Using Language Model to Bootstrap Human Activity Recognition Ambient Sensors Based in Smart Homes

Long Short Term Memory (LSTM)-based structures have demonstrated their efficiency for daily living recognition activities in smart homes by capturing the order of sensor activations and their temporal dependencies. Nevertheless, they still fail in dealing with the semantics and the context of the sensors. More than isolated id and their ordered activation values, sensors also carry meaning. Indeed, their nature and type of activation can translate various activities. Their logs are correlated with each other, creating a global context. We propose to use and compare two Natural Language Processing embedding methods to enhance LSTM-based structures in activity-sequences classification tasks: Word2Vec, a static semantic embedding, and ELMo, a contextualized embedding. Results, on real smart homes datasets, indicate that this approach provides useful information, such as a sensor organization map, and makes less confusion between daily activity classes. It helps to better perform on datasets with competing activities of other residents or pets. Our tests show also that the embeddings can be pretrained on different datasets than the target one, enabling transfer learning. We thus demonstrate that taking into account the context of the sensors and their semantics increases the classification performances and enables transfer learning.

The Method of Static Semantic Map Construction Based on Instance Segmentation and Dynamic Point Elimination

Semantic information usually contains a description of the environment content, which enables mobile robot to understand the environment and improves its ability to interact with the environment. In high-level human–computer interaction application, the Simultaneous Localization and Mapping (SLAM) system not only needs higher accuracy and robustness, but also has the ability to construct a static semantic map of the environment. However, traditional visual SLAM lacks semantic information. Furthermore, in an actual scene, dynamic objects will reduce the system performance and also generate redundancy when constructing map. these all directly affect the robot’s ability to perceive and understand the surrounding environment. Based on ORB-SLAM3, this article proposes a new Algorithm that uses semantic information and the global dense optical flow as constraints to generate dynamic-static mask and eliminate dynamic objects. then, to further construct a static 3D semantic map under indoor dynamic environments, a fusion of 2D semantic information and 3D point cloud is carried out. the experimental results on different types of dataset sequences show that, compared with original ORB-SLAM3, both Absolute Pose Error (APE) and Relative Pose Error (RPE) have been ameliorated to varying degrees, especially on freiburg3-walking-xyz, the APE reduced by 97.78% from the original average value of 0.523, and RPE reduced by 52.33% from the original average value of 0.0193. Compared with DS-SLAM and DynaSLAM, our system improves real-time performance while ensuring accuracy and robustness. Meanwhile, the expected map with environmental semantic information is built, and the map redundancy caused by dynamic objects is successfully reduced. the test results in real scenes further demonstrate the effect of constructing static semantic maps and prove the effectiveness of our Algorithm.

Negative existentials

Negative existentials containing empty NPs are understood colloquially as representing how things stand in the world. Moreover, utterances of such sentences seem to express propositions or thoughts that are informative and true. Standard static semantic theories cannot provide a straightforward account of these intuitive phenomena. In such frameworks, sentences with empty NPs are considered as being unable to express truth-evaluable contents. This paper investigates two alternative theories of negative existentials. A common feature of these theories is that they adopt a dynamic approach to meaning. I will argue that neither of these alternatives provides a reassuring solution to the apparent truth-conditional problem generated by the utterances of negative existentials.

The DSD Schema Language and its Applications

XML (eXtensible Markup Language), a linear syntax for trees, has gathered a remarkable amount of interest in industry. The acceptance of XML opens new venues for the application of formal methods such as specification of abstract syntax tree sets and tree transformations. A user domain may be specified as a set of trees. For example, XHTML is a user domain corresponding to the set of XML documents that make sense as<br />HTML. A notation for defining such a set of XML trees is called a schema language. We believe that a useful schema notation must identify most of the syntactic<br />requirements that the documents in the user domain follow; allow efficient parsing; be readable to the user; allow a declarative default notation `a la CSS; and be<br />modular and extensible to support evolving classes of XML documents. In the present paper, we give a tutorial introduction to the DSD (Document Structure Description) notation as our bid on how to meet these requirements. The<br />DSD notation was inspired by industrial needs, and we show how DSDs help manage aspects of complex XML software through a case study about interactive voice<br />response systems (automated telephone answering systems, where input is through the telephone keypad or speech recognition). The expressiveness of DSDs goes beyond the DTD schema concept that is already<br />part of XML. We advocate the use of nonterminals in a top-down manner, coupled with boolean logic and regular expressions to describe how constraints on tree nodes depend on their context. We also support a general, declarative mechanism for inserting default elements and attributes that is reminiscent of Cascading<br />Style Sheets (CSS), a way of manipulating formatting instructions in HTML that is built into all modern browsers. Finally, we include a simple technique for evolving DSDs through selective redefinitions. DSDs are in many ways much more expressive than XML Schema (the schema language proposed by the W3C), but their syntactic and semantic definition in English is only 1/8th the size. Also, the DSD notation is self-describable: the syntax of legal DSD documents and all static semantic requirements can be captured in a DSD document, called the meta-DSD.