Diyar Qader Zeebaree

One of the main causes of increased mortality among women is breast cancer. The ultrasound scan is the most widely used method for diagnosing geological disease i.e. breast cancer. The first step for identifying the abnormality of the breast cancer (malignant from benign), is the extraction of the region of interest (ROI). In order to achieve this, a new approach to breast ROI extraction is proposed for the purpose of reducing false positive cases (FP). The proposed model was built based on the local pixel information and neural network. It includes two stages namely, training and testing. In the training stage, a trained model was built by extracting the number of batches from both ROI and background. The testing stage involved scanning the image with a fixed size window to detect the ROI from the background. Afterwards, a distance transform was used to identify the ROI and remove non-ROI. Experiments were conducted on the on-data set with 250 ultrasound images (150 benign and 100 malignant) the preliminary results show that the proposed method achieves a success rate of about 95.4% for breast contour extraction. The performance of the proposed solution also has been compared with the existing solutions that have been used to segment different types of images. ... Read More

Gene expression profiles could be generated in large quantities by utilizing microarray techniques. Currently, the task of diagnosing diseases relies on gene expression data. One of the techniques which helps in this task is by utilizing deep learning algorithms. Such algorithms are effective in the identification and classification of informative genes. These genes may subsequently be used in predicting testing samples' classes. In cancer identification, the microarray data typically possesses minimal samples number with a huge feature collection size which are hailing from gene expression data. Lately, applications of deep learning algorithms are gaining much attention to solve various challenges in artificial intelligence field. In the present study, we investigated a deep learning algorithm based on the convolutional neural network (CNN), for classification of microarray data. In comparison to similar techniques such as Vector Machine Recursive Feature Elimination and improved Random Forest (mSVM-RFE-iRF and varSeIRF), CNN showed that not all the data have superior performance. Most of experimental results on cancer datasets indicated that CNN is superior in terms of accuracy and minimizing gene in classifying cancer comparing with hybrid mSVM-RFE-iRF. ... Read More

Machine learning and data mining have established several effective applications in gene selection analysis. This paper review semi-supervised learning algorithms and gene selection. Semi-Supervised learning is learning that includes experiences that are familiar with the environment because it can deal with labelled and unnamed data. Gene selection is dimension reduction defined as the discovery process of the perfect selection of attributes comprising the whole collected dataset. We review many previous studies on gene selection in semi-supervised learning where each previous research paper tests a group of algorithms to select a gene on a specific set of selected medical data. Each study proposes its algorithm and compares it with previous existing algorithms and compares their accuracy. ... Read More

In developing countries breast cancer has been found to be one of the diseases that threatens the lives of women, and that is why finding ways of detecting efficiently is of great importance. The detection of breast cancer at an early stage through self-examination is very difficult. In this study, we proposed a new descriptor that can help to identify the abnormality of the breast by enhancing the features of LBP texture and enhance the LPB descriptor by using a new threshold that can help to identify the important information for the detection of abnormal cases. In the next stage, the significant features are extracted from the breast tumours images that have been segmented. Such features could be found in frequency or spatial domain. The extracted features for diagnosing tumour automatically, are additional and different from those features which the radiologist extracts manually. The proposed method demonstrates the possibility of using the LBP based texture feature with the new proposed method for categorising ultrasound images, which registered a high accuracy of 96%, the sensitivity of 94%, specificity of 97%. ... Read More

Breast cancer (BC) is a main killer disease for women and men. It can be cured and controlled only if it is detected at its early detection. BC initial identification can be realized by the help of computer support identification approaches. From the detailed study on previous researches, it is found that, there is no system producing high accuracy because of one or more reasons. Absence of effective preprocessing is the discussed reason that obstructs the detection accuracy of Computer-aided diagnosis (CAD) method. Noise removal and contrast enhancement are the two types of preprocessing. There is no system performs the preprocessing on mammogram image. This work is an attempt to develop an enhanced preprocessing method for CAD of breast cancer by incorporating suitable noise reduction and contrast enhancement methods in the conventional CAD system. Contrast enhancement after noise reduction double enhances the mammogram image and the proposed methods MSE value for the mammogram image mdb072 has been 1.44% reduced. Reduction in MSE increases the PSNR to 0.16%. Many mammogram images have been tested and the result shows that, increase in contrast, decrease in mean square error and increase in peak signal to noise ratio when comparing to existing methods ... Read More

