Статьи журнала - International Journal of Information Technology and Computer Science
Все статьи: 1195
A Survey on Current Repertoire for 5G
Статья научная
Cellular technology progressed miraculously in the last decade. It has redefined communication paradigm. Statistics provided by Ericson and Cisco show the number of mobile connected devices will reach figures of 9.2 billion and 11.6 billion respectively by 2020. Overall connected devices will surpass 50 billion then. Extremely higher data rates, zero latency, massively scalable, connecting everything anywhere is what that 5G promises. To meet such ambitious goals which apparently seems challenging, the tools and technologies that mobile communication has in its repertoire and what it needs more either enhancement in existing solutions or new solution or joint venture of both, is a question that demands an answer. To realize 5G, evolution and revolution both approaches are being employed. Evolution seeks enhancements in existing technologies while revolution looks for new innovations and technologies. Extension in frequency spectrum, network densification, MIMO, carrier aggregation, Centralized-RAN, HetNets, and Network Functionality Virtualization are the key enablers. This paper disseminates information about ongoing research and development of 5G.
Бесплатно
A Survey on Fault Tolerant Multi Agent System
Статья научная
A multi-agent system (MAS) is formed by a number of agents connected together to achieve the desired goals specified by the design. Usually in a multi agent system, agents work on behalf of a user to accomplish given goals. In MAS co-ordination, co-operation, negotiation and communication are important aspects to achieve fault tolerance in MAS. The multi-agent system is likely to fail in a distributed environment and as an outcome of such, the resources for MAS may not be available due to the failure of an agent, machine crashes, process failure, software failure, communication failure and/or hardware failure. Therefore, many researchers have proposed fault tolerance approaches to overcome the failure in MAS. So we have surveyed these approaches in this paper, whereby our contribution is threefold. Firstly, we have provided taxonomy of faults and techniques in MAS. Secondly, we have provided a qualitative comparison of existing fault tolerance approaches. Thirdly, we have provided an evaluation of existing fault tolerance techniques. Results show that most of the existing schemes are not very efficient, due to various reasons like high computation costs, costly replication and large communication overheads.
Бесплатно
A Survey on Security Threats to Machine Learning Systems at Different Stages of its Pipeline
Статья научная
In recent years, Machine learning is being used in various systems in wide variety of applications like Healthcare, Image processing, Computer Vision, Classifications, etc. Machine learning algorithms have shown that it can solve complex problem-solving capabilities close to humans or beyond humans as well. But recent studies show that Machine Learning Algorithms and models are vulnerable to various attacks which compromise security the systems. These attacks are hard to detect because they can hide in data at various stages of machine learning pipeline without being detected. This survey aims to analyse various security attacks on machine learning and categorize them depending on position of attacks in machine learning pipeline. This paper will focus on all aspects of machine learning security at various stages from training phase to testing phase instead of focusing on one type of security attack. Machine Learning pipeline, Attacker’s goals, Attacker’s knowledge, attacks on specified applications are considered in this paper. This paper also presented future scope of research of security attacks in machine learning. In this Survey paper, we concluded that Machine Learning Pipeline itself is vulnerable to different attacks so there is need to build a secure and robust Machine Learning Pipeline. Our survey has categorized these security attacks in details with respect to ML Pipeline stages.
Бесплатно
A Swarm Intelligence Based Model for Mobile Cloud Computing
Статья научная
Mobile Computing (MC) provides multi services and a lot of advantages for millions of users across the world over the internet. Millions of business customers have leveraged cloud computing services through mobile devices to get what is called Mobile Cloud Computing (MCC). MCC aims at using cloud computing techniques for storage and processing of data on mobile devices, thereby reducing their limitations. This paper proposes architecture for a Swarm Intelligence Based Mobile Cloud Computing Model (SIBMCCM). A model that uses a proposed Parallel Particle Swarm Optimization (PPSO) algorithm to enhance the access time for the mobile cloud computing services which support different E Commerce models and to better secure the communication through the mobile cloud and the mobile commerce transactions.
