{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T19:00:22Z","timestamp":1784142022194,"version":"3.55.0"},"reference-count":28,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T00:00:00Z","timestamp":1723680000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"US Air Force Office of Scientific Research","award":["FA8655-20-1-7037"],"award-info":[{"award-number":["FA8655-20-1-7037"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>The potential of neuromorphic (NM) solutions often lies in their low-SWaP (Size, Weight, and Power) capabilities, which often drive their application to domains that could benefit from this. Nevertheless, spiking neural networks (SNNs), with their inherent time-based nature, present an attractive alternative also for areas where data features are present in the time dimension, such as time series forecasting. Time series data, characterized by seasonality and trends, can benefit from the unique processing capabilities of SNNs, which offer a novel approach for this type of task. Additionally, time series data can serve as a benchmark for evaluating SNN performance, providing a valuable alternative to traditional datasets. However, the challenge lies in the real-valued nature of time series data, which is not inherently suited for SNN processing. In this work, we propose a novel spike-encoding mechanism and two loss functions to address this challenge. Our encoding system, inspired by NM event-based sensors, converts the derivative of a signal into spikes, enhancing interoperability with the NM technology and also making the data suitable for SNN processing. Our loss functions then optimize the learning of subsequent spikes by the SNN. We train a simple SNN using SLAYER as a learning rule and conduct experiments using two electricity load forecasting datasets. Our results demonstrate that SNNs can effectively learn from encoded data, and our proposed DecodingLoss function consistently outperforms SLAYER\u2019s SpikeTime loss function. This underscores the potential of SNNs for time series forecasting and sets the stage for further research in this promising area of research.<\/jats:p>","DOI":"10.3390\/computers13080202","type":"journal-article","created":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T04:29:57Z","timestamp":1723782597000},"page":"202","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Time Series Forecasting via Derivative Spike Encoding and Bespoke Loss Functions for Spiking Neural Networks"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8963-5050","authenticated-orcid":false,"given":"Davide Liberato","family":"Manna","sequence":"first","affiliation":[{"name":"Neuromorphic Sensor Signal Processing (NSSP) Lab, Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1XW, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2370-6562","authenticated-orcid":false,"given":"Alex","family":"Vicente-Sola","sequence":"additional","affiliation":[{"name":"Neuromorphic Sensor Signal Processing (NSSP) Lab, Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1XW, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5905-6816","authenticated-orcid":false,"given":"Paul","family":"Kirkland","sequence":"additional","affiliation":[{"name":"Neuromorphic Sensor Signal Processing (NSSP) Lab, Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1XW, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2431-2749","authenticated-orcid":false,"given":"Trevor Joseph","family":"Bihl","sequence":"additional","affiliation":[{"name":"Air Force Research Laboratory (AFRL), Wright-Patterson AFB, Dayton, OH 45433, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7256-0897","authenticated-orcid":false,"given":"Gaetano","family":"Di Caterina","sequence":"additional","affiliation":[{"name":"Neuromorphic Sensor Signal Processing (NSSP) Lab, Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1XW, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,8,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"022501","DOI":"10.1088\/2634-4386\/ac4a83","article-title":"2022 roadmap on neuromorphic computing and engineering","volume":"2","author":"Christensen","year":"2022","journal-title":"Neuromorphic Comput. Eng."},{"key":"ref_2","unstructured":"Vicente-Sola, A., Manna, D.L., Kirkland, P., Di Caterina, G., and Bihl, T. (2022). Evaluating the temporal understanding of neural networks on event-based action recognition with DVS-Gesture-Chain. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Iyer, L.R., Chua, Y., and Li, H. (2021). Is neuromorphic mnist neuromorphic? analyzing the discriminative power of neuromorphic datasets in the time domain. Front. Neurosci., 15.","DOI":"10.3389\/fnins.2021.608567"},{"key":"ref_4","unstructured":"Box, G.E.P., Reinsel, G.C., and Jenkins, G.M. (2015). Time Series Analysis 5e, John Wiley & Sons."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"902","DOI":"10.1016\/j.rser.2017.02.085","article-title":"A review on time series forecasting techniques for building energy consumption","volume":"74","author":"Deb","year":"2017","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_6","first-page":"2162","article-title":"A Comparative Study of Crime Event Forecasting Using ARIMA Versus LSTM Model","volume":"102","author":"Muthamizharasan","year":"2024","journal-title":"J. Theor. Appl. Inf. