Mohammed J. Alghamdi

Umm al-Qura University

*This is an algorithmically generated author record based on publicly available information.

See Latest Publications

See Most Cited Publications

SciProfiles

ORCID Profile

Google Scholar

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Umm al-Qura University

Research Subjects

Research Interests

Mohammed J. Alghamdi has a total of 28 co-authors. Here are the top co-authors by number of shared publications:

Hedi Sakli
LR-Sys’Com, LR-99-ES21, National Engineering School of Tunis (ENIT), University of Tunis El Manar, Le Belvédère Campus, Tunis 1002, Tunisia
2 shared publications
Mohamed Ali Mahjoub
Laboratory of Advanced Technology and Intelligent Systems (LATIS), University of Sousse, Sousse 4023, Tunisia
2 shared publications
Mourad Mars
Department of Artificial Intelligence, College of Computer Engineering and Sciences, Prince Mohammad Bin Fahd University, Al-Khobar 31952, Saudi Arabia
2 shared publications
Muhammad Rashid
Computer and Network Engineering Department, Umm Al-Qura University, Makkah 24382, Saudi Arabia
2 shared publications
Ryan Alturki
Department of Software Engineering, College of Computing, Umm Al-Qura University, Makkah, Saudi Arabia
2 shared publications
Valerie Gay
University of Technology Sydney
2 shared publications

