|
ARPN Journal of Engineering and
Applied Sciences
December 2020 | Vol. 15 No.
24 |
|
|
Title: |
Influence of nano-flux powder on the
hardness and tensile strength of steel welded joints |
Author (s): |
Sunday A. Afolalu, Samson O. Ongbali,
Moses E. Emetere and Omolayo M. Ikumapayi |
Abstract: |
The
use of flux during welding is important because it prevents the
formation of oxides thereby giving a better profile to the weld. In this
study, nano- flux powder (CaO) developed from agrowastes (eggshell) and
commercial flux powder were used during Metal Inert Gas (MIG) Welding.
Materials prepared and welded were galvanized, stainless and mild steel
plates and rods of 50 x 50 x 10 mm. The SEM and EDX of the fluxes were
carried out while the welded joints of each samples were subjected to
tensile, hardness and surface morphology tests using SEM. The high
volume of 57.10% Iron and 29.45% Calcium respectively confirmed that the
fluxes were Iron and Calcium Oxides suitable as fluxes for the welding.
The mechanical properties of the joints proved better in nano flux than
the commercial and when no flux applied. |
|
|
Full Text |
|
|
Title: |
Effect of hybrid fibers on bond strength
of fiber reinforced concrete |
Author (s): |
Waleed A. Almatrudi, Mansour Alturki, Omar
M. Alawad, Saleh M. Alogla, Ahmed F. Elragi and Elsaid Bayoumi |
Abstract: |
Essential additives, such as fibers, are widely used to improve the
mechanical properties and performance of concrete. Fibers can be added
to concrete in a mono or hybrid form of both metallic and non-metallic
type. Although benefits of hybrid fibers addition to concrete are
established in the literature, the bond stress slip response of embedded
reinforcing steel in hybrid fiber reinforced concrete is not thoroughly
studied. In this study, the bond stress-slip behavior of reinforcing
steel bars embedded in concrete containing hooked end steel fibers and
polypropylene fibers is assessed by carrying out pull-out tests. The
variables considered in this study include polypropylene fiber volume
(i.e. 0.1% and 0.2%), hooked end steel fiber volume (i.e. 0.5% and 1%),
and the diameter of embedded reinforcement bars (i.e. 10 mm and 12 mm).
The experimental results indicate that adding hybrid fibers of 0.1%
polypropylene and 1% hooked end steel fibers yield the highest bond
strength and hence the highest reduction in the embedded (development)
length. The addition of hybrid fibers to concrete also improved the
toughness of concrete and increased the slip measurements prior to
failure of the bond between rebar and concrete. |
|
|
Full Text |
|
|
Title: |
Comparison of the impact of power bumps
and conventional bumps on vehicles and users |
Author (s): |
Stella M., Morris A. G. Ezra, Chew K. W.
and Hans Y. M. |
Abstract: |
Energy plays an important role in a country’s development. Traffic
energy is one of the alternative energies being investigated worldwide.
Over the years, investigations are being carried out to improve the
functionality and efficiency of various types of devices used in traffic
energy harvesting. There are still questions on the possible impact
these traffic energy harvesters impose on vehicles and users. However,
there is a limited study on the impact of traffic energy harvesters on
vehicles and users. A detailed investigation of the possible impact of
traffic energy harvesters is necessary to identify and mitigate the
challenges which would help promote this promising alternative energy in
the future. In this paper, a MATLAB simulation was carried out to
investigate the impact of a rack-and-pinion based speed bump on vehicles
and users in comparison with that of a conventional speed bump, in terms
of its fuel consumption rate, impact on vehicle suspension, and ride
comfort. The investigation revealed that power bumps do have negative
influences on vehicles’ performance compared to that of conventional
speed bumps. |
|
|
Full Text |
|
|
Title: |
Reactivity calculation using the Boolean
rule with exponential filter |
Author (s): |
Daniel Suescún-Díaz, Freddy Humberto
Escobar and Faiber Robayo Betancourt |
Abstract: |
A
different way to reduce fluctuations in the reactivity calculation using
the exponential filter and the inverse point kinetics equation is shown.
