Papers by Mohammad Aljanabi
Advances in medical education, research, and ethics (AMERE) book series, Apr 12, 2024
Bio web of conferences/BIO web of conferences, 2024
Deleted Journal, Feb 25, 2024
Arabic, known for its rich morphological and syntactic complexity, poses significant challenges f... more Arabic, known for its rich morphological and syntactic complexity, poses significant challenges for natural language processing technologies. This study presents a comparative evaluation of two artificial intelligence tools, ChatGPT and Cloude, in their abilities to parse Arabic sentences accurately. Five sentences embodying diverse linguistic features were selected, and the parsing outputs were evaluated by three Arabic language experts. The results revealed a clear performance gap, with Cloude outperforming ChatGPT in overall accuracy (72.9% vs. 33.3%). Cloude excelled in handling morphological complexities and basic syntactic relationships but encountered difficulties with highly idiomatic expressions and ambiguous constructions. Conversely, ChatGPT struggled with complex morphology and long-distance dependencies. The findings highlight the importance of developing specialized Arabic language processing tools while acknowledging the potential of general-purpose language models with further fine-tuning. Recommendations include incorporating domain-specific knowledge, leveraging transfer learning, and exploring ensemble approaches to enhance the accuracy and robustness of AI-based Arabic parsing systems.
Deleted Journal, Mar 2, 2024
International journal of cognitive computing in engineering, 2024
Iraqi journal for computer science and mathematics, Feb 6, 2024
Today, cardiovascular diseases occupy first place among the most dangerous diseases in this unive... more Today, cardiovascular diseases occupy first place among the most dangerous diseases in this universe as well as the death rate is rising at an alarming rate . The prevalence of heart disease is caused by harmful behaviors sustained over extended periods such as lack of sports activity, malnutrition, and the use of toxic substances such as drugs and tobacco (smoking) . Despite widespread awareness efforts, the habits mentioned earlier are widespread in our society and result in a high mortality rate. Older adults are more susceptible to cardiovascular disease because age plays a major role in weakening the role of the cardiovascular system [7][8]. Therefore, these diseases are getting more severe with the advancing individuals' age. In 2019 , the American Heart Association conducted a study on heart disease and stroke and found that the incidence of these conditions was highest in older age groups. People between the ages of 40 to 60 had an average incidence of 35-40%. For those between 60 to 80, the average incidence was 75-78%. And for those over 80 years old, the incidence was alarmingly high, at over 80%. The literature have shown that there is a marked disparity between the sexes in terms of the occurrence of heart disease . This is due to the impact of sex hormones and the higher occurrence of metabolic syndrome in women. The website "Our World in Data" has published statistics from the years 1990 2019 indicating that cardiovascular diseases are the most prevalent type of illness (as shown in Figure ) . The most typical heart diseases are aneurysms, heart ischemia, arrhythmias, and heart failure. Changes in the regular pattern or sequence of electrical impulses generated by the heart indicate abnormal behavior or a defect in the heart, where an irregular heartbeat occurs, and the patient may feel that the heartbeat is accelerating or slowing down [15][16]. This disease can be classified into two types; the first type poses a threat to the patient's life and requires medical intervention from healthcare workers. The second type does not pose a danger but rather requires conducting a set of diagnostics to find out the leading cause of the disease, following the physician's recommendations, and adhering to treatment and psychological comfort. An electrocardiogram (ECG) is a widely utilized test to detect heart problems ABSTRACT: Heart disease is the leading cause of death in developed countries, as it causes many deaths annually. Despite the availability of effective treatments, heart disease remains a significant challenge to public health, so early detection is essential in enhancing patient outcomes and reducing mortality. Artificial intelligence seeks to help physicians make the right decisions about a patient's health condition. In this regard, the authors decided to utilize machine learning techniques (k-nearest neighbor, decision tree, linear regression, support vector machine, naïve bayes, multilayer perceptron, random forest) to contribute to the classification of the heart disease dataset, where it is determined whether a person is suffering or not. After that, the execution of all techniques will be measured, and the accuracy of each technique will be compared to determine the most suitable performer. The public dataset is organized from the UC Irvine machine learning repository and have significantly different characteristics. The dataset will be divided such that 80% of the data is designated for training and 20% is designated for testing. This article concluded that the adequate performance is for the multilayer perceptron technique, as it gained an accuracy of more than 88%, while the poor performance is for the decision tree technique, as it gained an accuracy of more than 79%.