Latest Publications

Sort by

Open Access
Website
Google Scholar
- 8 November 2026
- Published by MDPI AG in Technologies
Counterfactual Neuro-Symbolic Proof-Carrying Memory for Auditable Multi-Hop Reasoning on Unstructured Data
by Wyssem Fathallah, Abdelweheb Gueddes, Mourad Mars, Mohammed J. AlGhamdi, Mohamed Ali Mahjoub, Hedi Sakli
Knowledge-intensive language understanding suffers a structural reliability bottleneck: fluent answers can be produced without logically sufficient support, especially in multi-hop question answering and dynamic knowledge graphs where edge drift degrades retrieval. We introduce Counterfactual Neuro-Symbolic Proof-Carrying Memory (CNS-PCM), a backbone-agnostic neuro-symbolic harness that decouples frozen neural representations from inspectable symbolic verification checks. Candidate reasoning chains are discovered via ontology-constrained beam search ( $Γ$ ) and compiled into a compact proof-carrying memory carrying crisp domain validity flags ( $κ_{k}$ ), NLI-derived contradiction scores ( $ρ_{k}$ ), and textual support confidences ( $α_{k}$ ). At inference time, a counterfactual verifier stress-tests prediction stability across a targeted pool of $J = 12$ graph interventions sampled via betweenness centrality, requiring $O (J \cdot K \cdot d)$ localized re-scoring operations over the $K \leq 16$ retained proofs (or $O (J \cdot d)$ at fixed memory capacity K, where empirical proof depth satisfies $d \leq 3$ for $> 94 %$ of retained paths under a search ceiling $m_{\max} = 6$ , bounding verifier latency overhead to ≈45 ms per query), and abstains when evidence is unstable. Rather than invasive early token fusion or prompt linearization, CNS-PCM externalizes verification into an inspectable audit record while training lightweight adapter heads using task, logical-consistency, intervention-invariance, and differentiable Brier calibration objectives. Evaluated on official public splits of HoVer, HotpotQA, and FEVEROUS with headline F1 scoring ABSTAIN as incorrect, CNS-PCM achieves test F1 scores of $80.6 %$ , $75.2 %$ , and $79.0 %$ , outperforming LLaMA-2-7B + CoT ( $72.4 % / 67.1 % / 70.2 %$ ), GraphRAG ( $78.5 % / 73.8 % / 77.4 %$ ), and unthresholded Logic-LM ( $79.1 % / 74.1 % / 77.9 %$ ). Specifically, CNS-PCM reduces total gold-unsupported accepted assertions on the validation splits by up to $2.4$ percentage points (lowering total unsupported rate from $16.4 %$ to $14.7 %$ , and correct-but-ungrounded assertions from $6.8 %$ to $5.3 %$ ) and reduces Expected Calibration Error (ECE) to $6.5 %$ , maintaining $95.2 %$ final test coverage via a bounded re-try feedback loop ( $\bar{R} = 0.471$ re-tries). Component ablations confirm that training invariance and inference gating provide complementary gains, while sensitivity analyses identify Stage-2 entity linking as the primary reliability lever.
Website
Google Scholar
- 8 November 2026
- Published by MDPI AG in Technologies
Open Access
Counterfactual Neuro-Symbolic Proof-Carrying Memory for Auditable Multi-Hop Reasoning on Unstructured Data
by Wyssem Fathallah, Abdelweheb Gueddes, Mourad Mars, Mohammed J. AlGhamdi, Mohamed Ali Mahjoub, Hedi Sakli
Knowledge-intensive language understanding suffers a structural reliability bottleneck: fluent answers can be produced without logically sufficient support, especially in multi-hop question answering and dynamic knowledge graphs where edge drift degrades retrieval. We introduce Counterfactual Neuro-Symbolic Proof-Carrying Memory (CNS-PCM), a backbone-agnostic neuro-symbolic harness that decouples frozen neural representations from inspectable symbolic verification checks. Candidate reasoning chains are discovered via ontology-constrained beam search ( $Γ$ ) and compiled into a compact proof-carrying memory carrying crisp domain validity flags ( $κ_{k}$ ), NLI-derived contradiction scores ( $ρ_{k}$ ), and textual support confidences ( $α_{k}$ ). At inference time, a counterfactual verifier stress-tests prediction stability across a targeted pool of $J = 12$ graph interventions sampled via betweenness centrality, requiring $O (J \cdot K \cdot d)$ localized re-scoring operations over the $K \leq 16$ retained proofs (or $O (J \cdot d)$ at fixed memory capacity K, where empirical proof depth satisfies $d \leq 3$ for $> 94 %$ of retained paths under a search ceiling $m_{\max} = 6$ , bounding verifier latency overhead to ≈45 ms per query), and abstains when evidence is unstable. Rather than invasive early token fusion or prompt linearization, CNS-PCM externalizes verification into an inspectable audit record while training lightweight