Бесплатно
A System Call Randomization Based Method for Countering Code-Injection Attacks
Статья научная
Code-injection attacks pose serious threat to today’s Internet. The existing code-injection attack defense methods have some deficiencies on performance overhead and effectiveness. To this end, we propose a method that uses system called randomization to counter code injection attacks based on instruction set randomization idea. System calls must be used when an injected code would perform its actions. By creating randomized system calls of the target process, an attacker who does not know the key to the randomization algorithm will inject code that isn’t randomized like as the target process and is invalid for the corresponding de-randomized module. The injected code would fail to execute without calling system calls correctly. Moreover, with extended complier, our method creates source code randomization during its compiling and implements binary executable files randomization by feature matching. Our experiments on built prototype show that our method can effectively counter variety code injection attacks with low-overhead.
Бесплатно
A Systematic Literature Review of Studies Comparing Process Mining Tools
Статья научная
Process Mining (PM) and PM tool abilities play a significant role in meeting the needs of organizations in terms of getting benefits from their processes and event data, especially in this digital era. The success of PM initiatives in producing effective and efficient outputs and outcomes that organizations desire is largely dependent on the capabilities of the PM tools. This importance of the tools makes the selection of them for a specific context critical. In the selection process of appropriate tools, a comparison of them can lead organizations to an effective result. In order to meet this need and to give insight to both practitioners and researchers, in our study, we systematically reviewed the literature and elicited the papers that compare PM tools, yielding comprehensive results through a comparison of available PM tools. It specifically delivers tools’ comparison frequency, methods and criteria used to compare them, strengths and weaknesses of the compared tools for the selection of appropriate PM tools, and findings related to the identified papers' trends and demographics. Although some articles conduct a comparison for the PM tools, there is a lack of literature reviews on the studies that compare PM tools in the market. As far as we know, this paper presents the first example of a review in literature in this regard.
Бесплатно
A Systematic Literature Review on SMS Spam Detection Techniques
Статья научная
Spam SMSes are unsolicited messages to users, which are disturbing and sometimes harmful. There are a lot of survey papers available on email spam detection techniques. But, SMS spam detection is comparatively a new area and systematic literature review on this area is insufficient. In this paper, we perform a systematic literature review on SMS spam detection techniques. For that purpose, we consider the available published research works from 2006 to 2016. We choose 17 papers for our study and reviewed their used techniques, approaches and algorithms, their advantages and disadvantages, evaluation measures, discussion on datasets and finally result comparison of the studies. Although, the SMS spam detection techniques are more challenging than email spam detection techniques because of the regional contents, use of abbreviated words, unfortunately none of the existing research addresses these challenges. There is a huge scope of future research in this area and this survey can act as a reference point for the future direction of research.
Бесплатно
A Systematic Review of Natural Language Processing in Healthcare
Статья научная
The healthcare system is a knowledge driven industry which consists of vast and growing volumes of narrative information obtained from discharge summaries/reports, physicians case notes, pathologists as well as radiologists reports. This information is usually stored in unstructured and non-standardized formats in electronic healthcare systems which make it difficult for the systems to understand the information contents of the narrative information. Thus, the access to valuable and meaningful healthcare information for decision making is a challenge. Nevertheless, Natural Language Processing (NLP) techniques have been used to structure narrative information in healthcare. Thus, NLP techniques have the capability to capture unstructured healthcare information, analyze its grammatical structure, determine the meaning of the information and translate the information so that it can be easily understood by the electronic healthcare systems. Consequently, NLP techniques reduce cost as well as improve the quality of healthcare. It is therefore against this background that this paper reviews the NLP techniques used in healthcare, their applications as well as their limitations.
