Measuring statistical properties of network traffic can improve our understanding of traffic distribution and help us detect short and long-term anomalies. However, computing the exact value of these properties requir...
详细信息
ISBN:
(数字)9798350380385
ISBN:
(纸本)9798350380392
Measuring statistical properties of network traffic can improve our understanding of traffic distribution and help us detect short and long-term anomalies. However, computing the exact value of these properties requires significant storage and computation, which limits their application in high-speed networks. Hardware accelerators provide the computational power to process a large sequence of network packets with high throughput and low latency, but their performance is ultimately limited by the amount of on-chip memory available on the device. Consequently, researchers have proposed sketch-based algorithms to estimate properties of a data stream with sub linear memory and theoretical estimation error bounds. In this paper, we present a streaming algorithm and hardware accelerator for quantile estimation, which is based on the architecture of the KLL sketch. Implemented on an AMD Virtex XCU55 UltraScale+ FPGA, the accelerator operates at a clock frequency of 356 MHz, thereby achieving a minimum line rate of 182 Gbps and a maximum estimation latency of 4.33 µs. When processing a set of 10 real traffic traces of up to 123 million packets, the accelerator estimates 1000 packet-size quantiles per trace with a median error of 0.39% or less, and a maximum error of 1.3% or less across all traces.
Our surroundings' auditory landscapes are a wealth of knowledge, providing insights into a range of outdoor pursuits. The automatic classification of these actions using audio event detection and classification (A...
详细信息
During vascular occlusions, the blood flow distribution in the cerebroarterial tree changes and can lead to insufficient blood flow, which can in turn cause tissue damage or ischemia. In such situations, predicting bl...
详细信息
ISBN:
(数字)9798331520526
ISBN:
(纸本)9798331520533
During vascular occlusions, the blood flow distribution in the cerebroarterial tree changes and can lead to insufficient blood flow, which can in turn cause tissue damage or ischemia. In such situations, predicting blood flow dynamics in a timely manner is crucial as it provides information about regions at risk, enabling clinicians to select optimal sites for revascularization procedures. This paper presents the development of a hemodynamic simulator designed to model pressure and flow, enabling detailed analysis of blood flow redistribution in response to arterial blockages. We focused on the role of Circle of Willis to provide immediate compensation for the loss of blood supply to the distal sites of occluded vessels. For this purpose, the angioarchitecture of a cerebral arterial tree was acquired using magnetic resonance angiography from a human subject with a complete Circle of Willis, and in-vivo blood flow measurements were used to obtain subject-specific boundary conditions. A 1D arterial network simulator was developed to predict the flow through the entire cerebral vascular tree model after five different scenarios of arteries occlusion. The blood flow in the communicating arteries, particularly in the right middle cerebral artery, significantly changed in different occlusion cases showing their importance for blood flow accommodation after occlusion.
The development of the internet is getting faster, participating in encouraging the emergence of new and innovative information. In filtering the various information that appears, we need a recommended system to perfo...
详细信息
Gradient-based attacks are a primary tool to evaluate robustness of machine-learning models. However, many attacks tend to provide overly-optimistic evaluations as they use fixed loss functions, optimizers, step-size ...
详细信息
In this paper, we investigate the fundamental limits of reliable communication over a discrete memoryless channel (DMC) when there are a large number of noisy views of a transmitted symbol, i.e., when several copies o...
详细信息
ISBN:
(数字)9798350382846
ISBN:
(纸本)9798350382853
In this paper, we investigate the fundamental limits of reliable communication over a discrete memoryless channel (DMC) when there are a large number of noisy views of a transmitted symbol, i.e., when several copies of a single symbol are sent independently through the DMC. We argue that the channel capacity and dispersion of such a multi-view DMC converge exponentially quickly in the number of views to to the entropy and varentropy of the input distribution, respectively, and identify the exact rate of convergence. This rate equals the smallest Chernoff information between two conditional distributions of the output given unequal inputs. Our results hence help us characterize the largest finite-blocklength rates achievable for any fixed error probability. We also present a new channel model that we call the Poisson approximation channel-of possible independent interest-whose capacity closely approximates the capacity of the multi-view binary symmetric channel (BSC).