adapter heads using task, logical-consistency, intervention-invariance, and differentiable Brier calibration objectives. Evaluated on official public splits of HoVer, HotpotQA, and FEVEROUS with headline F1 scoring ABSTAIN as incorrect, CNS-PCM achieves test F1 scores of $80.6 %$ , $75.2 %$ , and $79.0 %$ , outperforming LLaMA-2-7B + CoT ( $72.4 % / 67.1 % / 70.2 %$ ), GraphRAG ( $78.5 % / 73.8 % / 77.4 %$ ), and unthresholded Logic-LM ( $79.1 % / 74.1 % / 77.9 %$ ). Specifically, CNS-PCM reduces total gold-unsupported accepted assertions on the validation splits by up to $2.4$ percentage points (lowering total unsupported rate from $16.4 %$ to $14.7 %$ , and correct-but-ungrounded assertions from $6.8 %$ to $5.3 %$ ) and reduces Expected Calibration Error (ECE) to $6.5 %$ , maintaining $95.2 %$ final test coverage via a bounded re-try feedback loop ( $\bar{R} = 0.471$ re-tries). Component ablations confirm that training invariance and inference gating provide complementary gains, while sensitivity analyses identify Stage-2 entity linking as the primary reliability lever.
Open Access
Website
Google Scholar
- 6 November 2026
- Published by MDPI AG in Technologies
Neuro-Symbolic Graph Transformers with Ontology-Guided Attention for Context-Aware Social Discourse Analysis
by Wyssem Fathallah, Abdelweheb Gueddes, Mourad Mars, Mohammed J. AlGhamdi, Mohamed Ali Mahjoub, Hedi Sakli
Social media messages are short and noisy: the same tokens can denote a mention, a follow, or a reply depending on the surrounding user graph. Pre-trained language models frequently propose relations that a formal domain ontology forbids, whereas graph embeddings largely ignore message wording. This paper presents HyKGA (Hybrid Knowledge-Graph Attention), a single-pass neuro-symbolic encoder that (i) injects k-hop, time-decayed graph neighbors and multi-scale centrality encodings at tokenization under a strictly causal, target-edge-excised protocol, (ii) compiles the type axioms and the irreflexivity and cardinality constraints of a Description Logic ontology into two pre-Softmax masks, on self-attention and on the relation classifier, and (iii) aligns text and graph representations with an InfoNCE contrastive objective. On the Twitter Social Alignment Benchmark (TSAB), HyKGA reaches an F1 score of $0.91$ and a filtered link-prediction MRR of $0.574$ , 5 points above QLoRA-fine-tuned LLaMA-3-8B and a late-fusion BERT–GraphSAGE hybrid, with an Ontological Violation Rate of $2.0 %$ on relational projections ( $1.6 %$ on active positive predictions and $1.0 %$ across all thresholded predictions) against 14–35% ( $10.2$ – $15.8 %$ on positive predictions and $6.7$ – $9.9 %$ across all thresholded predictions) for neural baselines. Controlled ablations show that pre-Softmax masking adds $3.8$ F1 points over post hoc ontology filtering. Gains of 3 to 4 macro-F1 points carry over to RumourEval, PHEME and Twitter15 as task transfer. When 20% of the axioms are removed, F1 degrades gracefully to $0.88$ . End-to-end latency is $18.7$ ms per message, $7.6$ to $11.7$ times lower than retrieval-augmented pipelines on the same GPU.
Website
Google Scholar
- 6 November 2026
- Published by MDPI AG in Technologies
Open Access
Neuro-Symbolic Graph Transformers with Ontology-Guided Attention for Context-Aware Social Discourse Analysis
by Wyssem Fathallah, Abdelweheb Gueddes, Mourad Mars, Mohammed J. AlGhamdi, Mohamed Ali Mahjoub, Hedi Sakli
Social media messages are short and noisy: the same tokens can denote a mention, a follow, or a reply depending on the surrounding user graph. Pre-trained language models frequently propose relations that a formal domain ontology forbids, whereas graph embeddings largely ignore message wording. This paper presents HyKGA (Hybrid Knowledge-Graph Attention), a single-pass neuro-symbolic encoder that (i) injects k-hop, time-decayed graph neighbors and multi-scale centrality encodings at tokenization under a strictly causal, target-edge-excised protocol, (ii) compiles the type axioms and the irreflexivity and cardinality constraints of a Description Logic ontology into two pre-Softmax masks, on self-attention and on the relation classifier, and (iii) aligns text and graph representations with an InfoNCE contrastive objective. On the Twitter Social Alignment Benchmark (TSAB), HyKGA reaches an F1 score of $0.91$ and a filtered link-prediction MRR of $0.574$ , 5 points above QLoRA-fine-tuned LLaMA-3-8B and a late-fusion BERT–GraphSAGE hybrid, with an Ontological Violation Rate of $2.0 %$ on relational projections ( $1.6 %$ on active positive predictions and $1.0 %$ across all thresholded predictions) against 14–35% ( $10.2$ – $15.8 %$ on positive predictions and $6.7$ – $9.9 %$ across all thresholded predictions) for neural baselines. Controlled ablations show that pre-Softmax masking adds $3.8$ F1 points over post hoc ontology filtering. Gains of 3 to 4 macro-F1 points carry over to RumourEval, PHEME and Twitter15 as task transfer. When 20% of the axioms are removed, F1 degrades gracefully to $0.88$ . End-to-end latency is $18.7$ ms per message, $7.6$ to $11.7$ times lower than retrieval-augmented pipelines on the same GPU.
