Sunday, May 30, 2021

HATE SPEECH DETECTION OF ARABIC SHORTTEXT

Author :  Abdullah Aref

Affiliation :  University for Technology

Country :  Jordan

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

The aim of sentiment analysis is to automatically extract the opinions from a certain text and decide its sentiment. In this paper, we introduce the first publicly-available Twitter dataset on Sunnah and Shia (SSTD), as part of a religious hate speech which is a sub problem of the general hate speech. We, further, provide a detailed review of the data collection process and our annotation guidelines such that a reliable dataset annotation is guaranteed. We employed many stand-alone classification algorithms on the Twitter hate speech dataset, including Random Forest, Complement NB, DecisionTree, and SVM and two deep learning methods CNN and RNN. We further study the influence of word embedding dimensions FastText and word2vec. In all our experiments, all classification algorithms are trained using a random split of data (66% for training and 34% for testing). The two datasets were stratified sampling of the original dataset. The CNN-FastText achieves the highest F-Measure (52.0%) followed by the CNN-Word2vec (49.0%), showing that neural models with FastText word embedding outperform classical feature-based mode.

Keyword :  HateSpeech, Dataset, Text classification, Sentiment analysis.

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100507.pdf

Friday, May 28, 2021

LINKING SOCIAL MEDIA POSTS TO NEWS WITH SIAMESE TRANSFORMERS

Author :  Jacob Danovitch

Affiliation :  Carleton University

Country :  Canada

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

Many computational social science projects examine online discourse surrounding a specific trending topic. These works often involve the acquisition of large-scale corpora relevant to the event in question to analyze aspects of the response to the event. Keyword searches present a precision-recall trade-off and crowd-sourced annotations, while effective, are costly. This work aims to enable automatic and accurate ad-hoc retrieval of comments discussing a trending topic from a large corpus, using only a handful of seed news articles.

Keyword :  Deep Learning, Natural Language Processing, Information Retrieval, Social Media, News Articles.

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100506.pdf

COMMUNICATION BETWEEN COROUTINES ON SUNWAY MANY-CORE PLATFORM

Author :  Shaodi Li

Affiliation :  University of Science and Technology of China, Suzhou

Country :  China

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

Communication between parallel programs is an indispensable part of parallel computing. SW26010 is a heterogeneous many-core processor used to build the Sunway TaihuLight supercomputer, which is well suited for parallel computing. Our team is designing and implementing a coroutine scheduling system on SW26010 processor to improve its concurrency, it is very important and necessary to achieve communication between coroutines for the coroutine scheduling system in advance. Therefore, this paper proposes a communication system for data and information exchange between coroutines on SW26010 processor, which contains the following parts. First, we design and implement a producer-consumer mode channel communication based on ring buffer, and designs synchronization mechanism for condition of multi-producer and multi-consumer based on the different atomic operation on the MPE (management processing element) and the CPE (computing processing element) of SW26010. Next, we design a wake-up mechanism between the producer and the consumer, which reduces the waiting of the program for communication. At last, we test and analyse the performance of channel in different numbers of producers and consumers, draw the conclusion that when the number of producers and consumers increases, the channel performance will decrease.

Keyword :  Coroutine, SW26010, Many-core, Parallel Communication, Synchronization

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100505.pdf

Tuesday, May 25, 2021

LEADING DEVOPS PRACTICE AND PRINCIPLE ADOPTION

Author :  Krikor Maroukian

Affiliation :  Microsoft, Kifissias Ave., Athens

Country :  Greece

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

This research, undertaken in highly structured software-intensive organizations, outlines challenges associated to agile, lean and DevOps practices and principles adoption. The approach collected data via a series of thirty (30) interviews, with practitioners from the EMEA region (Czech Republic, Estonia, Italy, Georgia, Greece, The Netherlands, Saudi Arabia, South Africa, UAE, UK), working in nine (9) different industry domains and ten (10) different countries. A set of agile, lean and DevOps practices and principles, which organizations choose to include in their DevOps adoption journeys were identified. The most frequently adopted structured service management practices, contributing to DevOps practice adoption success, indicate that those with software development and operation roles in DevOps-oriented organizations benefit from existence of highly structured service management approaches such as ITIL®.

