samer saeed issa
@ruc.edu.iq
computer science department
Al-Rafidain University College
RESEARCH INTERESTS
network and Data Security
Scopus Publications
Scholar Citations
Scholar h-index
Scopus Publications
Mohanad Sameer Jabbar and Samer Saeed Issa
Institute of Advanced Engineering and Science
<span lang="EN-US">Nowadays, secure transmission massive volumes of medical data (such as COVID-19 data) are crucial but yet difficult in communication between hospitals. The confidentiality and integrity are two concerning challenges must be addressing to healthcare data. Also, the data availability challenge that related to network fail which may reason concerns to the arrival the COVID-19 data. The second challenge solved with the different tools such as virtual privet network (VPN) or blockchain technology. Towards overcoming the aforementioned for first challenges, a new scheme based on crypto steganography is proposed to secure updating (COVID-19) data. Three main contributions have been consisted within this study. The first contribution is responsible to encrypt the COVID-19 data prior to the embedding process, called hybrid cryptography (HC). The second contribution is related with the security in random blocks and pixels selection in hosting image. Three iterations of the Hénon Map function used with this contribution. The last contribution called inversing method which used with embedding process. <span>Three important measurements were used the peak signal-to-noise ratio (PSNR), the Histogram analysis and structural similarity index measure (SSIM). Based on the findings, the present scheme gives evidence to increase capacity, imperceptibility, and security to ovoid the existing methods problem.</span></span>
Mohanad Sameer Jabbar, Samer Saeed Issa, and Adnan Hussein Ali
Institute of Advanced Engineering and Science
<span lang="EN-US">Wireless sensor networks (WSNs) has a major designing feature representing by energy. Specifically, the sensor nodes have limited battery energy and are deployed remote from base station (BS); therefore, the actual enhancement dealing with energy turns into the Clustering routing protocols fundamentals which concerned in network lifetime improvement. Though, unexpected and energy insensible of the clusters head (CH) selection is not the best of WSN for greatly lowering lifetime network. A presentation article of an WSNs incoming routing approach using a mix of the fuzzy approach besides hybrid energy-efficient distributing (HEED) algorithm for increasing the lifetime and node’s energy. The FLH-P proposal algorithm is split into two parts. The stable election protocol HEED approach is used to arrange WSNs into clusters. Then, using a combination of fuzzy inference and the low energy adaptive clustering hierarchy (LEACH) algorithm, metrics like residual energy, minimal hops, with node traffic counts are taken into account. A comparison of FLH-P proposal algorithm with LEACH algorithm, fuzzy approach, and HEED utilizing identical guiding standards was used for demonstrating the performance of the suggested technique from where corresponding consumed energy as well as lifetime maximization. The suggested routing strategy considerably increases the network lifetime and transmitted packet throughput, according to simulation findings.</span>
Mohanad Sameer Jabbar and Samer Saeed Issa
Institute of Advanced Engineering and Science
One of the most pressing issues in wireless sensor networks (WSNs) is energy efficiency. Sensor nodes (SNs) are used by WSNs to gather and send data. The techniques of cluster-based hierarchical routing significantly considered for lowering WSN’s energy consumption. Because SNs are battery-powered, face significant energy constraints, and face problems in an energy-efficient protocol designing. Clustering algorithms drastically reduce each SNs energy consumption. A low-energy adaptive clustering hierarchy (LEACH) considered promising for application-specifically protocol architecture for WSNs. To extend the network's lifetime, the SNs must save energy as much as feasible. The proposed developed cluster-based load-balanced protocol (DCLP) considers for the number of ideal cluster heads (CHs) and prevents nodes nearer base stations (BSs) from joining the cluster realization for accomplishing sufficient performances regarding the reduction of sensor consumed energy. The analysis and comparison in MATLAB to LEACH, a well-known cluster-based protocol, and its modified variant distributed energy efficient clustering (DEEC). The simulation results demonstrate that network performance, energy usage, and network longevity have all improved significantly. It also demonstrates that employing cluster-based routing protocols may successfully reduce sensor network energy consumption while increasing the quantity of network data transfer, hence achieving the goal of extending network lifetime.