Open Access
Website
Google Scholar
Cited by 1
- 5 June 2026
- Published by Elsevier in Results in Engineering
Optimizing arithmetic resource allocation in configurable NTT hardware for area-constrained homomorphic encryption
by Omar S. Sonbul, Muhammad Rashid, Amar Y. Jaffar, Mohammed J. Alghamdi, Muhammad I. Masud, Mohammed Aman
Website
Google Scholar
- 5 June 2026
- Published by Elsevier in Results in Engineering
Open Access
Optimizing arithmetic resource allocation in configurable NTT hardware for area-constrained homomorphic encryption
by Omar S. Sonbul, Muhammad Rashid, Amar Y. Jaffar, Mohammed J. Alghamdi, Muhammad I. Masud, Mohammed Aman
Cited by 1
Open Access
Website
Google Scholar
Cited by 1
- 16 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
From Segmentation to Disease Prediction: A Systematic Review of AI Methods for Adipose Tissue Analysis in Medical Imaging
by Mohammed J. Alghamdi, Muhammad Rashid, Muhammad Arif
Accurate segmentation and classification of adipose tissue are critical tasks in the field of medical imaging, as they contribute to enhanced medical diagnostics. However, manual segmentation and classification are time-consuming and prone to variability. These limitations drive the development of automated and efficient artificial intelligence (AI) methods, including machine learning (ML) and deep learning (DL). A wide range of ML and DL techniques now exist, offering diverse strategies for medical image analysis and early disease detection. Given this growing body of work, a systematic literature review is necessary to synthesize evidence, compare methodologies, and identify research gaps. Existing literature reviews on adipose segmentation and classification often focus on specific imaging modalities or limited disease applications. Nevertheless, none provide a systematic quantitative evaluation of ML and DL methods. Such a systematic quantitative evaluation is essential for a fair comparison of methodologies and guiding the development of more robust AI models. Moreover, existing reviews overlook key challenges, including limited annotated datasets, feature extraction, and predictive modeling for disease risk. This systematic literature review investigates ML and DL techniques for adipose tissue segmentation, classification, and disease risk prediction. An extensive search across four major scientific databases is conducted, followed by rigorous selection criteria that yield forty high-quality studies. The selected studies are classified into two types: ML-based segmentation and classification, covering fourteen studies, and DL-based segmentation and classification, covering twenty-six studies. Within the ML-based approaches, further analysis focuses on four major radiomic features, providing deeper insights into feature extraction techniques. In contrast, among the twenty-six DL-based studies, nine specifically address limited annotated data, with a focus on semi-supervised learning strategies and data augmentation methods. The review also presents a critical analysis of dataset constraints as well as the inherent limitations of both ML and DL architectures. To provide a more detailed perspective, ML and DL techniques are further examined across applications in ten different disease types. In addition, the role of adipose tissue biomarkers in disease risk prediction is analyzed. Despite these advancements, the review identifies challenges related to dataset limitations, annotation constraints, feature extraction, model interpretability, prediction reliability in disease risk assessment, and integration into clinical practice. Consequently, future research directions should focus on improving imaging modalities, expanding standardized datasets, advancing DL architectures and hybrid models, enhancing generalization and interpretability, and ensuring seamless clinical workflow integration.
Website
Google Scholar
- 16 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
Open Access
From Segmentation to Disease Prediction: A Systematic Review of AI Methods for Adipose Tissue Analysis in Medical Imaging