The reactivity is calculated using the Boolean rule for different time
steps, the neutron density is supposed that contains Gaussian noise
around of the mean values. There are four terms of convolution sum
between the nuclear density population and the impulse response. The
convolution sum represents a finite impulse response filter. The
different numerical experiments show that it is possible to reduce the
fluctuations using the proposed method. |
|
|
Full Text |
|
|
Title: |
Snowfall noise elimination using the
convex hull-type moving object synthesis method |
Author (s): |
Yoshihiro Sato, Koya Kokubo and Yue Bao |
Abstract: |
In
recent years, the use of surveillance cameras is increasingly
recommended and they have been installed in many places. Snowy
conditions at the time of an accident were associated with the problem
that cars and accident circumstances become difficult to discern in
images shot during snowfall. Previous techniques proposed methods for
elimination of noise caused by snow using image shift or dedicated
filters for the elimination of snowfall in video. However, these are
associated with issues such as inability to cope with heavy snowfall or
moving objects fading from view or being hard to discern. The present
study proposes a method for snowfall noise elimination by extracting
moving objects using the travel and the size of the moving object region
between continuous frames, shaping a moving object using a convex hull
algorithm, and compositing images while using the difference mask image
excluding the moving object area. By distinguishing between falling snow
and other moving objects, we can prevent objects other than snowfall
becoming invisible. In addition, the convex hull can prevent to get out
of shape of moving objects other than snowfall. In order to confirm the
effectiveness of the proposed method by experiments, we used a video in
which cars actually run in a snowfall environment. As shown in the
experimental results, it can be confirmed that the snow grains are
removed and the shapes of the cars in the image are kept well. |
|
|
Full Text |
|
|
Title: |
Design, simulation and analysis of grid
connected photovoltaic based inverter |
Author (s): |
N. Chandrasekaran and A. Karthikeyan |
Abstract: |
Supplying and sharing power with grid has become one of the most wanted
photovoltaic applications (PV). Moreover, PV based inverter and DC to DC
converters are getting more attention in recent days mainly in remote
areas where connection to the grid is technically not possible. Power
generation by Photovoltaic is free and reliable. This paper presents the
novel technique for maximum-power point tracking based on perturb and
observe algorithm of photovoltaic (PV) energy conversion system. In
order to obtain the maximum power extracted from the PV array, usually
two parameters are considered, namely solar irradiation and temperature,
most of the research work has been carried out by considering these two
parameters. The proposed technique gives optimum utilization of PV array
and enhances the applications of PV systems for both stand alone and
grid connected systems. The study has been carried out in the
MATLAB-Simulink environment. And also validation of the simulated
results with the theoretical results shows proper matching. The results
obtained from the simulation of the system are very much satisfactory.
It is found that PV fed inverter system is working better. |
|
|
Full Text |
|
|
Title: |
Estimation of base saturation flow rates
for signalized intersections in Jordan and Kuwait |
Author (s): |
Bashar H. Al-Omari and Yousef B. Musa |
Abstract: |
The
design and analysis procedures of signalized intersections depend on
several factors including the base saturation flow rate. The Highway
Capacity Manual (HCM) assumes a base saturation flow rate of 1900
passenger car/hour/lane (PCPHPL) for areas with population of more than
or equal 250,000 and 1750 PCPHPL for areas with population of less than
250,000. This research aimed at determining the base saturation flow
rate in Jordan and Kuwait based on field data collected from 60
signalized intersection approaches. The methodology was based on the
direct field measurement of saturation flow rate and its main
influencing factors. The HCM standard procedure was followed in the
field data collection and results showed that the HCM base saturation
flow rate value of 1900 PCPHPL is not suitable for Jordan and Kuwait.
The study recommends a value of 2050 PCPHPL for Jordan and 2100 PCPHPL
for Kuwait, while a value of 2075 PCPHPL may be used for other Middle
Eastern countries that do not have field measured values. The saturation
flow rate was found to be significantly affected by the speed limit,
lane marking, city, and location (CBD/ Non-CBD) at 95 % confidence. On
the other hand, the saturation flow rate was found not significantly
affected by the number of lanes, time period, traffic volume, land use,
area type, and development density at 95 % confidence. |
|
|
Full Text |
|
|
Title: |
New technology of data transmission: Li-Fi |
Author (s): |
Sanida Yessenbek, Abdurazak Kasymov,
Salima Nugmanova and Lidiya Taimuratova |
Abstract: |
Motivated by the looming radio frequency (RF) spectrum crisis, this
paper aims at demonstrating that optical wireless communication (OWC)
has now reached a state where it can demonstrate that it is a viable and
matured solution to this fundamental problem. In particular, for indoor
communications where most mobile data traffic is consumed, light
fidelity (Li-Fi) which is related to visible light communication (VLC)
offers many key advantages, and effective solutions to the issues that
have been posed in the last decade. This paper discusses all key
component technologies required to realize optical cellular
communication systems referred to here as optical attocell networks.
