Computer Science

A construction of a 3D geological model of Yamama Formation to explain the distribution of petrophysical properties (shale volume, effective porosity and hydrocarbon saturation) by using Petrel software. Five wells were selected in order to build structural and petrophysical models based on interpretation of well logs and petrophysical properties. Yamama reservoir is divided into four main units (YA, YB, YC, and YD), YA is divided into five secondary reservoir units (YA1, YA2, YA3, YA4, and YA5), YB is divided into two secondary reservoir units (YB1 and YB2), YC is divided into two secondary reservoir units (YC1 and YC2) and YD is divided into three secondary reservoir units (YD1, YD2, and YD3). Structural model showed Faihaa oil field represented by anticlinal fold with double plunging. Petrophysical models (shale volume, effective porosity and hydrocarbon saturation) constructed for each subunit of Yamama reservoir using sequential Gaussian simulation executed with Petrel software...

In this paper, we present BASRAH, a system that automatically identifies the meter of Arabic verse, which is an operation that requires a certain level of human expertise. BASRAH uses the numerical prosody method, which depends on verse coding that is derived from the general concept of al-Khalil's feet through using the two primary units (cord=2 and peg=3). BASRAH has proved to be an efficient tool to help inexperienced users to determine the meters of Arabic verses when we tested it on thousands of old and modern Arabic verses.

In this paper, we propose a post decoding system combination approach for automatic transcribing Malay broadcast news. This approach combines the hypotheses produced by parallel automatic speech recognition (ASR) systems. Each ASR system uses different language models, one which is generic domain model and another is domain specific model. The main idea is to take advantage of different ASR knowledge to improve ASR decoding result. It uses the language score and time information to produce a 1-best lattice, and then rescore the 1-best lattice to get the most likely word sequence as the final output. The proposed approach was compared with conventional combination approach, the recognizer output voting error reduction (ROVER). Our proposed approach improved the word error rate (WER) from 33.9% to 30.6% with an average relative WER improvement of 9.74%, and it is better than the conventional ROVER approach.

The main motivation of this paper is to improve the automatic speech recognition (ASR) hypothesis in the Malay language. Manual news transcription is too expensive and takes a long time. Hence, without an ASR system, access to audio archives and searches within them would be restricted to the limited number of textual documents that have been manually transcribed by humans or indexed with keywords. Multiple hypotheses are useful because the single best recognition output still has numerous errors, even for state-of-the-art systems. In this paper, we propose an approach to reduce the word error rate (WER) in an ASR hypothesis. This approach is known as the three-pass combination method using parallel ASR systems. The three-pass combination system based on grapheme rescoring and phone rescoring re-evaluates all of the hypotheses produced by the ASR systems to produce a more accurate hypothesis. To evaluate the performance of the proposed approach, Malay broadcast news contains speech from newscaster, reporter and interviewers in noisy environments recorded from Malaysia local news channels are employed. This approach reduced the WER by 4.4% from 34.5% to 30.1%. The performance of the proposed approach was compared with six approaches that are frequently used for ASR rescoring and combination.

Coronavirus (COVID-19) pandemic detection considers a critical and challenging task for the doctors. The coronavirus disease spread so rapidly between people and infected roughly fourteen million people worldwide. For this reason, it is very much necessary to detect infected people with coronavirus and take the action to prevent of spread this virus. In this study, the COVID-19 classification methodology is adopted to detect the infected patient with coronavirus using CT images. The deep learning is applied to recognize the affected CT images of COVID-19 from others by employing the deep feature. This methodology can be beneficial for the medical practitioner to diagnosis the infected patient with coronavirus. The result is based on new data collections named BasrahDataset that included different CT scan video for Iraqi patients. The system gives promised results with 99% F1-score for detecting COVID-19.

This paper represents a new approach for face recognition that incorporates Prewitt edge detection, Gabor filter and Zernike moments to transform the image into a unified domain. On this joint domain, five distance metrics are constructed using Schoenberg transform for the purpose of defining efficient similarity measures for holistic face recognition. The proposed Schoenberg similarity applies Schoenberg transform to the logarithm of five existing distance metrics: Minkowski, City-Block, Euclidean, Soergel and Lorentzian metrics. The constructed Schoenberg logarithmic metrics are called SL-Minkowski, SL-City-Block, SL-Euclidean, SL-Soergel and SL-Lorentzian. These distance metrics are utilized as similarity measures after being normalized over the range [0,1] for fair comparison with existing measures. The proposed Schoenberg system can resist three problems: Change in illumination, pose and facial expression. Simulation results show that the proposed distance measures have superio...

