@alayen.edu.iq
Al-Ayen University
Al-Ayen University
Raaid Alubady received his Ph.D. degrees in Information Technology from the Universiti Utara Malaysia, in 2017. He got a Bachelor's degree in Computer Sciences from University of Babylon-Iraq, a Higher Diploma in Data Security from Iraqi Commission for Computers and Informatics-Iraq, and a Master's degree in Information Technology from UUM- Malaysia. Alubady is a lecturer at the Network Information Department, College of Information Technology, University of Babylon- Iraq. He is a member of IEEE and actively involved in IEEE activities. In addition, he is a member of the Internet Society Malaysia Chapter; a member of the Iraqi Association for IT Specialists, Iraq; and a reviewer of several international academic journals and conferences. Currently attached to the InterNetWorks Research Laboratory (IRL).
Future Internet (ICN and NDN), Wireless Networking/MANET/VANET/FANET, Sensor Networking (WSN, WBAN and IoT), Fog and Cloud Computing, Blockchain Technology, Routing Protocols, Network Security as wellas Network Performance Analysis and Evaluation.
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Ali A. Shati, F. Al-dolaimy, Mohammad Y. Alfaifi, R.Z. Sayyed, Sofiene Mansouri, Zafar Aminov, Raaid Alubady, Kumaraswamy Gandla, Ahmed Hussien Radie Alawady, and Ali Hashiem Alsaalamy
Elsevier BV
Sanaa Jafaar Hassan Al-Shakarchi and Raaid Alubady
Institute of Advanced Engineering and Science
Mobile ad-hoc networks (MANETs) have been a crucial element of next-generation wireless networking technologies during the last decade. Because they allow users to access information and communicate with each other without infrastructure. Selfishness is one of the numerous undesirable behaviors that MANET network nodes may exhibit since this selfish node attempts to safeguard its own resources while accessing the services of other nodes and consuming their resources. Hence, a potential that the network's overall performance may degrade. This study developed a new method named detection, reintroduced, and collaborative of selfish node (DRCSN) that proposed detecting selfish nodes based on two factors: energy and the communication ratio (CR) and handling the rate of selfish nodes. Thus, selfish nodes were exploited to the maximum degree and significantly improve network performance. DRCSN was implemented inside ad-hoc on-demand distance vector (AODV) protocol. The test scenarios were implemented using the network simulator-2 (NS-2); many scenarios were created according to two important network parameters: the number of nodes and movement nodes. The proposed method improved the MANET's performance by increasing both the throughput and packet delivery ratio in the network in addition to that it reduced retransmission rate, delay, and power consumption compared to the related methods.
Raaid Alubady, Mays Salman, and Ahmed S. Mohamed
Springer Science and Business Media LLC
Hasan Harith Jameel Mahdi, Ammar H. Shnawa, Ragheed Hussam, Raaid Alubady, Mustafa Al-Tahee, and Imad Matti
IEEE
Scatterometry (SC) is a microwave radar sensor that scans the surface from an aircraft or a satellite and measures the normalizing radar crossing section of the surface; the scatterometer can measure wave height and other pertinent data, although the altimeter is more limited in its scope. Presently, the challenging characteristics in scatterometry measurement data, which include natural energy intensity, wind speed stability, improper disaster management, earth atmosphere, predicting ocean current wave height from the observed challenges in this research developing an improved machine learning (MLSC) assisted scatterometer data allows a network program to learn and adapt to new data without the need for human intervention. It keeps a device's built-in algorithms up to date regardless of changes in the global economy. In machine learning-enabled scatterometry data, supervised learning (SL) has been proposed to reduce the natural energy intensity in significant wave height scatterometry measurement and analyze the atmosphere and wind speed stability by improving remote sensing measurement data gathered by sensors. Reinforcement learning (RL) has been included, which helps to reduce the risk of controlling the improper disaster management to improve the predicting ocean current wave height with the impact of earth's atmosphere changes in the climate, the release of pollutants into the atmosphere condition, which helps to enhance the prediction of significant wave height form scatterometry measurement data. The experimental results show the proposed model improves natural energy intensity, wind speed stability, improper disaster management, earth atmosphere, and predicting current ocean waves in the reinforcement learning method.