Networks have evolved very rapidly, which allow secret data transformation speedily through the Internet. However, the security of secret data has posed a serious threat due to openness of these networks. Thus, researchers draw their attention on cryptography field for this reason. Due to the traditional cryptographic techniques which are vulnerable to intruders nowadays. Deoxyribonucleic Acid (DNA) considered as a promising technology for cryptography field due to extraordinary data density and vast parallelism. With the help of the various DNA arithmetic and biological operations are also Blum Blum Shub (BBS) generator, a multi-level of DNA encryption algorithm is proposed here. The algorithm first uses the dynamic key generation to encrypt sensitive information as a first level; second, it uses BBS generator to generate a random DNA sequence; third, the BBS-DNA sequence spliced with a DNA Gen Bank reference to produce a new DNA reference. Then, substitution, permutation, and dynamic key are used to scramble the new DNA reference nucleotides locations. Finally, for further enhanced security, an injective mapping is established to combine encrypted information with encrypted DNA reference using Knight tour movement in Hadamard matrix. The National Institute of Standard and Technology (NIST) tests have been used to test the proposed algorithm. The results of the tests demonstrate that they effectively passed all the randomness tests of NIST which means they can effectively resist attack operations. ... Read More

The Data Compression is a creative skill which defined scientific concepts of providing contents in a compact form. Thus, it has turned into a need in the field of communication as well as in different scientific studies. Data transmission must be sufficiently secure to be utilized in a channel medium with no misfortune; and altering of information. Encryption is the way toward scrambling an information with the goal that just the known receiver can peruse or see it. Encryption can give methods for anchoring data. Along these lines, the two strategies are the two crucial advances that required for the protected transmission of huge measure of information. In typical cases, the compacted information is encoded and transmitted. In any case, this sequential technique is time consumption and computationally cost. In the present paper, an examination on simultaneous compression and encryption technique depends on DNA which is proposed for various sorts of secret data. In simultaneous technique, both techniques can be done at single step which lessens the time for the whole task. The present work is consisting of two phases. First phase, encodes the plaintext by 6-bits instead of 8-bits, means each character represented by three DNA nucleotides whereas to encode any pixel of image by four DNA nucleotides. This phase can compress the plaintext by 25% of the original text. Second phase, compression and encryption has been done at the same time. Both types of data have been compressed by their half size as well as encrypted the generated symmetric key. Thus, this technique is more secure against intruders. Experimental results show a better performance of the proposed scheme compared with standard compression techniques. ... Read More

Networks are important today in the world and data security has become a crucial area of study. An IDS monitors the status of the software and hardware of the network. Curing problems for current IDSs remain they improve detection precision, decrease false alarm rates and track unknown attacks after decades of advancement. Many researchers have focused on the development of IDSs using machine learning approaches to solve the above-described problems. With the high precision of computer teachings, the basic distinctions between usual and irregular data can be recognized automatically. Unknown threats may also be detected because of their generalizability via machine learning system. This paper suggests a taxonomy of IDS, which uses the primary dimension of data objects to classify and sum up IDS literatures based on and dependent on deep learning. We assume this kind of taxonomy is sufficient for researchers in cyber security. We selected three algorithms from machine learning (Bayes Net, Random Forest, Neural Network) and two algorithms of deep learning (RNN, LSTM), and we tested them on KDD cup 99 and evaluated accuracy algorithms, and we used a program WEKA To calculate the accuracy. ... Read More

Machine learning algorithms have been used in many fields, like economics, medicine, etc. Education data mining is one of the areas concerned with exploring patterns of data in an educational environment. One of the most important uses is to predict students' performance to improve the existing educational situation. It can be considered as one of the data mining sciences. The ability to predict in advance in many areas has many benefits. In the case of learning, it enables us to know students' levels in advance and identify students who need special attention. This paper proposes using the algorithm (GBDT) which is a machine learning technology used for regression, classification, and ranking tasks, and is part of the Boosting method family to predict university students' performance in final exams. It compares the proposed system's performance with selected machine learning algorithms (Support vector machine, Logistic Regression, Naive Bayes, Gradient Boosted Trees). ... Read More

Coronavirus (COVID-19) is a new contagious disease reasoned by a new virus that is widely spread over the world, this virus never has been identified in humans before. Respiratory disease can be affected by this virus such as flu with several symptoms, for example, fever, headache, cough, and pneumonia. COVID-19 presence in humans can be tested through blood samples or sputum while the result can be obtained in days. Further, biomedical image analysis assists in showing signs of pneumonia in a patient. Therefore, this paper aims to provide a fully automatic COVID-19 identification system by proposing a new fusion scheme of texture features for CT scan images. This paper presents a fusion scheme based on a machine learning system using three significant texture features, namely, Local Binary Pattern (LBP), Fractal Dimension (FD), and Grey Level Co-occurrence Matrices (GLCM). In experimental results, to demonstrate the efficiency of the proposed scheme we have collected 300 CT scan images from a publicly available database. The experimental result shows the performance of LBP, FD, and GLCM obtained an accuracy of 89.87%, 87.84%, and 90.98%, respectively while the proposed scheme yields better results by achieving 96.91% accuracy. ... Read More

