Adnan Miski
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Adnan Miski has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Omer Bafail
Department of Industrial Engineering, King Abdulaziz University, Jeddah, Saudi Arabia
2 shared publications- Omer Bafail
Department of Industrial Engineering, Faculty of Engineering, King Abdulaziz University, Jeddah, Saudi Arabia
2 shared publications - Anas Ahmad Makki
Department of Industrial Engineering, Faculty of Engineering—Rabigh, King Abdulaziz University, Jeddah 21589, Saudi Arabia
1 shared publication - Mazen A. Ismail
Department of Medical Education, Faculty of Medicine, King Abdulaziz University, Jeddah, Saudi Arabia
1 shared publication Moayad Alshangiti
College of Computer Science and Engineering, University of Jeddah
1 shared publication
Latest Publications
- Open Access
- 12 November 2026
- Published by Springer Nature in Scientific Reports
Multi-criteria ranking of open automatic speech recognition models under alternative deployment priorities
Automatic speech recognition (ASR) models differ in accuracy, throughput, and parameter count, so choosing a model involves trade-offs. This study ranks 69 license-eligible open ASR model configurations from the July 2026 open ASR leaderboard, which covers eight short-form English test sets. Criterion weights were derived with the fuzzy analytic hierarchy process (fuzzy AHP) under three illustrative scenarios, each prioritizing one criterion: word error rate (WER), inverse real-time factor (RTFx), or parameter count. The models were then ranked with the technique for order preference by similarity to ideal solution (TOPSIS). NVIDIA Parakeet-TDT-CTC-110M ranked first in the WER-prioritized scenario, and NVIDIA FastConformer-CTC-large ranked first in the other two. The sensitivity analysis tested three further ranking methods (VIKOR, MABAC, and ARAS), classical AHP and entropy weights, stronger dominance ratings, min–max normalization, 171 weight combinations, and alternative WER measures. Across the four ranking methods and three scenarios, the top rank was always held by one of three NVIDIA models: Parakeet-TDT-CTC-110M, FastConformer-CTC-Large, or Conformer-CTC-Small. Classical AHP weights produced nearly identical rankings (Spearman rank correlation of at least 0.998), and Parakeet-TDT-CTC-110M or FastConformer-CTC-Large ranked first in 163 of the 171 TOPSIS weight combinations. However, under the strongest WER priority tested, the more accurate but larger NVIDIA Parakeet-TDT-0.6B-v2 ranked first in the WER-prioritized scenario, and ARAS favored the smallest models. The rankings are specific to this benchmark rather than validated recommendations for particular sectors, and any model’s suitability must be verified on representative audio and target hardware before deployment. The framework offers a transparent, reproducible way to compare ASR models under different deployment priorities.
- 12 November 2026
- Published by Springer Nature in Scientific Reports
Open AccessMulti-criteria ranking of open automatic speech recognition models under alternative deployment priorities
Automatic speech recognition (ASR) models differ in accuracy, throughput, and parameter count, so choosing a model involves trade-offs. This study ranks 69 license-eligible open ASR model configurations from the July 2026 open ASR leaderboard, which covers eight short-form English test sets. Criterion weights were derived with the fuzzy analytic hierarchy process (fuzzy AHP) under three illustrative scenarios, each prioritizing one criterion: word error rate (WER), inverse real-time factor (RTFx), or parameter count. The models were then ranked with the technique for order preference by similarity to ideal solution (TOPSIS). NVIDIA Parakeet-TDT-CTC-110M ranked first in the WER-prioritized scenario, and NVIDIA FastConformer-CTC-large ranked first in the other two. The sensitivity analysis tested three further ranking methods (VIKOR, MABAC, and ARAS), classical AHP and entropy weights, stronger dominance ratings, min–max normalization, 171 weight combinations, and alternative WER measures. Across the four ranking methods and three scenarios, the top rank was always held by one of three NVIDIA models: Parakeet-TDT-CTC-110M, FastConformer-CTC-Large, or Conformer-CTC-Small. Classical AHP weights produced nearly identical rankings (Spearman rank correlation of at least 0.998), and Parakeet-TDT-CTC-110M or FastConformer-CTC-Large ranked first in 163 of the 171 TOPSIS weight combinations. However, under the strongest WER priority tested, the more accurate but larger NVIDIA Parakeet-TDT-0.6B-v2 ranked first in the WER-prioritized scenario, and ARAS favored the smallest models. The rankings are specific to this benchmark rather than validated recommendations for particular sectors, and any model’s suitability must be verified on representative audio and target hardware before deployment. The framework offers a transparent, reproducible way to compare ASR models under different deployment priorities.
