Chiroma Haruna | University of Malaya, Malaysia (original) (raw)

Papers by Chiroma Haruna

Petroleum is the live wire of modern technology and its operations, with economic development bei... more Petroleum is the live wire of modern technology and its operations, with economic development being positively linked to petroleum consumption. Many meta-heuristic algorithms have been proposed in literature for the optimization of Neural Network (NN) to build a forecasting model. In this paper, as an alternative to previous methods, we propose a new flower pollination algorithm with remarkable balance between consistency and exploration for NN training to build a model for the forecasting of petroleum consumption by the Organization of the Petroleum Exporting Countries (OPEC). The proposed approach is compared with established meta-heuristic algorithms. The results show that the new proposed method outperforms existing algorithms by advancing OPEC petroleum consumption forecast accuracy and convergence speed. Our proposed method has the potential to be used as an important tool in forecasting OPEC petroleum Accepted for Publication in Applied Soft Computing – Elsevier, 2.8 Impact Factor 2 consumption to be used by OPEC authorities and other global oil-related organizations. This will facilitate proper monitoring and control of OPEC petroleum consumption.

The expansion of big data and the evolution of Internet of Things (IoT) technologies have played ... more The expansion of big data and the evolution of Internet of Things (IoT) technologies have played an important role in the feasibility of smart city initiatives. Big data offer the potential for cities to obtain valuable insights from a large amount of data collected through various sources, and the IoT allows the integration of sensors, radio-frequency identification, and Bluetooth in the real-world environment using highly networked services. The combination of the IoT and big data is an unexplored research area that has brought new and interesting challenges for achieving the goal of future smart cities. These new challenges focus primarily on problems related to business and technology that enable cities to actualize the vision, principles, and requirements of the applications of smart cities by realizing the main smart environment characteristics. In this paper, we describe the existing communication technologies and smart-based applications used within the context of smart cities. The visions of big data analytics to support smart cities are discussed by focusing on how big data can fundamentally change urban populations at different levels. Moreover, a future business model that can manage big data for smart cities is proposed, and the

3D map for mobile devices provide more realistic view of an environment and serves as better navi... more 3D map for mobile devices provide more realistic view of an environment and serves as better navigation aid. Previous research studies shows differences in 3D maps effect on acquiring of spatial knowledge. This is attributed to the differences in mobile device computational capabilities. Crucial to this is the time it takes for 3D map dataset to be rendered for a required complete navigation task. Different findings suggest different approaches on solving the problem of time required for both in-core (inside mobile) and out-core (remote) rendering of 3D dataset. Unfortunately, studies on analytical techniques required to show the impact of computational resources required for the use of 3D map on mobile devices were neglected by the research communities. This paper uses Support Vector Machine (SVM) to analytically classified mobile device computational capabilities required for 3D map that will be suitable for use as navigation aid. Fifty different Smart phones were categorized on the bases of their Graphical Processing Unit (GPU), display resolution, memory and size. The result of the proposed classification shows high accuracy.

In healthcare system, the sensor nodes are usually deployed in an unattended field or environment... more In healthcare system, the sensor nodes are usually deployed in an unattended field or environment and replacement of batteries is very difficult if not impossible. In this paper, Low-Energy Adaptive Clustering Hierarchy (LEACH) protocol was modified (MoLEACH) to improve energy efficiency of the LEACH for healthcare applications. In cluster head selection, the MoLEACH consider the residual energy of each node for calculation of the threshold value for the next round, unlike the original LEACH that uses the residual energy of the network. Comparative simulation analysis between the MoLEACH and LEACH in testing different parameters such as first node dead, half node dead, the effect of the number of nodes to the network lifetime, and energy distribution was performed. The simulation results show that the number of nodes affects the network lifetime in which increments of number of nodes decrease the network lifetime. In small area, minimum number of nodes is better for network lifetime in both MoLEACH and LEACH protocols. The MoLEACH shows improvement of energy efficiency over the LEACH in energy distribution. The MoLEACH was found to improve the energy efficiency of the LEACH, hence, prolong the network lifetime, thus achieved high residual battery capacity. The MoLEACH proposed in this study can be used effectively in healthcare applications, thereby reduces the need for frequent recharging or replacement of batteries. The MoLEACH is an alternative to the LEACH in healthcare application systems such as in in-home monitoring, in-hospital monitoring, ambulatory monitoring, vital sign monitoring in-hospitals, monitoring elderly people at home care, monitoring in mass-casualty disasters and clinical monitoring for automatic patient monitoring without disturbing patient comfort by the need for frequent recharging or replacement of batteries.

