Abstract: Selecting an appropriate image representation is the most important factor in implementing an effective Content-Based Image Retrieval (CBIR) system. This paper presents a multi-feature fusion approach for efficient CBIR, based on the distance distribution of features and relative feature weights at the time of query processing. It is a simple yet effective approach, which is free from the effect of features' dimensions, ranges, internal feature normalization and the distance measure. This approach can easily be adopted in any feature combination to improve retrieval quality. The proposed approach is empirically evaluated using two benchmark datasets for image classification (a subset of the Corel dataset and Oliva and Torralba) and compared with existing approaches. The performance of the proposed approach is confirmed with the significantly improved performance in comparison with the independently evaluated baseline of the previously proposed feature fusion approaches.
Abstract: Mobile augmented reality (MAR) tracking targets from the surroundings and aids operators for interactive data and procedures visualization, potential equipment and system understandably. Operators remotely communicate and coordinate with each other for the continuous tasks, information and data exchange between control room and work-site. In the routine work, distributed control system (DCS) monitoring and work-site manipulation require operators interact in real-time manners. The critical question is the improvement of user experience in cooperative works through applying Augmented Reality in the traditional industrial field. The purpose of this exploratory study is to find the cognitive model for the multiple task performance by MAR. In particular, the focus will be on the comparison between different tasks and environment factors which influence information processing. Three experiments use interface and interaction design, the content of start-up, maintenance and stop embedded in the mobile application. With the evaluation criteria of time demands and human errors, and analysis of the mental process and the behavior action during the multiple tasks, heuristic evaluation was used to find the operators performance with different situation factors, and record the information processing in recognition, interpretation, judgment and reasoning. The research will find the functional properties of MAR and constrain the development of the cognitive model. Conclusions can be drawn that suggest MAR is easy to use and useful for operators in the remote collaborative works.
Abstract: Flow instability during gas lift operation is caused by three major phenomena – the density wave oscillation, the casing heading pressure and the flow perturbation within the two-phase flow region. This paper focuses on the causes and the effect of flow instability during gas lift operation and suggests ways to control it in order to maximise productivity during gas lift operations. A laboratory-scale two-phase flow system to study the effects of flow perturbation was designed and built. The apparatus is comprised of a 2 m long by 66 mm ID transparent PVC pipe with air injection point situated at 0.1 m above the base of the pipe. This is the point where stabilised bubbles were visibly clear after injection. Air is injected into the water filled transparent pipe at different flow rates and pressures. The behavior of the different sizes of the bubbles generated within the two-phase region was captured using a digital camera and the images were analysed using the advanced image processing package. It was observed that the average maximum bubbles sizes increased with the increase in the length of the vertical pipe column from 29.72 to 47 mm. The increase in air injection pressure from 0.5 to 3 bars increased the bubble sizes from 29.72 mm to 44.17 mm and then decreasing when the pressure reaches 4 bars. It was observed that at higher bubble velocity of 6.7 m/s, larger diameter bubbles coalesce and burst due to high agitation and collision with each other. This collapse of the bubbles causes pressure drop and reverse flow within two phase flow and is the main cause of the flow instability phenomena.
Abstract: Green tea is made from the top two leaves and buds of a shrub, Camellia sinensis, of the family Theaceae and the order Theales. The green tea leaves are picked and immediately sent to be dried or steamed to prevent fermentation. Fluid bed drying technique is a common drying method used in drying green tea because of its ease in design and construction and fluidization of fine tea particles. Major problems in this method are significant loss of chemical content of the leaf and green appearance of tea, retention of high moisture content in the leaves and bed channeling and defluidization. The energy associated with the drying technology has been shown to be a vital factor in determining the quality of green tea. As part of the implementation, prototype dryer was built that facilitated sequence of operations involving steaming, cooling, pre-drying and final drying. The major findings of the project were in terms of quality characteristics of tea leaves and energy consumption during processing. The optimal design achieved a moisture content of 4.2 ± 0.84%. With the optimum drying temperature of 100 ºC, the specific energy consumption was 1697.8 kj.Kg-1 and evaporation rate of 4.272 x 10-4 Kg.m-2.s-1. The energy consumption in a fluidized system can be further reduced by focusing on energy saving designs.