Бесплатно
A Taxonomy of Data Management Models in Distributed and Grid Environments
Статья научная
The distributed environments vary largely in their architectures, from tightly coupled cluster environment to loosely coupled Grid environment and completely uncoupled peer-to-peer environment, and thus differ in their working environments as well as performance. To meet the specific needs of these environments for data organization, replication, transfer, scheduling etc. the data management systems implement different data management models. In this paper, major data management tasks in distributed environments are identified and a taxonomy of the data management models in these environments is presented. The taxonomy is used to highlight the specific data management requirements of each environment and highlight the strengths and weakness of the implemented data management models. The taxonomy is followed by a survey of different distributed and Grid environments and the data management models they implement. The taxonomy and the survey results are used to identify the issues and challenges of data management for future exploration.
Бесплатно
A Temporal Reasoning System for Diagnosis and Therapy Planning
Статья научная
The research is based on the designing of Clinical Temporal Mediator for medical domain. The Clinical Temporal Mediator incorporates the concept of artificial intelligence for performing temporal reasoning tasks. The designing of reasoning system involves the implementation of various mathematical models of insulin-glucose metabolism. The reasoning system consists of three subsystems: Nuti-Diet subsystem, Insulin-Glucose subsystem and Therapy Planner and Diagnosis subsystem. The paper discusses about the designing of TPD subsystems. The temporal mediator perform diagnosis on patient's time oriented database and also suggest therapy planning for diabetes mellitus patient.
Бесплатно
Статья научная
Predicting human behavior based on the usage of text on social networking sites can be a challenging area of interest to a particular community. Text mining being a major interest in Data Mining has vast applications in various fields. Clients can assess an individual’s behavior using the proposed framework that is based on person’s textual interaction with other people. In this paper, a framework is proposed for predicting human behavior in three phases- Text Extraction, Text cleaning and Text Analysis. For cleaning text, all the stop words have been removed and then the text is utilized for further processing. Then, the terms from the text are clustered based on semantic similarity and then gets associated with respective physiological parameters that identify a human behavior. This application is best suited for the fields of Criminal Sciences, Medical Sciences, Human Resource Department and Political Science and even for Matrimonial purposes. The proposed framework is applied on some famous world known celebrities and the results are quite encouraging.
Бесплатно
A Tool for Diabetes Prediction and Monitoring Using Data Mining Technique
Статья научная
Data mining is the process of analyzing different aspects of data and aggregating it into useful information. Classification is a data mining task generally used in medical data mining. The goal here is to discover new and useful patterns to provide meaningful and useful information for the users about the diabetes. Here a diabetes prediction and monitoring system is designed and implemented using ID3 classification algorithm. The symptoms causing diabetes are identified and are applied to the prediction model based on which the prediction is done. The monitoring module analyzes the laboratory test reports of the blood sugar levels of the patient and provides proper awareness messages to the patient through mail and bar chart.
Бесплатно
A Trust Management System for the Nigerian Cyber-health Community
Статья научная
Trust is a basic requirement for the acceptance and adoption of new services related to health care, and therefore, vital in ensuring that the integrity of shared patient information among multi-care providers is preserved and that no one has tampered with it. The cyber-health community in Nigeria is in its infant stage with health care systems and services being mostly fragmented, disjointed, and heterogeneous with strong local autonomy and distributed among several healthcare givers platforms. There is the need for a trust management structure for guaranteed privacy and confidentiality to mitigate vulnerabilities to privacy thefts. In this paper, we developed an efficient Trust Management System that hybridized Real-Time Integrity Check (RTIC) and Dynamic Trust Negotiation (DTN) premised on the Confidentiality, Integrity, and Availability (CIA) model of information security. This was achieved through the design and implementation of an indigenous and generic architectural framework and model for a secured Trust Management System with the use of the advanced encryption standard (AES-256) algorithm for securing health records during transmission. The developed system achieved Reliabity score, Accuracy and Availability of 0.97, 91.30% and 96.52% respectively.