Zainab. R. Abdulsada, Ibrahem Ahmed, Raaid Alubady, Hayder Mahmood Salman Mazin, Mustafa Al-Tahee, and Saad Abdulaziz
IEEE
The educational system has a general evaluation of the effects of physical education on universities that give students instruction without the involvement of educators. Physical education (PE) teachers face several obstacles in the classroom, including the difficulty of conveying complex concepts like proper form, correct pupil mobility, and adequate exercise assignments. Increasing the effectiveness of university education programmes and student activity is necessary. Therefore, utilizing improved machine learning, the Hidden Markov model-assisted correction system (HMMCS) has been suggested in this research to improve student behaviour in the physical education classroom. The student's CS examines how the college physical education classroom has improved. University physical education instruction is evaluated using HMM, and university physical education learning is estimated using a mathematical calculation. The experiment's outcome demonstrates that encouraging physical education teacher performance assessment in colleges is advantageous. The simulation outcomes depicts that proposed HMM-CS model improves the predictive rate of 98.8%, overall efficiency of 96.8%, probability ratio of 97.3%, score analysis rate of 98.5%, and an error occurance of 20.3% in contrast to the state-of-the-art alternatives.
Ahmed R. Hassan, Raaid Alubady, Zain Jaffer, Mustafa Al-Tahee, Angham Khalid Hussain, and Zainab Majeed
IEEE
When it comes to supply chains, it means a centralized system for managing both products and services. Controlling the supply chain can reduce costs and speed up delivery. Supply chain management seems essential as it requires storing and processing data. In supply chain management, the task continues to be carried out to develop effective data mining and processing systems that can be scaled up and work consistently. So, this research aims to develop an innovative data mining framework for supply chain management (DMF-SCM). This framework uses the Internet of Things (IoT) and machine intelligence to mine and process data for the reliable supply chain management. The proposed multi-stage data mining frameworks use a deep neural network with optimized data fusion for the supply chain management. The text data was used to divide the suppliers into groups using a new fuzzy-based deep learning method. The computational evaluation of the proposed framework shows that it outperforms the conventional methods in terms of segmentation accuracy (98.1%), efficiency (97.9%), error rate (35.1%), data loss (95.8%), and scaling up (98.3% ).
Hiba Abdulameer Hasan, Mohaned Adile, Ahmed Hussian, Sahar R. Abdul Kadeem, Raaid Alubady, and Imad Matti
IEEE
Adolescent Brain Cognitive Development (ABCD) has been studied in ways never before possible because to breakthroughs in brain imaging technology. Indirectly, the accuracy and interpretability of findings affect our understanding of neurodevelopmental processes, highlighting the crucial necessity of dependable techniques. There are a wide variety of obstacles to overcome in this field, from the intricacies of researching developing brains to the subtle interplay of different cognitive processes. Overcoming these problems demands creative approaches and enhanced procedures that can capture the changing character of cognitive growth. The goal of this framework is to improve the accuracy and sensitivity of cognitive neuroscience studies, leading to a deeper comprehension of the complex mechanisms at play during brain development. In this study, there is a method called functional magnetic resonance-based tensor imaging (FMR-TI) that combines the strengths of both methods to provide more precise mapping of cognitive growth throughout time. As a bonus, the suggested method uses simulation analyses to verify its efficiency and resilience in capturing the nuances of cognitive development, making the results of the study more trustworthy. The proposed methodology can be used to a wide range of fields, such as educational neuroscience, clinical psychology, and developmental neuroscience. Understanding cognitive growth better has far-reaching effects on educational programs, diagnostic methods, and treatment plans. Moreover, this methodological improvement holds promise for unraveling the neurological foundations of neurodevelopmental diseases, helping to the development of focused therapies and tailored treatment strategies. The robustness of the processing, the flexibility of the paradigm, and the validity of the simulation are all taken into account during the investigation.
