39 research outputs found
Improvised qibla direction formula by Vec-M / Shahrul Nizam Ishak, Samsul Setumin and Mohd Shaiful Sharipudin
No full textQibla is a most important direction which is needed to alive as well as to dead. Every Muslim has to face this direction five times a day to perform his obligatory prayer. Facing this direction is necessary condition for the prayer’s validity. The qibla is the direction to Kaabah, but what precisely is that direction? A classical definition for determination of qibla direction is given by Ibn al-Haytham:
"the qibla is the direction such that when a human observer faces it, it is as if he is looking at the diameter of the earth passing through the Kaabah”
Here, we proposed new technique called Vector Method [Vec-M\ for determining qibla direction. The problem of determining the direction of qibla is a problem of mathematical geography. Thus, this project describes about the methods of the mathematical calculation of qibla by using modern approach. Methods discuss are Spherical Trigonometry Method and Vector Method. The accuracy of the proposed method were compared. Besides, the discussion is confined to the scientific aspects of the subject and the religion rulings are analyzed only for an underlying scientific assumption and also for knowledge purposes
Car plate recognition based on stroke composition technique / Samsul Setumin, Mohd Ikmal Fitri Maruzuki and Shahrul Nizam Ishak.
No full textIn this research, a license plate recognition algorithm using a stroke analysis will be done. Stroke analysis is a method of character recognition that is most commonly used in recognition of oriental handwritten characters using languages such as Japanese, Chinese and Korean. This technique identifies the various strokes that combine to form a particular character and based on that a conclusion is made. Stroke analysis involves the study of a common representation scheme to provide a structure hierarchy for different characters, whose most primitive building blocks are strokes.
Stroke analysis is a popular method used in recognition of Chinese, Japanese and Korean characters mainly because the characters in these languages comprise of combining strokes to form a particular character. Besides, these characters are rather complex. Thus, strokes analysis in these characters would be the best method for carrying out recognition in terms of accuracy and speed compared to other techniques such as neural networks and template matching. Generally, strokes can be divided into two groups. The two groups are simple strokes and complex strokes.
There are many synonymous terms with stroke analysis. Some of the terminologies which have the same meaning with strokes analysis are chain coding, stroke approximation and boundary representations. Many researches have proposed various different approaches at carrying out stroke analysis in the process of character recognition. These different approaches are customized for their various applications. In this algorithm however, it comprises two main processes; character extraction and stroke analysis. In addition, the stroke analysis itself generally consists of two parts. These two parts are stroke tracing and stroke recognition.
Although stroke analysis is a powerful technique in the recognition of characters, it is a rather difficult and complicated technique to be implemented. The biggest challenge posed by the usage of this technique is that of extracting the strokes from the character images. Extracting the strokes from the image of a character is a complicated task. As such, various researchers have proposed various different approaches for obtaining strokes from the character image
Comparative analysis in shoreline changes in Kelantan, Malaysia using Digital Shoreline Analysis System (DSAS) / Muhammad Zakwan Anas Abd Wahid, Mohamed Syazwan Osman and Samsul Setumin
No full textKelantan is a Malaysian state renowned for its beautiful jungles and coastal districts. Kelantan, which is susceptible to monsoons and tidal waves, witnessed a tsunami-like inundation that affected its coastline landscape in 2014. This study does a comparative examination of shoreline alterations between 2013 and 2021 using the Digital Shoreline Analysis System (DSAS) technology. The coastline has grown by approximately 4.03 percent, from 62.1 kilometres to 64.6 kilometres, as a result of the implementation of digitalisation procedures. This highlights the increase in coastline areas between 2013 and 2021. Using GIS and satellite data, the study identifies considerable sedimentation in Pantai Geting and Lagun Jubakar, Tumpat, as well as severe erosion in Pantai Kundur and Pantai Cahaya Bulan, Kota Bharu. The analysis of the Shoreline Change Envelope (SCE) and Net Shoreline Movement (NSM) reveals an accretion rate of 728.44 m/year and a negative distance of -281.91 m/year, which indicates erosion. The paper concludes by emphasising Kelantan's shoreline expansion over the previous decade, stressing the significance of monitoring coastal changes for effective environmental management and catastrophe preparedness
Artificial neural network: physico-chemical and macronutrients parameters in an aquaponic system / Qistina Khadijah Abd Rahman, T.s Mohamed Syazwan Osman and Dr Samsul Setumin