- Open Access
- 6 November 2026
- Published by Springer Nature in Scientific Reports
A fuzzy DEMATEL–ISM framework for unpacking barriers to digital twin adoption in high-density crowd management
- 6 November 2026
- Published by Springer Nature in Scientific Reports
Open AccessA fuzzy DEMATEL–ISM framework for unpacking barriers to digital twin adoption in high-density crowd management
- Open Access
- 28 October 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (21) , 3552
Comparing Lightweight Models for Physician-Consensus Pharyngitis Classification from Primary-Care Smartphone Images
Background/Objectives: Smartphone-acquired throat images could support accessible pharyngitis assessment, but the performance and computational efficiency of lightweight models on such images require further evaluation. This study compared five lightweight models for predicting physician-consensus bacterial versus nonbacterial labels from smartphone throat images. Methods: We analyzed PGUPharyngitis, a public dataset of smartphone throat images collected in general practice. The final cohort comprised 635 patients, of whom 105 (16.5%) had bacterial physician-consensus labels. The reference outcome was physician consensus based on images and clinical information rather than microbiological testing. Five ImageNet-pretrained lightweight classifiers—four convolutional neural networks (CNNs; MobileNetV3-Small, EfficientNet-B0, ShuffleNetV2, and YOLO26n-cls) and one CNN–Transformer hybrid (MobileViT-XS)—were fine-tuned using patient-level five-fold cross-validation. Performance was assessed using area under the precision–recall curve (PR-AUC) and area under the receiver operating characteristic curve (AUROC), alongside computational efficiency. Device-only and clinical-variable logistic-regression models provided non-image comparisons. Results: Mean PR-AUC across folds ranged from 0.317 to 0.372 and AUROC from 0.663 to 0.708, with no clearly superior architecture. Bacterial-label prevalence differed by acquisition device (Samsung 9.2% versus Xiaomi 26.9%); the device-only and clinical-variable comparators achieved AUROCs of 0.650 and 0.598, respectively. At validation-selected high-sensitivity thresholds, the models flagged 65–78% of patients, with positive predictive values of only 19–22%. All models contained fewer than five million parameters, making them compact candidates for future evaluation on resource-constrained devices. Conclusions: Lightweight models showed moderate performance against physician-consensus labels. However, acquisition device was associated with the reference labels, image-model AUROCs were not clearly distinguishable from that of the device-only comparator, and device-related confounding cannot be excluded. Because performance was measured against these labels and positive predictive values were low, the findings do not establish diagnostic accuracy or clinical applicability, which require validation against microbiological reference standards in independent clinical cohorts.