Hayder Mahmood Salman, Waleed Hameed, Ragheed Hussam, Zahraa N. Abdulhussain, Raaid Alubady, and Zainab Majeed
IEEE
Analysts can apply this arising worldview in computer programming with cutting-edge and modern applications through the viable utilization of astute advancements in medical care. The normal planning of clinical issues in the digital world is the essential variable of progress. A wise ecological plan can demonstrate heterogeneous, progressive, and independent medical care administrations because of computerized reasoning advancements. Smart Environmental Multi Area Body Network (SEMABN) the plan is applied to mind-boggling and savvy frameworks because of a realistic plan from single wellbeing action, for example, research-driven clinical frameworks and complete clinical units. Ecological design in wellbeing administrations has opened the way for new advances, like customized and associated clinical frameworks. This adaptable utilization of Query Based Modelling (QBM) ecological plan has presented new issues for science, including security, correspondence, and social issues. In light of this examination, artificial reasoning-based climate configuration has been utilized in medical services to building exactness and execution.
Munqith Saleem, Raaid Alubady, Maryam Ghassan Majeed, Sarah Kadhim Mohsin, Adnan Allwi Ftaiet, and Marwa Ibrahem
IEEE
The digital twin (DT) is a real-world object that can only be used virtually. The digital twin connects the actual and virtual worlds so that data can be collected and analyzed in real time, and vice versa. The data analytics used to process the characteristics of the actual product or manufacturing method have been included into the virtual product in real time. Real-time processing data analytics based on actual product or manufacturing processing characteristics are included in this virtual product. Since DT offers a tool for realizing IoT-enabled, digitally-driven production, it has gained popularity as information technology has progressed. It is possible to anticipate the need for asset repair using digital twins' data. In this study, a Digital Twin in Braiding Machinery based on IoT (DTBM-IoT) has been proposed to increase overall business efficiency while saving money by minimizing operational costs and asset interruptions. The system is used to collect experimental data when an imbalance fault happens. The input is then sent into a digital twin model of the rotor system to test its ability to quantify and pinpoint imbalances for identifying defects. IoT sensors, Extended Reality (XR) capabilities, and Artificial Intelligence-powered analytics enable DT technology to predict the need for asset maintenance. The nonlinear dynamics and unpredictable nature of the equipment degradation process make it challenging to construct DT models that are flexible and appropriate. The results show that the developed DT in braiding equipment enables precise diagnostic and dynamic degradation analysis with 37% improvement in efficiency over traditional methods.
Marwa Saad Mahdi Hussin, Aymen Mohammed, Raaid Alubady, Mazin Riyadh Al-Hameed, Mustafa Al-Tahee, and Ahmed Ali
IEEE
Integrated marketing communication (IMC) is a platform for marketers to launch their product or service that meets those requirements and fosters long-lasting, mutually beneficial associations. IMC helps marketers understand company regulations and customer requirements. Determining customer preferences, attitudes, and behaviour patterns due to new technology, including the goods and services they use and the communication strategies they adopt, is an important area in studying IMC. an Assessment of Integrated Marketing Communication using machine learning (AIMC-ML) has been proposed in this research; therefore, important firm stakeholders should comprehend customers' behaviour and purchasing preferences. Feature extraction methods from data mining techniques can be employed to predict customers' shopping habits. This study proposes narrowband Internet of Things (NB-IoT) technology using big data to investigate marketing communication data analytics. Due to the simulation results with improved accuracy, reliability, and performance of 94.9%, research shows that our handheld interface offers useful solutions for network optimization, increasing market share, and increasing penetration rate.
