Recently, the demand for human activity recognition has become more and more urgent. It is widely used in indoor positioning, medical monitoring, safe driving, etc. Existing activity recognition approaches require either the location information of the sensors or the specific domain knowledge, which are expensive, intrusive, and inconvenient for pervasive implementation. In this paper, a human activity recognition algorithm based on SDAE (Stacking Denoising Autoencoder) and LightGBM (LGB) is proposed. The SDAE is adopted to sanitize the noise in raw sensor data and extract the most effective characteristic expression with unsupervised learning. The LGB reveals the inherent feature dependencies among categories for accurate human activity recognition. Extensive experiments are conducted on four datasets of distinct sensor combinations collected by different devices in three typical application scenarios, which are human moving modes, current static, and dynamic behaviors of users. The experimental results demonstrate that our proposed algorithm achieves an average accuracy of 95.99%, outperforming other comparative algorithms using XGBoost, CNN (Convolutional Neural Network), CNN + Statistical features, or single SDAE.

The information really useful to humans must be the trinity of its three components, the form termed syntactic information, the meaning termed semantic information, and the utility termed pragmatic information. But the theory of information set up by Shannon in 1948 is a statistical theory of syntactic information. Thus, the trinity of information theories needs be established as urgently as possible. Such a theory of semantic information will be presented in the paper and it will also be proved that it is the semantic information that is the unique representative of the trinity. This is why the title of the paper is set to “a theory of semantic information” without mentioning the pragmatic information.

The ecological approach studied in this paper is a new level of information studies. It allows for achieving a better understanding of information processes in society as well as more efficient creation of information processing systems. At first, in Section 2, we describe and analyze ecological studies in different areas ranging from biology to technology to sociology to knowledge and information. Then, in Section 3, we present elements of general ecology building methodological and philosophical foundation for information ecology. In Section 4 and Section 5, we elaborate a concise definition of information ecology and further develop information ecology as a methodological base for information studies in general based on the concepts and principles of the general theory of information.

Training a generalized reliable model is a great challenge since sufficiently labeled data are unavailable in some open application scenarios. Few-shot learning (FSL) aims to learn new problems with only a few examples that can tackle this problem and attract extensive attention. This paper proposes a novel few-shot learning method based on double pooling squeeze and excitation attention (dSE) for the purpose of improving the discriminative ability of the model by proposing a novel feature expression. Specifically, the proposed dSE module adopts two types of pooling to emphasize features responding to foreground object channels. We employed both the pixel descriptor and channel descriptor to capture locally identifiable channel features and pixel features of an image (as opposed to traditional few-shot learning methods). Additionally, in order to improve the robustness of the model, we designed a new loss function. To verify the performance of the method, a large number of experiments were performed on multiple standard few-shot image benchmark datasets, showing that our framework can outperform several existing approaches. Moreover, we performed extensive experiments on three more challenging fine-grained few-shot datasets, the experimental results demonstrate that the proposed method achieves state-of-the-art performances. In particular, this work achieves 92.36% accuracy under the 5-way–5-shot classification setting of the Stanford Cars dataset.

Scientific methodology is widely accepted as macroscopic reflect of the scientific view on one hand and as the general guideline to a certain class of research works on the other hand. Therefore, methodology employment is extremely crucial in scientific research. Whether the methodology employed in a field of research works is proper would, to a large extent, determine whether the achievements in the field of research could be made. However, there is no one single general methodology existed that can be applied to all fields of research with success. Which of the methodology should be employed in a certain field of research depends on which kind of phenomenon is studied. This paper will discuss the methodology consideration for information Studies and the methodology of information ecology is recommended.