- 28 October 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (21) , 3552
Open AccessComparing Lightweight Models for Physician-Consensus Pharyngitis Classification from Primary-Care Smartphone Images
Background/Objectives: Smartphone-acquired throat images could support accessible pharyngitis assessment, but the performance and computational efficiency of lightweight models on such images require further evaluation. This study compared five lightweight models for predicting physician-consensus bacterial versus nonbacterial labels from smartphone throat images. Methods: We analyzed PGUPharyngitis, a public dataset of smartphone throat images collected in general practice. The final cohort comprised 635 patients, of whom 105 (16.5%) had bacterial physician-consensus labels. The reference outcome was physician consensus based on images and clinical information rather than microbiological testing. Five ImageNet-pretrained lightweight classifiers—four convolutional neural networks (CNNs; MobileNetV3-Small, EfficientNet-B0, ShuffleNetV2, and YOLO26n-cls) and one CNN–Transformer hybrid (MobileViT-XS)—were fine-tuned using patient-level five-fold cross-validation. Performance was assessed using area under the precision–recall curve (PR-AUC) and area under the receiver operating characteristic curve (AUROC), alongside computational efficiency. Device-only and clinical-variable logistic-regression models provided non-image comparisons. Results: Mean PR-AUC across folds ranged from 0.317 to 0.372 and AUROC from 0.663 to 0.708, with no clearly superior architecture. Bacterial-label prevalence differed by acquisition device (Samsung 9.2% versus Xiaomi 26.9%); the device-only and clinical-variable comparators achieved AUROCs of 0.650 and 0.598, respectively. At validation-selected high-sensitivity thresholds, the models flagged 65–78% of patients, with positive predictive values of only 19–22%. All models contained fewer than five million parameters, making them compact candidates for future evaluation on resource-constrained devices. Conclusions: Lightweight models showed moderate performance against physician-consensus labels. However, acquisition device was associated with the reference labels, image-model AUROCs were not clearly distinguishable from that of the device-only comparator, and device-related confounding cannot be excluded. Because performance was measured against these labels and positive predictive values were low, the findings do not establish diagnostic accuracy or clinical applicability, which require validation against microbiological reference standards in independent clinical cohorts.
- Open Access
- 27 October 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (10) , e0349608
Lightweight CNN and transformer detectors for real-time single-fruit date-variety recognition on edge GPU hardware
Manual sorting of date fruits is time-consuming and labor-intensive, while automated optical sorting lines remain costly for small- and medium-sized enterprises (SMEs). This study presents a deployment-oriented benchmark of five lightweight object detectors for single-fruit date-variety recognition, namely the Convolutional Neural Network (CNN)-based YOLOv8, YOLOv10, YOLOv11, and YOLOv12 Nano variants and the Transformer-based D-Fine-Nano, with RT-DETR-Large included as a high-capacity accuracy reference. Models were evaluated on 1,658 controlled-environment images of nine commercial varieties using grouped 5-fold cross-validation, which kept identified repeat photographs of the same fruit within the same cross-validation fold. Latency was measured on an NVIDIA T4-class edge GPU/industrial-PC accelerator, and the CNN detectors were also exported to Open Neural Network Exchange (ONNX) and TensorRT half-precision (FP16) engines. All Nano models met the 30 frames-per-second threshold for model-side detection latency under the tested conditions and achieved high accuracy, while a Friedman–Nemenyi analysis detected no statistically significant accuracy difference among the lightweight models. Under TensorRT FP16, YOLOv10-Nano achieved the lowest model-side end-to-end latency of 6.27 ms with no observed accuracy degradation. YOLOv8-Nano attained the lowest inference-stage latency of 3.31 ms, but its mean average precision (mAP@50–95) decreased by 1.2 percentage points after TensorRT FP16 conversion. YOLOv12-Nano had the numerically highest mean cross-validation mAP@50–95 and the lowest fold-to-fold variability, albeit at higher latency. These findings characterize model-level detector behavior rather than a complete sorting line. Within that scope, YOLOv10-Nano represents one practical configuration for a T4/TensorRT FP16 pipeline, while the other models offer different speed, stability, and deployment trade-offs, providing SMEs with a well-characterized starting point for the vision component of affordable date-sorting systems.