Samer Saeed Issa, Ahmed Alkhayyat, Ali S. Abosinnee, Sahar R. Abdul Kadeem, Zain Jaffer, and Abbas Hameed Abdul Hussein
IEEE
Due to the new developments in the Internet of Things (IoT) and their application in various fields, like the industrial domain, by linking millions of instruments and devices, IoT has progressed as a new pattern called the Industrial Internet of Things (IIoT). However, there was potential for several cyberattacks due to its diverse nature and wide connectivity. Many cyberattacks point to smart factories to execute malware. Therefore, a solution which proficiently recognizes the malware is needed to monitor and examine the network traffic in the IIoT environment. However, achieving accurate real-time malware detection in such environments is difficult. To combat the threats in the IIoT environment, this article focuses on improving the detection of threats using the parameter-tuned extreme gradient boosting (IDT-PTEGB) Model in the IIoT environment. The presented IDT-PTEGB model initially performs min-max normalization and Local Outlier Factor (LOF) based outlier removal process. Besides, an extreme gradient boosting (XGBoost) classifier is utilized to identify threats in the IIoT environment. To boost the efficacy of the XGBoost model, the political optimizer (PO) algorithm is exploited in this study. An extensive experimental analysis is conducted to ensure better outcomes for the IDT-PTEGB method. The comparison study pointed out the better outcomes of the IDT-PTEGB model over the other state of art approaches with increased accuracy of 99.05%.
Hanaa Ali Abed, Abbas Hameed Abdul Hussein, Samer Saeed Issa, Sahar R. Abdul Kadeem, Safa Majed, and Hassan M. Al-Jawahry
IEEE
Computational intelligence (CI) is a group of nature-simulated computational models and processes for addressing difficult real-life problems. The CI is useful in the UAV domain as it produces efficient, precise, and rapid solutions. Besides, unmanned aerial vehicles (UA V) developed a hot research topic in the smart city environment. Despite the benefits of UAVs, security remains a major challenging issue. In addition, deep learning (DL) enabled image classification is useful for several applications such as land cover classification, smart buildings, etc. In this view, this study proposes novel meta-heuristics with a deep learning-driven secure UAV image classification (MDLS-UAVIC) model in a smart city environment. The major purpose of the MDLS-UAVIC algorithm is to securely encrypt the images and classify them into distinct class labels. The proposed MDLS-UAVIC model follows a two-stage process: encryption and image classification. The encryption technique for image encryption effectively encrypts the UAV images. Next, the image classification process involves an Xception-based deep convolutional neural network for the feature extraction process. Finally, shuffled shepherd optimization (SSO) with a recurrent neural network (RNN) model is applied for UAV image classification, showing the novelty of the work. The experimental validation of the MDLS-UA VIC approach is tested utilizing a benchmark dataset, and the outcomes are examined in various measures.
Hanaa Ali Abed, Hassan M. Al-Jawahry, Samer Saeed Issa, Safa Majed, Sahar R. Abdul Kadeem, and Abbas Hameed Abdul Hussein
IEEE
In the zone of pattern recognition and machine learning, object detection and tracking are gaining interest because of its range of applications like visual surveillance. Recently, several deep learning-related techniques are provided for object classification however, there exists some set of concerns or problems that minimizes the overall classifier accuracy. Congest conditions, complex backgrounds, and similarities among various objects become some challenging problems. Large scale variation over object samples, and particularly, the task of detecting small objects turns out to be one such factor for the performance differences. This study introduces an Artificial Intelligence Enabled Scale Invariant Object Detection and Tracking (AIE-SIODC) model on Color Images. The presented AIE-SIODC model intends to recognize and track the objects exist in the color images irrespective of scaling. It follows a two stage process namely object detection and objects classification. At the initial stage, the presented AIE-SIODC technique applies path augmented RetinaNet (PA-RetinaNet) based object detection module, which improves the feature extraction process. To improvise the network potentiality of the PA-RetinaNet method, the deer hunting optimization (DHO) algorithm is utilized. Finally, extreme gradient boosting (XGBoost) classifier is exploited for classification procedures. For examining the effectual object detection outcomes of the AIE-SIODC technique, a wide ranging experimental validation process can be performed. The simulation values confirmed the enhancements of the AIE-SIODC method over other DL models.