A Coronavirus disease 2019 (COVID-19) pandemic detection considers a critical and challenging task for the medical practitioner. The coronavirus disease spread so rapidly between people and infected more than one hundred and seventy million people worldwide. For this reason, it is necessary to detect infected people with coronavirus and take action to prevent virus spread. In this study, a COVID-19 classification methodology was adopted to detect infected people using computed tomography (CT) images. Deep learning was applied to recognize COVID-19 infected cases for different patients by employing deep features. This methodology can be beneficial for medical practitioners to diagnose infected patients. The results were based on a new data collection named BasrahDataset that includes different CT scan videos for Iraqi patients. The proposed system gave promised results with a 99% F1-score for detecting COVID-19.

Herein we describe the latent semantic algorithm method for identifying broadcast news story boundaries. The proposed system uses the pronounced forms of words to identify story boundaries based on popular noun unification. Commonly used clustering methods use latent semantic analysis (LSA) because of its excellent performance and because it is based on deep semantic rather than shallow principles. In this study, the LSA algorithm with and without unification was used to identify boundaries of Malay spoken broadcast news stories. The LSA algorithm with the noun unification approach resulted in less error and better performance than the LSA algorithm without noun unification.

An information retrieval (IR) is a system that locates information in collections of unstructured or semistructured document which are relevant to the user query. Usually, the query represented by short query that have a few features or keywords that used to describe the user needed of information. These short queries containing only a few words can be vague and ambiguous. As a result, IR system returns documents that are generally not relevant to the user’s information needs. In this paper, an automatic approach of query expansion is proposed based on latent semantic indexing (LSI) method in order to enhance the performance of the information retrieval system. Development database of queries are used to find the best match between the user query and the development queries by using LSI algorithm. The best result that obtained from LSI will combine with the user query to create a new query that used later as new input in information retrieval system to retrieve the documents. To eva...

Aircraft detection is an essential and noteworthy area of object detection that has received significant interest from scholars, especially with the progress of deep learning techniques. Aircraft detection is now extensively employed in various civil and military domains. Automated aircraft detection systems play a crucial role in preventing crashes, controlling airspace, and improving aviation traffic and safety on a civil scale. In the context of military operations, detection systems play a crucial role in quickly locating aircraft for surveillance purposes, enabling decisive military strategies in real time. This article proposes a system that accurately detects airplanes independent of their type, model, size, and color variations. However, the diversity of aircraft images, including variations in size, illumination, resolution, and other visual factors, poses challenges to detection performance. As a result, an aircraft detection system must be designed to distinguish airplanes clearly without affecting the aircraft's position, rotation, or visibility. The methodology involves three significant steps: feature extraction, detection, and evaluation. Firstly, deep features will be extracted using a pre-trained VGG19 model and transfer learning principle. Subsequently, the extracted feature vectors are employed in One Class Support Vector Machine (OCSVM) for detection purposes. Finally, the results are assessed using evaluation criteria to ensure the effectiveness and accuracy of the proposed system. The experimental evaluations were conducted across three distinct datasets: Caltech-101, Military dataset, and MTARSI dataset. Furthermore, the study compares its experimental results with those of comparable publications released in the past three years. The findings illustrate the efficacy of the proposed approach, achieving F1-scores of 96% on the Caltech-101 dataset and 99% on both Military and MTARSI datasets.

Parallel manipulators have a rigid structure and can pick up the heavy objects. Therefore, a parallel manipulator has been developed based on the cooperative of three arms of a robotic system to make the whole system suitable for solving many problems such as materials handling and industrial automation. The three revolute joints are used to achieve the mechanism operation of the parallel planar robot. Those revolute joints are geometrically designed using an open-loop spatial robotic platform. In this paper, the geometric structure with three revolute joints is used to drive and analyze the inverse kinematic model for the 3RRR parallel planar robot. In the proposed design, three main variables are considered: the length of links of the 3RRR parallel planar robot, base positions of the platform, and joint angles’ geometry. Cayley-Menger determinants and bilateration are proposed to calculate these three variables to determine the final position of the platform and to move specific objects according to given desired trajectories. The proposed structure of the 3RRR parallel planar robot is simulated and different desired trajectories are tested to study the performance of the proposed stricter. Furthermore, the hardware implementation of the proposed structure is accomplished to validate the design in practical terms.

