands in high reliability and high temperature power electronic applications. Due to the new package is just starting to re ...

This article proposes a swirling actuator that uses the electromagnetic radial force and mechanical gears to generate rotational torque. The proposed actuator generates a rotating radial force between an inner stator and a swirler. The gears on the swirler ...

Wearable solutions based on Deep Learning (DL) for real-time ECG monitoring are a promising alternative to detect life-threatening arrhythmias. However, DL models suffer of a large memory footprint, which hampers their adoption in portable technologies. Th ...

Energy geostructures (EGs) employ heat exchangers embedded in concrete geostructures, such as piles, walls, tunnels, and sewers. In this study, energy walls (EWs) are studied with an emphasis on the following objectives: (1) to understand the fundamentals ...

Diffusion adaptation is a powerful strategy for distributed estimation and learning over networks. Motivated by the concept of combining adaptive filters, this work proposes a combination framework that aggregates the operation of multiple diffusion strate ...

In this talk, we describe excitation of time-varying dipolar particles (time-modulated meta-atoms) by external time-varying fields from a nonstationary and causal perspective. For a time-harmonic excitation, we introduce a complex-valued function, called t ...

Investigations of the fatigue performance of composite materials have accompanied their introduction in several engineering domains since the 1950s. An abundance of publications have emerged dealing with the experimental investigation of the fatigue perfor ...

The Swiss Plasma Center (SPC) has developed a layout of Toroidal Field (TF) coil for EUROfusion DEMO tokamak, based on the reference tokamak baseline of 2015. Each TF coil winding pack is wound with graded Nb3Sn conductors and consists of 12 single layers, ...

Federated learning is a useful framework for centralized learning from distributed data under practical considerations of heterogeneity, asynchrony, and privacy. Federated architectures are frequently deployed in deep learning settings, which generally giv ...

Objective. Translational studies on motor control and neurological disorders require detailed monitoring of sensorimotor components of natural limb movements in relevant animal models. However, available experimental tools do not provide a sufficiently ric ...

Modern ammonia production plants are equipped with efficient energy integration networks able to recover an important fraction of the waste heat exergy available throughout the chemical system. However, in order to drive the endothermic reforming reactions ...

Structural damage usually happens during earthquake events. This had caused damage of properties and even worse, loss of lives. Usually, the greatest losses were not caused by the quake specifically, but rather because of the fall of the structures. The vu ...

Stress urinary incontinence (SUI) is a life changing condition, affecting 20 million women worldwide. In this study, we developed a bioactive, injectable bulking agent that consists of Permacol (TM) (Medtronic, Switzerland) and recombinant insulin like gro ...

This work presents a cooperative yielding maneuver planner that allows automated vehicles circulating inside single-lane roundabouts to create feasible merging gaps for oncoming cars. The maneuver is triggered once its impact on the predicted evolution of ...

The state-of-the art RF and millimeter-wave first-cut circuits design requires simple hand calculation methods to avoid time-consuming iterative simulations. The classical MOSFET sizing methods used in advanced technologies, still rely on questionable and ...

Post Hoc Explainability for Time Series Classification Toward a signal processing perspective

Chat with Graph Search

Effects of prestress implementation on self-stress state in large-scale tensegrity structure

The Sparsity of Cycle Spinning for Wavelet-Based Solutions of Linear Inverse Problems

A comprehensive review of digital twin-part 2: roles of uncertainty quantification and optimization, a battery digital twin, and perspectives (vol 66, 1, 2022)

Exploring the effectiveness of using internal CNC system signals for chatter detection in milling process

Brain Fingerprinting Using Fmri Spectral Signatures On High-Resolution Cortical Graphs

Aging investigation of the latest standard dual power modules using improved interconnect technologies by power cycling test

Principle and Analysis of Radial-Force-Based Swirling Actuator for Low-Speed High-Torque Applications

Hardware-oriented pruning and quantization of Deep Learning models to detect life-threatening arrhythmias

Hydrothermal interactions in energy walls

Affine Combination of Diffusion Strategies Over Networks

From Polarizability to Effective Permittivity of Time-Varying Materials

The history of fiber-reinforced polymer composite laminate fatigue

Inter-Layer Joint of Nb3Sn React&Wind Cables for Fusion Magnets

Second-Order Guarantees In Federated Learning

A versatile robotic platform for the design of natural, three-dimensional reaching and grasping tasks in monkeys

Combined exergy analysis, energy integration and optimization of syngas and ammonia production plants: A cogeneration and syngas purification perspective

Vulnerability Assessment of Buildings in Ranau Township: Methodological Design

A bioactive injectable bulking material; a potential therapeutic approach for stress urinary incontinence

Cooperative Circulating Behavior at Single-Lane Roundabouts

Analog RF and mm-Wave Design Tradeoff in UTBB FDSOI: Application to a 35 GHz LNA