Rabei Raad Ali, Laith Fouad, Raaid Alubady, Wasan Saad Ahmed, Ibrahem Ahmed, and Israa Abed Jawad
IEEE
Human-computer interaction (HCI) is crucial to improving public transportation in low-resource settings. The degree that people give up control to computers is a topic of discussion in various settings, including implementing smart transportation systems in rural areas. Disaster occurs because people don't believe in the system or try to change its decisions. Therefore, this study proposes a Service-Oriented Human-Computer Interaction (SO-HCI) model for efficient rural public transit. An inter-agent strategy for monitoring the rural transportation channel and the user information service is described in the service-oriented model. Human-computer interaction (HCI) is designed to maximize a predetermined level of mechanized efficiency; this efficiency level can be achieved in various automation settings, and HCI's way of thinking can shift over time. In the SO-HCI model, the uncertainty of misleading user expectations and a routine and formally defined transportation system result from implementing the Markov framework paradigm. Based on empirical evidence, the proposed SO-HCI model for rural smart transportation systems significantly outperforms the state-of-the-art in terms of rural mobility (97.6%), accessibility (95.4%), demand response (94.5%), travel behavior prediction (98.7%), and operating cost (11.2%).
Najlaa Nsrulaah Faris, Mohaned Adile, Raaid Alubady, Sura Rahim Alatba, Tamarah Alaa Diame, and Sadiq Nabeel Sadiq
IEEE
The use of real-time technology is crucial in fmthe field of industrial computerization. Much speculation has been about the huge growth in sophisticated networked devices such establishments use. It's often called “Industry 4.0” or “the Industrial Internet of Things.” Many goods mean many uses, which are widely dispersed. Therefore, in real-world settings, a single device is insufficient. The impact of communication on applications' overall temporal behavior is growing. Due to this need, many Industrial Ethernet (IE) methods have been created. Successful IE countermeasures often include custom-built software or non-standard adjustments to existing protocols. It undermines interoperability and creates expensive gear incompatible with other IE or regular Ethernet alternatives. A P2P computing-based deterministic communication (P2PDC) framework is proposed in this article. P2PDC presents a P2P technique that offers a deterministic connection through standard Ethernet on a full software basis. While it does allow for real-time interactions and is based only on industry-standard protocols, it does have a few drawbacks. P2PDC's low network utilization, hash attack control, and congestion prioritization are singled out in the report as the most important limits and solutions to these problems. The experimental results show the P2PDC to achieve an accuracy ratio of 92.21 %, precision ratio of 92.65%, efficiency ratio of 89.97%, F -score ratio of 90.14%, recall ratio of 88.78% and less packet drop ratio of 33.3% compared to other methods.
Aymen Mohammed, Mohammed Jameel Alsalhy, Mustafa Al-Tahee, Raaid Alubady, Angham Khalid Hussain, and Taha Raad Al-Shaikhli
IEEE
Entrepreneurs in the business economy use the value creation in demand and the availability of sources model to obtain an edge over the competition. Recently, AI and big data analytics have matured into tactics that can both automate product creation for startups and enable for the optimization of value maintenance. Performance Management in Entrepreneurship (AI-PMEB) using a Big Data Analytical Model is a valuable tool for moving the field forward. It has been suggested that big data may be used to track the success of startups by measuring the demand they generate. This study aims to determine the nature of the need for performance management in the realm of entrepreneurship. This allows for the development of suitable performance to improve the demand strategy. The research is used to fine-tune the AI-PMEB strategy model. Extensive AI data analysis is also used as the foundation for business strategies, which then move on to identifying the data, application design, and cutting-edge technology. Our research suggests that (AI-PMEB) be used in the future to carry out the plan that has been developed. The experimental results show that the recommended method outperforms the state-of-the-art in terms of precision (93.2%), performance rate (94.3%), management efficiency (90.2%), and error rate (10.9%).
