the proceedings contain 20 papers. the topics discussed include: is artificial intelligence (AI) taking over the world? are humans losing out to AI in the work place?;we all want to remain in our own homes;natural pur...
ISBN:
(纸本)9781450364874
the proceedings contain 20 papers. the topics discussed include: is artificial intelligence (AI) taking over the world? are humans losing out to AI in the work place?;we all want to remain in our own homes;natural pursuits for eye tracker calibration;respiration rate estimation with depth cameras: an evaluation of parameters;fewer samples for a longer life span: towards long-term wearable PPG analysis;mobile assisted living: smartwatch-based fall risk assessment for elderly people;analysis of a public repository for the study of automatic fall detection algorithms;exploring accelerometer-based step detection by using a wheeled walking frame;real-time joint axes estimation of the hip and knee joint during gait using inertial sensors;attribute representation for human activity recognition of manual order picking activities;theodor: a step towards smart home applications with electronic noses;a machine learning approach to violin bow technique classification: a comparison between IMU and MOCAP systems;using wrist-worn activity recognition for basketball game analysis;activity recognition using head worn inertial sensors;combining off-the-shelf image classifiers with transfer learning for activity recognition;dense 3D optical flow co-occurrence matrices for human activity recognition;towards a task-driven framework for multimodal fatigue analysis during physical and cognitive tasks;and outlining a novel framework for monitoring user's vital signs and activity data in caregiving facilities.
Over the past five years, we witnessed the world we live in entirely disrupted by improvements in artificial intelligence (AI), machine learning and control engineering. algorithms and machine learning are trading mil...
详细信息
Over the past five years, we witnessed the world we live in entirely disrupted by improvements in artificial intelligence (AI), machine learning and control engineering. algorithms and machine learning are trading millions of dollars in financial markets;they are predicting what people want to search for online;facial recognition helps police identify criminals. Soon, AI could be driving our cars and trains even airplanes, Intelligent Robotic and Control Engineering will have a fundamental impact on the society in the next few years.
Total Knee Replacement (TKR) is an increasingly common surgery worldwide. A significant contributor to TKR success is post-surgical rehabilitation. In this work, we present fun-Knee (TM), a novel sensor-equipped knee ...
详细信息
ISBN:
(纸本)9781509054824
Total Knee Replacement (TKR) is an increasingly common surgery worldwide. A significant contributor to TKR success is post-surgical rehabilitation. In this work, we present fun-Knee (TM), a novel sensor-equipped knee support complemented by mobile device-supported games, specifically designed for "gamified" TKR rehabilitation. Two inclinometers are used to measure the knee angle, which is used as the main input to the developed game. Human-Centered Design theory is applied throughout the game design to ensure a customized, dynamic gaming experience to maximize the pain distraction effect and to increase the exercise compliance and improve the rehabilitation outcome. Preliminary survey results collected from practicing physiotherapists show promising outcomes of the developed prototype, in terms of hardware and software characteristics, usability, clinical utility and overall effectiveness.
the different topologies and control strategies of multilevel inverters (MLIs) have been studied and discussed for more than two decades due to MLIs involved in many applications. the superior performance of MLIs tech...
详细信息
the different topologies and control strategies of multilevel inverters (MLIs) have been studied and discussed for more than two decades due to MLIs involved in many applications. the superior performance of MLIs technology has drawn tremendous interest among researchers from industry and academia in recent years. this paper describes the use of an improved of firefly algorithms in order to find the switching angles withthe optimum values of a single phase of modified cascaded H-Bridge Multilevel inverters (CHB-MLs) for five levels. Even though there are a lot of techniques of optimization in determining of switching angles, firefly algorithm still has an advantages due to this algorithm is taking less computation time and enables to minimize the harmonics problems of the output voltage and current waveforms of the modified CHB-MLIs. In order to verify the performance of the proposed algorithm an appropriate model has been developed based on MARLAB/SIMULINK. then the simulation results demonstrate be compared withthe results obtained using particle swarm optimization (PSO) and Newton Raphson (NR) algorithms and it is found that the proposed technique offers reduced total harmonic distortion (thD) of the voltage and current waveforms of modified CHB-MLIs with less computation period.
Martin Kotyrba, Eva Volna, Ivan Zelinka; 5thinternational Symposium on Intelligent Systems and algorithms, ISA 2018, AIP conference Proceedings, Volume 2116, I
Martin Kotyrba, Eva Volna, Ivan Zelinka; 5thinternational Symposium on Intelligent Systems and algorithms, ISA 2018, AIP conference Proceedings, Volume 2116, I
In this study, a robust language identification (LID) system is investigated with vowel region detection scheme incorporated at the front-end. the background noise is known to severely reduce language identification p...
