FusionCL: a machine-learning based approach for OpenCL kernel fusion to increase system performance

Computing ◽  
2021 ◽  
Author(s):  
Yasir Noman Khalid ◽  
Muhammad Aleem ◽  
Usman Ahmed ◽  
Radu Prodan ◽  
Muhammad Arshad Islam ◽  
...  
Keyword(s):  
Machine Learning ◽  
System Performance ◽  
Kernel Fusion

Machine learning based system performance prediction model for reactor control

2018 ◽  
Vol 113 ◽  
pp. 270-278 ◽  
Author(s):  
Yuyun Zeng ◽  
Jingquan Liu ◽  
Kaichao Sun ◽  
Lin-wen Hu
Keyword(s):  
Machine Learning ◽  
Prediction Model ◽  
Performance Prediction ◽  
System Performance ◽  
Reactor Control

Intelligent Tracking and Positioning of Targets Using Passive Sensing Systems

2019 ◽  
pp. 286-305
Author(s):  
Saad Iqbal ◽  
Usman Iqbal ◽  
Syed Ali Hassan
Keyword(s):  
Machine Learning ◽  
Signal Processing ◽  
System Performance ◽  
Target Localization ◽  
The Other ◽  
Conventional System ◽  
Sensing Systems ◽  
Passive Sensing ◽  
Indoor Scenarios ◽  
Localization And Tracking

Target localization and tracking has always been a hot topic in all eras of communication studies. Conventional system used radars for the purpose of locating and/or tracking an object using the classical methods of signal processing. Radars are generally classified as active and passive, where the former uses both transmitter and receivers simultaneously to perform the localization task. On the other hand, passive radars use existing illuminators of opportunity such as wi-fi or GSM signals to perform the aforementioned tasks. Although they perform detection using classical correlation methods and CFAR, recently machine learning has been used in various application of passive sensing to elevate the system performance. The latest developed models for intelligent RF passive sensing system for both outdoor and indoor scenarios are discussed in this chapter, which will give insight to the readers about their designing.

Machine Learning Approach for Multi-Layered Detection of Chemical Named Entities in Text

2020 ◽  
pp. 1496-1512
Author(s):  
Usha B. Biradar ◽  
Harsha Gurulingappa ◽  
Lokanath Khamari ◽  
Shashikala Giriyan
Keyword(s):  
Machine Learning ◽  
System Performance ◽  
Conditional Random Fields ◽  
Learning Approach ◽  
Named Entities ◽  
Machine Learning Approach ◽  
Feature Optimization ◽  
Multi Level ◽  
Corpus Generation ◽  
Substantial Effort

Identification of chemical named entities in text and subsequent linkage of information to biological events is of immense value to fulfill the knowledge needs of pharmaceutical and chemical R&D. A significant amount of investigation has been carried out since a decade for identifying chemical named entities at morphological level. However, a barrier still remains in terms of value proposition to scientists at chemistry level. Therefore, the work described here aims to circumvent the information barrier by adaptation of a Conditional Random Fields-based approach for identifying chemical named entities at various levels namely generic chemical level, morphological level, and chemistry level. Substantial effort has been invested on generation of suitable multi-level annotated corpora. Recommended machine learning practices such as active learning-based training corpus generation and feature optimization have been systematically performed. Evaluation of system performance and benchmarking against the other state-of-the-approaches showed improved results.

scholarly journals A Recommendation System for People Analytics

2021 ◽  
Vol 12 (2) ◽  
pp. 1-12
Author(s):  
Nan Wang ◽  
Evangelos Katsamakas
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Decision Support System ◽  
Support System ◽  
System Performance ◽  
Recommendation System ◽  
Business Value ◽  
Computational Experiments ◽  
Hybrid Architecture ◽  
Learning Approaches

Companies seek to leverage data and people analytics to maximize the business value of their talent. This article proposes a recommendation system for personalized workload assignment in the context of people analytics. The article describes the system, which follows a novel two-level hybrid architecture. We evaluate the system performance in a series of computational experiments and discuss future extensions. Overall, the proposed system could create significant business value as a decision support system that could help managers make better decisions. The article demonstrates how computational and machine learning approaches can complement humans in improving the performance of organizations.

Telescope performance real-time monitoring based on machine learning

2020 ◽  
Vol 500 (1) ◽  
pp. 388-396
Author(s):  
Tian Z Hu ◽  
Yong Zhang ◽  
Xiang Q Cui ◽  
Qing Y Zhang ◽  
Ye P Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
System Performance ◽  
High Performance ◽  
High Efficiency ◽  
Peak Performance ◽  
Source Image ◽  
Detection Accuracy ◽  
Real Time Monitoring ◽  
Active Optics

ABSTRACT In astronomy, the demand for high-resolution imaging and high-efficiency observation requires telescopes that are maintained at peak performance. To improve telescope performance, it is useful to conduct real-time monitoring of the telescope status and detailed recordings of the operational data of the telescope. In this paper, we provide a method based on machine learning to monitor the telescope performance in real-time. First, we use picture features and the random forest algorithm to select normal pictures captured by the acquisition camera or science camera. Next, we cut out the source image of the picture and use convolutional neural networks to recognize star shapes. Finally, we monitor the telescope performance based on the relationship between the source image shape and telescope performance. Through this method, we achieve high-performance real-time monitoring with the Large Sky Area Multi-Object Fibre Spectroscopic Telescope, including guiding system performance, focal surface defocus, submirror performance, and active optics system performance. The ultimate performance detection accuracy can reach up to 96.7 per cent.