Бесплатно
A Turkish Wikipedia Text Summarization System for Mobile Devices
Статья научная
Today Wikipedia provides a very large and reliable domain-independent encyclopedic repository. With this study a mobile system which summarizes Turkish Wikipedia text is presented. The presented system selects the sentences due to structural features of Turkish language and semantic features of the sentences. The performance evaluation is made based on judgments of human experts. The results are tested due to precision and recall values of a ranked sentence list and it is concluded that, the summarization results are promising.
Бесплатно
A Web-Based Skin Disease Diagnosis Using Convolutional Neural Networks
Статья научная
Skin diseases are reported to be the most common disease in humans among all age groups and a significant root of infection in sub-Saharan Africa. The diagnosis of skin diseases using conventional approaches involves several tests. Due to this, the diagnosis process is seen to be intensely laborious, time-consuming and requires an extensive understanding of the domain. The enhancement of computer vision through artificial intelligence has led to a more straightforward and quicker way of detecting patterns in images, which can be harnessed to equip diagnosis process. Despite the breakthrough in technology, the dermatological process in Ghana is yet to be automated, making the diagnosis process complicated and time-consuming. Hence, this study sought to propose a web-based skin disease detection system named medilab-plus using a convolutional neural network classifier built upon the Tensorflow framework for detecting (atopic dermatitis, acne vulgaris, and scabies) skin diseases. Experimental results of the proposed system exhibited classification accuracy of 88% for atopic dermatitis, 85% for acne vulgaris, and 84.7% for scabies. Again, the computational time (0.0001 seconds) of the proposed system implies that any dermatologist, who decides to implement this study, can attend to not less than 1,440 patients a day compared to the manual diagnosis process. It is estimated that the proposed system will enhance accuracy and offer fasting diagnosis results than the traditional method, which makes this system a trustworthy and resourceful for dermatological disease detection. Additionally, the system can serve as a realtime learning platform for students studying dermatology in medical schools in Ghana.
Бесплатно
A Web-based Portal for Ornamental Plants and Flowers in Arusha City, Tanzania
Статья научная
There is a wide collection of invaluable varie-ties of ornamental plants and flowers available for sale by vendors in Arusha city contributing to local employment, and food security. Horticulture in Tanzania is dominated by small scale farmers in Arusha that contribute to about 70% of the produces in the sector. However, there are challenges that need to be addressed including; inadequate information for the development of the sector and livelihoods of the vendors. The information on the varied species of ornamental plants and flowers are mainly undocumented and not digitized. This limits access to the scientific community and the general public bringing on these varieties in Arusha a growing conservation concern. The other challenge is that the small-scale vendors have limited visibility to regional markets and international market places which hinders their business growth. On this study, a Web portal was developed for inventory, mapping and digitization of the various species of ornamental plants and flowers as a solution to above challenges. Data collection was conducted using various data collection techniques such as; Interviews, observations, Questionnaire (Open Data Kit) and re-viewing numerous research papers in seven wards of Arusha city where the vendors grow and sell a number of species of ornamental plants and flowers. Both qualitative and quantitative methods mentioned above were deployed to provide insights on the ornamental plants and flower business operations. For the survey, 70 varieties of ornamental plants and flowers were gathered and arranged categorically in terms of taxonomy and usage and uploaded on the portal. The portal developed indicates the potential to help stakeholders find plants’ and flowers’ varieties infor-mation, images, and sales location online, the vendors will be able to advertise their products on the portal and conduct business with customers online. In addition, it will also help Arusha City Representatives with baseline information on the sector to make informed plans and decisions.