Sequential dataset is a collection of records written and read in sequential order. Information f... more Sequential dataset is a collection of records written and read in
sequential order. Information from the sequential dataset is very useful in
understanding the sequential patterns and finally making an appropriate
decision. However, generating of sequential dataset from log file is quite
complicated and difficult. Therefore, in this study we proposed a sequential
preprocessing model (SPM) and sequential preprocessing tool (SPT) as an
attempt to generate the sequential dataset. The result shows that SPT can be
used in generating the sequential dataset. We evaluated the performance of the
developed model against the log activities captured from UMT’s e-Learning
System called myLearn. With the minimum modification of the dataset, it can
be used by other data mining tool for further sequential patterns analysis

Collaborative Virtual Environment (CVE) is becoming popular in the last few years; this is becaus... more Collaborative Virtual Environment (CVE) is becoming popular in the last few years; this is because CVE is
designed to allow geographically distributed users to work together over the network. Currently, in the
development of CVE Systems, Client server architectures with multiple servers are used with TCP as
update transmitting transport protocol because of its reliability. With the increasing number of
collaborators, the transport protocol is inadequate to meet the system requirements in terms of timely data
transmission. The transport protocol (TCP) throughput deteriorates in the network with large delay which
leads to unsatisfactory consistency requirement of the CVE systems.We proposed a cloud based
architectural model for improving scalability and consistency in CVE in an earlier study. The current paper
aims at evaluating and comparing the performance of different TCP variants (Tahoe, Reno, New Reno,
Vegas, SACK, Fack and Linux) with the cloud based CVE architecture to determine the suitability of each
TCP variant for CVE. A comparative analysis between the different TCP variants is presented in terms of
throughput verses elapse time, with increasing number of users in the system. TCP Vegas with the cloud
based model was found to be effective for CVE systems based on Cloud Computi

The purpose of this research is to propose an alternative framework that can meet the needs of th... more The purpose of this research is to propose an alternative framework
that can meet the needs of the real-world practical application of crude oil price
prediction. This study presents an alternative model based on a neural network
and genetic algorithm (neuro-genetic) for the prediction of crude oil price while
considering the impact of uncertainties. The model was able to learn patterns
from volatile crude oil price datasets that were distorted by the Gulf War, Asian
financial crises, Iraq War, Venezuelan unrest and global financial crises. The
crude oil price predicted by the neuro-genetic model and the actual price were
found to be statistically equal. The results obtained by the neuro-genetic model
are significantly better than those of the comparison methods in terms of both
accuracy and CPU processing time. The model has the potential for realistic,
practical application in the real world

Cryptography refers to protecting transmitted information from unauthorized interception or tampe... more Cryptography refers to protecting transmitted information from unauthorized
interception or tampering, while cryptanalysis is art of breaking such secret ciphers and reading
information, or perhaps replacing it with different information. The research highlights a new
encryption technique called randomized text encryption. The algorithm proposed increases the
complexity of cryptanalyst to decrypt the ciphertext and restricts them to break the security of
encoded file. The proposed technique uses random numbers added to plaintext along with
encryption key. After applying encryption technique, each time same plaintext will be converted to
different ciphertext provided that encryption key is same or different. Two different characters are
generated against single character of plaintext that doubles the size of encrypted text. Decryption
process doesn’t require random numbers but only needs encryption key to decipher the encrypted
text. Consequently, the proposed technique is safe to different cryptanalytic attacks like Frequency
analysis, Brute-Force, Linear and Differential Cryptanalysis. Copyright © 2014 Praise Worthy
Prize S.r.l. - All rights reserved.