by Mohammed J. Alghamdi, Muhammad Rashid, Muhammad Arif
Accurate segmentation and classification of adipose tissue are critical tasks in the field of medical imaging, as they contribute to enhanced medical diagnostics. However, manual segmentation and classification are time-consuming and prone to variability. These limitations drive the development of automated and efficient artificial intelligence (AI) methods, including machine learning (ML) and deep learning (DL). A wide range of ML and DL techniques now exist, offering diverse strategies for medical image analysis and early disease detection. Given this growing body of work, a systematic literature review is necessary to synthesize evidence, compare methodologies, and identify research gaps. Existing literature reviews on adipose segmentation and classification often focus on specific imaging modalities or limited disease applications. Nevertheless, none provide a systematic quantitative evaluation of ML and DL methods. Such a systematic quantitative evaluation is essential for a fair comparison of methodologies and guiding the development of more robust AI models. Moreover, existing reviews overlook key challenges, including limited annotated datasets, feature extraction, and predictive modeling for disease risk. This systematic literature review investigates ML and DL techniques for adipose tissue segmentation, classification, and disease risk prediction. An extensive search across four major scientific databases is conducted, followed by rigorous selection criteria that yield forty high-quality studies. The selected studies are classified into two types: ML-based segmentation and classification, covering fourteen studies, and DL-based segmentation and classification, covering twenty-six studies. Within the ML-based approaches, further analysis focuses on four major radiomic features, providing deeper insights into feature extraction techniques. In contrast, among the twenty-six DL-based studies, nine specifically address limited annotated data, with a focus on semi-supervised learning strategies and data augmentation methods. The review also presents a critical analysis of dataset constraints as well as the inherent limitations of both ML and DL architectures. To provide a more detailed perspective, ML and DL techniques are further examined across applications in ten different disease types. In addition, the role of adipose tissue biomarkers in disease risk prediction is analyzed. Despite these advancements, the review identifies challenges related to dataset limitations, annotation constraints, feature extraction, model interpretability, prediction reliability in disease risk assessment, and integration into clinical practice. Consequently, future research directions should focus on improving imaging modalities, expanding standardized datasets, advancing DL architectures and hybrid models, enhancing generalization and interpretability, and ensuring seamless clinical workflow integration.
Cited by 1
Open Access
Website
Google Scholar
Cited by 1
- 13 January 2026
- Published by PeerJ in PeerJ Computer Science
MS-YieldStackNet: multi-source data fusion for wheat yield estimation using a stacked ensemble neural network
by Waqas Ali, Zeeshan Ramzan, Muhammad Shahbaz, Qamar Ul Zaman Bhutta, Muhammad Talha, Mohammed J. AlGhamdi
Accurate crop yield prediction is vital for ensuring food security and informing agricultural policy, particularly in wheat-dependent regions like Pakistan where manual estimation methods are labor-intensive and imprecise. This study introduces a novel algorithmic framework, MS-YieldStackNet, to predict wheat yield with high spatial resolution by integrating multispectral satellite imagery, in-situ soil analytics, and meteorological variables. A unified feature space is constructed using Normalized Difference Vegetation Index (NDVI) and Difference Vegetation Index (DVI), soil physicochemical attributes, and temporal climate patterns, processed through a stacked ensemble neural architecture (MS-YieldStackNet) combining three parallel feed-forward neural networks (FFNNs) and a Random Forest meta-learner. The model achieved robust performance with an R-squared of 0.81, Mean Squared Error (MSE) of 6,114.30 kg/ha, root mean squared error (RMSE) of 78.19 kg/ha, mean absolute error (MAE) of 59.07 kg/ha, and mean absolute percentage error (MAPE) of 3.55%, demonstrating its potential for precise and scalable crop yield forecasting.
Website
Google Scholar
- 13 January 2026
- Published by PeerJ in PeerJ Computer Science
Open Access
