Fall accidents are critical issues in an aging and aged society. Recently, many researchers developed "pre-impact fall detection systems" using deep learning to support wearable-based fall protection systems...
详细信息
Fall accidents are critical issues in an aging and aged society. Recently, many researchers developed "pre-impact fall detection systems" using deep learning to support wearable-based fall protection systems...
详细信息
Fall accidents are critical issues in an aging and aged society. Recently, many researchers developed "pre-impact fall detection systems" using deep learning to support wearable-based fall protection systems for preventing severe injuries. However, most works only employed simple neural network models instead of complex models considering the usability in resource-constrained mobile devices and strict latency requirements. In this work, we propose a novel pre-impact fall detection via CNN-ViT knowledge distillation, namely PreFallKD, to strike a balance between detection performance and computational complexity. The proposed PreFallKD transfers the detection knowledge from the pre-trained teacher model (vision transformer) to the student model (lightweight convolutional neural networks). Additionally, we apply data augmentation techniques to tackle issues of data imbalance. We conduct the experiment on the KFall public dataset and compare PreFallKD with other state-of-the-art models. The experiment results show that PreFallKD could boost the student model during the testing phase and achieves reliable F1-score (92.66%) and lead time (551.3 ms).
Identifying influential people as a node in a graph theory commonly calculated by social network analysis. The social network data has the user as node and edge as relation forming a friend relation graph. This resear...
Identifying influential people as a node in a graph theory commonly calculated by social network analysis. The social network data has the user as node and edge as relation forming a friend relation graph. This research is conducting different meaning of every nodes relation in the social network. Ontology was perfect match science to describe the social network data as conceptual and domain. Ontology gives essential relationship in a social network more than a current graph. Ontology proposed as a standard for knowledge representation for the semantic web by World Wide Web Consortium. The formal data representation use Resource Description Framework (RDF) and Web Ontology Language (OWL) which is strategic for Open Knowledge-Based website data. Ontology used in the semantic description for a relationship in the social network, it is open to developing semantic based relationship ontology by adding and modifying various and different relationship to have influential people as a conclusion. This research proposes a model using OWL and RDF for influential people identification in the social network. The study use degree centrality, between ness centrality, and closeness centrality measurement for data validation. As a conclusion, influential people identification in Facebook can use proposed Ontology model in the Group, Photos, Photo Tag, Friends, Events and Works data.
The research is focused on designing collaborative learning-oriented framework fulfilment service in teaching SQL Oracle 10g. Framework built a foundation of academic fulfilment service performed by a layer of the wor...
The research is focused on designing collaborative learning-oriented framework fulfilment service in teaching SQL Oracle 10g. Framework built a foundation of academic fulfilment service performed by a layer of the working unit in collaboration with program Studi Manajemen Informatika. In the design phase defined what form of collaboration models and information technology proposed for program Studi Manajemen Informatika by using a framework of collaboration inspired by the stages of modelling a Service Oriented Architecture (SOA). Stages begin with analyzing subsystems, this activity is used to determine subsystem involved and reliance as well as workflow between the subsystems. After the service can be identified, the second phase is designing the component specifications, which details the components that are implemented in the service to include the data, rules, services, profiles can be configured, and variations. The third stage is to allocate service, set the service to the subsystems that have been identified, and its components. Implementation framework contributes to the teaching guides and application architecture that can be used as a landing realize an increase in service by applying information technology.
Modification planning of business transformation involving technological utilization required a system of transition and migration planning process. Planning of system migration activity is the most important. The mig...
Modification planning of business transformation involving technological utilization required a system of transition and migration planning process. Planning of system migration activity is the most important. The migration process is including complex elements such as business re-engineering, transition scheme mapping, data transformation, application development, individual involvement by computer and trial interaction. TOGAF ADM is the framework and method of enterprise architecture implementation. TOGAF ADM provides a manual refer to the architecture and migration planning. The planning includes an implementation solution, in this case, IT solution, but when the solution becomes an IT operational planning, TOGAF could not handle it. This paper presents a new model framework detail transitions process of integration between TOGAF and ITIL. We evaluated our models in field study inside a private university.
Open Geospatial Consortium (OGC) has a standard for cartographic over web service; there are Web Map Service (WMS) used by MapServer, Web Feature Service (WFS), and Web Map Tile Service. There is research on comparing...
Open Geospatial Consortium (OGC) has a standard for cartographic over web service; there are Web Map Service (WMS) used by MapServer, Web Feature Service (WFS), and Web Map Tile Service. There is research on comparing two cartography information between WMS and WFS, so this research extends to proposed solution by comparing WMS and WMTS computation cost and created a product called Sampeu. Sampeu has proposed a solution by creating WMTS protocol over WMS. WMTS work on the tile-ing system where the data transform from big picture to part of the Tile is. A lot of Tile making a pyramid of cartography and serving to client one by one, so the computation cost can be decreasing.
Many researches proposes geospatial web framework over the popularity of the Internet. Based on that, research on securing geospatial web framework is necessary. In this research aimed Peuyeum. Peuyeum is geospatial w...
Many researches proposes geospatial web framework over the popularity of the Internet. Based on that, research on securing geospatial web framework is necessary. In this research aimed Peuyeum. Peuyeum is geospatial web framework with Encrypted Universal Resource Locator (URL). Advance Encryption Standard (AES)-Cipher Block Chaining (CBC) chosen as the method in this research. By calculating attack time, the brute force attack will reduce by this approach and resistance time will improve.
Artificial intelligence (AI) has advanced rapidly and is becoming a cornerstone technology that drives innovation and efficiency in various industries. This paper examines the real-world application of AI in multiple ...
详细信息
Falls are the public health issue for the elderly all over the world since the fall-induced injuries are associated with a large amount of healthcare cost. Falls can cause serious injuries, even leading to death if th...
Falls are the public health issue for the elderly all over the world since the fall-induced injuries are associated with a large amount of healthcare cost. Falls can cause serious injuries, even leading to death if the elderly suffers a “long-lie.” Hence, a reliable fall detection (FD) system is required to provide an emergency alarm for first aid. Due to the advances in wearable device technology and artificial intelligence, some fall detection systems have been developed using machine learning and deep learning methods to analyze the signal collected from accelerometer and gyroscopes. In order to achieve better fall detection performance, an ensemble model that combines a coarse-fine convolutional neural network and gated recurrent unit is proposed in this study. The parallel structure design used in this model restores the different grains of spatial characteristics and capture temporal dependencies for feature representation. This study applies the FallAllD public dataset to validate the reliability of the proposed model, which achieves a recall, precision, and F-score of 92.54%, 96.13%, and 94.26%, respectively. The results demonstrate the reliability of the proposed ensemble model in discriminating falls from daily living activities and its superior performance compared to the state-of-the-art convolutional neural network long short-term memory (CNN-LSTM) for FD.
Falls are the public health issue for the elderly all over the world since the fall-induced injuries are associated with a large amount of healthcare cost. Falls can cause serious injuries, even leading to death if th...
详细信息
暂无评论