Deleted Journal, Feb 26, 2023
This bibliometric analysis explores research trends and patterns in the intersection of decision-... more This bibliometric analysis explores research trends and patterns in the intersection of decision-making and cybersecurity. Using Scopus data, we conducted a systematic search and identified 4,637 relevant documents published between 2018-2024. Quantitative analysis reveals rising annual publications with a peak in 2023, the predominance of journal articles, and robust international collaboration networks. China and the USA lead global scientific production. Key topics include risk assessment, network security, decision support systems, and emerging technologies like machine learning and artificial intelligence. Core journals with high citation impact such as IEEE Access and Expert Systems with Applications highlight significant sources of literature. The study provides a holistic overview of the landscape, evolution, contributors, and themes within decision-making and cybersecurity research.
Babylonian Journal of Internet of Things, May 16, 2023
Internet of Medical Things (IoMT) environments introduce vast security exposures including vulner... more Internet of Medical Things (IoMT) environments introduce vast security exposures including vulnerabilities to data poisoning threats that undermine integrity of automated patient health analytics like diagnosis models. This research explores applying trustworthy artificial intelligence (AI) methodologies including explainability, bias mitigation, and adversarial sample detection to substantially enhance resilience of medical intrusion detection systems. We architect an integrated anomaly detector featuring purpose-built modules for model interpretability, bias quantification, and advanced malicious input recognition alongside conventional classifier pipelines. Additional infrastructure provides fulllifecycle accountability via independent auditing. Our experimental intrusion detection system design embodying multiple trustworthy AI principles is rigorously evaluated against staged electronic record poisoning attacks emulating realistic threats to healthcare IoMT ecosystems spanning wearables, edge devices, and hospital information systems. Results demonstrate significantly strengthened threat response capabilities versus baseline detectors lacking safeguards. Explainability mechanisms build justified trust in model behaviors by surfacing rationale for each prediction to human operators. Continuous bias tracking enables preemptively identifying and mitigating unfair performance gaps before they widen into operational exposures over time. SafeML classifiers reliably detect even camouflaged data manipulation attempts with 97% accuracy. Together the integrated modules restore classification performance to baseline levels even when overwhelmed with 30% contaminated data across all samples. Findings strongly motivate prioritizing adoption of ethical ML practices to fulfill duty of care around patient safety and data integrity as algorithmic capabilities advance.
Mesopotamian Journal of Big Data, Dec 6, 2023
This systematic literature review scrutinizes the landscape of research at the intersection of fe... more This systematic literature review scrutinizes the landscape of research at the intersection of federated learning, big data processing, and data poisoning attacks. Employing a meticulous search strategy across multiple databases, the study unveils a surge in annual scientific production, emphasizing a growing interest in federated learning and related fields. However, a critical research gap becomes evident during the investigation of data poisoning attacks specifically in the context of federated learning when processing big data. The most relevant keywords and a visually compelling word cloud further illuminate the prevailing themes and emphases within the literature, emphasizing the lack of explicit focus on detecting data poisoning attacks. This identified gap presents a significant avenue for future research, offering opportunities to enhance the security and robustness of federated learning systems against adversarial threats in large-scale data scenarios.
Iraqi Journal for Computer Science and Mathematics, Aug 2, 2023
The Metaverse is a continuous online community that combines digital simulation with the real wor... more The Metaverse is a continuous online community that combines digital simulation with the real world. It is founded on the combination of Virtual Reality (VR) and Augmented Reality (AR), two technologies that permit multimodal interactions with digital worlds, objects, and people. Therefore, the Metaverse is a system of interdependent, durable multiuser platforms that house social, networked, immersive environments. It makes it possible for users to communicate and engage with digital artifacts in a fluid, bodily manner in real time. In its original form, it was a network of interconnected virtual worlds where users' avatars could freely move around. Social, immersive VR platforms that work with Massively Multiplayer Online games (MMOs), open game worlds, and augmented reality (AR) collaborative spaces are a hallmark of the modern incarnation of the Metaverse [2]. The Metaverse refers to a collection of virtual reality platforms that are designed to be social and immersive. These platforms are compatible with various forms of online gaming, including massively multiplayer online games, as well as open game environments and augmented reality collaborative spaces [3]. The concept of the Metaverse is a futuristic idea at the crossroads of technology, virtual reality, and human interaction. It imagines a persistent, multiuser environment where physical reality and computer virtuality blend. Science fiction authors imagined immersive virtual worlds and interconnected digital domains in the Metaverse. Technology and calculation have made this once-fantastic idea possible [4].VR and AR technologies made designing immersive and interactive digital places possible. These innovations made digital surroundings more immersive and realistic. Online gaming and social media shaped the Metaverse. More permanent, connected, and sharing virtual locales were needed as online communities. Grew. Blockchain technology and NFTs fueled the idea of a metaverse where users could trade digital commodities and assets. Techies, entrepreneurs, and scholars are intrigued by the Metaverse. This has sparked discussions about how it might impact communication, entertainment, the economy, and society. Even though the Metaverse is still young, people are becoming increasingly interested and investing more money in discovering its capabilities and meaning. As technology improves, creating a full-fledged Metaverse is a daunting aim, but it promises a digital area that will transform everything [5].