MS-YieldStackNet: multi-source data fusion for wheat yield estimation using a stacked ensemble neural network
by Waqas Ali, Zeeshan Ramzan, Muhammad Shahbaz, Qamar Ul Zaman Bhutta, Muhammad Talha, Mohammed J. AlGhamdi
Accurate crop yield prediction is vital for ensuring food security and informing agricultural policy, particularly in wheat-dependent regions like Pakistan where manual estimation methods are labor-intensive and imprecise. This study introduces a novel algorithmic framework, MS-YieldStackNet, to predict wheat yield with high spatial resolution by integrating multispectral satellite imagery, in-situ soil analytics, and meteorological variables. A unified feature space is constructed using Normalized Difference Vegetation Index (NDVI) and Difference Vegetation Index (DVI), soil physicochemical attributes, and temporal climate patterns, processed through a stacked ensemble neural architecture (MS-YieldStackNet) combining three parallel feed-forward neural networks (FFNNs) and a Random Forest meta-learner. The model achieved robust performance with an R-squared of 0.81, Mean Squared Error (MSE) of 6,114.30 kg/ha, root mean squared error (RMSE) of 78.19 kg/ha, mean absolute error (MAE) of 59.07 kg/ha, and mean absolute percentage error (MAPE) of 3.55%, demonstrating its potential for precise and scalable crop yield forecasting.
Cited by 1
Open Access
Website
Google Scholar
Cited by 3
- 18 August 2025
- Published by MDPI AG in Sustainability
Mapping the Global Discourse on Sustainable Development: A Sentiment-Based Clustering of SDG Narratives Across 100 Countries
by Fahim Sufi, Mohammed J. Alghamdi, Musleh Alsulami
Understanding how media narratives frame the Sustainable Development Goals (SDGs) is essential for global sustainability governance. This study presents a novel, data-driven analysis of 135,000 news articles mapped to SDGs 1–17 across 100 countries. Using polarity-based sentiment aggregation and principal component analysis (PCA), we reduce high-dimensional SDG sentiment profiles into a two-dimensional space and identify emergent clusters of countries using K-means. To contextualize these clusters, we integrate national-level indicators like Human Development Index (HDI), GDP per capita, CO₂ emissions, and press freedom scores, revealing robust correlations between sentiment structure and developmental attributes. Countries with higher HDI and freer media environments produce more optimistic and diverse SDG narratives, while lower-HDI countries tend toward more polarized or crisis-framed coverage. Our findings offer a typology of SDG discourse that reflects geopolitical, environmental, and informational asymmetries, providing new insights to support international policy coordination and sustainability communication. This work contributes a scalable methodology for monitoring global sustainability sentiment and underscores the importance of narrative equity in achieving Agenda 2030.
Website
Google Scholar
- 18 August 2025
- Published by MDPI AG in Sustainability
Open Access
Mapping the Global Discourse on Sustainable Development: A Sentiment-Based Clustering of SDG Narratives Across 100 Countries
by Fahim Sufi, Mohammed J. Alghamdi, Musleh Alsulami
Understanding how media narratives frame the Sustainable Development Goals (SDGs) is essential for global sustainability governance. This study presents a novel, data-driven analysis of 135,000 news articles mapped to SDGs 1–17 across 100 countries. Using polarity-based sentiment aggregation and principal component analysis (PCA), we reduce high-dimensional SDG sentiment profiles into a two-dimensional space and identify emergent clusters of countries using K-means. To contextualize these clusters, we integrate national-level indicators like Human Development Index (HDI), GDP per capita, CO₂ emissions, and press freedom scores, revealing robust correlations between sentiment structure and developmental attributes. Countries with higher HDI and freer media environments produce more optimistic and diverse SDG narratives, while lower-HDI countries tend toward more polarized or crisis-framed coverage. Our findings offer a typology of SDG discourse that reflects geopolitical, environmental, and informational asymmetries, providing new insights to support international policy coordination and sustainability communication. This work contributes a scalable methodology for monitoring global sustainability sentiment and underscores the importance of narrative equity in achieving Agenda 2030.
Cited by 3
Open Access
Website
Google Scholar
Cited by 5
- 6 June 2024
- Published by MDPI AG in Applied Sciences