Management of higher education must continue to evaluate on an ongoing basis in order to improve ... more Management of higher education must continue
to evaluate on an ongoing basis in order to improve the
quality of institutions. This will be able to do the necessary
evaluation of various data, information, and knowledge of
both internal and external institutions. They plan to use
more efficiently the collected data, develop tools so that to
collect and direct management information, in order to
support managerial decision making. The collected data
could be utilized to evaluate quality, perform analyses and
diagnoses, evaluate dependability to the standards and
practices of curricula and syllabi, and suggest alternatives in
decision processes. Data minings to support decision making
are well suited methods to provide decision support in the
education environments, by generating and presenting relevant
information and knowledge towards quality improvement
of education processes. In educational domain, this
information is very useful since it can be used as a base for
investigating and enhancing the current educational standards
and managements. In this paper, a review on data
mining for academic decision support in education field is
presented. The details of this paper will review on recent
data mining in educational field and outlines future researches
in educational data mining.

Abstract: This paper proposes a support vector machine (SVM) model to advance the prediction accu... more Abstract: This paper proposes a support vector machine (SVM) model to
advance the prediction accuracy of global land-ocean temperature (GLOT),
which is globally significant for understanding the future pattern of climate
change. The GLOT dataset was collected from NASA’s GLOT index (C)
(anomaly with base: 1951–1980) for the period 1880 to 2013. We categorise
the dataset by decades to describe the behaviour of the GLOT within those
decades. The dataset was used to build an SVM Model to predict future values
of the GLOT. The performance of the model was compared with a multilayer
perceptron neural network (MLPNN) and validated statistically. The SVM was
found to perform significantly better than the MLPNN in terms of mean square
error and root mean square error, although computational times for the two
models are statistically equal. The SVM model was used to project the GLOT
from the pre-existing NASA’s GLOT index (C) (anomaly with base:
1951–1980) for the next 20 years (2013–2033). The projection results of our
study can be of value to policy makers, such as the intergovernmental
organisations related to environmental studies, e.g., the intergovernmental
panel on climate change (IPCC).

This study investigated the prediction of crude oil price based on energy product prices using ge... more This study investigated the prediction of crude oil price based on
energy product prices using genetically optimized Neural Network
(GANN). It was found from experimental evidence that the
international crude oil price can be predicted based on energy
product prices. The comparison of the prediction performance
accuracy of the propose GANN with Support Vector Machine
(SVM), Vector Autoregression (VAR), and Feed Forward NN
(FFNN) suggested that the propose GANN was more accurate
than the SVM, VAR, and FFNN in the prediction accuracy and
time computational complexity. The propose GANN was able to
improve the performance accuracy of the comparison algorithms.
Our approach can easily be modified for the prediction of similar
commodities.

This paper utilize ANNs model to predict closing price of AshakaCem Security in Nigeria Stock Mar... more This paper utilize ANNs model to predict closing price of AshakaCem Security in Nigeria Stock Market price index. In this paper, AshakaCem Security historical technical data were collected for four years trading period (2005 – 2008), the data was partition into training, cross validation and testing set in the ratio 70%:10%:20% respectively. Architectural configuration of Feed Forward Artificial Neural Networks (FFANN) with parameters of three (3) layers, four (4) input nodes, one (1) hidden layer, eighteen (18) hidden nodes, one (1) output layer and one (1) output node was obtained and FFANN was build with the calibrations, trained with 268 exemplars, cross validated with 37 exemplars and tested on 76 exemplars and evaluated on four (4) performance indicators which include Mean Square Error (MSE), Correlation Coefficient (r), Normalize Mean Square Error (NMSE) and Mean Absolute Error (MAE). The technical data were subjected to sensitivity analysis. FFANN predictor was developed and modeled historical trading data of AshakaCem Security and pattern was captured in the historical data with a trend accuracy of 80%, Efficient Market Hypothesis was contradicted in this paper and sensitivity analysis shows that previous closing price (pclose) is the most significant input on FFANN predictor output. FFANN predictor build was evaluated and result shows that MSE = 3.59739909, NMSE = 0.039391504, MAE = 1.3407 and r = 0.981331937. It is possible to trained ANNs with controlled parameters using technical data of AshakaCem Security to capture pattern in the historical data and generalize well on unseen data.

