“…The proposed methodology, being a generic one, can be extended to specific methods for different domain areas (along with the illustrated financial area) 31,[44][45][46][47][48] :…”
In a first study, this paper argues and demonstrates that spiking neural networks (SNN) can be successfully used for predictive and explainable modelling of multimodal streaming data. The paper proposes a new method, where both time series and on-line news are integrated as numerical streaming data in the same time domain and then used to train incrementally a SNN model. The connectivity and the spiking activity of the SNN are then analyzed through clustering and dynamic graph extraction to reveal on-line interaction between all input variables in regard to the predicted one. The paper answers the main research question of how to understand the dynamic interaction of time series and on-line news through their integrative modelling. It offers a new method to evaluate the efficiency of using on-line news on the predictive modelling of time series. Results on financial stock time series and online news are presented. In contrast to traditional machine learning techniques, the method reveals the dynamic interaction between stock variables and news and their dynamic impact on model accuracy when compared to models that do not use news information. Along with the used financial data, the method is applicable to a wide range of other multimodal time series and news data, such as economic, medical, environmental and social. The proposed method, being based on SNN, promotes the use of massively parallel and low energy neuromorphic hardware for multivariate on-line data modelling.
“…The proposed methodology, being a generic one, can be extended to specific methods for different domain areas (along with the illustrated financial area) 31,[44][45][46][47][48] :…”
In a first study, this paper argues and demonstrates that spiking neural networks (SNN) can be successfully used for predictive and explainable modelling of multimodal streaming data. The paper proposes a new method, where both time series and on-line news are integrated as numerical streaming data in the same time domain and then used to train incrementally a SNN model. The connectivity and the spiking activity of the SNN are then analyzed through clustering and dynamic graph extraction to reveal on-line interaction between all input variables in regard to the predicted one. The paper answers the main research question of how to understand the dynamic interaction of time series and on-line news through their integrative modelling. It offers a new method to evaluate the efficiency of using on-line news on the predictive modelling of time series. Results on financial stock time series and online news are presented. In contrast to traditional machine learning techniques, the method reveals the dynamic interaction between stock variables and news and their dynamic impact on model accuracy when compared to models that do not use news information. Along with the used financial data, the method is applicable to a wide range of other multimodal time series and news data, such as economic, medical, environmental and social. The proposed method, being based on SNN, promotes the use of massively parallel and low energy neuromorphic hardware for multivariate on-line data modelling.
“…TinyM2Net also enables the system and algorithm to incorporate fresh sensor data that are tailored to a variety of real-world settings. The suggested framework is built on a convolutional neural network, which has previously been recognized as one of the most promising methodologies for audio and visual data classification; [59]: a technique for addressing multimodal analytics within a single data processing approach in order to obtain a streamlined architecture that can fully use the potential of Big Data infrastructures' parallel processing.…”
Section: Multimodal ML Available Frameworkmentioning
Machine Learning (ML) and Deep Learning (DL) are derivatives of Artificial Intelligence (AI) that have already demonstrated their effectiveness in a variety of domains, including healthcare, where they are now routinely integrated into patients’ daily activities. On the other hand, data heterogeneity has long been a key obstacle in AI, ML and DL. Here, Multimodal Machine Learning (Multimodal ML) has emerged as a method that enables the training of complex ML and DL models that use heterogeneous data in their learning process. In addition, Multimodal ML enables the integration of multiple models in the search for a single, comprehensive solution to a complex problem. In this review, the technical aspects of Multimodal ML are discussed, including a definition of the technology and its technical underpinnings, especially data fusion. It also outlines the differences between this technology and others, such as Ensemble Learning, as well as the various workflows that can be followed in Multimodal ML. In addition, this article examines in depth the use of Multimodal ML in the detection and prediction of Cardiovascular Diseases, highlighting the results obtained so far and the possible starting points for improving its use in the aforementioned field. Finally, a number of the most common problems hindering the development of this technology and potential solutions that could be pursued in future studies are outlined.
“…The article selects the number of research and development institutions and the number of employees in research and development institutions; the second is the output of SATI, including the direct output of science and technology results and the transformation of science and technology results in two aspects, respectively, the number of published science and technology papers, the number of patent applications, effective invention patents, and technology market turnover are selected to reflect, the first two represent the direct output of science and technology results, and the latter two represent the transformation and marketization of science and technology results. The third aspect is the basic support of SATI, these are the prerequisites for the development of SATI, and the article selects four indicators most related to scientific research and development to reflect them, which are the number of higher education schools, the number of public libraries, the number of Internet access and the new fixed assets of urban scientific research and technology service industry [9][10]. The details of the indicator system are shown in Table 1.…”
Section: Construction Of the Index System Of Eg And The Level Of Deve...mentioning
In recent years, the global economy has been weak, and scientific and technological innovation (SATI) has become a new driving force for economic development (ED), while the construction of SATI requires a large amount of capital investment as a guarantee. As the core of modern economy, economic growth (EG) can rely on its own advantages to gather social idle funds to invest in ED, so it has a very good role in supporting and promoting the promotion of SATI. This paper takes Shaanxi Province as the main research object, and based on big data analysis (BDA), studies and analyzes the EG and technological innovation (TI) of the belt and road (BAR) region of Shaanxi Province. This paper plans to select the spatial econometric model of computer technology to estimate the financial support for SATI in the five northwestern provinces. By drawing on the good experience of EG and TI at home and abroad, and combining with the specific empirical and theoretical analysis results of the five northwest provinces, this paper analyzes the EG and TI of Shaanxi Province; The results show that Shaanxi Province needs to continue to strengthen the support of EG for SATI; We should also strengthen regional cooperation to form a good spatial spillover effect of EG and SATI; More importantly, we should seize the opportunity of the construction and development of the the BAR, give full play to regional advantages, and extensively absorb domestic and foreign EG funds to promote regional SATI.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.