Search

Activity recognition based on channel state information (CSI) plays an increasingly important role in human computer interaction. However most CSI activity recognition systems need to re-collect a large amount of samples and retrain model when they are used in new environments or recognize new types of activities, which greatly reduces the practicality of CSI activity recognition. To address this problem we design an adaptable CSI activity recognition system based on meta-learning, which only needs to fine-tune model with very little train effort when it is used in new environments or recognize new types of activities. Specifically, we first use meta-learning algorithm to get the pre-trained model that adapts to task distribution, when the environment or activity category changes, our system doesn't need to retrain the model and has maximal performance after updates the pre-trained model through one or more gradient steps computed with a small amount of samples from new activities. To prevent the loss of CSI time information after feature extraction with multi-layer CNN, we add time encoding on CSI data as the input of CNN neural network. Considering that CSI data may be labeled incorrectly during labeling process, we improve categorical cross entropy loss(CCE) to enhance the system's robustness to these mislabeled data. We test our system on the gesture dataset and the body activity dataset, and the experimental results show that our system achieves average accuracy of 72 percent with one sample of each new activity and 89.6 percent with five samples of each new activity. [ABSTRACT FROM AUTHOR]

Spiking Neural Networks (SNNs) is promising to enable low power and high performance edge computing hardware design and have recently attracted attentions of researchers. Compared to Artificial Neural Networks (ANNs), SNNs, which present more realistic brain-inspired computing models, are developed as an alternative to ANNs. However, the temporal primitive of SNNs causes irregular and repeated data accesses, leading to high latency and extra power consumption. In this work, we propose an efficient architecture for SNNs by exploiting event-based characteristics. A reconfigurable spiking neuron processing unit is proposed to support a variety of spike-layers. Furthermore, to reduce the cycles needed per frame, an efficient dataflow with fast-filtering mechanism is introduced to leverage the sparsity of discrete spikes. The results show that this design achieves 67.5 $\mu \text{J}$ /image prediction energy with a throughput of 2.2K FPS. The core size is 0.89 mm2 under 28-nm technology, with 90.98% computing hardware utilization and a competitive accuracy 97.10% on a driving dataset. [ABSTRACT FROM AUTHOR]

The in-band full-duplex (IBFD) systems can send and receive data simultaneously in the same frequency band. Although the electromagnetic interference among RF channels can be released using radio over fiber (RoF) links, the receiving antenna is susceptible to the signal leakage from adjacent transmitting antennas. Due to the electronic bottlenecks, traditional RF self-interference cancellation (SIC) systems have some problems, such as low operating frequency, narrow transmission bandwidth, and electromagnetic interference, which seriously reduces the communication performance. In this paper, a photonic RF SIC system based on dual-phase modulation in a Sagnac loop is proposed to further increase the resistance to electromagnetic interference of the IBFD systems. Based on the principle of polarization multiplexing, the damaged received signal and local interference signal are modulated on two beams of a light wave with orthogonal polarization states. The received interference signal can be canceled by polarization adjustment. In the experiment, a single- frequency interference cancelation depth of 45 dB is achieved in the proposed photonic SIC system over the operating frequency range of 5–20 GHz. Also, a demonstration of cancellation for modulated interference with a center frequency of 10 GHz and bandwidths of 20, 30, and 50 MHz is carried out. [ABSTRACT FROM AUTHOR]

We propose a stability preserved Arnoldi algorithm for matrix exponential in the time domain simulation of large-scale power delivery networks (PDNs), which are formulated as semi-explicit differential-algebraic equations (DAEs). The matrix exponential and vector products (MEVPs) compose the solution of DAEs in multistep integration methods and can be efficiently approximated with the rational Krylov subspace. To produce stable simulation results for the ill-conditioned system from semi-explicit DAEs, the revised Arnoldi algorithm introduces a new structured orthogonalization process to construct the Krylov subspace. We demonstrate the performance of the new algorithm with theoretical proof and experiments. In the computation of MEVPs, we utilize the exponential related φ functions to improve the numerical accuracy. We further explore the optimal ratio to confine the spectrum in the rational Krylov subspace. Finally, the transient framework is tested on a group of system-level PDNs, showing that matrix exponential-based algorithms could achieve high efficiency and accuracy. [ABSTRACT FROM AUTHOR]