We present a preliminary investigation into a novel approach to natural gas prediction. Experimen... more We present a preliminary investigation into a
novel approach to natural gas prediction. Experimental data
were extracted from the Energy Information Administration of
the US Department of Energy. The datasets were pre-processed
and used to build a feed-forward neural network intelligent
system for predicting natural gas prices based on gold, silver, soy
and copper. The validation of the intelligent system indicated a
Regression (R) = 0.79972 when the reserved datasets were tested
on the intelligent system. Natural gas prices can be predicted
using non-oil commodities as independent variables. With little
additional information, the proposed design can be used to
construct intelligent decision support systems to support decision
making in the government and private sector.

The dynamics of watermark features after embedded into audio streams through digital watermarking... more The dynamics of watermark features after
embedded into audio streams through digital watermarking
techniques are unstable. The audio streams exits as a series of
waveform amplitude of sound over the range of information it
contains. Within this range, there are variations of the
presentation of the stream taken per second and given in hertz.
The precision of the stream representations is measured by the
number of bits per stream. The fact that the streams bits are high
is a sign for data already existing which means that within empty
streams additional information can be embedded. In general,
added information is described as noise and these audio streams
are considered as noise tolerant. Watermarks are embedded into
a spatial or transformed domain with the effect that the
presentation of some bit streams will be affected. This paper
investigates the dynamics of watermarks embedded in an audio
stream, the contained file being noise intolerant. The watermark
file is embedded in several positions within the audio signal
stream by spread spectrum techniques. The most suitable
positions for embedding the watermark is identified which
ensures a strong and robust watermark as a result.

The aim of navigation aid in general is to provide an optimal route from the current position to ... more The aim of navigation aid in general is to provide an optimal route
from the current position to the destination. Unfortunately, there
are lot of drawbacks from many navigation aids such as giving
wrong directions to the destination, and lack of interaction with
other users. This paper presents pedestrian positions and pathway
determination for the design of 3D mobile interactive navigation
aid. The system was developed and aims to help people navigate
in an unfamiliar locations and to overcome the weaknesses of
conventional 2D maps, which require users to interpret its various
symbols and legends and also to present desired locations and
routes to a high degree of accuracy. The system allows several
mobile device users to view their own and other users’ locations
at the same time, while being stationary or on-the-move. The role
of 3D view is to add to an existing individual cognitive map.
Voronoi diagram and its dual Delaunay triangulation are the
algorithms used for establishing user positions and the optimum
pathway to a target destination. Using this technique contributes
to a well-defined positioning and pathway establishment in the
design of navigation assisted systems.

In this chapter, we build an intelligent model based on soft computing technologies to improve th... more In this chapter, we build an intelligent model based on soft
computing technologies to improve the prediction accuracy of Energy
Consumption in Greece. The model is developed based on Genetic Algorithm
and Co-Active Neuro Fuzzy Inference System (GACANFIS) for the prediction
of Energy Consumption. For verification of the performance accuracy, the
results of the propose GACANFIS model were compared with the performance
of Backpropagation Neural network (BP-NN), Fuzzy Neural Network (FNN),
and Co-Active Neuro Fuzzy Inference System (CANFIS). Performance analysis
shows that the propose GACANFIS improve the prediction accuracy of Energy
Consumption as well as CPU time. Comparison of the results with previous
literature further proved the effectiveness of the proposed approach. The
prediction of Energy Consumption is required for expanding capacity, strategy
in Energy supply, investment in capital, analysis of revenue, and management
of market research.