Keyword :  Agile, Lean, Practices and Principles, DevOps Leadership, IT service management

For More Details https://aircconline.com/csit/papers/vol10/csit100504.pdf

Thursday, May 20, 2021

TRANSCRIPT LEVEL ANALYSIS IMPROVES THE UNDERSTANDING OF BLADDER CANCER

Author :  Xiang Ao

Affiliation :  City University of Hong Kong

Country :  Hong Kong

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

Bladder cancer (BC) is one of the most globally prevalent diseases, attracting various studies on BC relevant topics. High-throughput sequencing renders it convenient to extensively explore genetic changes, like the variation in gene expression, in the development of BC. In this study, we did differential analysis on gene and transcript expression (DGE and DTE) and differential transcript usage (DTU) analysis in an RNA-seq dataset of 42 bladder cancer patients. DGE analysis reported 8543 significantly differentially expressed (DE) genes. In contrast, DTE analysis detected 14350 significantly DE transcripts from 8371 genes, and DTU analysis detected 27914 significantly differentially used (DU) transcripts from 8072 genes. Analysis of the top 5 DE genes demonstrated that DTE and DTU analysis provided the source of changes in gene expression at the transcript level. The transcript-level analysis also identified some DE and DU transcripts from previously reported mutated genes that related to BC, like ERBB2, ESPL1, and STAG2, suggesting an intrinsic connection between gene mutation and alternative splicing. Hence, the transcript-level analysis may help disclose the underlying pathological mechanism of BC and further guide the design of personal treatment.

Keyword :  Bladder Cancer, Differential Gene Expression, Differential Transcript Expression, Differential Transcript Usage

For More Details https://aircconline.com/csit/papers/vol10/csit100503.pdf

 

Wednesday, May 19, 2021

CONTEXTUAL FACTORS INFLUENCING THE DESIGN AND MANAGEMENT OF HEALTH INFORMATION SYSTEMS’ NTEROPERABILITY

Author :  Grace Kobusinge

Affiliation :  Gothenburg University

Country :  Sweden

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

Due to their renowned great information processing and dissemination power, Health information systems (HIS) can readily avail past patient medical information across the continuum of care in order to facilitate ongoing treatment. However, a number of existing HIS are designed as vertical silos with no interoperability onuses and therefore, cannot exchange patient information. At the same time, there is limited knowledge about the intricacies and factors that surround HIS’ interoperability implementations. This study therefore, employs an institutional lens perspective to investigate contextual factors influencing HIS’ interoperability designing. Through this perspective, seven contextual factors were arrived at institutional autonomism, intended system goals, existing health-information-systems, national HIS implementation guidelines, interoperability standards, policy and resources in terms of money and labour. A further study implication is the use of institutional lens in making sense of the institutions’ context of integration in order to discover salient factors that might influence health-information-systems’ interoperability designing.

Keyword :  Health Information Systems’ Interoperability, Design and Management, Contextual Factors.

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100502.pdf

Monday, May 17, 2021

IDENTIFICATION OF TECHNOLOGYRELEVANT ENTITIES BASED ON TREND CURVES

Author :  Sukhwan Jung

Affiliation :  University of South Alabama

Country :  USA

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

Technological developments are not isolated and are influenced not only by similar technologies but also by many entities, which are sometimes unforeseen by the experts in the field. The authors propose a method for identifying technology-relevant entities with trend curve analysis. The method first utilizes the tangential connection between terms in the encyclopedic dataset to extract technology-related entities with varying relation distances. Changes in their term frequencies within 389 million academic articles and 60 billion web pages are then analyzed to identify technology-relevant entities, incorporating the degrees and changes in both academic interests and public recognitions. The analysis is performed to find entities both significant and relevant to the technology of interest, resulting in the discovery of 40 and 39 technology-relevant entities, respectively, for unmanned aerial vehicle and hyperspectral imaging with 0.875 and 0.5385 accuracies. The case study showed the proposed method can capture hidden relationships between semantically distant entities.

Keyword :  Technology Forecasting, Trend Curve, Big Data, Academic Articles, Web Pages

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100501.pdf

Sunday, May 16, 2021

ESTIMATION OF LOCATION AND SEPARATION BETWEEN ACOUSTIC EMITTING SOURCES : A COMPARISON BETWEEN CLASSICAL AND MODERN METHODS

Author :  Mujahid F. AL-Azzo

Affiliation :  Ninevah University

Country :  Iraq

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 04, April, 2020

Abstract :

A mathematical model for localization of acoustical sources with separation between them is derived and presented. A classical (Fourier transform) method and a modern, parametric, (Burg) method are used. The results show the capability of Burg method to resolve the adjacent sources when compared with Fourier transform method, as well as the localization of the sources. The performance is studies with varying some parameters relating to the problem.