Optical attocells are the next step in the progression towards ever
smaller cells, a progression which is known to be the most significant
contributor to the improvements in network spectral efficiencies in RF
wireless networks. In this paper we analyzed the Li-Fi system using an
optisystem simulation tool. In this analysis, we considered two
propagation models. In a LOS propagation model in the receiving end, we
can regenerate approximated transmitted signal. |
|
|
Full Text |
|
|
Title: |
Spatio-temporal data analysis for human
daily life activities |
Author (s): |
Saeed Ullah, Kashif Rizwan, Nasir Ayub and
Nadeem Mahmood |
Abstract: |
Pakistan currently has the largest percentage of young people in its
history that makes Pakistan one of the youngest country in the world and
second in Asia Pacific region. To understand the macro level pattern of
daily life activities for everyone can reveal significant information
about people of a particular region. This information at the persons’
own end can be used to adapt a desirable, more healthy and smart options
to plan further. On the other hand this information if used by mass
planning and governments to promote and plan future strategies in wide
range. This study entangles a case study for the daily life activities
of Pakistani peoples. In Pakistan there is no such platform exists where
people can understand the life pattern of their daily life activities
with respect to time and location. We used dynamic flowing bubble graph
technique (Force Directed Graph) and scatter plots to observe and
analyse human daily life activities. We used 20 volunteers of age group
between 19 to 29 years residents of Islamabad/ Rawalpindi. We modeled
spatial and temporal features of data by catering 18 distinct daily life
activities of each person. A dataset generated with 6 attributes having
709 daily life activity instances of volunteers. This comprises a web
based application coupled with a mobile application to represent the
human daily life activities using force-directed graph. Results shows
the desired offline analysis of Pakistani peoples’ daily life
activities. |
|
|
Full Text |
|
|
Title: |
Optical properties of the freestanding
(2,2) single-walled boron nitride nanotube |
Author (s): |
Riri Jonuarti, Freddy Haryanto and
Suprijadi |
Abstract: |
We
present results of our calculations on the optical properties of the
freestanding (2,2) singled-walled boron nitride nanotube (SWBNNT) using
the density functional theory (DFT) and random phase approximation (RPA).
Previous study shows that freestanding (2,2) SWBNNT holds a narrow band
gap of 3.01 eV. Then, our optical calculations exhibit that freestanding
(2,2) SWBNNT generates the main absorption peaks are in the ultraviolet
(UV) energy ranges. Furthermore, the freestanding (2,2) SWBNNT can
absorb light at longer wavelengths. It starts from the visible light
until the ultraviolet type C (UVC). These findings offer a chance that
material can be applied as a photocatalyst. |
|
|
Full Text |
|
|
Title: |
The development of system for algorithms
visualization using simjava |
Author (s): |
Jamil Abedalrahim Jamil Alsayaydeh, Maslan
Zainon, A. Oliinyk, Azwan Aziz, A. I. A. Rahman and Zikri Abadi
Baharudin |
Abstract: |
Algorithm visualization which is a form of high-level dynamic
visualization of software that uses user interface techniques to portray
and monitor the computational steps of algorithms. Moreover, algorithm
visualization systems are also useful tools in algorithm engineering,
particularly at several stages during the design, implementation,
analysis, tuning, experimental evaluation, and presentation of the
algorithms process. Algorithms are a captivating use case for
visualization. It does not simply fit data to a chart to visualize an
algorithm, there is no main data set. Rather there are consistent
principles that depict conduct. This is because algorithm visualizations
are so uncommon, as designer’s experiment with novel forms to better
communicate. Algorithm visualization (AV) uses graphics to portray an
algorithm's actions. AV holds the promise of helping computer science
students understand algorithms more effectively and in more prominent
profundity. The purpose of this study is to design a system for sorting
algorithm visualization and implement the system. |
|
|
Full Text |
|
|
Title: |
Wavelet thresholding based de-noising
technique for color image |
Author (s): |
Jeevan K. M., Anne Gowda A. and M. Ramesha |
Abstract: |
Image
de-noising is an important part in every image processing techniques. At
the same time it can be considered as one of the primary challenges in
image processing and computer vision. This paper describes wavelet
thresholding based de-noising technique for color images. In this method
the optimal threshold is determined using NeighShrink thresholding
method with Stein’s unbiased risk estimate (SURE). Mean square error (MSE)
and peak signal to ratio (PSNR) are used for the evaluation of image
quality after de-noising. |
|
|
Full Text |
|
|
Title: |
Determining optimal border parameters to
design a reused mine working |
Author (s): |
Vadym Fomychov, Lyudmila Fomychova, Andrii
Khorolskyi, Oleksandr Mamaikin and Viktor Pochepov |
Abstract: |
Applying the methods of computational mathematics in terms of specific
optimal operational indices of a reused mine working makes it possible
to reduce resource intensity of the operations performed at that stage.
