GCRIS :: Search

Search Results

Now showing 1 - 10 of 27

Citation - WoS: 1
Citation - Scopus: 2
Potential of Support-Vector Regression for Forecasting Stream Flow
(Univ Osijek, Tech Fac, 2014) Radzi, Mohd Rashid Bin Mohd; Shamshirband, Shahaboddin; Aghabozorgi, Saeed; Misra, Sanjay; Akib, Shatirah; Kiah, Laiha Mat; Computer Engineering
Stream flow is an important input for hydrology studies because it determines the water variability and magnitude of a river. Water resources engineering always deals with historical data and tries to estimate the forecasting records in order to give a better prediction for any water resources applications, such as designing the water potential of hydroelectric dams, estimating low flow, and maintaining the water supply. This paper presents three soft-computing approaches for dealing with these issues, i.e. artificial neural networks (ANNs), adaptive-neuro-fuzzy inference systems (ANFISs), and support vector machines (SVMs). Telom River, located in the Cameron Highlands district of Pahang, Malaysia, was used in making the estimation. The Telom River's daily mean discharge records, such as rainfall and river-level data, were used for the period of March 1984-January 2013 for training, testing, and validating the selected models. The SVM approach provided better results than ANFIS and ANNs in estimating the daily mean fluctuation of the stream's flow.
Citation - WoS: 21
Citation - Scopus: 34
An Artificial Neural Network Model for Road Accident Prediction: a Case Study of a Developing Country
(Budapest Tech, 2014) Ogwueleka, Francisca Nonyelum; Misra, Sanjay; Ogwueleka, Toochukwu Chibueze; Fernandez-Sanz, L.; Computer Engineering
Road traffic accidents (RTA) are one of the major root causes of the unnatural loses of human beings all over the world. Although the rates of RTAs are decreasing in most developed countries, this is not the case in developing countries. The increase in the number of vehicles and inefficient drivers on the road, as well as to the poor conditions and maintenance of the roads, are responsible for this crisis in developing countries. In this paper, we produce a design of an Artificial Neural Network (ANN) model for the analysis and prediction of accident rates in a developing country. We apply the most recent (1998 to 2010) data to our model. In the design, the number of vehicles, accidents, and population were selected and used as model parameters. The sigmoid and linear functions were used as activation functions with the feed forward-back propagation algorithm. The performance evaluation of the model signified that the ANN model is better than other statistical methods in use.
Citation - WoS: 13
Citation - Scopus: 18
An E-Environment System for Socio-Economic Sustainability and National Security
(Politechnika Lubelska, 2018) Okewu, Emmanuel; Misra, Sanjay; Fernandez Sanz, Luis; Maskeliunas, Rytis; Damasevicius, Robertas; Computer Engineering
Though there are adequate institutional frameworks and legal instruments for the protection of the Sub-Saharan African environment, their impact on the development and conservation (protection) of the environment leaves much to be desired. This assertion is substantiated by the reality that inspite of these regulatory frameworks, the environment is largely degraded with negative ramifications for the twin goals of attaining sustainable socio-economic advancement and realization of environmental rights. Both national and regional state of environment (SoE) reports show that degradation is apparent. It is worthy of mention that almost all African countries have ratified and domesticated the various regional and subregional environmental agreement. Efforts to solve the puzzle have revealed that corruption and environmental degradation in Sub-Saharan Africa are closely linked. Financial impropriety in ecological funds management, poorly equipped environmental protection institutions, and inadequate citizens' environmental management awareness campaigns are outcomes of corruption in the public sector. Since corruption thrives in the absence of transparency and accountability, this study proposes a cutting-edge technology-based solution that promotes participatory environmental accountability using an e-Environment system. The web-based multi-tier e-Environment system will empower both citizens and government officials to deliberate online real-time on environmental policies, programmes and projects to be embarked upon. Both parties will equally put forward proposals on the use of tax payers money in the environment sector while monitoring discrepancies between amount budgeted, amount released and actual amount spent. We applied design and software engineering skills to actualize the proposed solution. Using Nigeria as case study, our research methodology comprised literature review, requirements gathering, design of proposed solution using universal modelling language (UML) and development/implementation on the Microsoft SharePoint platform. In view of our determination to evolve a zero-defect software, we applied Cleanroom Software Engineering techniques. The outcome obtained so far has proved that the model supports our expectations. The system is not only practical, but ecologically sound. It is anticipated that the full-scale implementation of such an enterprise e-Environment system will decrease the current tide of corruption in the environment sector, mitigate environmental degradation and by extension, reduce social-economic tensions and guarantee national security.