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Percival, D.B., and Walden, A.T. (2000). Wavelet Methods for Time Series Analysis, Cambridge University Press.","DOI":"10.1017\/CBO9780511841040"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Bloomfield, P. (2000). Fourier Analysis of Time Series, John Wiley & Sons. [2nd ed.].","DOI":"10.1002\/0471722235"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1109\/JETCAS.2019.2911739","article-title":"E-LSTM: An Efficient Hardware Architecture for Long Short-Term Memory","volume":"9","author":"Wang","year":"2019","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Nan, G., Wang, C., Liu, W., and Lombardi, F. (2020, January 10\u201321). DC-LSTM: Deep Compressed LSTM with Low Bit-Width and Structured Matrices. Proceedings of the 2020 IEEE International Symposium on Circuits and Systems (ISCAS), Online.","DOI":"10.1109\/ISCAS45731.2020.9180869"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"044009","DOI":"10.1088\/2634-4386\/ac999b","article-title":"Simple and complex spiking neurons: Perspectives and analysis in a simple STDP scenario","volume":"2","author":"Manna","year":"2022","journal-title":"Neuromorphic Comput. Eng."},{"key":"ref_12","unstructured":"Weidel, P., and Sheik, S. (2021). WaveSense: Efficient temporal convolutions with spiking neural networks for keyword spotting. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4234","DOI":"10.1038\/s41467-021-24427-8","article-title":"An adaptive threshold neuron for recurrent spiking neural networks with nanodevice hardware implementation","volume":"12","author":"Shaban","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"044001","DOI":"10.1088\/2634-4386\/ac8bef","article-title":"Keys to accurate feature extraction using residual spiking neural networks","volume":"2","author":"Manna","year":"2022","journal-title":"Neuromorphic Comput. Eng."},{"key":"ref_15","unstructured":"Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., and Garnett, R. (2018). SLAYER: Spike Layer Error Reassignment in Time. Advances in Neural Information Processing Systems 31, Curran Associates, Inc."},{"key":"ref_16","unstructured":"Gerstner, W., Kistler, W.M., Naud, R., and Paninski, L. (2009). Neuronal Dynamics, Cambridge University Press."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yarga, S.Y.A., Rouat, J., and Wood, S. (2022, January 27\u201329). Efficient spike encoding algorithms for neuromorphic speech recognition. Proceedings of the International Conference on Neuromorphic Systems 2022, Knoxville, TN, USA.","DOI":"10.1145\/3546790.3546803"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Sharma, V., and Srinivasan, D. (2010, January 18\u201323). A spiking neural network based on temporal encoding for electricity price time series forecasting in deregulated markets. Proceedings of the 2010 International Joint Conference on Neural Networks (IJCNN), Barcelona, Spain.","DOI":"10.1109\/IJCNN.2010.5596676"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"5023","DOI":"10.1016\/j.procs.2021.09.280","article-title":"Financial Time Series Forecasting: Comparison of Traditional and Spiking Neural Networks","volume":"192","author":"Kozina","year":"2021","journal-title":"Procedia Comput. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Reid, D., Hussain, A.J., and Tawfik, H. (2014). Financial Time Series Prediction Using Spiking Neural Networks. PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0103656"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Aguilar Madrid, E., and Antonio, N. (2021). Short-Term Electricity Load Forecasting with Machine Learning. Information, 12.","DOI":"10.3390\/info12020050"},{"key":"ref_22","first-page":"11106","article-title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","volume":"35","author":"Zhou","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2333","DOI":"10.1109\/JSSC.2014.2342715","article-title":"A 240 \u00d7 180 130 dB 3 \u03bcs Latency Global Shutter Spatiotemporal Vision Sensor","volume":"49","author":"Brandli","year":"2014","journal-title":"IEEE J.-Solid-State Circuits"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1007\/BF00057939","article-title":"The enemy within: Autocorrelation bias in content analysis of narratives","volume":"30","author":"Hogenraad","year":"1997","journal-title":"Comput. Humanit."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"103600","DOI":"10.1016\/j.cities.2022.103600","article-title":"Removing spatial autocorrelation in urban scaling analysis","volume":"124","author":"Xiao","year":"2022","journal-title":"Cities"},{"key":"ref_26","unstructured":"(2024, August 05). Lava: A Software Framework for Neuromorphic Computing. Available online: https:\/\/github.com\/lava-nc\/lava."},{"key":"ref_27","first-page":"620","article-title":"Recherches Quantitatives sur l\u2019Excitation Electrique des Nerfs Trait\u00e9e comme une Polarization","volume":"9","author":"Lapicque","year":"1907","journal-title":"J. Physiol. Pathol. Gen."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1007\/s11265-022-01772-5","article-title":"Efficient Neuromorphic Signal Processing with Resonator Neurons","volume":"94","author":"Frady","year":"2022","journal-title":"J. Signal Process. Syst."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/13\/8\/202\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:37:19Z","timestamp":1760110639000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/13\/8\/202"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,15]]},"references-count":28,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["computers13080202"],"URL":"https:\/\/doi.org\/10.3390\/computers13080202","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,15]]}}}