- 27 October 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (10) , e0349608
Open AccessLightweight CNN and transformer detectors for real-time single-fruit date-variety recognition on edge GPU hardware
Manual sorting of date fruits is time-consuming and labor-intensive, while automated optical sorting lines remain costly for small- and medium-sized enterprises (SMEs). This study presents a deployment-oriented benchmark of five lightweight object detectors for single-fruit date-variety recognition, namely the Convolutional Neural Network (CNN)-based YOLOv8, YOLOv10, YOLOv11, and YOLOv12 Nano variants and the Transformer-based D-Fine-Nano, with RT-DETR-Large included as a high-capacity accuracy reference. Models were evaluated on 1,658 controlled-environment images of nine commercial varieties using grouped 5-fold cross-validation, which kept identified repeat photographs of the same fruit within the same cross-validation fold. Latency was measured on an NVIDIA T4-class edge GPU/industrial-PC accelerator, and the CNN detectors were also exported to Open Neural Network Exchange (ONNX) and TensorRT half-precision (FP16) engines. All Nano models met the 30 frames-per-second threshold for model-side detection latency under the tested conditions and achieved high accuracy, while a Friedman–Nemenyi analysis detected no statistically significant accuracy difference among the lightweight models. Under TensorRT FP16, YOLOv10-Nano achieved the lowest model-side end-to-end latency of 6.27 ms with no observed accuracy degradation. YOLOv8-Nano attained the lowest inference-stage latency of 3.31 ms, but its mean average precision (mAP@50–95) decreased by 1.2 percentage points after TensorRT FP16 conversion. YOLOv12-Nano had the numerically highest mean cross-validation mAP@50–95 and the lowest fold-to-fold variability, albeit at higher latency. These findings characterize model-level detector behavior rather than a complete sorting line. Within that scope, YOLOv10-Nano represents one practical configuration for a T4/TensorRT FP16 pipeline, while the other models offer different speed, stability, and deployment trade-offs, providing SMEs with a well-characterized starting point for the vision component of affordable date-sorting systems.
- Open Access
- 17 June 2026
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3884
Navigating the digital foundations: a multi-criteria evaluation of Layer-1 blockchains for Web3 and the metaverse
The rapidly expanding landscape of Web3 and the metaverse profoundly accentuates the escalating challenge of rigorously assessing and strategically selecting foundational Layer-1 digital blockchain platforms. Decision-makers frequently contend with the imperative of rational choice amidst a complex confluence of often conflicting technological attributes. This study directly addresses this critical exigency by utilizing robust benchmarking and validation for the comparative ranking of 10 prominent blockchain platforms. By applying a suite of five established multi-criteria decision-making (MCDM) methods, namely TOPSIS, ARAS, RAPS, RAMS, and RATMI, a comprehensive evaluation is undertaken, scrutinizing performance across three pivotal criteria categories: performance/scalability, security, and economic/activity. The weights for the entire criteria set were determined using the objective entropy method. Using the entropy approach to determine weights based on randomness, the criteria weights were determined as follows: Speed 12.9%, Market Cap 7.2%, Hash Rate 43.7%, Time to Finality 12.1%, Total Transactions 10.8%, and Number of Nodes 13.3%. The empirical analysis consistently identifies Bitcoin as the top-ranking platform, securing first position across all five MCDM methodologies. This finding validates its unparalleled robustness and security based on the defined criteria. Hyperliquid and Sui also emerged as exemplary performers, consistently exhibiting strong aggregate scores and securing second and third positions, respectively. Conversely, other blockchains, such as the BNB Chain and Tron, demonstrated significant ranking volatility across the different evaluation methods. This study provides a validated, data-driven benchmarking tool, offering stakeholders a transparent framework for strategic decision-making. This application contributes to the conceptual accuracy of evaluating sustainable digital infrastructure.
- 17 June 2026
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3884
Open AccessNavigating the digital foundations: a multi-criteria evaluation of Layer-1 blockchains for Web3 and the metaverse
The rapidly expanding landscape of Web3 and the metaverse profoundly accentuates the escalating challenge of rigorously assessing and strategically selecting foundational Layer-1 digital blockchain platforms. Decision-makers frequently contend with the imperative of rational choice amidst a complex confluence of often conflicting technological attributes. This study directly addresses this critical exigency by utilizing robust benchmarking and validation for the comparative ranking of 10 prominent blockchain platforms. By applying a suite of five established multi-criteria decision-making (MCDM) methods, namely TOPSIS, ARAS, RAPS, RAMS, and RATMI, a comprehensive evaluation is undertaken, scrutinizing performance across three pivotal criteria categories: performance/scalability, security, and economic/activity. The weights for the entire criteria set were determined using the objective entropy method. Using the entropy approach to determine weights based on randomness, the criteria weights were determined as follows: Speed 12.9%, Market Cap 7.2%, Hash Rate 43.7%, Time to Finality 12.1%, Total Transactions 10.8%, and Number of Nodes 13.3%. The empirical analysis consistently identifies Bitcoin as the top-ranking platform, securing first position across all five MCDM methodologies. This finding validates its unparalleled robustness and security based on the defined criteria. Hyperliquid and Sui also emerged as exemplary performers, consistently exhibiting strong aggregate scores and securing second and third positions, respectively. Conversely, other blockchains, such as the BNB Chain and Tron, demonstrated significant ranking volatility across the different evaluation methods. This study provides a validated, data-driven benchmarking tool, offering stakeholders a transparent framework for strategic decision-making. This application contributes to the conceptual accuracy of evaluating sustainable digital infrastructure.