No full textAquaponic system which integrates conventional aquaculture and hydroponic in one closed-loop system plays a significant role as an alternative way to produce very least waste effluent to the environment by recycling back the nutrients (fish waste) for plant growth. Prediction of water quality parameter in wastewater using conventional mathematical modeling is very complex to simulate and model out the system. Therefore, this paper proposed ANN model to evaluate graph comparison between the performances of the actual data from aquaponics activity and forecast data from simulated artificial neural network (ANN). Then, the best algorithms will be selected in a variety of neuron numbers of the ANN’s model. The parameter such as pH, DO, TAN, and percent total sludge of Phosphorus (P) and Nitrogen (N) were investigated by taking the input and target data value from the selected research paper covering the fields of aquaponic. In this study, Levenberg-Marquardt (LM) and Scaled Conjugate Gradient (SCG) training function were used to measure those parameters to obtain the predict values. For parameter pH, DO, TAN, ranges hidden neurons of 4, 6, 8, 10, 12, 13 neurons were studied. Meanwhile, ranges hidden neurons of 3, 4, 6, 9, 12 neurons were studied for total sludge (P and N). Different range neurons value was used for pH, DO, TAN, and Total Sludge (P and N) due to different input data found in the literature. The outputs from the model of training function LM show the most optimum neuron number for each parameter of pH, DO, TAN at neuron 6. As for total sludge (N and P), the most optimum neuron number at neuron 3. For the training function SCG, the most optimum neuron number at neuron 4 for each parameter pH, DO, TAN and at neuron 9 and neuron 4 were the most optimum neuron number for parameter Total Sludge (N and P). The result for the most optimum neuron number can be explained by the value of Sum Squared Error (SSE) and Mean Absolute Percentage Error (MAPE%) with the lowest value. The investigated forecast parameters of the trained neural network according to correlation coefficient (R) and Mean Square Error (MSE) showed LM performed better rather than SCG
Forensic Sketch To Mugshot Matching Algorithm Based On Dynamic Difference Of Gaussian Oriented Gradient Histogram
No full textAn automatic photo retrieval system based on facial sketch has very useful application in criminal investigations. The face sketch and photograph are from different modality. In inter-modality matching approach, it is unclear which descriptor is the most modality-invariant. Next, the real-world photo may be exposed to lighting variation and the sketch may experience some degrees of shape exaggeration with very less accurate details. With these effects, the retrieval rate reduces significantly. In this research work, at the beginning, the most modality-invariant local hand craftedde scriptor is determined. Next, a new fiducial points for face alignment and a newdescriptor called Difference of Gaussian Oriented Gradient Histogram (DoGOGH) are introduced to reduce the factor of shape exaggeration and to minimize the illumination effects, respectively. It is followed by new feature extraction methods called Dynamic DoGOGH (D-DoGOGH) and Cascaded Static and Dynamic DoGOGH (C-DoGOGH) to really cater for the shape exaggeration effects. The accuracy and speed are improved further after incorporating feature fusion, Patch of Interest (PoI) and score fusion into the proposed method. The experimental results for CUHK Face Sketch Database (CUFS) and CUHK Face Sketch FERET Database (CUFSF) datasets demonstrate that the proposed method outperforms the state-of-the-art methods. It gives rank-1 accuracy of 100% and 95.48% for the CUFS and CUFSF datasets, respectively. The evaluation is extended further to semi-forensic and forensic sketch datasets to indicate that the proposed method is feasible to be used in the real-world criminal investigations. It gives rank-1 accuracy improvements of 28.56% and 66.77% for the semi-forensic and forensic sketch datasets, respectively
Plate recognition for Malaysian vehicles using stroke analysis technique
No full textThe Road Transport Department of Malaysia has endorsed a specification for vehicle plates that includes the font and size of characters that must be followed by car owners. However, there are a special plate number where this specification is not followed such as Proton, BAMbee, Putrajaya, Tiara, Satria and Perodua. This will cause problems in the recognition phase because existing systems will find difficulty in recognizing these plates. Therefore, this project is aimed of an implementing a recognition system that is capable of solving the mentioned issues using stroke analysis technique. The system is an offline system where the vehicle image is loaded manually from a directory. The loaded image is then pre-processed using image processing techniques. Consequently, the image is converted into a binary image. The plate region is extracted prior to characters extraction. All the characters then undergo thinning process before stroke analysis performs tracing and recognition of the characters. The system displays the output in readable text. The performance analysis has shown that the system is able to recognize Malaysian vehicle plate with more than 95 percent accuracy
Electronic CAD schematic and printed circuit board design course at Kolej Komuniti Seberang Jaya / Asmalia Zanal
No full textOn August 5th, a total of 12 academic and support staff participated in the Electronic CAD Schematic and Printed Circuit Board Design Course, which was conducted in collaboration with Kolej Komuniti Seberang Jaya.
The program is led by Dr. Samsul Setumin, the Coordinator of the Diploma Program. Its successful implementation aims to enhance the skills and expertise of cademic staff and supporting staff in line with current technology. Additionally, this collaboration aims to foster relationships and facilitate the exchange of knowledge and expertise among the academic staff of Kolej Komuniti Seberang Jaya
The Performance of Siamese Neural Network for Face Recognition using Different Activation Functions
No full text
An Empirical Investigation on the Effect of Shape Exaggeration in Face Sketch to Photo Matching
No full text
