The aim of this paper is to present a novel indoor human activity recognition system designated for ambient. assisted living environments. To overcome the drawbacks of current solutions in terms of equipment costs and...
详细信息
ISBN:
(纸本)9781728190808
The aim of this paper is to present a novel indoor human activity recognition system designated for ambient. assisted living environments. To overcome the drawbacks of current solutions in terms of equipment costs and computational complexity, we propose a simple yet robust activity recognition system that combines the output of an activity classification algorithm using smartphone sensors such as accelerometer and gyroscope with a Beacon-based indoor localization predictor to detect more complex activities based on a decision rule system. For the multiclass classification algorithm we employ a ConvL-STM algorithm, while for the positioning system we propose an ensemble based solution combining Multilayer Perceptron with Gradient Boosted Regression and k Nearest Neighbors. Our solution has been tested in a controlled home environment setup achieving an average localization error of 0.4m while for the final activity recognition system we report an accuracy of 91.0% concluding that the proposed solution is accurate enough to be integrated as a monitoring tool facility within ambient assisted living systems.
In today’s environment the aim of wireless sensor network is not restricted to data gathering. But also focus on extraction of useful information. Data aggregation is the term used for extraction of useful informatio...
详细信息
Up to now a distributed optical fiber Temperature sensor (DTS) based on the Raman scattering exhibits a relatively low characteristic causes sharp temperature changes to be improved. Modeling metrological characterist...
详细信息
ISBN:
(纸本)9781728180960
Up to now a distributed optical fiber Temperature sensor (DTS) based on the Raman scattering exhibits a relatively low characteristic causes sharp temperature changes to be improved. Modeling metrological characteristics has a long history but essential progress did not achieved. This paper presents a novel technique of the extremal filtration developed to improve the DTS temperature and partially spatial resolution. The algorithm is based on wavelet transformation of backscattered anti-Stokes and Stokes signals and deconvolution on high-frequency components with total regularization of variations. Experimental results correctly agree with real modeling values with denoising ones. The advantage is the ability to reconstruct temperature with 0.01 degree accuracy at fixed spatial resolution. We present a lot of simulations and figures demonstrated the efficacy of the proposed technique.
In this paper, architecture of a digital thermal sensor has been analyzed and developed using 10nm Complementary Metal-Oxide Semiconductor (CMOS) technology. This work proposed to integrate the bandgap-based voltage r...
详细信息
ISBN:
(纸本)9781728148762
In this paper, architecture of a digital thermal sensor has been analyzed and developed using 10nm Complementary Metal-Oxide Semiconductor (CMOS) technology. This work proposed to integrate the bandgap-based voltage reference with Analog-to-Digital-Converter (ADC) to realize a digital thermal sensor with improved accuracy. The voltage reference is designed with. 1% inaccuracy from -40 degrees C to 130 degrees C, with a temperature coefficient of 0.64 ppm/degrees Celsius, Power supply rejection ratio (PSRR) of -40 dB at 10 GHz and a line regulation of 0.12 %/V. Analog voltages generated by Bandgap Reference (BGR) are fed to the ADC having two inputs from a voltage reference for further processing. One is bandgap voltage that is the reference voltage, and the other one is Emitter-Base voltage of a pnp transistor that, is a Complementary to absolute temperature (CTAT) voltage. With These two input voltages, the 8-bit ADC, generates unique raw code at respective temperatures varying from -40 degrees C to 130 degrees C with 10 degrees C step size. Calibration is done then to convert the respective raw codes into the equivalent temperature values. The contribution of this work is to present a design of the bandgap voltage reference and its integration into an ADC, which serves as a temperature measurement device using Cadence Virtuoso tool.
Most off-the-shelf wearable devices do not provide reliable synchronization interfaces, causing multi-device sensing and machine learning approaches, e.g. for activity recognition, still to suffer from inaccurate cloc...
详细信息
ISBN:
(纸本)9781665404242;9781665447249
Most off-the-shelf wearable devices do not provide reliable synchronization interfaces, causing multi-device sensing and machine learning approaches, e.g. for activity recognition, still to suffer from inaccurate clock sources and unmatched time. Instead of using active online synchronization techniques, such as those based on bidirectional wireless communication, we propose in this work to use the human heartbeat as a reference signal that is continuously and ubiquitously available throughout the entire body surface. We introduce PulSync, a novel approach that enables the alignment of sensor data across multiple devices utilizing the unique fingerprint-like character of the heart rate variability interval function. In an evaluation on a dataset from 25 subjects, we demonstrate the reliable alignment of independent ECG recordings with a mean accuracy of -0.71±3.44 samples, respectively -2.86±11.43 ms at 250 Hz sampling rate.