Abstract: There are about 1% of the world population suffering
from the hidden disability known as epilepsy and major developing
countries are not fully equipped to counter this problem. In order to
reduce the inconvenience and danger of epilepsy, different methods
have been researched by using a artificial neural network (ANN)
classification to distinguish epileptic waveforms from normal brain
waveforms. This paper outlines the aim of achieving massive
ANN parallelization through a dedicated hardware using bit-serial
processing. The design of this bit-serial Neural Processing Element
(NPE) is presented which implements the functionality of a complete
neuron using variable accuracy. The proposed design has been tested
taking into consideration non-idealities of a hardware ANN. The NPE
consists of a bit-serial multiplier which uses only 16 logic elements
on an Altera Cyclone IV FPGA and a bit-serial ALU as well as a
look-up table. Arrays of NPEs can be driven by a single controller
which executes the neural processing algorithm. In conclusion, the
proposed compact NPE design allows the construction of complex
hardware ANNs that can be implemented in a portable equipment
that suits the needs of a single epileptic patient in his or her daily
activities to predict the occurrences of impending tonic conic seizures.
Abstract: Edge detection is one of the most important tasks in image processing. Medical image edge detection plays an important role in segmentation and object recognition of the human organs. It refers to the process of identifying and locating sharp discontinuities in medical images. In this paper, a neuro-fuzzy based approach is introduced to detect the edges for noisy medical images. This approach uses desired number of neuro-fuzzy subdetectors with a postprocessor for detecting the edges of medical images. The internal parameters of the approach are optimized by training pattern using artificial images. The performance of the approach is evaluated on different medical images and compared with popular edge detection algorithm. From the experimental results, it is clear that this approach has better performance than those of other competing edge detection algorithms for noisy medical images.
Abstract: Recent developments on multi-agent system have brought a new research field on image processing. Several algorithms are used simultaneously and improved in deferent applications while new methods are investigated. This paper presents a new automatic method for edge detection using several agents and many different actions. The proposed multi-agent system is based on parallel agents that locally perceive their environment, that is to say, pixels and additional environmental information. This environment is built using Vector Field Convolution that attract free agent to the edges. Problems of partial, hidden or edges linking are solved with the cooperation between agents. The presented method was implemented and evaluated using several examples on different synthetic and medical images. The obtained experimental results suggest that this approach confirm the efficiency and accuracy of detected edge.
Abstract: The photoacoustic images are obtained from a custom developed linear array photoacoustic tomography system. The biological specimens are imitated by conducting phantom tests in order to retrieve a fully functional photoacoustic image. The acquired image undergoes the active region based contour filtering to remove the noise and accurately segment the object area for further processing. The universal back projection method is used as the image reconstruction algorithm. The active contour filtering is analyzed by evaluating the signal to noise ratio and comparing it with the other filtering methods.
Abstract: Ionic liquids are finding a wide range of applications from reaction media to separations and materials processing. In these applications, Vapor–Liquid equilibrium (VLE) is the most important one. VLE for six systems at 353 K and activity coefficients at infinite dilution [(γ)_i^∞] for various solutes (alkanes, alkenes, cycloalkanes, cycloalkenes, aromatics, alcohols, ketones, esters, ethers, and water) in the ionic liquids (1-ethyl-3-methylimidazolium bis (trifluoromethylsulfonyl)imide [EMIM][BTI], 1-hexyl-3-methyl imidazolium bis (trifluoromethylsulfonyl) imide [HMIM][BTI], 1-octyl-3-methylimidazolium bis(trifluoromethylsulfonyl) imide [OMIM][BTI], and 1-butyl-1-methylpyrrolidinium bis (trifluoromethylsulfonyl) imide [BMPYR][BTI]) have been used to train neural networks in the temperature range from (303 to 333) K. Densities of the ionic liquids, Hildebrant constant of substances, and temperature were selected as input of neural networks. The networks with different hidden layers were examined. Networks with seven neurons in one hidden layer have minimum error and good agreement with experimental data.