Keyword :  Burg method, spectral estimation, location of sources

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100411.pdf

Thursday, May 13, 2021

MINERVA: A PORTABLE MACHINE LEARNING MICROSERVICE FRAMEWORK FOR TRADITIONAL ENTERPRISE SAAS APPLICATIONS

Author :  Venkata Duvvuri

Affiliation :  Purdue University

Country :  USA

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 04, April, 2020

Abstract :

In traditional SaaS enterprise applications, microservices are an essential ingredient to deploy machine learning (ML) models successfully. In general, microservices result in efficiencies in software service design, development, and delivery. As they become ubiquitous in the redesign of monolithic software, with the addition of machine learning, the traditional applications are also becoming increasingly intelligent. Here, we propose a portable ML microservice framework Minerva (microservices container for applied ML) as an efficient way to modularize and deploy intelligent microservices in traditional “legacy” SaaS applications suite, especially in the enterprise domain. We identify and discuss the needs, challenges and architecture to incorporate ML microservices in such applications. Minerva’s design for optimal integration with legacy applications using microservices architecture leveraging lightweight infrastructure accelerates deploying ML models in such applications.

Keyword :  Microservices, Enterprise SaaS applications, Machine Learning, Oracle Cloud Infrastructure, Docker

For More Details https://aircconline.com/csit/papers/vol10/csit100410.pdf


Wednesday, May 12, 2021

An Internet of Things (IoT) Solution to Optimise the Livestock Feed Supply Chain

Author :  David Raba

Affiliation :  Universitat Oberta de Catalunya

Country :  Spain

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 04, April, 2020

Abstract :

The animal feed supply chain to farm, mainly represented by the feed suppliers and livestock farmers, currently faces great inefficiencies due to outdated supply chain management. Stakeholders struggle with the timing and quantity evaluation when restocking their feed bins, significantly affecting cost and labour efficiency. However, the lack of accurate and cost-effective sensors to measure stock levels of solid materials stored in containers and open piles is preventing the implementation of these strategies in a large number of industrial sectors. In these cases, traditional technologies cannot offer a convenient solution due to an inevitable trade-off between accuracy and cost. This work develops an integral feedstock management system to optimise the entire supply chain. A new monitoring system based on an RGB-D sensor is presented as well as the data processing pipeline from raw depth measurements to bin specific daily consumption rates.

Keyword :  Inventory management, Vendor Managed Inventories, Internet of Things.

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100409.pdf

Monday, May 10, 2021

CODE GENERATION BASED ON INFERENCE AND CONTROLLED NATURAL LANGUAGE INPUT

Author :  Howard Dittmer

Affiliation :  DePaul University, Chicago

Country :  USA

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 04, April, 2020

Abstract :

Over time the level of abstraction embodied in programming languages has continued to grow. Yet, most programming languages still require programmers to conform to the language's rigid constructs. These constructs have been implemented in the name of efficiency for the computer. The continual increase in computing power allows us to consider techniques that are no longer limited by this constraint. To this end, we have created CABERNET, a Controlled Nature Language (CNL) approach. CABERNET allows programmers to use a simple outline-based syntax. This allows increased programmer efficiency and syntax flexibility. CNLs have successfully been used for writing requirements documents. We propose taking this approach well beyond this to fully functional programs. Our approach uses heuristics and inference to analyze and determine the programmer's intent. The goal is for programs to be aligned with the way that the humans think rather than the way computers process information

Keyword :  Controlled Natural Language, Literate Programming, Programming Language, ComputerAided Software

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100408.pdf

Friday, May 7, 2021

AN ANALYSIS OF THE EMOTIONAL TENDENCY OF NEW WORDS IN CHINESE TEXT BASED ON WORD2VEC

Author :  Jiang Quan

Affiliation :  Wuhan University of Technology

Country :  China

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 04, April, 2020

Abstract :

At present, there are many new words expressing emotions on the Internet, but the expressions of these new words have rich meanings but lack of accurate definitions, so it is difficult to analyze their emotional tendentiousness, This thesis studies the feasibility and framework design of word2vec based analysis method of emotional neologisms' tendency, and conducts experiments on Weibo corpus. The results show that new words can analyze their emotional tendency from their similar words.

Keyword :  Word vector; New word discovery; Emotional word; Tendentiousness analysis; Word2Vec

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100407.pdf 

Thursday, May 6, 2021

Privacy Enhanced Attribute based eSign

Author :  Puneet Bakshi

Affiliation :  Indian Institute of Technology

Country :  India

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 04, April, 2020

Abstract :

In recent years, Government of India has introduced many Aadhaar based online services. Although these initiatives helped India compete in digital revolution across world and were acclaimed by many, they have also raised some concerns about security especially the privacy aspects. One of the initiative in this direction is eSign which provides an online electronic signature service to its subscribers. Although most of the security aspects are addressed by eSign, some of the privacy aspects are yet to be addressed. This paper presents a scheme to implement privacy enhanced eSign using Attribute based Signatures (ABS). For the practical and efficient realization of the scheme, a token based approach is proposed.

