Technology Forecasting Using Deep Learning Neural Network: Taking the Case of Robotics

Abstract

Technology forecasting not only helps business managers to make the right decisions but also helps researchers to grasp the direction of technology development. Technology forecasting, which facilitates the identification of the development technologies with high potential, can be an effective tool to support the management and plan for the future research activities. For this purpose, this paper firstly constructs Multi-modal input based on deep learning (MIDL) text classification model to extract relevant SCI papers from Web of Science database from 1996 to 2019 for topic classification, and then apply the Ensemble Empirical Mode Decomposition (EEMD) and Long Short-Term Memory (LSTM) neural networks to build an EEMD-LSTM technology forecasting model to predict the future development of each research field. Besides, we verify the validity of the method by taking robotics as an example in this paper. The results show that the accuracy, recall and F1 of MIDL text classification model are 0.826, 0.822 and 0.824 respectively. As compared with the optimal results of other classification models, the accuracy, recall and F1 are improved by 4.1%, 3.5%, and 3.8% respectively. The mean MAPE of the EEMD-LSTM model is 7%, which is 11% lower than ARIMA, 8% lower than LSTM, and 10% lower than 2-layer-LSTM.

Quantitative Technology Forecasting: A Review of Trend Extrapolation Methods

“…LSTM (Long Short-Term Memory), introduced by Hochreiter and Schmidhuber (1997), is a special type of recurrent neural network (RNN) that is able to not only model sequential events with standard RNNs but learn much longer-term temporal dependencies between events than standard RNNs, which suffer the loss of ability to link information as the time steps between events increase. It has been used in a large variety of tasks, such as machine translation (Sutskever et al, 2014), speech recognition (Graves et al, 2013), and technology forecasting (Gui and Xu, 2021). In an LSTM unit, a memory cell is introduced, in addition to the existing hidden state of RNNs, to keep information of past events in memory for long periods of time.…”

Couplet Analysis of Linguistic Topology Using Deep Neural Networks in Cognitive Linguistics

“…According to the above statement, every language has its own topology. Although there may be different topologies in other aspects, the function of topology is to reasonably divide languages into different categories [ 17 , 18 ]. In the 19th century, some scholars focused on the lexical classification of languages in early linguistics, and this classification was regarded as the topological classification.…”

Monophonic Music Generation With a Given Emotion Using Conditional Variational Autoencoder

“…Being an important basis for human-machine interaction success, emotion recognition is also a popular field of exploration. Over the last decades, a wide range of deep learning techniques based on various models and databases [12], [13], research on feature extraction algorithms [14], [15], etc. have been conducted.…”