However, the obtained results are hard to interpolate with respect to
the whole mine working network. The problem is aggravated when mining
and geological conditions of mine working drivage differ considerably
within one and the same mine field. Grid methods of solution allow
modeling peculiarities of a geomechanical model in a wide range; though,
they have a set of features preventing from guaranteeing unambiguously
the calculation quality. Field experiment, which is possible to carry
out only after mine working drivage, is a standard practice to
substantiate the efficiency of the developed technological solutions. In
terms of the considered mining and engineering conditions, stress and
strain of the geomechanical model components are to be measured
throughout the mine working length. Consequently, it is possible to
confirm the selection quality of support parameters of the mine working
only when it is completely driven. In some cases, optimal indices may be
obtained at the expense of changes in the mine working border shape;
that requires considerable complication of the procedure to optimize
computational models. The developed calculation methodology of
calculation and performance of a field experiment has made it possible
to implement the procedure of optimization of selecting the support for
a reused mine working by comparing analysis of stress and strain state
patterns for similar geomechanical models. |
|
|
Full Text |
|
|
Title: |
Application of binders based on technical
lignin in the production of castings |
Author (s): |
Falah Mustafa Al- Saraireh and Yuri
Svinoroev |
Abstract: |
In
this paper are studied the possibilities of using technical lignin as a
promising raw material for the development of various types of binder
for foundry. In order to overcome the resource deficit problem, new
technical solutions are required for the use of new materials, the
advantages of which are to rationalize the use of the available resource
potential of the plant processing industry, using technical lignin's as
an example. Experimental studies have been conducted to find effective
modifiers of technical lignin. A class of substances has been
established that makes it possible to increase the binding ability of
technical lignosulfonates in a technologically acceptable level. The
results of the development of foundry binder material based on technical
lignin (TLS) allow us to talk about the technological feasibility of
creating binder materials based on lignin materials that can
successfully compete with phenol-based synthetic resins widely used now.
Lignosulfonate materials can be considered as a typical example of
technology for resource conservation and rational use of secondary raw
materials produced from renewable natural resources. |
|
|
Full Text |
|
|
Title: |
Quality characteristic of chikuwa made
from different species of fish |
Author (s): |
Fronthea Swastawati, Abdul Syakur, Ima
Wijayanti and Putut Har Riyadi |
Abstract: |
This
research was aimed to compare the quality characteristics of “chikuwa”
(a Japanese jelly-like food product made from ingredients such as fish
surimi, salt, sugar, starch). In this study four species of fish such as
catfish, milkfish, tilapia and red snapper were produced with the
addition of 2% liquid smoke as flavouring agent. The parameters includes
the changes of hedonic test, amino acid profile and proximate
composition (moisture content, protein content, fat content and ash
content) in chikuwa without addition of liquid smoke (control) and by
the treatment of adding 2% liquid smoke to the safety level and
characteristics of chikuwa. Different fish species and methods gave
significantly different effect (p<0.05) to quality of “chikuwa”. The
results showed the water content was found between 65.107% to 79.112%,
protein content between 8.897% to 17.757% and fat content between 0.634%
to 2.158% and ash content between 0.928% to 4.63%. There were about 16
amino acids found in this study, whereas the fatty acids were found
about 11. Amino acid profile highest content in fresh milkfish was
lysine of 221.8086 ppm and fatty acids content in composition was oleic
acid ranging from 7.85% – 50.75% with an average of 40.42%. Chikuwa made
from tilapia was found as the most acceptable by panelist with hedonic
values; 8.68 < µ < 8.69. |
|
|
Full Text |
|
|
Title: |
Stratigraphy and morphometry of the
dryland drainage basins for the flash flood and groundwater occurrence
in Wadi Ramliya, Egypt |
Author (s): |
Wafaa I. Shahat and M. El Bastawesy |
Abstract: |
This
search integrates stratigraphical and morphometrical analyses to
identify the control of geological development on drainage networks and
ground water occurrence in a dryland catchment (Wadi Ramliya). I is a
flood prone area, incised in the sedimentary plateau in the northern
part of the Eastern Desert of Egypt. The morphometrical characteristics
are delineated using remote sensing and GIS. The available Digital
Elevation Model (DEM) was hydrologically processed into Geographic
Information System (GIS) using ArcGIS algorithms to compute the
morphometric parameters according to the established linear formulas.