- Open Access
- 18 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 75918-75932
Benchmarking Lightweight YOLO Architectures for Real-Time Eggshell Defect Detection Toward Augmented-Reality Inspection in Poultry Supply Chains
Ensuring the integrity of eggshells across poultry supply chains is vital to minimize economic losses and mitigate the risk of pathogen ingress. Manual visual inspection remains inconsistent, labor-intensive, and increasingly inadequate for modern production volumes. This study conducts a comprehensive comparative evaluation of lightweight deep-learning models for automated eggshell defect detection, assessing their suitability for deployment on resource-constrained augmented-reality (AR) smart glasses. A mixed dataset was assembled by combining 186 privately collected images of brown cage-free eggs with 794 publicly available images of primarily white eggs. Ten architectures, comprising nine lightweight detectors across the YOLOv5, YOLOv8, YOLOv9, and YOLOv10 families alongside a transformer RT-DETR-l baseline, were benchmarked. The YOLOv8n model achieved the highest detection accuracy with a 5-fold cross-validated mAP@0.5:0.95 of 91.2%, demonstrating no statistically significant difference relative to RT-DETR-l. However, YOLOv10n provided the optimal accuracy-efficiency balance for AR deployment as it delivered a mAP@0.5:0.95 of 89.5% and a proxy CPU inference time of 34.2 ms, while an INT8-quantized TFLite export reduced its memory footprint to 2.59 MB. By providing a mixed-egg dataset and a thorough benchmark of lightweight detectors, this comparative study identifies YOLOv10n as the most suitable architecture for real-time AR-based inspection. These findings advance precision agriculture by outlining an efficient, empirically validated pathway toward hands-free, AI-driven quality control.
- 18 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 75918-75932
Open AccessBenchmarking Lightweight YOLO Architectures for Real-Time Eggshell Defect Detection Toward Augmented-Reality Inspection in Poultry Supply Chains
Ensuring the integrity of eggshells across poultry supply chains is vital to minimize economic losses and mitigate the risk of pathogen ingress. Manual visual inspection remains inconsistent, labor-intensive, and increasingly inadequate for modern production volumes. This study conducts a comprehensive comparative evaluation of lightweight deep-learning models for automated eggshell defect detection, assessing their suitability for deployment on resource-constrained augmented-reality (AR) smart glasses. A mixed dataset was assembled by combining 186 privately collected images of brown cage-free eggs with 794 publicly available images of primarily white eggs. Ten architectures, comprising nine lightweight detectors across the YOLOv5, YOLOv8, YOLOv9, and YOLOv10 families alongside a transformer RT-DETR-l baseline, were benchmarked. The YOLOv8n model achieved the highest detection accuracy with a 5-fold cross-validated mAP@0.5:0.95 of 91.2%, demonstrating no statistically significant difference relative to RT-DETR-l. However, YOLOv10n provided the optimal accuracy-efficiency balance for AR deployment as it delivered a mAP@0.5:0.95 of 89.5% and a proxy CPU inference time of 34.2 ms, while an INT8-quantized TFLite export reduced its memory footprint to 2.59 MB. By providing a mixed-egg dataset and a thorough benchmark of lightweight detectors, this comparative study identifies YOLOv10n as the most suitable architecture for real-time AR-based inspection. These findings advance precision agriculture by outlining an efficient, empirically validated pathway toward hands-free, AI-driven quality control.