Zamen latef Naser, Ahmed Taha, Raaid Alubady, Hasan Harith Jameel Mahdi, Zain Jaffer, and Taha Raad Al-Shaikhli
IEEE
Smart cities are designed to maximize efficiency and equity in resource utilization and distribution. One of the primary goals of a smart city is to improve communication between citizens and their government at all levels. People can live peacefully and harmoniously in a city with a well-developed public transportation system. A shortage of traffic data, inefficient use of available resources, and inadequate demographic and ethnic data are all factors that complicate the design of a system for managing transportation. Real-time data that can be relied upon is essential for any transportation system. Congestion causes delays in the flow of people, goods, and government services. Sharing information about traffic congestion is sufficient for efficient operation. Intelligent transportation systems improve the quality of life in a city by easing traffic, reducing pollution, and improving accessibility. A cognitive sensor network framework (CSNF) is offered to manage transportation in smart cities better. The CSNF plans a transportation system to aid in the smart city's design, which constantly analyzes traffic flow and attends to potential problems in advance. The results of the CSNF's experiments show that it can cut traffic volumes by 92.23 percent while simultaneously achieving an efficiency of 96.67 percent, a performance that is unreachable using conventional methods.
Haider Sharif, Mohammed Jameel Alsalhy, Raaid Alubady, Sarah Kadhim Mohsin, Ragheed Hussam, and Jamal K. Abbas
IEEE
These days, it's crucial in financial services to analyze investor actions to ascertain consumers' choices, projections, studies, and revisions. The study of the investing process known as “behavioral finance” has shown that investors do not always act logically, as they frequently become excessively driven by their desires and can't regulate their emotions, leading to poor decisions regarding investments under pressure. This research offers Bayesian Learning-Based Investor Behavior Analysis (BLIBA) to increase profits in a new market and maintain consistency in Equity outcomes. Income shocks from changes in the stock price are the driving force behind the suggested BLIBA weights caused by conservative and reflective investors in this minimalist model of investing emotions. Using these weightings, one can establish a mathematical relationship between market anomalies and the investing preferences of individuals. The result demonstrates the importance of an investment decision on investor behaviour, Psychology Behaviour, underreaction, assurance, and the ultimate choice of the investment itself
Raaid Alubady, Sahar R. Abdul Kadeem, Ahmed Taha, Sarah Ali, Abdulkareem Haider Al-Chilibi, and Sadiq Nabeel Sadiq
IEEE
Diabetic retinopathy (DR) is a retinal condition caused by diabetes that leads to blindness due to an eye infection. The DR is caused by diabetes mellitus, which affects over 80% of the world's population. Hemorrhage happens when DR is misdiagnosed at an early stage when retinal bleeding has already begun. Early detection of retinal bleeding and infection is crucial for avoiding a potentially blinding scenario. As a result, the clinical analysis of DR uses sophisticated computing approaches to boost the total detection rate. Current study methods need additional time investment to make a correct bleeding diagnosis in retinal analysis. So, in this work, introduce the deep reinforcement hemorrhage candidate filtering (DR-HCF) approach is applied to improve the hemorrhage detection accuracy. Hemorrhage candidate characteristics are derived from retinal pictures using a color and shape analysis and extraction technique. Diabetic retinopathy therapy is administered based on the derived characteristics, reducing the risk of permanent visual loss. Several datasets are used to measure the DR-HCF system's computation time of 24.5%, sensitivity ratio of 98.3%, specificity ratio of 97.6%, and accuracy efficacy ratio of 99.45%.
Rabei Raad Ali, Mohaned Adile, Raaid Alubady, Mustafa Nazar Dawood, Zain Jaffer, and Israa Abed Jawad
IEEE
The presence of music in our daily lives is ubiquitous. Digital musical works are created utilizing Distributed Ledger Technology and Deep learning, with their creation serving as a case study for the exploration of computerized computation, analysis of copyright, and online music administration. The problems of copyright validity and code safety are not yet fully handled in digital music. This study proposes the Digital Music Copyright and Protection (DMCP) model to analyze digital music's legal protection and management. Two-stage deep learning and distributed ledger technology are used to implement DMCP in digital music production. With the automated structure and deployment of neural network-based approaches geared toward deep learning, the Deep Neural Network (DNN) is launched. Blockchain technology improvement examines the problems with traditional copyright rights and digital music administration. Digital music copyright and protection now incorporate blockchain, which fully accounts for ownership, usage rights, and security. The DMCP concept provides the highest level of security available by combining automated computers, digital music, and distributed ledger technology. The experimental outcomes of the proposed methodology have improved prediction accuracy, music quality, music sustain ability, and copyright protection.