Keyword :  eSign · Aadhaar · eSign · Privacy

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100406.pdf

INFORMATION TECHNOLOGY OF LASER COAGULATION STRATEGY SELECTION IN DIABETIC RETINOPATHY TREATMENT

Author :  Shirokanev Alexander

Affiliation :  IPSI RAS - branch of the FSRC «Crystallography and Photonics» RAS, Molodogvardejskaya street 151

Country :  Russia

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 04, April, 2020

Abstract :

Diabetic retinopathy is frequent, the most dangerous fundus disease. Diabetic retinopathy can result in many serious diseases. For various reasons, patients lose vision in untimely or incorrect treatment of diabetic retinopathy. The current method of treating diabetic retinopathy is laser coagulation. The ophthalmologist decides which zones need to be shelled to reduce edema based on his experience. Laser radiation parameters and distance between laser shots are also selected based on the experience of previous operations. However, the accuracy of the selection of these parameters can affect the result of treatment. Achieving high accuracy is empirical difficult. The present paper proposes a technology for selecting an effective laser coagulation strategy consisting in application of a genetic efficiency optimization algorithm based on solving of the problems of mathematical simulation of laser burns. Technology solves the problem of choosing accurate laser coagulation parameters.

Keyword :  Diabetic retinopathy, laser coagulation, ocular fundus, information technology, mathematical modeling, thermal conductivity equation

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100405.pdf

Tuesday, May 4, 2021

THE PORT Z3R0 EFFECT! HUMAN BEHAVIORS RELATED TO SUSCEPTIBILITY

Author :  Henry Collier

Affiliation :  Norwich University

Country :  USA

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 04, April, 2020

Abstract :

Current practices to defend networks against threats involve hardening systems by limiting points of ingress into the system. The most common method of limiting ingress into a system is by limiting which ports are allowed through the firewall. Port limitation as a method of defense is normally effective. Ports in a firewall range from 0 through 65,535 and covers the technical aspects of information security. One method of ingress not covered by technical ports is the human port, coined “port Z3r0” for this paper. To better defend against port Z3r0, we must understand the human better and why they are susceptible. This paper explores the basic human behaviors related to susceptibility and identifies the classifications of traits that increase a person’s susceptibility level. Additionally, this paper will address the issue of how the current model of teaching end-users to defend themselves is lacking and needs to be improved.

Keyword :  Information Security, Non-Malicious Insider Threat, Susceptibility, Human Behaviors, Cognition

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100404.pdf

Monday, May 3, 2021

DRIVING PRODUCT SALES PERFORMANCE USING PRODUCT PRELAUNCH LINGUISTICS ANALYTIC APPROACH

Author :  Winnie Ng

Affiliation :  The Hong Kong Polytechnic University

Country :  Hong Kong

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 04, April, 2020

Abstract :

This paper uses a natural linguistics analytic approach, by studying product prelaunch events’ script, to investigate the determinants of driving the product sales. This research contributes to the theoretical framework of identifying the customer values which impact the product sales. Moreover, we investigate how product sales be driven by the optimism attitude and affective forecasting, which are vocal during product prelease events. Through the pilot study of analysing the essential words, which represent the underlying customer values from the script of Apple Inc. product prelaunch events, we found that product functional and experiential/ hedonic of customer values drive product sales. Induced affective forecasting message negatively moderated the impact of cost/ sacrifices values on product sales. In addition to the theoretical framework contributions, this research provides practical guidelines of how to shape the product prelaunch speech to maximize the sales of the to-be-released products.

Keyword :  Product Preannouncement, Product Sales, Signalling, Communications, Speech Recognition

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100403.pdf

Sunday, May 2, 2021

COMPARATIVE ANALYSIS OF WORD EMBEDDINGS FOR CAPTURING WORD SIMILARITIES

Author :  Martina Toshevska

Affiliation :  Cyril and Methodius University, Skopje

Country :  Macedonia

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 04, April, 2020

Abstract :

Distributed language representation has become the most widely used technique for language representation in various natural language processing tasks. Most of the natural language processing models that are based on deep learning techniques use already pre-trained distributed word representations, commonly called word embeddings. Determining the most qualitative word embeddings is of crucial importance for such models. However, selecting the appropriate word embeddings is a perplexing task since the projected embedding space is not intuitive to humans. In this paper, we explore different approaches for creating distributed word representations. We perform an intrinsic evaluation of several state-of-the-art word embedding methods. Their performance on capturing word similarities is analysed with existing benchmark datasets for word pairs similarities. The research in this paper conducts a correlation analysis between ground truth word similarities and similarities obtained by different word embedding methods.

Keyword :  Word Embeddings, Distributed Word Representation, Word Similarity

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100402.pdf