Hybrid Multi-Modal Deep Learning using Collaborative Concat Layer in Health Bigdata

Abstract

A health model based on data has various missing values depending on the user situation, and the accuracy of a health model requiring variables that the user cannot collect appears low. A deep learning health model is fitted by learning weights to increase accuracy. This implies that additional learning is required when the environment changes, such as when new variables are added or deleted depending on the user situation. In the process of applying a deep-learning-based health model to the user situation, accuracy may be degraded if learning is omitted. In this paper, we propose hybrid multimodal deep learning using a collaborative concat layer in health big data. The proposed method uses a machine learning technique to alleviate the issue caused by the change in the data observation range according to a change in the user situation, and occurring in multimodal health deep learning. It is a layer composed of the connection, input, and output of the model of the collaborative node (CN). A CN is a node that predicts absent variables through filtering using the similarity of input values. With CN, a collaborative concat layer (CCL) that handles missing values from the input of the health model can be configured, and the issue related to missing values occurring in the health model can be resolved. With the proposed CCL, it is possible to reuse existing models or construct new models through the concatenation of several single-modal deep learning models. By evaluating the effect on the input and output of the model according to the structural position of the CCL, various networks can be configured, and the performance of the single-modal model can be maintained. In particular, the accuracy of a deep learning model is more stable when the CCL is used, suggesting the experiment progress based on the assumption that a specific variable is absent depending on the user situation.

A multi-sensor cooperative detection target tracking method based on radar-optical linkage control

“…To achieve effective tracking of targets, it is necessary to establish the target's movement mode reasonably and select appropriate filtering and tracking methods. In the case of manoeuvring target QINGWEN LONG, WENJIN HE, LING YIN, WENXING WU movements, it is difficult to be precise with an accurate numerical model due to the lack of sufficient a priori [18]. Therefore, there are only a few more accurate movement models for simulation under different conditions.…”

A mini-review of machine learning in big data analytics: Applications, challenges, and prospects

“…Another thrilling revelation is that most studies [70,77,79,84,94,97,106,108,[116][117][118][119][120][121] used Deep Neural Networks (DNN), such as LSTM and Convolutional Neural Network (CNN), as shown in Fig. 6.…”

“…ML algorithm's hybridisation is an excellent technique to compensate for the weakness in the individual algorithm [9] . However, it was revealed that few studies out of 66 papers reviewed adopted it [70,83,85,88,101,102,107,108,118,122] . From Fig.…”

Specific Radar Recognition Based on Characteristics of Emitted Radio Waveforms Using Convolutional Neural Networks

“…The second CNN structure uses three structures similar to the model described above. The structures are connected by concatenate layer [63] and work together simulta neously processing PRI, PD parameters and TW to determine the class of input signals The last layer of this structure is the dense type and makes final recognition of the signa (Figure 8 and Table 4). The model described here is depicted in more detail in Figure 8.…”