Abstract: Medical digital images usually have low resolution because of nature of their acquisition. Therefore, this paper focuses on zooming these images to obtain better level of information, required for the purpose of medical diagnosis. For this purpose, a strategy for selecting pixels in zooming operation is proposed. It is based on the principle of analog clock and utilizes a combination of point and neighborhood image processing. In this approach, the hour hand of clock covers the portion of image to be processed. For alignment, the center of clock points at middle pixel of the selected portion of image. The minute hand is longer in length, and is used to gain information about pixels of the surrounding area. This area is called neighborhood pixels region. This information is used to zoom the selected portion of the image. The proposed algorithm is implemented and its performance is evaluated for many medical images obtained from various sources such as X-ray, Computerized Tomography (CT) scan and Magnetic Resonance Imaging (MRI). However, for illustration and simplicity, the results obtained from a CT scanned image of head is presented. The performance of algorithm is evaluated in comparison to various traditional algorithms in terms of Peak signal-to-noise ratio (PSNR), maximum error, SSIM index, mutual information and processing time. From the results, the proposed algorithm is found to give better performance than traditional algorithms.
Abstract: This paper considers people’s driving skills
diagnosis under real driving conditions. In that sense, this research
presents an approach that uses GPS signals which have a direct
correlation with driving maneuvers. Besides, it is presented a novel
expert-driving-criteria approximation using fuzzy logic which
seeks to analyze GPS signals in order to issue an intelligent driving
diagnosis.
Based on above, this works presents in the first section the
intelligent driving diagnosis system approach in terms of its own
characteristics properties, explaining in detail significant
considerations about how an expert-driving-criteria approximation
must be developed. In the next section, the implementation of our
developed system based on the proposed fuzzy logic approach is
explained. Here, a proposed set of rules which corresponds to a
quantitative abstraction of some traffics laws and driving secure
techniques seeking to approach an expert-driving- criteria
approximation is presented.
Experimental testing has been performed in real driving
conditions. The testing results show that the intelligent driving
diagnosis system qualifies driver’s performance quantitatively with
a high degree of reliability.
Abstract: Cooperative groups through much research have been
recognized to churn remarkable achievements instead of solitary or
individualistic efforts. Based on Johnson and Johnson’s model of
cooperative learning, the five key components of cooperation are
positive interdependence, face-to-face promotive interaction,
individual accountability, social skills, and group processing. In
2011, the Malaysian Ministry of Higher Education (MOHE)
introduced the Holistic Student Development policy with the aim to
develop morally sound individuals equipped with lifelong learning
skills. The Community Service project was included in the
improvement initiative. The purpose of this study is to assess the
relationship of team-based learning in facilitating particularly
students’ positive interdependence and face-to-face promotive
interaction. The research methods involve in-depth interviews with
the team leaders and selected team members, and a content analysis
of the undergraduate students’ reflective journals. A significant
positive relationship was found between students’ progressive
outlook towards teamwork and the highlighted two components. The
key findings show that students have gained in their individual
learning and work results through teamwork and interaction with
other students. The inclusion of Community Service as a MOHE
subject resonates with cooperative learning methods that enhances
supportive relationships and develops students’ social skills together
with their professional skills.