A Novel OFDM Approach Using Error Correcting Codes and Continuous Phase Modulation for Underwater Acoustic Communication
by Mohsin Murad, Imran A. Tasadduq, Mohammed J. Alghamdi, Pablo Otero, Miguel-Ángel Luque-Nieto
In this work, the performance of coded continuous phase modulation (CPM) transceivers for orthogonal frequency-division multiplexing (OFDM) in underwater acoustic channels is evaluated. The proposed technique employs the Bose–Chaudhuri–Hocquenghem (BCH) class of cyclic codes, and a CPM-based mapper is being used in place of a traditional OFDM mapper. Bit-error-rates (BERs) for various distances are evaluated. We use the Bellhop acoustic channel simulator that is considered to be very close to a real underwater channel. The performance of the proposed system is evaluated for 23 values of the CPM modulation index $h$ as a function of the distance between the transmitter (Tx) and receiver (Rx). Based upon the error performance, we identified several best-performing CPM indices. We also observed that for Tx–Rx distances of 100 and 250 m, the proposed system gives acceptable performance without the need for equalization. We also compared the out-of-band radiation of the proposed system with PSK-OFDM and observed that the uncoded CPM-OFDM has a better out-of-band (OOB) performance than the traditional OFDM. Moreover, a comparison of BERs with the traditional PSK-OFDM system shows that the proposed system outperforms the traditional OFDM system by a wide margin.
Website
Google Scholar
- 6 June 2024
- Published by MDPI AG in Applied Sciences
Open Access
A Novel OFDM Approach Using Error Correcting Codes and Continuous Phase Modulation for Underwater Acoustic Communication
by Mohsin Murad, Imran A. Tasadduq, Mohammed J. Alghamdi, Pablo Otero, Miguel-Ángel Luque-Nieto
In this work, the performance of coded continuous phase modulation (CPM) transceivers for orthogonal frequency-division multiplexing (OFDM) in underwater acoustic channels is evaluated. The proposed technique employs the Bose–Chaudhuri–Hocquenghem (BCH) class of cyclic codes, and a CPM-based mapper is being used in place of a traditional OFDM mapper. Bit-error-rates (BERs) for various distances are evaluated. We use the Bellhop acoustic channel simulator that is considered to be very close to a real underwater channel. The performance of the proposed system is evaluated for 23 values of the CPM modulation index $h$ as a function of the distance between the transmitter (Tx) and receiver (Rx). Based upon the error performance, we identified several best-performing CPM indices. We also observed that for Tx–Rx distances of 100 and 250 m, the proposed system gives acceptable performance without the need for equalization. We also compared the out-of-band radiation of the proposed system with PSK-OFDM and observed that the uncoded CPM-OFDM has a better out-of-band (OOB) performance than the traditional OFDM. Moreover, a comparison of BERs with the traditional PSK-OFDM system shows that the proposed system outperforms the traditional OFDM system by a wide margin.
Cited by 5
Retracted
Open Access
Website
Google Scholar
Cited by 21
- 21 December 2021
- Published by Wiley in Journal of Healthcare Engineering
Towards Understanding the Usability Attributes of AI-Enabled eHealth Mobile Applications
by Adel Saeed Alzahrani, Valerie Gay, Ryan Alturki, Mohammad J AlGhamdi
Mobile application (app) use is increasingly becoming an essential part of our daily lives. Due to their significant usefulness, people rely on them to perform multiple tasks seamlessly in almost all aspects of everyday life. Similarly, there has been immense progress in artificial intelligence (AI) technology, especially deep learning, computer vision, natural language processing, and robotics. These technologies are now actively being implemented in smartphone apps and healthcare, providing multiple healthcare services. However, several factors affect the usefulness of mobile healthcare apps, and usability is an important one. There are various healthcare apps developed for each specific task, and the success of these apps depends on their performance. This study presents a systematic review of the existing apps and discusses their usability attributes. It highlights the usability models, outlines, and guidelines proposed in previous research for designing apps with improved usability characteristics. Thirty-nine research articles were reviewed and examined to identify the usability attributes, framework, and app design conducted. The results showed that satisfaction, efficiency, and learnability are the most important usability attributes to consider when designing eHealth mobile apps. Surprisingly, other significant attributes for healthcare apps, such as privacy and security, were not among the most indicated attributes in the studies.