The morphometric analyses indicated that Wadi Ramliya is a young wadi of
structurally controlled geologic developments as the drainage pattern is
relatively coarse and the subtle relief variation of the longitudinal
profile still high. The stratigraphic analyses showed that the catchment
is built up of two main lithostratigraphic successions of various
sedimentary natures related to Eocene (limestone and marl) and
Pliocene-Quaternary (clays, sands and gravels) dominated in the lower
part of the catchment. Thus, the calcareous and impermeable plateau
promotes the development of significant runoff, which is being routed
through the alluvial channels. Applying stratigraphic correlation of
surface and subsurface successions enabled access to the water bearing
formation and interpreted the subsurface stratigraphic occurrence of the
Pliocene-Quaternary deposits as essentially related to irregularities in
the Pliocene basin of deposition that resulted in a graben-like
structure. The groundwater aquifer is therefore, suggested to occupy the
shallow, near earth surface zone. The borehole data confirmed the
development of a local groundwater aquifer due to the accumulation of
water-saturated gravely deposits in the southern side of downstream.
Furthermore, the catchment has been subdivided into cascading
upstream-downstream time area zones to compute the synthetic hydrographs
of the flash floods. The estimated flash floods, even of limited
development, pose dangerous threat to the different anthropogenic
activities occupying or obstructing the pathways of the main Wadi trunk.
Therefore, it is strongly recommended to construct flash flood
controlling dyke on the outlet of the graben-like area to replenish the
fragile aquifer system. |
|
|
Full Text |
|
|
Title: |
Frequency domain identification applied to
an electromechanical plant |
Author (s): |
Faiber Robayo Betancourt |
Abstract: |
In
this work, a frequency domain method based on the Transfer Function
Analyzer (TFA) technique for the identification of an electromechanical
system was developed. The novelty of the study used variable sample time
in the chirp signal used as the input for the identification. The TFA
identification was applied to the system to identify the Bode response.
The bode response with the TFA method was quite similar to the obtained
with the mathematical model. Although the resonance frequencies
estimated with the TFA algorithm were not the same frequencies
calculated with the mathematical model, they were very close. |
|
|
Full Text |
|
|
Title: |
User credential-based authentication
mechanism for securing data access in public Cloud environment |
Author (s): |
S. Hendry Leo Kanickam and L. Jayasimman |
Abstract: |
Cloud
Computing is an emerging technology. It allows users to enjoy on-demand
services, broad network access without the burden of data storage and
maintenance costs. However, the outsourcing of resources was accessing;