scholarly journals Deteksi Bot Spammer pada Twitter Berbasis Sentiment Analysis dan Time Interval Entropy

2016 ◽  
Vol 7 (3) ◽  
Author(s):  
Christian Sri Kusuma Aditya ◽  
Mamluatul Hani’ah ◽  
Alif Akbar Fitrawan ◽  
Agus Zainal Arifin ◽  
Diana Purwitasari
Keyword(s):  
Machine Learning ◽  
Sentiment Analysis ◽  
System Performance ◽  
New Method ◽  
Time Interval ◽  
Knowledge Based ◽  
Legitimate User

Abstract. Spam is an abuse of messaging undesired by recipients. Those who send spam are called spammers.  Popularity of Twitter has attracted spammers to use it as a means to disseminate spam messages. The spams are characterized by a neutral emotional sentiment or no particular users’ preference perspective. In addition, the regularity of tweeting behavior periodically shows automation performed by bot. This study proposes a new method to differentiate between bot spammer and legitimate user accounts by integrating the sentiment analysis (SA) based on emotions and time interval entropy (TIE). The combination of knowledge-based and machine learning-based were used to classify tweets with positive, negative and neutral sentiments. Furthermore, the collection of timestamp is used to calculate the time interval entropy of each account. The results show that the precision and recall of the proposed method reach up to 83% and 91%. This proves that the merging SA and TIE can optimize overall system performance in detecting Bot Spammer.Keywords: bot spammer, twitter, sentiment analysis, polarity, entropy Abstrak. Spam merupakan penyalahgunaan pengiriman pesan tanpa dikehendaki oleh penerimanya, orang yang mengirimkan spam disebut spammer. Ketenaran Twitter mengundang spammer untuk menggunakannya sebagai sarana menyebarluaskan pesan spam. Karakteristik dari tweet yang dikategorikan spam memiliki sentimen emosi netral atau tidak ada preferensi tertentu terhadap suatu perspektif dari user yang memposting tweet. Selain itu keteraturan waktu perilaku saat memposting tweet secara periodik menunjukkan otomatisasi yang dilakukan bot. Pada penelitian ini diusulkan metode baru untuk mendeteksi antara bot spammer dan legitimate user dengan mengintegrasikan sentimen analysis berdasarkan emosi dan time interval entropy. Pendekatan gabungan knowledge-based dan machine learning-based digunakan untuk mengklasifikasi tweet yang memiliki sentimen positif, negatif dan tweet netral. Selanjutnya kumpulan timestamp digunakan untuk menghitung time interval entropy dari tiap akun. Hasil percobaan menunjukan bahwa precision dan recall dari metode yang diusulkan mencapai 83% dan 91%. Hal ini membuktikan penggabungan Sentiment Analysis (SA) dan Time Interval Entropy (TIE) dapat mengoptimalkan performa sistem secara keseluruhan dalam mendeteksi Bot Spammer.Kata Kunci:  bot spammer, twitter, sentiment analysis,  polarity, entropy

scholarly journals Healthcare Consultancy System

2021 ◽  
pp. 439-443
Author(s):  
Prof. Asma Mokashi ◽  
Pratik Rughe ◽  
Yashashri Malvi ◽  
Neha Ghodekar
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
System Performance ◽  
Healthcare Delivery ◽  
Present Situation ◽  
Structured Data ◽  
Machine Learning Algorithms ◽  
Doctor Who ◽  
Healthcare Delivery System ◽  
Similarity Model

Under the present situation, the healthcare delivery system is prohibitively expensive, inefficient, and unsustainable. Machine Learning (ML) has revolutionized the way businesses and individuals use data to increase system performance. Strategists can work with a range of organized, non - structured, and semi-structured data using machine learning algorithms. This device provides a virtual assistant who can converse with patients in their native language to understand their symptoms, recommend doctors, and monitor health metrics. To process users' complaints and find the closest doctor who can help handle the user's case, the solution relies on natural language processing models and machine learning analytic methodology. A deep bilinear similarity model is also proposed by the framework to boost the generated SQL queries used for predictions and algorithms. BERT and SQLOVA models are used to train the device data collection.

scholarly journals Discovering Customer Paths from Location Data with Process Mining

2020 ◽  
Vol 3 (1) ◽  
pp. 139-145
Author(s):  
Onur Dogan
Keyword(s):  
Machine Learning ◽  
System Performance ◽  
Process Mining ◽  
Tracking Data ◽  
Human Behaviors ◽  
Location Data ◽  
Machine Learning Methods ◽  
Visit Duration ◽  
Individual Tracking ◽  
Visual Results

customer paths can be used for several purposes, such as understanding customer needs, defining bottlenecks, improving system performance. Two of the principal difficulties depend on discovering customer paths due to dynamic human behaviors and collecting reliable tracking data. Although machine learning methods have contributed to individual tracking, they have complex iterations and problems to produce understandable visual results. Process mining is a methodology that can rapidly create process flows and graphical representations. In this study, customer flows are created with process mining in a supermarket. The differences between the paths of customers purchased and non-purchased are discussed. The results show that both groups have almost similar visit duration, which is 87.5 minutes for purchased customers and 86.6 minutes for non-purchased customers. However, the duration of aisles is relatively small in non-purchased customer flows because customers aim to return or change the item instead of buying.

Sign in / Sign up

Export Citation Format

Share Document