Citation - WoS: 9
Citation - Scopus: 14
A Comparative Study of Agile, Component-Based, Aspect-Oriented and Mashup Software Development Methods
(Univ Osijek, Tech Fac, 2012) Patel, Ahmed; Seyfi, Ali; Taghavi, Mona; Wills, Christopher; Na, Liu; Latih, Rodziah; Misra, Sanjay; Computer Engineering
This paper compares Agile Methods, Component-Based Software Engineering (CBSE), Aspect-Oriented Software Development (AOSD) and Mashups as the four most advanced software development methods. These different approaches depend almost totally on their application domain but their usability can be equally applied across domains. The purpose of this comparative analysis is to give a succinct and clear review of these four methodologies. Their definitions, characteristics, advantages and disadvantages are considered and a conceptual mind-map is generated that sets out a foundation to assist in the formulation and design of a possible new integrated software development approach. This includes supportive techniques to benefit from the examined methods' potential advantages for cross-fertilization. It is a basis upon which new thinking may be initiated and further research stimulated in the software engineering subject field.
Citation - WoS: 12
Citation - Scopus: 17
Entropy as a Measure of Quality of Xml Schema Document
(Zarka Private Univ, 2011) Basci, Dilek; Misra, Sanjay; Computer Engineering
In this paper, a metric for the assessment of the structural complexity of eXtensible Markup Language schema document is formulated. The present metric 'Schema Entropy is based on entropy concept and intended to measure the complexity of the schema documents written in W3C XML Schema Language due to diversity in the structures of its elements. The SE is useful in evaluating the efficiency of the design of Schemas. A good design reduces the maintainability efforts. Therefore, our metric provides valuable information about the reliability and maintainability of systems. In this respect, this metric is believed to be a valuable contribution for improving the quality of XML-based systems. It is demonstrated with examples and validated empirically through actual test cases.
Citation - WoS: 7
Citation - Scopus: 15
Lossless Text Compression Technique Using Syllable Based Morphology
(Zarka Private Univ, 2011) Akman, Ibrahim; Bayindir, Hakan; Ozleme, Serkan; Akin, Zehra; Misra, Sanjay; Computer Engineering
In this paper, we present a new lossless text compression technique which utilizes syllable-based morphology of multi-syllabic languages. The proposed algorithm is designed to partition words into its syllables and then to produce their shorter bit representations for compression. The method has six main components namely source file, filtering unit, syllable unit, compression unit, dictionary file and target file. The number of bits in coding syllables depends on the number of entries in the dictionary file. The proposed algorithm is implemented and tested using 20 different texts of different lengths collected from different fields. The results indicated a compression of up to 43%.
Citation - WoS: 6
Citation - Scopus: 6
Model-Driven Engineering and Creative Arts Approach To Designing Climate Change Response System for Rural Africa: a Case Study of Adum-Aiona Community in Nigeria
(Politechnika Lubelska, 2017) Okewu, Emmanuel; Misra, Sanjay; Okewu, Jonathan; Computer Engineering
Experts at the just concluded climate summit in Paris (COP21) are unanimous in opinion that except urgent measures are taken by all humans, average global temperature rise would soon reach the deadly 2 degrees C mark. When this happens, socio-economic livelihoods, particularly in developing economies, would be dealt lethal blow in the wake of associated natural causes such as increased disease burden, soil nutrient destruction, desertification, food insecurity, among others. To avert imminent dangers, nations, including those from Africa, signed a legally binding universally accepted climate control protocol to propagate and regulate environmentally-friendly behaviours globally. The climate vulnerability of Africa as established by literature is concerning. Despite contributing relatively less than other continents to aggregate environmental injustice, the continent is projected to bear the most brunt of environmental degradation. This is on account of her inability to put systems and mechanisms in place to stem consequences of climate change. Hence, our resolve to use a combination of scientific and artistic models to design a response system for tackling climate challenges in Africa. Our model formulation encompasses computational model and creative arts model for drawing attention to environmentally friendly behaviours and climate adaptation and mitigation strategies. In this work, we focus on rural Africa to share experience of climate change impact on agriculture mainstay of rural African economy. We examine the carbon footprints of a rural community in Nigeria the Adum-Aiona community as case study and for industrial experience. The authors will provide operational data to substantiate claims of existential threats posed by greenhouse gas (GHG) generation on livelihoods of rural dwellers. The study