Sensing tongue movements enables various applications in hands-free interaction and alternative communication. We propose BARTON, a BARometer based low-power and robust TONgue movement sensing system. Using a low samp...
详细信息
ISBN:
(纸本)9781538632086
Sensing tongue movements enables various applications in hands-free interaction and alternative communication. We propose BARTON, a BARometer based low-power and robust TONgue movement sensing system. Using a low sampling rate of below 50 Hz, and only extracting simple temporal features from in-ear pressure signals, we demonstrate that it is plausible to distinguish important tongue gestures (left, right, forward) at low power consumption. We prototype BARTON with commodity earpieces integrated with COTS barometers for in-ear pressure sensing and an ARM micro-controller for signal processing. Evaluations show that BARTON yields 94% classification accuracy and 8.4 mW power consumption, which achieves comparable accuracy, but consumes 44 times lower energy than the state-of-the-art microphone-based solutions. BARTON is also robust to head movements and operates with music played directly from earphones.
作者：
Akandeh, AtraSalem, Fathi M.Circuits
Systems and Neural Networks Laboratory Computer Science and Engineering Electrical Computer Engineering Michigan State University East LansingMI48864-1226
We present five variants of the standard Long Shortterm Memory (LSTM) recurrent neural networks by uniformly reducing blocks of adaptive parameters in the gating mechanisms. For simplicity, we refer to these models as...
详细信息
作者：
Akandeh, AtraSalem, Fathi M.Circuits
Systems and Neural Networks Laboratory Computer Science and Engineering Electrical Computer Engineering Michigan State University East LansingMI48864-1226
This is part II of three-part work. Here, we present a second set of inter-related five variants of simplified Long Short-term Memory (LSTM) recurrent neural networks by further reducing adaptive parameters. Two of th...
详细信息
作者：
Akandeh, AtraSalem, Fathi M.Circuits
Systems and Neural Networks Laboratory Computer Science and Engineering Electrical Computer Engineering Michigan State University East LansingMI48864-1226
This is part III of three-part work. In parts I and II, we have presented eight variants for simplified Long Short Term Memory (LSTM) recurrent neural networks (RNNs). It is noted that fast computation, specially in c...
详细信息
A typical cyber-physical system (CPS) refers to a system that features a tight integration of computation, networking, and physical elements for interactions between cyber and physical spaces. The Internet of Things (...
详细信息
A typical cyber-physical system (CPS) refers to a system that features a tight integration of computation, networking, and physical elements for interactions between cyber and physical spaces. The Internet of Things (IoT) is considered to be the networking infrastructure of CPS. Applications of CPS cover numerous smart-world research areas that our daily life depends upon, including smart transportation, smart electrical power grid, smart cities, smart medical systems, smart manufacturing systems, and others. While major research on improving the efficiency and reliability of CPS by using advanced information and communication technologies has been conducted, the risks of cyberspace security and privacy breaches in CPS need to be seriously investigated before a massive deployment of CPS technologies can or should be realized.
Quantum key distribution (QKD) provides secure keys resistant to code-breaking quantum computers. As headed towards commercial application, it is crucial to guarantee the practical security of QKD systems. However, th...
详细信息
Cooperative localization has emerged as a promising technique which can complement or even replace global positioning systems (GPS) in many practical scenarios, such as GPS-denied environments. In this paper, we conce...
详细信息
In the vegetable greenhouse control technology transformation, intelligent control will become the key technology of it CO_2 is one of the main sources of photosynthesis of crops. Due to the closure of the greenhouse,...
详细信息
In the vegetable greenhouse control technology transformation, intelligent control will become the key technology of it CO_2 is one of the main sources of photosynthesis of crops. Due to the closure of the greenhouse, CO_2 concentrations indoor will be much lower than outdoor without new CO_2 injection, which is not conducive to crop growth. A neural network control algorithm based on structure and parameters of improved genetic algorithm training is proposed in this paper. It adopts a parallel fuzzy inference network, which has the characteristics of adaptive self-learning, and the controller obtained from the algorithm is used to control the input of CO_2 in the greenhouse. This method overcomes the shortcomings of the need for large amounts of data transmission and accurate mathematical models of existing control methods and uses Matlab to simulate. The simulation results show that the method is effective.
We report on a compact passive mode-locked Er:fiber ring laser operated at the fundamental repetition rate of 517 MHz, which we believe is the highest fundamental repetition rate ever reported in a ring cavity fiber *...
详细信息
We report on a compact passive mode-locked Er:fiber ring laser operated at the fundamental repetition rate of 517 MHz, which we believe is the highest fundamental repetition rate ever reported in a ring cavity fiber *** key technique is the employment of two innovative high-power wavelength domain multiplexer collimators with all gain fiber cavity suited for the high power(up to 2 W) pumping. The laser is featured with a direct chirpfree output pulse, which is 97 fs without extracavity compression at an average output power of 90 mW.
We report the composable security analysis for continuous-variablemeasurementdevice- independent quantum key distribution protocol, in which detection is conducted by an untrusted third party and naturally defend all ...
详细信息
暂无评论