Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313503347> ?p ?o ?g. }
- W4313503347 abstract "Spiking Neural Networks (SNNs), known for their potential to enable low energy consumption and computational cost, can bring significant advantages to the realm of embedded machine learning for edge applications. However, input coming from standard digital sensors must be encoded into spike trains before it can be elaborated with neuromorphic computing technologies. We present here a detailed comparison of available spike encoding techniques for the translation of time-varying signals into the event-based signal domain, tested on two different datasets both acquired through commercially available digital devices: the Free Spoken Digit dataset (FSD), consisting of 8-kHz audio files, and the WISDM dataset, composed of 20-Hz recordings of human activity through mobile and wearable inertial sensors. We propose a complete pipeline to benchmark these encoding techniques by performing time-dependent signal classification through a Spiking Convolutional Neural Network (sCNN), including a signal preprocessing step consisting of a bank of filters inspired by the human cochlea, feature extraction by production of a sonogram, transfer learning via an equivalent ANN, and model compression schemes aimed at resource optimization. The resulting performance comparison and analysis provides a powerful practical tool, empowering developers to select the most suitable coding method based on the type of data and the desired processing algorithms, and further expands the applicability of neuromorphic computational paradigms to embedded sensor systems widely employed in the IoT and industrial domains." @default.
- W4313503347 created "2023-01-06" @default.
- W4313503347 creator A5005432629 @default.
- W4313503347 creator A5010173029 @default.
- W4313503347 creator A5011857762 @default.
- W4313503347 creator A5032058759 @default.
- W4313503347 creator A5035474519 @default.
- W4313503347 date "2022-12-21" @default.
- W4313503347 modified "2023-10-14" @default.
- W4313503347 title "Spike encoding techniques for IoT time-varying signals benchmarked on a neuromorphic classification task" @default.
- W4313503347 cites W1536018596 @default.
- W4313503347 cites W1548049363 @default.
- W4313503347 cites W1857623347 @default.
- W4313503347 cites W1878915617 @default.
- W4313503347 cites W1967294650 @default.
- W4313503347 cites W1968311960 @default.
- W4313503347 cites W1973566875 @default.
- W4313503347 cites W1976433270 @default.
- W4313503347 cites W1995875735 @default.
- W4313503347 cites W2017634428 @default.
- W4313503347 cites W2044534939 @default.
- W4313503347 cites W2063695057 @default.
- W4313503347 cites W2065188087 @default.
- W4313503347 cites W2083250197 @default.
- W4313503347 cites W2089316513 @default.
- W4313503347 cites W2099848132 @default.
- W4313503347 cites W2105580042 @default.
- W4313503347 cites W2107662531 @default.
- W4313503347 cites W2112408199 @default.
- W4313503347 cites W2114249141 @default.
- W4313503347 cites W2118718620 @default.
- W4313503347 cites W2119836326 @default.
- W4313503347 cites W2124354910 @default.
- W4313503347 cites W2130459697 @default.
- W4313503347 cites W2134172620 @default.
- W4313503347 cites W2134313929 @default.
- W4313503347 cites W2140362090 @default.
- W4313503347 cites W2144187604 @default.
- W4313503347 cites W2144205281 @default.
- W4313503347 cites W2153041354 @default.
- W4313503347 cites W2153601172 @default.
- W4313503347 cites W2155776568 @default.
- W4313503347 cites W2173873847 @default.
- W4313503347 cites W2190569986 @default.
- W4313503347 cites W2292222414 @default.
- W4313503347 cites W2408153095 @default.
- W4313503347 cites W2443530087 @default.
- W4313503347 cites W2513853720 @default.
- W4313503347 cites W2547386190 @default.
- W4313503347 cites W2604594744 @default.
- W4313503347 cites W2612541527 @default.
- W4313503347 cites W2620661538 @default.
- W4313503347 cites W2625915976 @default.
- W4313503347 cites W2748617861 @default.
- W4313503347 cites W2749476078 @default.
- W4313503347 cites W2775079417 @default.
- W4313503347 cites W2779025322 @default.
- W4313503347 cites W2783525259 @default.
- W4313503347 cites W2788415486 @default.
- W4313503347 cites W2795101670 @default.
- W4313503347 cites W2798878556 @default.
- W4313503347 cites W2806066966 @default.
- W4313503347 cites W2807894615 @default.
- W4313503347 cites W2897070044 @default.
- W4313503347 cites W2898350988 @default.
- W4313503347 cites W2904620099 @default.
- W4313503347 cites W2941300701 @default.
- W4313503347 cites W2955596007 @default.
- W4313503347 cites W2963741408 @default.
- W4313503347 cites W2969335882 @default.
- W4313503347 cites W2972660824 @default.
- W4313503347 cites W2973017734 @default.
- W4313503347 cites W2985361718 @default.
- W4313503347 cites W3003360284 @default.
- W4313503347 cites W3038315492 @default.
- W4313503347 cites W3043133474 @default.
- W4313503347 cites W3081878198 @default.
- W4313503347 cites W3119554819 @default.
- W4313503347 cites W3128348732 @default.
- W4313503347 cites W3134784623 @default.
- W4313503347 cites W3154128550 @default.
- W4313503347 cites W3170094950 @default.
- W4313503347 cites W3183719272 @default.
- W4313503347 cites W4206609022 @default.
- W4313503347 cites W4206727444 @default.
- W4313503347 cites W4210357113 @default.
- W4313503347 cites W4220955212 @default.
- W4313503347 cites W4238992704 @default.
- W4313503347 cites W4243734861 @default.
- W4313503347 cites W4293054325 @default.
- W4313503347 cites W4308937689 @default.
- W4313503347 doi "https://doi.org/10.3389/fnins.2022.999029" @default.
- W4313503347 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36620463" @default.
- W4313503347 hasPublicationYear "2022" @default.
- W4313503347 type Work @default.
- W4313503347 citedByCount "1" @default.
- W4313503347 countsByYear W43135033472023 @default.
- W4313503347 crossrefType "journal-article" @default.
- W4313503347 hasAuthorship W4313503347A5005432629 @default.
- W4313503347 hasAuthorship W4313503347A5010173029 @default.