it makes some of the security issues happened. The customer registers
its authentication security module with the cloud security service, and
that security module is then used to control what persons or entities
can access information associated with the application. The most
important concerns are authentication and access control. This paper
proposes a novel mechanism compare with previous proposing solutions to
authentication issues in the Cloud environment. The main aim of this
paper to develop new authentication mechanisms related to cloud
services. This novel authentication mechanism is very useful for cloud
users whenever data are accessing the cloud. |
|
|
Full Text |
|
|
Title: |
Synthesis and antimicrobial properties of
new polymeric materials with immobilized peroxyacid groups |
Author (s): |
Murashevych B., Stepanskyi D., Toropin V.,
Koshova I., Maslak G., Prigozhaeva L., Kovalenko V. and Kotok V. |
Abstract: |
A
method has been developed for the modification of polymer materials of
the FIBAN brand, which allows to immobilize up to 5.5% of peroxyacid
functional groups on them without significant changes in their physical
and mechanical properties. It has been shown that the concentration of
active groups and the stability of the synthesized materials depend
strongly on the nature of the polymer carrier. Method for chemical
analysis of the concentration of immobilized peroxyacid groups have been
proposed, and the features of the IR spectra of modified materials have
been described. It has been proved that all synthesized materials
exhibit pronounced antimicrobial activity. Such materials can be used
for manufacturing goods with increased resistance to microbial
colonization, including medical masks, respirator filters, wound
dressings, etc. |
|
|
Full Text |
|
|
Title: |
Profile cutting of high-carbon,
high-chromium, cold-work steel in WEDM using molybdenum wire electrode |
Author (s): |
M. Saravanan, C. Thiagarajan and S.
Somasundaram |
Abstract: |
Profile cutting of high carbon-high chromium (HCHC) tool steel (AISI D3
steel) using molybdenum wire electrode in Wirecut-electrical discharge
machining (WEDM) was investigated in this work. Independent variables
considered were cutting speed, Ton and Toff, wire tension, servo feed
rate, input current, wire feed rate and servo voltage over the dependent
variables material removal rate (MRR) and surface roughness (SR).
Experimental design was formulated based on L18(21,37) and output
responses were optimized using Grey Relational Analysis (GRA). Outcomes
from experiment shows that, with increase in cutting speed, both MRR and
SR increases abruptly, higher Ton produces higher MRR and lower SR, but
with higher Toff a reduction in MRR and SR was observed. With higher
wire tension, MRR tends to increase whereas SR reduces considerably. SR
tends to increase with higher servo voltage, increasing the servo feed
rate decreases the MRR, whereas SR tends to reduce. The most influential
input parameter contributing towards grey relational grade was wire
tension by 22.94%, servo feed rate by 16.92% with an R2 value of 95.29%,
identified using Analysis of Variance (ANOVA). An error percentage of
1.46% was obtained between the confirmation experiment and predicted
GRGs. |
|
|
Full Text |
|
|
Title: |
Dynamic group formation in computer
supported collaborative learning |
Author (s): |
Ihtesham Hussain, Kashif Sultan and Iqra
Basharat |
Abstract: |
Computer-Supported Collaborative Learning (CSCL) emerges as an
instrument of learning and training that can encourage the social nature
of learning by adopting range of computer-mediated communication tools
and pedagogical methods. These tools are used to facilitate the learning
and instructional communication among students and learners in small
groups. In this process, group formation becomes painstaking and
challenging task. Various factors are involved affecting group formation
that includes; personal characteristics, social, cultural, psychological
and cognitive diversity. Although, this issue was addressed in various
research studies yet an optimal solution for dynamic group formation is
not discussed evidently. In dynamic groups, students work or collaborate
on a short-term task in a group that change frequently based on the
performance of students. In this research study we have proposed a
method for dynamic group formation and the impact of dynamic group
formation in collaborative learning among peers is demonstrated by
conducting an experiment. This experiment is conducted in two phases. In
first phase of the experiment, learning styles are assigned to the
students and their knowledge level is calculated. Whereas, in second
phase of the experiment, the impact of dynamic grouping on collaborative
learning of students is determined. Further, two algorithms are
proposed, first is used for determining initial number of clusters and
second algorithm is used for dynamic grouping after the completion of
each permutation. Results of our experiment shows a positive impact of
dynamic grouping on learning of students as the performance of
collaborative learning among peers is better than individual
performances. |
|
|
Full Text |
|
|
Title: |
Ensuring safety of pilgrims by efficient spatio-temporal data modeling and application for reporting and tracking of missing persons in a large crowd gathering scenario |
Author (s): |
Adnan Nadeem, Kashif Rizwan, Nauman Qadeer, Saeed Ullah, Nadeem Mahmood, Amir Mehmood, Fazal Noor, Muhammad Ashraf and Ali Al Zahrani |
Abstract: |