Attendance systems have become more modern, and one of the biometric systems without physical contact is face recognition. However, many face-based attendance systems still carry out attendance individually and cannot...
详细信息
ISBN:
(数字)9798350376968
ISBN:
(纸本)9798350376975
Attendance systems have become more modern, and one of the biometric systems without physical contact is face recognition. However, many face-based attendance systems still carry out attendance individually and cannot detect multiple faces simultaneously. In addition, capturing facial data in real-time is still a challenge because the relatively large distance between the camera and the individual reduces the ability to recognize faces. The general solution is to use super-resolution to generate better-quality faces while maintaining the main facial recognition features. One technique still being researched is super-resolution generative adversarial networks (SRGAN). SRGAN can enlarge the resolution of captured images and maintain image quality sufficient for face recognition. The attendance system can be easily integrated into edge devices such as the Jetson Nano. This paper proposes automatic and effective attendance systems with the super-resolution technique to detect and recognize faces in low-resolution input. The experimental results show that using face data capture with a resolution of 40 × 40 pixels and a four-fold magnification results in a resolution of 160 × 160 pixels. Combining Face SRGAN with FaceNet architecture as the basis of face recognition can achieve an accuracy rate of 78.19% and an F1-Score of 81.13% with an average processing time of 1.61 seconds per frame on a PC and 14.55 seconds per frame on a Jetson Nano at an average of face recognition per frame of as many as up to 8 faces simultaneously.
The rapid development of Internet of Things (IoT) technology has enabled the widespread deployment of health monitoring systems. Traditionally, the health monitoring system has been limited by centralized processing a...
详细信息
ISBN:
(数字)9798350392296
ISBN:
(纸本)9798350392302
The rapid development of Internet of Things (IoT) technology has enabled the widespread deployment of health monitoring systems. Traditionally, the health monitoring system has been limited by centralized processing and storage in the cloud, leading to latency issues and potential data loss. This paper introduces a smart sleep monitoring system based on edge computing, utilizing microservices architecture and caching techniques. The proposed system employs edge computing to enable data processing closer to the source, reducing latency and improving real-time monitoring capabilities. Caching is employed to reduce database load and optimize random access memory (RAM) usage. This research addresses latency and response time challenges on IoT health monitoring platforms in environments with poor network quality while optimizing database load and resource usage on Jetson Nano as the edge computing device. Using Electrocardiogram (ECG) data as input, the proposed system yields impressive performance metrics. The research results indicate that the proposed system can increase throughput by 26.92 KB/s, reduce response time by 18.8 ms, and decrease latency by 20.86 ms compared to the previous work. Message Queuing Telemetry Transport (MQTT) integration reduces CPU usage by approximately 40% and RAM usage by about 81.24%.
Miniaturized microscopes for monitoring neural activity are an indispensable tool for neuroscience research. We present a novel MEMS based miniature microscope with patterned optogenetic stimulation capabilities enabl...
详细信息
Sleep is the natural state of relaxation for human being. Sleep quality is an essential yet frequently neglected aspect of sleep in general. Sleep quality is essential because it allows the body to rest...
详细信息
Sleep is the natural state of relaxation for human being. Sleep quality is an essential yet frequently neglected aspect of sleep in general. Sleep quality is essential because it allows the body to restore itself and prepare for the next day. The standard method for evaluating sleep quality was subjective evaluation. Actigraphy devices, which can measure the sleep cycle, are now widely available. This study developed a method using Fuzzy Logic and an actigraphy device to measure and classify sleep quality. The fuzzy logic method was developed in several stages, which are determining the sleep quality measurement parameters, constructing the fuzzy set for each input variable, and developing the fuzzy rules. To evaluate the proposed fuzzy model, five individuals were invited to participate in the experiment and required to complete the PSQI subjective sleep questionnaire. The evaluation result shows that our proposed Fuzzy model achieves lower error compared to the existing method.
暂无评论