Nowadays, many businesses and organizations have begun to collect data on their future and current customers to evaluate churning rate and prevent the loss of potential customers while also keeping the current customers and making them happy. The challenging part, however, is not gathering the data, rather, it arises when these data are processed, and consumers are segmented based on the information collected. This paper aims to investigate the potentials of Data Mining in identifying potential churners from a business and more especially focusing on the Telecom industry. Many experiments are carried out, and various classification algorithms are tested to assess their impact and capability in predicting the potential churners, as this is a crucial information for businesses to keep their customers happy and subscribed to their services. ... Read More

Nature-inspired algorithms are often used by several diverse areas of engineering and science due to their easiness and versatility. Because metaheuristics operate by structurally changing and improving an established problem, they can often be extended to any optimization issues. The recent creation of metaheuristic algorithms has rendered them effective tools for solving NP problems. This paper presents a hybrid meta-heuristic method based on the Differential Evolution and Bird Mating Optimizer techniques to solve problems of global optimization. Bird Mating Optimizer is a novel method and is inspired by mating behavior of birds. Bird Mating Optimizer has some drawbacks such as producing poor results, trapping into local optima and slow convergence speed. Therefore, to conquer these insufficient it is hybridized with Differential Evolution approach. Differential Evolution technique is utilized to retain a preferable balance between both searches local and global. The performance and effectiveness of new Differential Evolution and Bird Mating Optimizer algorithm is tested and evaluated on 15 different functions of benchmark. The results of the experiment have shown the proposed technique possesses excellent performance in convergence speed, stability, and robustness, as compared to the well-known algorithms. It is proved that the Differential Evolution and Bird Mating Optimizer algorithm is very effective and superior to solve problems of global optimization. Experimental results indicate that the proposed hybrid Differential Evolution and Bird Mating Optimizer method is superior to previous existing state-of-the-art metaheuristic algorithms. ... Read More

Heart disease is one of the most common causes of death worldwide. Real-time methods for forecasting heart disease from medical data sources that explain a patient's current health status are discussed in this paper. The proposed system's main aim is to find the best data mining algorithm for predicting heart disease with high accuracy. We suggested using Decision Tree (DT), Support Vector Machine (SVM) and Naïve Bayes (NB) algorithms. All of these algorithms are classified as supervised learning and work better with training data. The main purpose of using three algorithms is to see which one is the best at predicting heart disease. The result shows that the DT algorithm provides the best accuracy with less training time when compared to SVM and Naïve Bayes(NB). ... Read More

The face is an essential characteristic of a person; it is used to distinguish between the personalities of two or more people in the real world. In recent years, different parts of the body have been manipulated to ensure that only the right person has access to their respective accounts, both physical and virtual. Biometrics, which involves identification such as fingerprints, palm veins, DNA, palm print, and face recognition, is one of the methods that has been developed. Similarly, this study would demonstrate how to use image processing to apply facial identification and recognition algorithms to create a device that can identify and recognize the frontal faces of students in a classroom. A face is a front part of a person’s head from the forehead to the chin or the corresponding part of an animal. The face is the most significant element in human experiences since it holds important details about a person or entity. Humans have the potential to recognize others depending on their faces. This paper proposed work to develop a working prototype of a system that will facilitate class control for Technical Informatics College of Akre lecturers in a classroom by detecting the frontal faces of students from an image taken in a classroom. Face recognition and identification technologies have been established in recent years as a result of testing. Many of them are used on social networking sites, financial applications, and government offices such as the Metropolitan Police Service, Facebook, and others. ... Read More

Data Mining is the process of finding knowledge through the processing of massive amounts of data from different viewpoints and combining them into valuable information; data mining has been a crucial part in various aspects of human life. It is used to recognize the covered up patterns in a huge amount of data. Classification methods are supervised learning methods that categorize the data item into known categories. Creating classification models from an input dataset is one of the most beneficial techniques in data mining; these methods typically create models that are used to forecast future patterns in data. This work has been done to assess the effectiveness of different classifiers algorithms such as Support Vector Machine (SVM), Naïve Bayes (NB), J48, and Neural Network (NN), these algorithms were applied on several datasets to determine the performance of the algorithm. All techniques were used with 10-fold cross-validation in the machine learning platform WEKA. According to the study’s findings, no algorithm has consistently performed best for each dataset. ... Read More

