The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Modern patient data tends to be large-scale and multi-dimensional, containing both spatial and temporal features. Learning good spatio-temporal features from large patient data is a challenging task, especially when there are missing observations. In this paper, we propose a spatio-temporal autoencoder (STAE), an unsupervised deep learning scheme, to learn features from large-scale and high-dimensional...
Asynchronous quasi-delay-insensitive (QDI) circuits are a promising solution for coping with aggressive process variations faced by modern technologies, as they can gracefully accommodate gate and wire delay variations. Furthermore, due to their inherent robustness, such circuits are also promising for deep voltage scaling applications, where delays are orders of magnitude larger. However, QDI design...
Fault tree analysis (FTA) is a prominent reliability analysis method widely used in safety-critical industries. Computing minimal cut sets (MCSs), i.e., finding all the smallest combination of basic events that result in the top level event, plays a fundamental role in FTA. Classical methods have been proposed based on manipulation of boolean expressions of fault trees and Binary Decision Diagrams...
Along with advances in modern VLSI technology, delay faults are becoming ever more important. On the other hand, the strength of SAT-solver engines has made them an attractive means for solving many Computer Aided Design (CAD) problems. This paper presents a new SAT-based Automatic Test Pattern Generation (ATPG) approach targeting transition delay faults using a novel 8-value encoding system. Experimental...
This paper presents an energy-efficient solution to overcome packet loss in Wireless Sensor Networks (WSNs) by adding seed-based Random Linear Network Coding to MQTT for Sensor Networks (MQTT-SN). Whereas most sensors integrated in common WSN devices consume little energy, using the radio is costly. To increase battery lifetime, devices try to minimize their radio uptime, while still satisfy timeliness...
The 10Gbase-KR protocol is widely used to accomplish the high speed data conversion in the Ethernet area. This paper presents a design of the critical controller in the physical coding sublayer based on the 10Gbase-KR. In order to satisfy the demand of the high speed data conversion, the scrambler and descrambler are specially designed to work in a parallel mode. The post-synthesis simulation results...
Privacy of data has become an increasing concern over the past years. With Fully Homomorphic Encryption (FHE), one can offload the processing of data to a third-party while keeping it private. A technique called batching has been proposed to accelerate FHE, allowing for several bits to be encrypted in the same ciphertext, which can be processed in parallel. Herein, we argue that for a certain class...
A new asynchronous early output section-carry based carry lookahead adder (SCBCLA) with alias carry output logic is presented in this paper. To evaluate the proposed SCBCLA with alias carry logic and to make a comparison with other CLAs, a 32-bit addition operation is considered. Compared to the weak-indication SCBCLA with alias logic, the proposed early output SCBCLA with alias logic reports a 13%...
In this paper we introduce and evaluate Haar based codec assisted medium and long range data transport structures, e.g., bus segments, Network on Chip interconnects, able to deal with technology scaling related phenomena (e.g., increased susceptibility to proximity coupling noise and transmission delay variability), targeting energy savings at the expense of a reasonably small overhead, i.e., 1 extra...
Encoders using generator polynomials and linear-feedback shift registers are the key parts of communication technologies widely used in most of today's integrated as well as field systems. This paper presents a detailed comparison of three ways of implementation of configurable encoders arranged in PENCA and implemented in Xilinx and Altera FPGAs.
The existing communication technologies for IOT have become either saturated or do not meet actual needs, regarding long distances or low power consumption. We propose a study about mobility for the LoRa protocol, a new Low Power Wide Area Network technology. The paper draws upon a short overview of LoRa physical layer protocol, as well as on our testing design, some distances achieved and signal...
Developing a technique for the automatic analysis of surveillance videos in order to identify the presence of violence is of broad interest. In this work, we propose a deep neural network for the purpose of recognizing violent videos. A convolutional neural network is used to extract frame level features from a video. The frame level features are then aggregated using a variant of the long short term...
The use of Recurrent Neural Networks for video captioning has recently gained a lot of attention, since they can be used both to encode the input video and to generate the corresponding description. In this paper, we present a recurrent video encoding scheme which can discover and leverage the hierarchical structure of the video. Unlike the classical encoder-decoder approach, in which a video is encoded...
Effective integration of local and global contextual information is crucial for dense labeling problems. Most existing methods based on an encoder-decoder architecture simply concatenate features from earlier layers to obtain higher-frequency details in the refinement stages. However, there are limits to the quality of refinement possible if ambiguous information is passed forward. In this paper we...
This work was developed in the context of European funded Project SelSus. Industrial clouds are heavily sensor based and Cloud Manufacturing Service frameworks are mostly grounded in the adoption of Internet of Things and Wireless Sensor Networks technologies. The SelSus framework combines both an Industrial Sensor Cloud and a Cyber Physical Production System. The Industrial Sensor Cloud supports...
Modeling of high order interactional context, e.g., group interaction, lies in the central of collective/group activity recognition. However, most of the previous activity recognition methods do not offer a flexible and scalable scheme to handle the high order context modeling problem. To explicitly address this fundamental bottleneck, we propose a recurrent interactional context modeling scheme based...
This paper presents a novel low power duobinary voltage mode transmitter in 90-nm CMOS process for wireline communication. As a matter of fact, voltage mode transmitters potentially save much more power than current mode transmitters. By adding a medium level, a half supply voltage, to conventional NRZ voltage mode transmitters, duobinary coding can simply be achieved. Post-layout simulation demonstrates...
With the rise and popular of artificial intelligence,the technology of conversation between human and machine get more and more attention. Using neural network model on the Encoder-Decoder framework has been wildly used in translation and human-machine conversation. This paper we propose a new hybrid neural network model (HNN) which consists of some essential neural network models (that is RNN, LSTM,...
Deep learning techniques are being used in skeleton based action recognition tasks and outstanding performance has been reported. Compared with RNN based methods which tend to overemphasize temporal information, CNN-based approaches can jointly capture spatio-temporal information from texture color images encoded from skeleton sequences. There are several skeleton-based features that have proven effective...
This paper presents a formal approach to verify multipliers that approximate integer multiplication by output truncation. The method is based on extracting polynomial signature of a truncated multiplier using algebraic rewriting. To efficiently compute the polynomial signature, a multiplier reconstruction approach is used to construct the precise multi- plier from the truncated one. The method consists...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.