WHOSA: Network Flow Classification Based on Windowed Higher-Order Statistical Analysis

AbstractThe objective of this study was to describe current obstetric, neonatal, and long-term neurodevelopmental outcomes of higher order multifetal gestations (≥ 3 fetuses) in the 1990s. We also intended to identify a target gestational age at which neonatal and neurodevelopmental morbidities are low. Records from all multifetal pregnancies (≥ 3 viable fetuses ≥ 20 weeks gestation) delivered at the two perinatal centers in Toronto, Ontario, Canada during the study period (January 1, 1990–December 31, 1996) were reviewed. Data were collected on obstetric, neonatal, and long-term neurodevelopmental outcomes. Follow up data were gathered regarding the presence of a severe deficit in four categories (vision, hearing, cognition, and motor skills). Statistical analysis was performed to determine a gestational age at which a significant decrease in deficit occurred. During the study period 165 multifetal pregnancies were delivered. This resulted in 511 fetuses, of which 496 were live births. Of these 496 infants, 453 survived to discharge. Follow up data were obtained on 332 (73.3 per cent) infants. Infant survival increased with gestational age, and was approximately 90 per cent or greater at 26 weeks or more. Of all infants followed, the proportion of those without deficit increased with increasing gestational age, such that the per cent without deficit was 96.9 at 31 weeks or greater. Of all infants followed, 301 (90.7 per cent) had no deficit. Statistical analysis revealed a significant difference in long-term neurodevelopmental outcome between infants born before and after 28 weeks gestation. The incidence of a major deficit was 44.1 per cent for those born earlier than and 5.4 per cent for those born later than this gestational age (p = 0.001). In our cohort, survival figures were high. Even in lower gestational groupings, survival was high, but not without serious concerns about severe morbidity. This information is useful when counseling parents of higher order multifetal pregnancies.

Download Full-text

A Preliminary Performance Evaluation of K-means, KNN and EM Unsupervised Machine Learning Methods for Network Flow Classification

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v6i2.pp778-784 ◽

2016 ◽

Vol 6 (2) ◽

pp. 778

Author(s):

Alhamza Alalousi ◽

Rozmie Razif ◽

Mosleh AbuAlhaj ◽

Mohammed Anbar ◽

Shahrul Nizam

Keyword(s):

Machine Learning ◽

Expectation Maximization ◽

Classification Accuracy ◽

Network Flow ◽

Processing Time ◽

Nearest Neighbor ◽

K Nearest Neighbor ◽

Popular Method ◽

Flow Classification ◽

Machine Learning Methods

Unsupervised leaning is a popular method for classify unlabeled dataset i.e. without prior knowledge about data class. Many of unsupervised learning are used to inspect and classify network flow. This paper presents in-deep study for three unsupervised classifiers, namely: K-means, K-nearest neighbor and Expectation maximization. The methodologies and how it’s employed to classify network flow are elaborated in details. The three classifiers are evaluated using three significant metrics, which are classification accuracy, classification speed and memory consuming. The K-nearest neighbor introduce better results for accuracy and memory; while K-means announce lowest processing time.

Download Full-text

AFBV: A High-Performance Network Flow Classification Method for Multi-Dimensional Fields and FPGA Implementation

Journal of Circuits System and Computers ◽

10.1142/s0218126619502372 ◽

2019 ◽

Vol 28 (14) ◽

pp. 1950237

Author(s):

Ling Zheng ◽

Zhiliang Qiu ◽

Weina Wang ◽

Weitao Pan ◽

Shiyong Sun ◽

...

Keyword(s):

High Throughput ◽

Network Flow ◽

High Speed ◽

High Performance ◽

Clock Frequency ◽

Pipeline Architecture ◽

Exact Matching ◽

Flow Classification ◽

Rule Sets ◽

Bit Vector

Network flow classification is a key function in high-speed switches and routers. It directly determines the performance of network devices. With the development of the Internet and various kinds of applications, the flow classification needs to support multi-dimensional fields, large rule sets, and sustain a high throughput. Software-based classification cannot meet the performance requirement as high as 100 Gbps. FPGA-based flow classification methods can achieve a very high throughput. However, the range matching is still challenging. For this, this paper proposes a range supported bit vector (RSBV) method. First, the characteristic of range matching is analyzed, then the rules are pre-encoded and stored in memory. Second, the fields of an input packet header are used as addresses to read the memory, and the result of range matching is derived through pipelined Boolean operations. On this basis, bit vector for any types of fields (AFBV) is further proposed, which supports the flow classification for multi-dimensional fields efficiently, including exact matching, longest prefix matching, range matching, and arbitrary wildcard matching. The proposed methods are implemented in FPGA platform. Through a two-dimensional pipeline architecture, the AFBV can operate at a high clock frequency and can achieve a processing speed of more than 100 Gbps. Simulation results show that for a rule set of 512-bit width and 1[Formula: see text]k rules, the AFBV can achieve a throughput of 520 million packets per second (MPPS). The performance is improved by 44% compared with FSBV and 30% compared with Stride BV. The power consumption is reduced by about 43% compared with TCAM solution.

Download Full-text

Higher Order Statistical Analysis for Thyroid Texture Classification and Segmentation in 2D ultrasound Images

2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) ◽

10.1109/embc.2019.8857380 ◽

2019 ◽

Author(s):

Naghmeh Mahmoodian ◽

Prabal Poudel ◽

Alfredo Illanes ◽

Michael Friebe

Keyword(s):

Statistical Analysis ◽

Texture Classification ◽

Higher Order ◽

Ultrasound Images ◽

2D Ultrasound

Download Full-text