详细信息
In this study, a robust language identification (LID) system is investigated with vowel region detection scheme incorporated at the front-end. the background noise is known to severely reduce language identification performance. In this work, Mel-frequency cepstral features extracted from the vowel regions instead of voiced speech are utilized for language identification system modeling. Experimentation is done using different vowel region detection algorithms on deep neural networks (DNN) and deep neural networks with attention (DNN-WA) based LID systems on IIIth Indian language dataset. Experimental results show that the accurate vowel region detection mechanism at the front-end of a LID system improved the performance in noisy environment.
Constant current (CC) / Constant voltage (CV) is the most optimum algorithm applied for lithium-ion battery charging used in EVs. However, major issue during this mode of charging are the switching transients. Subsequ...
详细信息
Constant current (CC) / Constant voltage (CV) is the most optimum algorithm applied for lithium-ion battery charging used in EVs. However, major issue during this mode of charging are the switching transients. Subsequently, smooth transition from CC to CV is required for minimizing switching losses and increasing the battery life expectancy. Generally, toggle switch is used to transit from CC to CV. It operates (CC to CV), when the output voltage reaches to predefined value of voltage. But due to the ripple in the output voltage, toggle switch changes its state from ON to OFF and OFF to ON. Hence, the output of the controller oscillate between CC to CV continuously. To mitigate this problem, a novel charging method, using Schmitt trigger, for optimum transition from CC to CV is proposed in this paper. Schmitt trigger operates in a specified band limit, which is decided by the voltage ripple. To verify this scheme, boost converter is modeled and its controllers for CC and CV mode are designed. Proposed scheme is implemented in MATLAB using real time simulator Opal-RT.
Tools and algorithms for the Construction and Analysis of Systems : 5thinternationalconference, Tacas '99, Held as Part of the Joint European conferences on theory and Practice of Software, Etaps '99, Amster...
详细信息
Tools and algorithms for the Construction and Analysis of Systems : 5thinternationalconference, Tacas '99, Held as Part of the Joint European conferences on theory and Practice of Software, Etaps '99, Amsterdam, the Netherlands, March 22-28, 1999 : Proceedings by Tacas '99 (1999 : Amsterdam, Netherlands); Cleaveland, W. R. (Walter Rance), 1961-; Etaps '99 (1999 : Amsterdam, Netherlands); published by Berlin ; New York : Springer
We discuss ideas and propose resources on humor facilitation, as an extension of previous work on this topic. Specifically, we describe a method for achieving humor facilitation as the combination of event detection a...
详细信息
ISBN:
(纸本)9783319586977;9783319586960
We discuss ideas and propose resources on humor facilitation, as an extension of previous work on this topic. Specifically, we describe a method for achieving humor facilitation as the combination of event detection and generation of funny comments. We focus on user's mistakes as the preferred unexpected and potentially humorous events. Moreover, we implemented an online testbed consisting of a humor facilitator and two interactive environments: a text editor and a video game. the system is meant to provide a tool for empirical evaluation of the proposed framework.
Shunt active power filter (SAPF) has been recognized as a feasible solution to current harmonics issues. In its controller, due to structure simplicity, synchronous reference frame (SRF) technique is best suited to be...
详细信息
Shunt active power filter (SAPF) has been recognized as a feasible solution to current harmonics issues. In its controller, due to structure simplicity, synchronous reference frame (SRF) technique is best suited to be applied in generating reference current. However, the existing SRF algorithm performs inefficiently due to limitations of numerical low-pass filter (LPF). Besides, the existing algorithm is as yet considered to have excessive features which are not required in the procedure of generating reference current. Most importantly, its dependency on traditional phase-locked loop (PLL) has greatly degraded its effectiveness when the source voltage is unbalanced and/or distorted. therefore, this paper presents a PLL-less SRF algorithm for generating reference current to effectively control performance of a SAPF developed based on three-level neutral-point-clamped (NPC) inverter. Specifically, three notable refinements are implemented: (1) eliminate the traditional use of LPF by replacing it with a mathematical-based average current detector; (2) reduce algorithm complexity by removing excessive features; (3) eliminate synchronization error of PLL by integrating a new self-tuning-filter (STF)-based synchronization technique. the proposed algorithm is created and assessed in MATLAB-Simulink. Simulation and experimental results are provided, demonstrating superiority of the proposed PLL-less SRF algorithm over the existing SRF algorithm.
暂无评论