Бесплатно
Статья научная
It is a tremendous challenge to transmit real-time video streams over wireless sensor network because of the poor wireless communication conditions and the high requirements of video transmission. The opportunistic routing protocol can take advantage of the broadcast nature of wireless communication and can improve transfer throughput significantly. But the bigger size of transmission unit also increases the end-to-end delay at the same time. In order to overcome this problem and improve the real-time video transmission quality in wireless video sensor network, we propose a source adaptive frame discard algorithm for MAC-independent Opportunistic Routing & Encoding (MORE) Protocol in this paper. In our approach, the historical transmission delay is recorded to estimate current network transmission rate. Based on the video deadline, frames predicted to be delayed are discarded adaptively in the source node to get better overall video quality. In some practice application scenarios, there are usually need to deliver multiple video streams over multi-hop wireless network. It can’t work effectively with the originally MORE protocol in such scenarios. Furthermore, we modify the MORE protocol and design an adaptive scheme to support multiple video streams over multi-hop wireless video sensor network in this paper. The simulation results show that our algorithm can reduce frame loss rate and improve video quality significantly.
Бесплатно
A comparative analysis and proposing ‘ANN Fuzzy AHP model’ for requirements prioritization
Статья научная
Requirements prioritization is an essential component of software release planning and requirement engineering. In requirement engineering the requirements are arranged as per their priority using prioritization techniques to develop high-quality software’s. It also helps to the decision makers for making good decisions about, which set of requirements should be executed first. In any software development industry a ‘software project’ may have a larger number of requirements and then it is very difficult to prioritize such type of larger number of requirements as per their priority when stakeholder’s priorities are in the form of linguistic variables. This paper presents a comparative analysis of existing seven techniques based on various aspects like: scale of prioritization, scalability, time complexity, easy to use, accuracy, and decision making, etc. It was found from literature survey none of the techniques can be considered as the best one. These techniques undergo from a number of drawbacks like: time complexity, lack of scalability, Negative degree of membership function, inconsistency ratio, rank updates during requirement development, and conflicts among stakeholders. This paper proposed a model called ‘ANN Fuzzy AHP model’ for requirements prioritization that will overcome these limitations and drawbacks. In the investigation of this proposed model, a case study is implemented. Ozcan et al [31] using a FAHP (Fuzzy AHP) with ANN based technique to choose the best supplier based on the multiple criteria. The examination on ANN with FAHP is performed on MATLAB software and outcome evaluated by fuzzy pair-wise comparison matrix with three supplier selection criteria states that the requirements prioritization outcome is better from existing techniques.with higher priority.
Бесплатно
A comparison between syllable, di-phone, and phoneme-based Myanmar speech synthesis
Статья научная
Among the speech synthesis approach, concatenative method is one of the most popular method which can produce more natural sounding speech output. The most important challenge in this method is choosing an appropriate unit for creating a database. The present used speech units are word, syllable, di-phone, tri-phone and phoneme. The speech quality may be trade-off between the selected speech units. This paper presents the three speech synthesis system of Myanmar language, respectively based on syllable, di-phone and phoneme speech units by using concatenation method. Then, we compare the speech quality of the three systems, using the subjective tests.
Бесплатно
A context-aware reference architecture for ambient assisted living information systems
Статья научная
AAL (Ambient Assisted Living) existing architectures lack the sense of abstraction. The overall existing designs propose a set of elements combined with specific technologies. These visions of AAL systems narrows the possibilities and the choices ahead of the engineers and strict the range of using new technologies, which are likely to be easier and affordable. In this paper, we propose a context-aware RA (Reference Architecture) suitable for the design of distributed AAL systems. Our design is standardized and technology independent. Our aim is to provide a common background for developers and deployers to achieve a common understanding while designing the systems. The major gain is to reduce the efforts made while integrating several systems into one complete and stable environment. Ignoring all the specifications, the details and the objectives of the systems, we introduce the standard qualifications, practices and experiences that assimilate the core of every AAL oriented system. Our perception is global, unified and standard. In addition, it presents an infrastructure that would survive the evolution of technologies. It is adjustable and adaptable to the different possibilities of AAL applications.
Бесплатно