Digital watermarking is getting more research and industry attention. Digital multimedia data allows for robust and simple data editing and modification. However, the spread of digital media presents concerns for digital content owners. It is important to note that digital data can be copied without quality or content loss. This has a considerable impact on copyright holders' ability to safeguard their intellectual property rights. The method of transmitting information by imperceptibly embedding it into digital media is digital watermarking. There are various methods in literature, such as DWT and DCT, which take full energy, are seen and integrated. New strategies and procedures for optimization are required. The present study proposes a novel design and computation technique based on the discrete wavelet and discrete cosine transforms. Watermarking techniques have been progressing to shield media content such as text, audio, video, etc. From copyright. The proposed hybrid DWT-DCT Bacterial Foraging Optimization (BFO) technique improves the efficiency of watermarking digital images by 97%. Bacterial foraging optimization (BFO) is an innovative technique for intelligent optimization. It is a widely used optimization algorithm in a wide variety of applications. However, when compared to other optimizers, the BFO performs poorly in terms of convergence. This technique uses a high-frequency image region. A variety of techniques are compared with the (NCC) Normalized Cross Correlations, (PSNR) Peak Noise Signal Ratio and IF (Image Fidelity). The highest performance is seen in DWT-DCT-BFO watermarking. ... Read More

Examination timetabling is a discrete, multi-objective and combinatorial optimization problem which tends to be solved with a cooperation of stochastic search approaches such as particle swarm optimization (PSO) and the Genetic Algorithm (GA). PSO is a well-known one of the popular swarm intelligent algorithm. used successfully for several complicated combinatorial optimization problems. Throughout the years, educational institutions have been confronted by the problems related to changing the time to their schedule. In order to compete for the growing number of students, educators must offer three or four final examinations every year. Furthermore, to approach this problem, in this study going to use the enhanced hybrid method for resolving the issue. The proposed study, a GA and PSO algorithms were utilized together to find a solution to the exam scheduling issue. The results of the study show that our approach exceeds the GA and PSO approaches by achieving 90% best of mean. The effectiveness of the approach can be hurt by any change to its parameters. ... Read More

Blood is one of the most vital and essential elements in human existence. When the population increases, so does the request for blood. People who need blood in an emergency are unable to provide it promptly. This paper suggests an effective method of contacting donors, that can be useful in an emergency. When a person requires blood, they request it through a website or mobile device; the request is then routed to the person who meets the matching blood type. The application is then sent an SMS to the donor to approve it, after accepting the request, the application will inform the requestor about it and he/she will get the donor's phone number by using an MCU ESP8266 and a SIM800L. The privacy of the person must be protected in the current environment. The donor will be deleted from the reception of notification for the next three months after the blood donation is done. User name, password, and phone number are used to check registered accounts. ... Read More

There have been quite a few studies on facial expression recognition over the years, and it is still a challenging subject due to the significant inter-class variability. Facial expression research in this field focuses on the development of techniques to identify, code, and extract facial expressions to improve prediction by computer. With great success of machine learning, the various texture descriptors are exploited to obtain a better performance. This paper proposes a method based on the aggregation between different descriptors Histogram of oriented Gradient (HOG) and Local Binary Pattern (LBP). First stage the input image has pre-processed to detect dace area which helps to extract most significant features. Then, Diagonal-HOG (D-HOG) also has extracted and aggregated all features. Finally, Support Vector Machine (SVM) has been used a classifier to classify each feature as well as aggregated features. We evaluate our method using Japanese Female Facial Expressions database (JAFFE), experimental results showed that the proposed method is accurate and efficient in recognizing facial expressions. ... Read More

Brain tumor diagnosis and classification is a major challenge for medical field. The majority of the time, Computer-Aided Diagnostic Systems (CADS) and methods involving Deep learning (DL) are utilized to find brain tumors quickly and precisely. Artificial diagnostic systems, on the other hand, are not very accurate, the physician is not using them very well when diagnosing Magnetic Resonance Images (MRI). By applying image processing principles, it is possible to conceptualize the different human tissue structures. It is difficult to detect diseased structures in the human brain using only the most fundamental imaging methods. In this research, we present a model-based Convolutional Neural Network (CNN) structure for identifying and classifying brain tumors. The proposed method consists of two parts: pre-processing and classification. In this study, CNN architecture outperformed in state-of-the-art methods, with 99.87% accuracy. F1-score 99.88%, 99.76% precision. ... Read More