The Holy Quran, due to it is full of many inspiring stories and multiple lessons that need to understand it requires additional attention when it comes to searching issues and information retrieval. Many works were carried out in the Holy Quran field, but some of these dealt with a part of the Quran or covered it in general, and some of them did not support semantic research techniques and the possibility of understanding the Quranic knowledge by the people and computers. As for others, techniques of data analysis, processing, and ontology were adopted, which led to directed these to linguistic aspects more than semantic. Another weakness in the previous works, they have adopted the method manually entering ontology, which is costly and time-consuming. In this paper, we constructed the ontology of Quranic stories. This ontology depended in its construction on the MappingMaster domain-specific language (MappingMaster DSL)technology, through which concepts and individuals can be creat...

In today’s world, social media has spread widely, and the social life of people have become deeply associated with social media use. They use it to communicate with each other, share events and news, and even run businesses. The huge growth in social media and the massive number of users has lured attackers to distribute harmful content through fake accounts, leading to a large number of people falling victim to those accounts. In this work, we propose a mechanism for identifying fake accounts on the social media site Twitter by using two methods to preprocess data and extract the most effective features, they are the spearman correlation coefficient and the chi-square test. For classification, we used supervised machine learning algorithms based on the ensemble system (stack method) by using random forest, support vector machine, and Naive Bayes algorithms in the first level of the stack, and the logistic regression algorithm as a meta classifier. The stack ensemble system was show...

Data security pressing issue, particularly in terms of ensuring secure and reliable data transfer over a network. Encryption and seganography play a fundamental role in the task of securing data exchanging. In this article, both steganography and cryptography were combined to produce a powerful hybrid securing stego-system. Firstly, a text message is encrypted with a new method using a bits cycling operation to give a cipher text. In the second stage, an enhanced LSB method is used to hide the text bits randomly in an audio file of a wav format. This hybrid method can provide effectually secure data. Peak signal-to-noise ratio (PSNR), mean squared error (MSE) and structural similarity (SSIM) were employed to evaluate the performance of the proposed system. A PSNR was in range (60-65) dB with the enhanced least significant bit (LSB) and the SSIM had been invested to calculate the signal quality, which scored 0.999. The experimental results demonstrated that our algorithm is highly ef...

Text data present in images contain useful information for automatic explanation, indexing, and structuring of images. Extraction of this information involves detection, localization, tracking, extraction, enhancement, and recognition of the text from a given image. However variations of text due to differences in size, style, orientation, and alignment, as well as low image contrast and complex background make the problem of automatic text extraction extremely challenging in the computer vision research area. The proposed methods compare two basic approaches for extracting text region in images: edge-based and connected-component based. The algorithms are implemented and evaluated using a set of images that vary along the dimensions of lighting, scale and orientation. Accuracy, precision and recall rates for each approach are analyzed to determine the success and limitations of each approach.

Automated visual inspection system has been developed to specify brick quality and the accepting of the bricks in a production line. This system is based on CMOS web-camera placed in manufacture line. Depending on diameters, area, perimeter and cracks of a brick, a strong algorithm has been developed, and this algorithm is created to befit the required for measuring bricks quality. The quality is measured by fuzzy system which can give percent accepting to a brick under the test. Fuzzy reasoning gives the system more reliability than other inspection system.

Many important features of chaotic systems can be exploited in cryptography such as: ergodicity, sensitivity to initial
condition, mixing property. These features lead to a significant relationship between cryptography and chaos. Sensor nodes in a wireless sensor network (WSN) are affected with resource constrained; they have limited processing speed, storage capacity, energy, and communication bandwidth. This paper proposes a new encryption scheme called Chaotic Block Cipher (CBC) to encrypt the message digest MD for WSNs data. The proposed method uses logistic chaotic method to create a number of chaotic
values and treats these values to obtain the encryption/decryption keys then mixing them with a plaintext to get a ciphertext. Simulation results demonstrate that, the execution time and the security achieved by the proposed method are very suitable for WSNs.