Samah Ali and Raaid Alubady
IEEE
The healthcare environment is one of the applications that require real-time monitoring to immediately process. Fog computing works in a real-time environment and offers connected devices for processing healthcare data with low latency compared with the cloud computing model. Load balancing is an important term in fog computing that avoids the situations of overload and underload in fog nodes. Many of the Quality of Service (QoS) metrics such as cost, response time, throughput, resource utilization, and performance can be improved by load balancing. In this paper, we proposed a load balancing mechanism called the Remind Weighted Round Robin (RWRR) algorithm to enhance the QoS metrics and load the tasks to the appropriate fog node based on the capabilities of this node that will be assigned by the proposed algorithm. The algorithm is applied in order to enhance the healthcare system in the fog computing environment. Results of the proposed algorithm demonstrate it enhances the overall performance system with 20.05%, an average response time of 120.25ms when compared with related work.
Arif Sari, Candra Zonyfar, Shavan Askar, Sherzod Abdullaev, Raaid Alubady, and M. K. Sharma
Informa UK Limited
Raaid Alubady, , , , , , , , Rawan A A.shlaka, Hussein Alaa Diame,et al.
ASPG Publishing LLC
Electronic health records are essential and sensitive since they include vital information and are routinely exchanged across several parties, such as hospitals and private clinics. This data must remain accurate, current, secret, and available only to authorized parties. Integrating these data improves the accuracy and cost-effectiveness of the present health data administration framework. Electronic Medical Records (EMRs) are now kept utilizing the structure of the clientserver via whom patient data information is maintained in the hospital. Multiple hospitals use the same database to track a single patient. These limitations prevent a custom health system from providing various associated experts and patients with a cohesive, integrated, secure, and confidential medical history. Modern healthcare systems are distinguished by their complexity and expense. However, this may be mitigated by enhanced health record management and blockchain technology. The blockchain's data availability, confidence, and security characteristics have a bright future in healthcare services, giving solutions to the issues of the traditional customerserver architecture EMR management platform: intricacy, confidence, dependability, compatibility, and anonymity. An e-health record management based on IoMT (EHRM-IoMT) is proposed in this article. This paper explores and analyzes blockchain efficiency and customerserver paradigms. The findings show that a patient-centered strategy may achieve remarkable success utilizing blockchain. Moreover, the immutable and accurate data of persons in blockchain may enable healthcare practitioners to better forecast and aid with diagnosis utilizing the Internet of Medical Things via machine learning and artificial intelligence (IoMT).
Tamarah Alaa Diame, , , , , , , , M. Abdul Jaleel. M., Sajad Ali Ettyem,et al.
ASPG Publishing LLC
Currently, Machine Learning (ML) seems very attractive since it may speed up business functions in enterprises, lower costs for supplying goods and services, and manage information to promote enterprise efficiency. Essential technological domains nowadays are the explosive period of growth in enterprise solutions, which are progressively used in almost all business platforms. The ML sessions will receive a thorough summary, and the relevant organizations will be shown procedures for relevant business processes. The data management unit is already been striving to solve related issues in ML applications for more than a generation, creating numerous customized analytical techniques. The approach described in the study uses a weighted directed graph displayed in an industrial environment to identify the core part of the neural network structure and then trains them using the relevant data source. The article proposed ML-assisted Enterprise Data Management (ML-EDM) for identifying the trade-off between ML growth in the financial sector and its consequences in precision and interpretability. According to the experimental findings, the ratio of AI for decision-making is 84.25%, the Speed and Agility proportion is 92.70%, the result of Earlier Prediction Management is 93.80%, the Infrastructure Development is 85.46%, with Data Efficiency is 84.5% and Performance efficiency of the system is 90.14%.
Ahmed Al-Ajeli, Eman S. Al-Shamery, and Raaid Alubady
Korean Institute of Intelligent Systems