The paper deals with the use of IoT technology for distributed collection of environmental data, focused mainly on local meteorology in urbanized environment. The requirements for a reliable and long-term use of IoT s...
详细信息
ISBN:
(纸本)9783030299934;9783030299927
The paper deals with the use of IoT technology for distributed collection of environmental data, focused mainly on local meteorology in urbanized environment. The requirements for a reliable and long-term use of IoT sensor network and the communication platform between nodes are summarized, with an emphasis placed on (data) reliability and long-term exterior use. Discussed is used technology, solution of data collection using IoT technologies, energy management of measuring nodes and network structure. Procedures for time series resampling with pseudorandom sampling are described for data processing.
The work implements the common DC bus electric vehicles (EVs) charging infrastructure based on hybrid renewable energy sources such as solar photovoltaic (PV) and fuel cell. The requisite to incorporate distributed en...
详细信息
ISBN:
(纸本)9781665447539
The work implements the common DC bus electric vehicles (EVs) charging infrastructure based on hybrid renewable energy sources such as solar photovoltaic (PV) and fuel cell. The requisite to incorporate distributed energy resources (DERs) is attributed to the escalating concern for decarbonisation with improved power quality requirements. Furthermore, the bidirectional flow of power enables the transition between modes of grid presence/absence. The utilization of an adaptive comb filter is achieved for satisfactory operation during mode with synchronization ability along with power transfer proficiency and improved power quality requirements. The utilization of common DC bus charging mechanism for EVs, facilitates fast charging capability at higher voltage levels. Thus, for validation and corroboration of the system behavior, its performance is authenticated during weak grid conditions in conjunction with grid connected/islanded modes of operation.
Increasing air pollution and depletion of fossil fuels are pushing the world towards renewable energy implementation. Renewable sources such as Solar Photovoltaics (PV) and Wind power are stochastic, and implementatio...
详细信息
The fifth generation (5G) mobile communication system will change the world through intelligent mobile devices and flexible networks to offer a new wide range of applications. mmWave radio propagation combined with a ...
详细信息
ISBN:
(纸本)9781665426060
The fifth generation (5G) mobile communication system will change the world through intelligent mobile devices and flexible networks to offer a new wide range of applications. mmWave radio propagation combined with a variety of new frequencies and bandwidth creates new radio measurement challenges. There are major limitations when it comes to mmWave components and measuring instruments. In this work we have designed and built a 7-GHz measuring system intended for in-situ channel characterization in environments where transmitters and receivers are located at different heights, like e.g. wireless sensor network installations. Such configurations are likely to be commonplace with the advent of e.g. Industry 4.0. The system has been tested in space experiments, where the distance and height between transmitter and receiver were changed. In addition, wave propagation behavior was studied through different materials placed between transmitter and receiver. The measurement system presented in this paper will provide an insight into the design of similar 5G test systems.
As a memory-based distributed big data computing framework, Spark has been widely used in big data processing systems. However, during the execution of Spark, due to the imbalance of input data distribution and the sh...
详细信息
ISBN:
(纸本)9781665408790
As a memory-based distributed big data computing framework, Spark has been widely used in big data processing systems. However, during the execution of Spark, due to the imbalance of input data distribution and the shortage of existing data partitioners in Spark, it is easy to cause partition skew problem and reduce the execution efficiency of Spark. Aiming at this problem, this paper proposes a balanced Spark data partitioner called BSDP (Balanced Spark Data Partitioner). By deeply analyzing the partitioning characteristics of Shuffle intermediate data, the Spark Shuffle intermediate data equalization partitioning model is established. The model aims to minimize the partition skew and find a Shuffle intermediate data equalization partitioning strategy. Based on the model, this paper designs and implements a data equalization partitioning algorithm of BSDP. This algorithm transforms the Shuffle intermediate data equalization partitioning problem into a classic List-Scheduling task scheduling problem, effectively realizes the balanced partitioning of Shuffle intermediate data. The experiment verifies that the BSDP can effectively realize the balanced partitioning of the Shuffle intermediate data and improve the execution efficiency of Spark.
暂无评论