- Open Access
- 24 December 2025
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Lightweight YOLO object detectors for PET and HDPE classification in recycling facilities
Growing volumes of plastic waste highlight the need for reliable sorting technologies. This study examines whether lightweight YOLO object detectors can distinguish polyethylene terephthalate (PET) bottles from high-density polyethylene (HDPE) bottles, two common packaging materials that must be separated for recycling. Two public PET and HDPE datasets were augmented offline to simulate the visual variation typical of industrial sorting lines, and eleven compact YOLO models–nano, tiny and small versions across versions 7–12–were fine-tuned on these data. Their accuracy was quantified using mean average precision (mAP) at multiple intersection-over-union thresholds and precision, recall and F1 scores; their efficiency was evaluated by inference time, size and floating-point operations. All models achieved mAP@0.5 above 99.2% and F1 scores exceeding 98% on test data. Among them, YOLOv11n delivered the best trade-off between accuracy and speed, it achieved mAP@0.5:0.95 of 93.7%, processed 640 \(\times\) 640 pixel images in around 38 ms on a CPU, and required just 5.5 MB of memory. These findings suggest that accurate polymer discrimination is possible on modest hardware, enabling resource-constrained recycling facilities to reduce mis-sorting, trim costs and support a circular economy.- 24 December 2025
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessLightweight YOLO object detectors for PET and HDPE classification in recycling facilities
Growing volumes of plastic waste highlight the need for reliable sorting technologies. This study examines whether lightweight YOLO object detectors can distinguish polyethylene terephthalate (PET) bottles from high-density polyethylene (HDPE) bottles, two common packaging materials that must be separated for recycling. Two public PET and HDPE datasets were augmented offline to simulate the visual variation typical of industrial sorting lines, and eleven compact YOLO models–nano, tiny and small versions across versions 7–12–were fine-tuned on these data. Their accuracy was quantified using mean average precision (mAP) at multiple intersection-over-union thresholds and precision, recall and F1 scores; their efficiency was evaluated by inference time, size and floating-point operations. All models achieved mAP@0.5 above 99.2% and F1 scores exceeding 98% on test data. Among them, YOLOv11n delivered the best trade-off between accuracy and speed, it achieved mAP@0.5:0.95 of 93.7%, processed 640 \(\times\) 640 pixel images in around 38 ms on a CPU, and required just 5.5 MB of memory. These findings suggest that accurate polymer discrimination is possible on modest hardware, enabling resource-constrained recycling facilities to reduce mis-sorting, trim costs and support a circular economy. - Open Access
An Advanced CNN-Based Framework for the Automated Detection of Uncovered PET in Recycling Streams
Contamination in recycling streams represents one of the most pervasive challenges confronting material recovery facilities (MRFs) globally. Among the various contamination sources in recycling streams, liquid contamination from PET bottles presents particularly severe challenges due to its capacity to spread throughout commingled materials. Object detection using neural networks enables detection at the collection stage of single or mixed recycling streams, allowing for targeted application in the early stage of the recycling cycle. YOLO (you only look once) models and other object detection models are beneficial due to their speed and accuracy in detecting multiple objects at once. This study aimed to design a model to detect contaminated PET bottles in real time. Several YOLO variations and model sizes were trained on a custom dataset with 7130 images. YOLOv8l achieved the highest performance, with mAP@0.5:0.95, mAP@0.5, precision, recall, and F1 score values of 89.7%, 93%, 89%, 88%, and 88%, respectively.
Open AccessAn Advanced CNN-Based Framework for the Automated Detection of Uncovered PET in Recycling Streams
Contamination in recycling streams represents one of the most pervasive challenges confronting material recovery facilities (MRFs) globally. Among the various contamination sources in recycling streams, liquid contamination from PET bottles presents particularly severe challenges due to its capacity to spread throughout commingled materials. Object detection using neural networks enables detection at the collection stage of single or mixed recycling streams, allowing for targeted application in the early stage of the recycling cycle. YOLO (you only look once) models and other object detection models are beneficial due to their speed and accuracy in detecting multiple objects at once. This study aimed to design a model to detect contaminated PET bottles in real time. Several YOLO variations and model sizes were trained on a custom dataset with 7130 images. YOLOv8l achieved the highest performance, with mAP@0.5:0.95, mAP@0.5, precision, recall, and F1 score values of 89.7%, 93%, 89%, 88%, and 88%, respectively.