Abstract: Obturator Foramen is a specific structure in Pelvic
bone images and recognition of it is a new concept in medical image
processing. Moreover, segmentation of bone structures such as
Obturator Foramen plays an essential role for clinical research in
orthopedics. In this paper, we present a novel method to analyze the
similarity between the substructures of the imaged region and a hand
drawn template as a preprocessing step for computation of Pelvic
bone rotation on hip radiographs. This method consists of integrated
usage of Marker-controlled Watershed segmentation and Zernike
moment feature descriptor and it is used to detect Obturator Foramen
accurately. Marker-controlled Watershed segmentation is applied to
separate Obturator Foramen from the background effectively. Then,
Zernike moment feature descriptor is used to provide matching
between binary template image and the segmented binary image for
final extraction of Obturator Foramens. Finally, Pelvic bone rotation
rate calculation for each hip radiograph is performed automatically to
select and eliminate hip radiographs for further studies which depend
on Pelvic bone angle measurements. The proposed method is tested
on randomly selected 100 hip radiographs. The experimental results
demonstrated that the proposed method is able to segment Obturator
Foramen with 96% accuracy.
Abstract: Rapid prototyping is a new group of manufacturing
processes, which allows fabrication of physical of any complexity
using a layer by layer deposition technique directly from a computer
system. The rapid prototyping process greatly reduces the time and
cost necessary to bring a new product to market. The prototypes
made by these systems are used in a range of industrial application
including design evaluation, verification, testing, and as patterns for
casting processes. These processes employ a variety of materials and
mechanisms to build up the layers to build the part. The present work
was to build a FDM prototyping machine that could control the X-Y
motion and material deposition, to generate two-dimensional and
three-dimensional complex shapes. This study focused on the
deposition of wax material. This work was to find out the properties
of the wax materials used in this work in order to enable better
control of the FDM process. This study will look at the integration of
a computer controlled electro-mechanical system with the traditional
FDM additive prototyping process. The characteristics of the wax
were also analysed in order to optimise the model production process.
These included wax phase change temperature, wax viscosity and
wax droplet shape during processing.
Abstract: Comparative analysis of the properties of melon seed,
coconut fruit and their oil yield were evaluated in this work using
standard analytical technique AOAC. The results of the analysis
carried out revealed that the moisture contents of the samples studied
are 11.15% (melon) and 7.59% (coconut). The crude lipid content are
46.10% (melon) and 55.15% (coconut).The treatment combinations
used (leaching time, leaching temperature and solute: solvent ratio)
showed significant difference (p < 0.05) in yield between the
samples, with melon oil seed flour having a higher percentage range
of oil yield (41.30 – 52.90%) and coconut (36.25 – 49.83%). The
physical characterization of the extracted oil was also carried out.
The values gotten for refractive index are 1.487 (melon seed oil) and
1.361 (coconut oil) and viscosities are 0.008 (melon seed oil) and
0.002 (coconut oil). The chemical analysis of the extracted oils shows
acid value of 1.00mg NaOH/g oil (melon oil), 10.050mg NaOH/g oil
(coconut oil) and saponification value of 187.00mg/KOH (melon oil)
and 183.26mg/KOH (coconut oil). The iodine value of the melon oil
gave 75.00mg I2/g and 81.00mg I2/g for coconut oil. A standard
statistical package Minitab version 16.0 was used in the regression
analysis and analysis of variance (ANOVA). The statistical software
mentioned above was also used to optimize the leaching process.
Both samples gave high oil yield at the same optimal conditions. The
optimal conditions to obtain highest oil yield ≥ 52% (melon seed)
and ≥ 48% (coconut seed) are solute - solvent ratio of 40g/ml,
leaching time of 2hours and leaching temperature of 50oC. The two
samples studied have potential of yielding oil with melon seed giving
the higher yield.