Potato research, Jun 24, 2024
Arabic, known for its rich morphological and syntactic complexity, poses significant challenges f... more Arabic, known for its rich morphological and syntactic complexity, poses significant challenges for natural language processing technologies. This study presents a comparative evaluation of two artificial intelligence tools, ChatGPT and Cloude, in their abilities to parse Arabic sentences accurately. Five sentences embodying diverse linguistic features were selected, and the parsing outputs were evaluated by three Arabic language experts. The results revealed a clear performance gap, with Cloude outperforming ChatGPT in overall accuracy (72.9% vs. 33.3%). Cloude excelled in handling morphological complexities and basic syntactic relationships but encountered difficulties with highly idiomatic expressions and ambiguous constructions. Conversely, ChatGPT struggled with complex morphology and long-distance dependencies. The findings highlight the importance of developing specialized Arabic language processing tools while acknowledging the potential of general-purpose language models with further fine-tuning. Recommendations include incorporating domain-specific knowledge, leveraging transfer learning, and exploring ensemble approaches to enhance the accuracy and robustness of AI-based Arabic parsing systems.
International Journal Papier Advance and Scientific Review
Federated learning (FL) offers collaborative machine learning across decentralized devices while ... more Federated learning (FL) offers collaborative machine learning across decentralized devices while safeguarding data privacy. However, data security and privacy remain key concerns. This paper introduces "Secure Federated Learning with a Homomorphic Encryption Model," addressing these challenges by integrating homomorphic encryption into FL. The model starts by initializing a global machine learning model and generating a homomorphic encryption key pair, with the public key shared among FL participants. Using this public key, participants then collect, preprocess, and encrypt their local data. During FL Training Rounds, participants decrypt the global model, compute local updates on encrypted data, encrypt these updates, and securely send them to the aggregator. The aggregator homomorphic ally combines updates without revealing participant data, forwarding the encrypted aggregated update to the global model owner. The Global Model Update ensures the owner decrypts the aggreg...
Iraqi journal for computer science and mathematics, May 26, 2023
ChatGPT, the cutting-edge language model developed by OpenAI, is one of the most exciting advance... more ChatGPT, the cutting-edge language model developed by OpenAI, is one of the most exciting advancements in the field of artificial intelligence. With its ability to generate human-like text and respond to complex questions, ChatGPT has already made a significant impact and is poised to continue its rapid progression in the coming years. As we look to the future of ChatGPT and large language models, there are many exciting possibilities and open opportunities for this technology to enhance our lives and change the way we interact with technology
Indonesian Journal of Electrical Engineering and Computer Science, Nov 1, 2021
In this paper the reliability of reduction oxygen supply system (ROSS) of a spacecraft which was ... more In this paper the reliability of reduction oxygen supply system (ROSS) of a spacecraft which was calculated as a complex system using minimal cut method. The reliability of each component of system was calculated as well as the reliability importance of the system. The cost of each component of the system was possible approaches of the allocation values of reliability based the minimization of the overall cost in this system. The advantage of this algorithm can be used to allocate the optimization of reliability for simple or complex system. This optimization is achieved using the Jaya algorithm. The proposed technique is based on the notion that a conclusion reached on a particular problem should pass near the best results and avoid the worst outcomes. The original findings of this paper are: i) the system used in this paper is a spacecraft's reduced oxygen supply system with the logarithmic cost function; and ii) the results obtained were by using the Jaya algorithm to solve specific system reliability optimization problems.
Uploads
Papers by Mohammad Aljanabi