Ensuring safety of the pilgrims is the top priority of Saudi government. More than two millions of pilgrims visit the holy cities of Makkah and Madinah, in KSA, to perform Hajj and Umrah rituals every year. Therefore, kingdom considers health, safety and security a red line that is not supposed to be crossed at any extent, considering the magnitude of related consequences. A higher tendency of persons is found who get separate from their group of members during Hajj and Umrah rituals; especially in the case of children and old-aged ones. Our survey from pilgrims who lost their elders or children shows that amongst the missing 8% were elderly persons and 92% were children. The lost elderly persons and children need an efficient system to track them. Therefore, this paper proposes a system model and a prototype application for effective reporting and tracking of lost and found persons in a huge crowd gathering scenario of Al-Nabawi mosque Madinah. Our proposed system’s model aims to facilitate both pilgrims and the center of lost and found persons in Madinah. It allows pilgrims to report and search lost persons effectively. It matches the reported spatio-temporal contextual information of lost persons along with integrated support of the face recognition and biometric verification techniques. We used an existing deep learning method based on a face recognition algorithm which results in high accuracy during small-scale testing on labeled faces in the Wild benchmark. The tracking procedure is made more efficient by coupling the face recognition technique employed with biometric verification and reported spatio-temporal features of lost pilgrims. |
|
|
Full Text |
|
|
Title: |
Lexicon-based sentiment analysis for Urdu language reviews |
Author (s): |
Aneela Zawar, Saeed Ullah, Abdul Mateen,and Kashif Rizwan |
Abstract: |
Today, social media is considered as the most powerful source of information flow and provides a portfolio for online discussion and sharing ideas with other people. Considering the key role of the social media in modern day life, it’s worth exploring to know the people feelings and opinion about particular event or product on media that known as sentiment analysis. It has been found that, large volumes of internet-web user are adopted to write Roman Urdu script instead of Urdu script, national language of Pakistan, on the internet. For better understanding of their expression in non-English language, it is need of time to mine Urdu data for the sentiment analysis about the desired information. Sentiment analysis tools or applications have been developed for other languages like English, Chinese and French; however, no work is reported on sentiment analysis for Urdu yet. Employing the lexicon-based approach, current study aimed to develop an application for sentiment analysis for Urdu data for user/customers’ reviews and comments. The data was collected from famous Urdu websites and databases. Given the raising internet users and growth of digital industry in the country, we anticipate that his research work will be worth of interest for Urdu language users.
|
|
|
Full Text |
|
|
Title: |
Career prediction of it applicants by
mining educational and alumni data
|
Author (s): |
Nadia Ghaffar, Abdul Mateen, Saeed Ullah, Rubina Adnan, Muhammad Javed and Kashif Rizwan |
Abstract: |
Technical education is becoming more and more career-oriented. Therefore, most of the researchers and studies have contributed their part by predicting students’ career. On the other hand, students’ career after graduation has become a major factor in building the reputation of the institutes. Predicting their degrees and future direction beforehand can help to take timely action by institutions. Data mining is a process of finding patterns and correlations within large datasets to predict outcomes. When the data mining process is used to study the learning characteristics, behaviour and performance of the student, it is called Educational Data Mining (EDM). This study implements a supervised machine learning technique to predict career of IT applicants whether IT or Non-IT by analyzing the data of those students’ who had graduated. The dataset is collected from the Course Management System (CMS) of Barani Institute of Information Technology (BIIT) PMAS, AAUR Rawalpindi and mapped with the alumni dataset which is collected from BIIT graduated students using Google forms to have one dataset for experimental use. The major concerns of this work is to develop an efficient student recommendation system for predicting career of BSCS/BSIT applicants’ whether IT or Non-IT at the time of admission and enhance the performance of learning model by re-sampling of dataset with SMOTE algorithm. This work also highlights the impact of selection of most relevant set of features for accurate results. The system efficiency has been tested upon the data of 3327 students. The total number of 11 attributes have been considered for career prediction i.e. gender, current degree program, demography details, SSC board, SSC subject, SSC grade, HSSC board, HSSC subject, HSSC grade, final degree CGPA and alumni job. To improve accuracy of learning models, re-sampling of dataset technique is sused to handle class imbalance problem by applying SMOTE algorithm. In this research, Random Forest, C4.5(J48) and Support Vector Machine (SVM) models are used to determine the best predictive model for supervised machine learning. 10-fold cross validation and standard performance evaluation measures such as: accuracy, precision, recall, F-Measure are used to evaluate the classifiers results. During the experiments Random Forest obtained 96.86% accuracy measure which is better than all of the learning algorithms, i.e., C4.5(J48) 96.55% and SVM 96.15% after handling class imbalance problem with SMOTE. This recommendation system may be more helpful by predicting career of IT department applicants’ at the time of enrollment.
|
|
|
Full Text |
|
|
|
|
|