will also design and test a Climate Change Response System (CCRS) that will enable people to adapt and reduce climate change impact. To achieve the research objective, the researchers will review literature, gather requirements, model the proposed system using Unified Modelling Language (UML), and test CCRS statically. We expect that the implementation of the proposed system will enable people mitigate the effects of, and adapt to, climate change-induced socio-economic realities. This is besides the fact that the empirical data provided by the study will help clear doubts about the real or perceived threats of climate change. Finally, the industrial experience and case study we share from Africa using model-driven engineering approach will scale up the repository of knowledge of both climate change research and model-driven engineering community.
Citation - WoS: 21
Citation - Scopus: 22
A Discussion on the Role of People in Global Software Development
(Univ Osijek, Tech Fac, 2013) Misra, Sanjay; Colomo-Palacios, Ricardo; Pusatli, Tolga; Soto-Acosta, Pedro; Computer Engineering
Literature is producing a considerable amount of papers which focus on the risks, challenges and solutions of global software development (GSD). However, the influence of human factors on the success of GSD projects requires further study. The aim of our paper is twofold. First, to identify the challenges related to the human factors in GSD and, second, to propose the solution(s), which could help in solving or reducing the overall impact of these challenges. The main conclusions of this research can be valuable to organizations that are willing to achieve the quality objectives regarding GSD projects.
Citation - WoS: 11
Citation - Scopus: 16
Deep Neural Networks for Curbing Climate Change-Induced Farmers-Herdsmen Clashes in a Sustainable Social Inclusion Initiative
(Politechnika Lubelska, 2019) Okewu, Emmanuel; Misra, Sanjay; Fernandez Sanz, Luis; Ayeni, Foluso; Mbarika, Victor; Damasevicius, Robertas; Computer Engineering
Peaceful coexistence of farmers and pastoralists is becoming increasingly elusive and has adverse impact on agricultural revolution and global food security. The targets of Sustainable Development Goal 16 (SDG 16) include promoting peaceful and inclusive societies for sustainable development, providing access to justice for all and building effective, accountable and inclusive institutions at all levels. As a soft approach and long term solution to the perennial farmers herdsmen clashes with attendant humanitarian crisis, this study proposes a social inclusion architecture using deep neural network (DNN). This is against the backdrop that formulating policies and implementing programmes based on unbiased information obtained from historical agricultural data using intelligent technology like deep neural network (DNN) can be handy in managing emotions. In this vision paper, a DNN-based Farmers-Herdsmen Expert System (FHES) is proposed based on data obtained from the Nigerian National Bureau of Statistics for tackling the incessant climate change induced farmers-herdsmen clashes, with particular reference to Nigeria. So far, many lives have been lost. FHES is modelled as a deep neural network and trained using farmers-herdsmen historical data. Input variables used include land, water, vegetation, and implements while the output is farmers/herders disposition to peace. Regression analysis and pattern recognition performed by the DNN on the farmers-herdsmen data will enrich the inference engine of FHES with extracted rules (knowledge base). This knowledge base is then relied upon to classify future behaviours of herdsmen/farmers as well as predict their dispositions to violence. Critical stakeholders like governments, service providers and researchers can leverage on such advisory to initiate proactive and socially inclusive conflict prevention measures such as, people-friendly policies, programmes and legislations. This way, conflicts can be averted, national security challenges tackled, and peaceful atmosphere guaranteed for sustainable development.
Citation - WoS: 9
Citation - Scopus: 22
Anomaly Detection Using Fuzzy Q-Learning Algorithm
(Budapest Tech, 2014) Shamshirband, Shahaboddin; Anuar, Nor Badrul; Kiah, Miss Laiha Mat; Misra, Sanjay; Computer Engineering
Wireless networks are increasingly overwhelmed by Distributed Denial of Service (DDoS) attacks by generating flooding packets that exhaust critical computing and communication resources of a victim's mobile device within a very short period of time. This must be protected. Effective detection of DDoS attacks requires an adaptive learning classifier, with less computational complexity, and an accurate decision making to stunt such attacks. In this paper, we propose an intrusion detection system called Fuzzy Q-learning (FQL) algorithm to protect wireless nodes within the network and target nodes from DDoS attacks to identify the attack patterns and take appropriate countermeasures. The FQL algorithm was trained and tested to establish its performance by generating attacks from the NSL-KDD and CAIDA DDoS Attack datasets during the simulation experiments. Experimental results show that the proposed FQL IDS has higher accuracy of detection rate than Fuzzy Logic Controller and Q-learning algorithm alone.

Filters

Settings

Sort By

Results per page

Search Results