Ali S. Abosinnee, Samer Saeed Issa, Ahmed Alkhayyat, Zamen Latef Naser, Zain Jaffer, and Ghazi Mohamad Ramadan
IEEE
Data mining is discovering interesting knowledge, namely associations, patterns, changes, significant structures, and anomalies, from enormous quantities of data stored in data warehouses, databases, or other data repositories. Association is the discovery of association correlations or relationships amongst a set of items. Associate rule mining is a method for identifying frequent patterns, correlations, associations, or causal structures in data sets found in numerous relational databases, transactional databases, and other data repositories. The algorithm performed is a fundamental process for mining association rules called a priori. In the healthcare field, association rules are useful as they offer the possibility to build important knowledge bases, conduct intelligent diagnoses, and extract invaluable information automatically and quickly. This study develops a Machine Learning based Association Rule Mining and Classification for Healthcare Data Management System (MLARMC-HDMS). The presented MLARMC-HDMS technique performs both classification and ARM processes. Initially, the MLARMC-HDMS technique employs the chimp optimization algorithm-based feature selection (COAFS) technique for attribute selection. Next, stochastic gradient descent with a multilayer perceptron (SGD-MLP) model is applied for the classification process. Moreover, the Apriori algorithm is used to determine the relationship between the attributes. To illustrate the enhanced performance of the presented MLARMC-HDMS model, a detailed experimental validation is performed on a benchmark medical dataset. The experimental values indicated the enhancements of the MLARMC-HDMS model over other methods with maximum accuracy of 99.75%.
Hanaa Ali Abed, Samer Saeed Issa, Sahar R. Abdul Kadeem, Safa Majed, Abbas Hameed Abdul Hussein, and Hassan M. Al-Jawahry
IEEE
For the recognition of automated modulation, algorithms based on frequency, amplitude, and signal phase were extensively used. But the algorithm is affected considerably by noise, and the performance is degraded significantly in low signal-to-noise ratio (SNR) conditions. Deep learning (DL) is an effective mechanism that has accomplished greater attainment in various applications. But the usage in transmission systems has not been well-studied. This study explores an algorithm for modulation classification and multi-signal detection that is substantial in different transmission techniques. In this aspect, this study develops an Automated Modulation Classification of Communication Signals using Metaheuristics with Deep Learning (AMCCS-MDL) model. The presented AMCCS-MDL technique focuses on identifying and classifying different types of modulations in communication signals. To attain this, the presented AMCCS-MDL technique follows the SqueezeNet-based transfer learning technique to extract features from the communication signals. In addition, the AMCCS-MDL technique uses an attention-based bidirectional long short-term memory (ABiLSTM) model for classification purposes. At last, improved artificial bee colony optimization (IABC) algorithm is employed for the hyperparameter optimization process. A wide-ranging experimental validation process is made to demonstrate the enhanced efficacy of the AMCCS-MDL technique.
Samer Saeed Issa, Mohanad Sameer Jabbar, Raed Khalid Ibrahim, Atheer Hani Herez, Adnan Hussein Ali, and Mohammed Mahdi Hashim
IEEE
Image encryption technique has emerged as a remarkable solution to shield the image against adversaries. Despite much advancement, a robust image encryption system is needed to achieve excellent encryption quality. Therefore, a highly-secured encryption algorithm needs impressive random key with excellent expansion method, small initial size and regeneratable capabilities, improved confusion and diffusion techniques. To achieve these goals a method for image encryption containing three major phases was developed. Firstly, an encryption and decryption key were generated and expanded with high level of randomness via Knight Tour (KT) algorithm with small initial size. Secondly, a new method of confusion was developed using switching technique and Discrete Diagonal-SCAN (DD-SCAN) approach for enhancing the level of pixel dispersion. Finally, an innovative method of diffusion was introduced to change the image pixels' value using bit wise operator and pixel circular shifting method. These involved steps such as generating a Ginger bread man image using the initial key, applying Arnold Cat Map (ACM) transform to dissolve flat regions in the ginger bread man image, and performing a bit-wise operation between the outcome from ACM transform, using results from DD-SCAN method, and utilizing the pixels circular shifting based on the generated key. The encryption key was proven to withstand against several types of attacks and tested using National Institute of Standards and Technology (NIST) randomness test. Thus, the pixel's value was altered and the cipher image was produced. The performance of the scheme was validated against forty-four images acquired from Signal and Image Processing Institute (SIPI) for standard image dataset. Shortly, the proposed image encryption scheme has been affirmed to be a superior image encryption scheme development.