Website
Google Scholar
- 21 December 2021
- Published by Wiley in Journal of Healthcare Engineering
Retracted
Open Access
Towards Understanding the Usability Attributes of AI-Enabled eHealth Mobile Applications
by Adel Saeed Alzahrani, Valerie Gay, Ryan Alturki, Mohammad J AlGhamdi
Mobile application (app) use is increasingly becoming an essential part of our daily lives. Due to their significant usefulness, people rely on them to perform multiple tasks seamlessly in almost all aspects of everyday life. Similarly, there has been immense progress in artificial intelligence (AI) technology, especially deep learning, computer vision, natural language processing, and robotics. These technologies are now actively being implemented in smartphone apps and healthcare, providing multiple healthcare services. However, several factors affect the usefulness of mobile healthcare apps, and usability is an important one. There are various healthcare apps developed for each specific task, and the success of these apps depends on their performance. This study presents a systematic review of the existing apps and discusses their usability attributes. It highlights the usability models, outlines, and guidelines proposed in previous research for designing apps with improved usability characteristics. Thirty-nine research articles were reviewed and examined to identify the usability attributes, framework, and app design conducted. The results showed that satisfaction, efficiency, and learnability are the most important usability attributes to consider when designing eHealth mobile apps. Surprisingly, other significant attributes for healthcare apps, such as privacy and security, were not among the most indicated attributes in the studies.
Cited by 21
Open Access
Website
Google Scholar
Cited by 8
- 28 June 2021
- Published by Wiley in Mobile Information Systems
Towards an Application Helping to Minimize Medication Error Rate
by Ali I. Alharbi, Valerie Gay, Mohammad J. AlGhamdi, Ryan Alturki, Hasan J. Alyamani
Medication errors related to medication administration done by both doctors and nurses can be considered a vital issue around the world. It is believed that systematisation and the introduction of main documents are done manually, which might increase the opportunities to have inaccuracies and errors because of unexpected wrong actions done by medical practitioners. Experts stated that the lack of pharmacological knowledge is one of the key factors, which play an important role in causing such errors. Doctors and nurses may face problems when they move from one unit to another and the medication administration list has changed. However, promoting public health activities and recent AI-enabled applications can provide general information about medication that helps both doctors and nurses administer the right medication. However, such an application can require a lot of time and effort to search and then find a medication. Therefore, this article aims to investigate whether AI-enabled applications can help avoid or at least minimize medication error rates.
Website
Google Scholar
- 28 June 2021
- Published by Wiley in Mobile Information Systems
Open Access
Towards an Application Helping to Minimize Medication Error Rate
by Ali I. Alharbi, Valerie Gay, Mohammad J. AlGhamdi, Ryan Alturki, Hasan J. Alyamani
Medication errors related to medication administration done by both doctors and nurses can be considered a vital issue around the world. It is believed that systematisation and the introduction of main documents are done manually, which might increase the opportunities to have inaccuracies and errors because of unexpected wrong actions done by medical practitioners. Experts stated that the lack of pharmacological knowledge is one of the key factors, which play an important role in causing such errors. Doctors and nurses may face problems when they move from one unit to another and the medication administration list has changed. However, promoting public health activities and recent AI-enabled applications can provide general information about medication that helps both doctors and nurses administer the right medication. However, such an application can require a lot of time and effort to search and then find a medication. Therefore, this article aims to investigate whether AI-enabled applications can help avoid or at least minimize medication error rates.
Cited by 8