Compressed sensing (CS) is becoming a hot topic in recent years for its advantages such as low-power consumption, low memory requirement, and low sampling frequency. However, high-dimensional nonlinear signals will inevitably introduce notable complexity and low efficiency in signal recovery. Generalized turbo signal recovery (G-Turbo-SR) is a cutting-edge method, which efficiently reduces complexity with a partial discrete Fourier transform (DFT) sensing matrix. However, in practical applications, G-Turbo-SR still suffers from high complexity for probability computations and matrix multiplications. This article optimizes the algorithm of G-Turbo-SR in scheduling to reduce the matrix multiplications by half. High-precision numerical approximation method is proposed to replace the complex integral calculation, which efficiently reduces the hardware cost with acceptable performance degradation. Based on the data-flow graph (DFG) analysis, detailed hardware architecture is proposed with module designs. Proper quantization scheme is selected according to the mean square error (MSE) performance. Pipelining, folding, and variable precision quantization (VPQ) scheme are employed for higher hardware efficiency. FPGA implementation on Xilinx 7k325tffg900-2 shows a higher throughput and hardware efficiency compared to existing recovery methods for CS. [ABSTRACT FROM AUTHOR]

Malwares are becoming increasingly stealthy, more and more malwares are using cryptographic algorithms (e.g., packing, encrypting C&C communication) to protect themselves from being analyzed. The use of cryptographic algorithms and truly transient cryptographic secrets inside the malware binary imposes a key obstacle to effective malware analysis and defense. To enable more effective malware analysis, forensics, and reverse engineering, we have developed CipherXRay a novel binary analysis framework that can automatically identify and recover the cryptographic operations and transient secrets from the execution of potentially obfuscated binary executables. Based on the avalanche effect of cryptographic functions, CipherXRay is able to accurately pinpoint the boundary of cryptographic operation and recover truly transient cryptographic secrets that only exist in memory for one instant in between multiple nested cryptographic operations. CipherXRay can further identify certain operation modes (e.g., ECB, CBC, CFB) of the identified block cipher and tell whether the identified block cipher operation is encryption or decryption in certain cases. We have empirically validated CipherXRay with OpenSSL, popular password safe KeePassX, the ciphers used by malware Stuxnet, Kraken and Agobot, and a number of third party softwares with built-in compression and checksum. CipherXRay is able to identify various cryptographic operations and recover cryptographic secrets that exist in memory for only a few microseconds. Our results demonstrate that current software implementations of cryptographic algorithms hardly achieve any secrecy if their execution can be monitored. [ABSTRACT FROM AUTHOR]

With abundant aggregate network bandwidth, continuous data streams are commonly used in scientific and commercial applications. Correspondingly, there is an increasing demand of authenticating these data streams. Existing strategies explore data stream authentication by using message authentication codes (MACs) on a certain number of data packets (a data block) to generate a message digest, then either embedding the digest into the original data, or sending the digest out-of-band to the receiver. Embedding approaches inevitably change the original data, which is not acceptable under some circumstances (e.g., when sensitive information is included in the data). Sending the digest out-of-band incurs additional communication overhead, which consumes more critical resources (e.g., power in wireless devices for receiving information) besides network bandwidth. In this paper, we propose a novel strategy, DaTA, which effectively authenticates data streams by selectively adjusting some interpacket delay. This authentication scheme requires no change to the original data and no additional communication overhead. Modeling-based analysis and experiments conducted on an implemented prototype system in an LAN and over the Internet show that our proposed scheme is efficient and practical. [ABSTRACT FROM AUTHOR]