This paper present a novel approach to crude oil price prediction based on co-active neuro-fuzzy ... more This paper present a novel approach to crude oil
price prediction based on co-active neuro-fuzzy inference
systems (CANFIS) instead of the commonly use fuzzy neural
network and adaptive network-based fuzzy inference
systems due to superiority and robustness of the
CANFIS model. Monthly data of West Texas Intermediate
crude oil price and organization for economic co – operation
and development (OECD) inventories, obtained from US
Department of Energy were used to built the propose model.
The CANFIS prediction model was trained, validated and
tested. The performance of our approach is measured using
mean square error, root mean square error, mean absolute
error and regression. Suggestion from the results shows that
the CANFIS demonstrated a high level of generalization
capability with relatively very low error and high correlation
which exhibited successful prediction performance of the
proposal. The model has the potential of being developed into
real life systems for use by both government and private
businesses for making strategic planning that can boost
economic activities.

Over the years an increasing demand for an automated security system begins to emerge. Many appli... more Over the years an increasing demand for an
automated security system begins to emerge. Many applications
that help in protecting life and properties are being developed.
Most of them are aimed at improving the work of security
personnel and security agencies. However, security is a
responsibility of everyone not only the security agencies or
security personnel alone. This paper present an interactive
security monitoring system based on passive infrared motion
detection sensor, which will capture the image of any intruding
persons and share it to the entire people that are using the
system on both Android platform and in an online portal
display. The people on the system can communicate with each
other and post information to a commonly accessible board in
the online system to discuss any issues or to see if anyone
recognizes the felons/intruder on the images. Images of interest
can then be transmitted to law enforcement authorities. This
could be use in anywhere that needs to be protected against
intruder. It will be best use in kindergarten, primary school and
or in a neighborhood. That is why we call it neighborhood
watch security system (NWSS). Preliminaries evaluation
indicated an accurate image captured in a real time with an
avoidance of false alarm.

Springer, 2020

Introduction This book will address both theories and empirical procedures for the applications o... more Introduction This book will address both theories and empirical procedures for the applications of machine learning and data mining to solve problems in emerging trends in cyber dynamics. Cyber dynamics is a term used to describe resilient algorithms, strategies, techniques and architectures for the development of the cyberspace environment such as cloud computing services, cyber security, data analytics, disruptive technologies like the blockchain, etc. The edited book intends to present new machine learning and data mining approaches in solving problems in emerging trends in cyber dynamics. Scope and Topics For better understanding by the readers, basic concepts, related work reviews, illustrations, empirical results and tables are expected to be integrated in each chapter to give the readers a maximum understanding and allow to easily follow the methodology and the results presented. The target audience of the edited book will come from different backgrounds. The audience will share and exchange novel knowledge, methods, industry experience and theories. The chapter contributions should described solving challenging issues using machine learning or data mining in any of the following domains:  Blockchain  Cryptocurrency  Next generation cloud computing e.g. serverless, edge, fog, volunteer, etc.  DeepFake detection and simulation  IoT Ransomeware  Cyber physical systems  Social Media  Internet of Vehicles, and others that may be suitable.

conference , 2020

Scope and Topics The EATI’2020 theme is the “emerging applications and technologies for Industry... more Scope and Topics
The EATI’2020 theme is the “emerging applications and technologies for Industry 4.0” and original papers are sought on any topic within the scope of the conference theme, including, but not limited to the following: Track 1: Applications and Techniques in Cyber Intelligence. Track 2: Applications and Techniques in Internet of Things. Track 3: Applications and Techniques in Industry 4.0. Track 4: Applications and Techniques in Information System. Track 5: Applications and Techniques in High Performance Computing and Networks. Track 6: Applications and Techniques in Computational Science. The detail for each track can be found in the conference website.

Proceedings Publication
All accepted, registered and presented papers will be published by Springer in Advances in Intelligent Systems and Computing Series indexed in ISI Web of Science, Scopus, Ei Compendex, DBLP, Google Scholar, etc.

Paper Submission
Papers should describe original work/survey/industry experience and unpublished related to the scope of the conference described in the scope and topic section. All manuscript will be screened through Turnitin and determine it is suitability before sending for review to three TPC members. The paper should be minimum of 8 pages and maximum of 10 in Springer format. The word and Latex template can be found here: https://www.springer.com/us/authors-editors/conference-proceedings/conference-proceedings-guidelines. Authors can submit their papers through EasyChair available at the conference website: www.eati2020.com.