Abstract: One of the most important challenging factors in
medical images is nominated as noise. Image denoising refers to the
improvement of a digital medical image that has been infected by
Additive White Gaussian Noise (AWGN). The digital medical image
or video can be affected by different types of noises. They are
impulse noise, Poisson noise and AWGN. Computed tomography
(CT) images are subjects to low quality due to the noise. Quality of
CT images is dependent on absorbed dose to patients directly in such
a way that increase in absorbed radiation, consequently absorbed
dose to patients (ADP), enhances the CT images quality. In this
manner, noise reduction techniques on purpose of images quality
enhancement exposing no excess radiation to patients is one the
challenging problems for CT images processing. In this work, noise
reduction in CT images was performed using two different
directional 2 dimensional (2D) transformations; i.e., Curvelet and
Contourlet and Discrete Wavelet Transform (DWT) thresholding
methods of BayesShrink and AdaptShrink, compared to each other
and we proposed a new threshold in wavelet domain for not only
noise reduction but also edge retaining, consequently the proposed
method retains the modified coefficients significantly that result good
visual quality. Data evaluations were accomplished by using two
criterions; namely, peak signal to noise ratio (PSNR) and Structure
similarity (Ssim).
Abstract: Multiple-input multiple-output (MIMO) radar has
received increasing attention in recent years. MIMO radar has many
advantages over conventional phased array radar such as target
detection,resolution enhancement, and interference suppression. In
this paper, the results are presented from a simulation study of MIMO
uniformly-spaced linear array (ULA) antennas. The performance is
investigated under varied parameters, including varied array size,
pseudo random (PN) sequence length, number of snapshots, and
signal to noise ratio (SNR). The results of MIMO are compared to a
traditional array antenna.
Abstract: This paper treats different aspects of entropy measure
in classical information theory and statistical quantum mechanics, it
presents the possibility of extending the definition of Von Neumann
entropy to image and array processing. In the first part, we generalize
the quantum entropy using singular values of arbitrary rectangular
matrices to measure the randomness and the quality of denoising
operation, this new definition of entropy can be implemented to
compare the performance analysis of filtering methods. In the second
part, we apply the concept of pure state in quantum formalism
to generalize the maximum entropy method for narrowband and
farfield source localization problem. Several computer simulation
results are illustrated to demonstrate the effectiveness of the proposed
techniques.
Abstract: DNA Barcode provides good sources of needed
information to classify living species. The classification problem has
to be supported with reliable methods and algorithms. To analyze
species regions or entire genomes, it becomes necessary to use the
similarity sequence methods. A large set of sequences can be
simultaneously compared using Multiple Sequence Alignment which
is known to be NP-complete. However, all the used methods are still
computationally very expensive and require significant computational
infrastructure. Our goal is to build predictive models that are highly
accurate and interpretable. In fact, our method permits to avoid the
complex problem of form and structure in different classes of
organisms. The empirical data and their classification performances
are compared with other methods. Evenly, in this study, we present
our system which is consisted of three phases. The first one, is called
transformation, is composed of three sub steps; Electron-Ion
Interaction Pseudopotential (EIIP) for the codification of DNA
Barcodes, Fourier Transform and Power Spectrum Signal Processing.
Moreover, the second phase step is an approximation; it is
empowered by the use of Multi Library Wavelet Neural Networks
(MLWNN). Finally, the third one, is called the classification of DNA
Barcodes, is realized by applying the algorithm of hierarchical
classification.
Abstract: Background subtraction and temporal difference are
often used for moving object detection in video. Both approaches are
computationally simple and easy to be deployed in real-time image
processing. However, while the background subtraction is highly
sensitive to dynamic background and illumination changes, the
temporal difference approach is poor at extracting relevant pixels of
the moving object and at detecting the stopped or slowly moving
objects in the scene. In this paper, we propose a simple moving object
detection scheme based on adaptive background subtraction and
temporal difference exploiting dynamic background updates. The
proposed technique consists of histogram equalization, a linear
combination of background and temporal difference, followed by the
novel frame-based and pixel-based background updating techniques.
Finally, morphological operations are applied to the output images.
Experimental results show that the proposed algorithm can solve the
drawbacks of both background subtraction and temporal difference
methods and can provide better performance than that of each method.