Scalability gaps in Computer Science

Representative open questions

Showing 30 of 163 — one per source paper, highest-quality first.

• Hybrid Deep Model for Pain Intensity Classification Using Fused ECG, EMG, and GSR Signals (2026) · doi

  The paper emphasizes that optimal signal sequence selection achieves performance improvements 'without increasing computational costs' but provides no computational complexity analysis, inference time comparisons, or memory footprint measurements for the BiLSTM-MHAT-CNN hybrid model versus the CNN baseline. Runtime and hardware requirements must be quantified to support claims of practical applicability in real-time automated pain recognition systems.

• Turbulence closure in Reynolds-averaged Navier–Stokes and flow inference around a cylinder using physics-informed neural networks and sparse experimental data (2026) · doi

  The discrete adjoint framework from DAFoam differentiates through the fully converged steady RANS system; the computational cost, memory requirements, and scalability of this adjoint-based training approach for larger domains, unsteady flows, or three-dimensional configurations in practical CFD solvers have not been characterized.

• William & Mary: Comprehensive AI Governance & Activity Inventory (2026) · doi

  No publicly available HPC strategic plan or capacity roadmap addressing AI/ML workload growth was identified. Given the documented research portfolio including deep learning for nuclear physics, CNNs for coastal monitoring, LLM agent research, and diffusion models, the alignment between current compute capacity (600 TFLOPS combined, 12 GPUs across both campuses) and research demand requires explicit capacity planning documentation.

• A novel deep learning approach for accurate and efficient design of LNOI power splitters (2026) · doi

  The MATLAB application demonstrates inverse design for binary power splitting ratios (e.g., 50:50, 30:70), but the paper does not address whether the DNN-based framework can be extended to multi-output scenarios with three or more waveguide outputs or to design specifications beyond simple power ratio targeting.

• Numerical Method for Nonlinear Kolmogorov PDEs via Sensitivity Analysis (2026) · doi

  The proof of Theorem 2.9 relies on Lemma 6.2 to bound moments of the canonical process X^o and the auxiliary process X̃^o under the reference measure, but the extension of these bounds to high-dimensional settings (d >> 10) and their interaction with the BDG inequality constants is not analyzed, leaving scalability of the sensitivity-based numerical method for high-dimensional Kolmogorov PDEs unverified.

• Prediction of sedimentation concentration profiles in inclined suspension systems: A data-driven neural network framework (2026) · doi

  Experimental validation was conducted at bench-scale geometry with a single fluid matrix and particle type; applicability of the ANN-based framework to field-scale directional drilling operations with varied fluid rheologies, particle size distributions, and higher solids concentrations requires investigation.

• Effectiveness of screening modalities for early detection of diabetic retinopathy: a systematic review and meta-analysis of tele-ophthalmology, AI-based tools, and conventional methods (2026) · doi

  Inter-grader variability in AI-assisted and physician-based DR assessment has been identified in single urban healthcare systems; provider-level variability assessment and quality control mechanisms for deep learning DR algorithms across geographically diverse settings remain underdeveloped.

• Federated learning for fair autism spectrum disorder screening across age-heterogeneous populations (2026) · doi

  The computational efficiency analysis measures communication cost and runtime scaling but focuses on model parameter transmission counts. The actual communication bandwidth requirements, energy consumption implications, and latency constraints for deploying these federated autism screening algorithms across resource-constrained healthcare institutions with varying network infrastructure have not been evaluated.

• A lazy and modular approach to int-blasting (2026) · doi

  The Eager algorithm implementation cannot handle 5,653 out of 25,223 SMT-LIB benchmarks due to stack-overflow errors from deeply nested bit-vector terms. The paper does not investigate alternative techniques or optimizations to handle deeply nested term structures, which represents a scalability limitation for the eager int-blasting approach.

• Pluriliteracies for global citizenship: the 4Rs framework for deeper learning in the modern language(s) classroom (2026) · doi

  The framework situates language-as-discipline within debates on disciplinary literacies and cites scholarship on history (Coffin, 2006) and science (Veel, 1997; Polias, 2016), but does not address how the 4Rs framework scales or adapts across different modern language contexts (e.g., classical languages, minority languages, heritage language learners, or multilingual contexts with L3/L4 acquisition).

• Phishing in the age of distributed intelligence: taxonomies, detection strategies, and the emerging role of federated learning (2026) · doi

  High communication overhead, device heterogeneity, and network heterogeneity restrict the scalability of federated learning for phishing detection, yet lightweight model architectures optimized for edge deployment in resource-constrained phishing detection scenarios have not been adequately developed or benchmarked.

• Securing Fog-assisted IoT: An Adaptable and Efficient Threat Identification Approach (2026) · doi

  The paper evaluates DEL models only up to 500 IoT devices; the scalability threshold and performance degradation patterns for large-scale deployments with thousands or tens of thousands of heterogeneous IoT devices connected to fog nodes remain unexplored. Specific investigation is needed on how latency, energy consumption, and detection accuracy scale beyond 500 devices.

• A Robust Hybrid Deep Learning Model for Multiclass Depression Classification from Speech Audio (2026) · doi

  Lightweight attention-based architectures balancing predictive performance and computational efficiency have not been explored; future research should develop and evaluate streamlined attention variants (e.g., efficient Transformers, local attention) for practical deployment of audio-based multiclass depression screening.

• Cardiovascular Risk Prediction Using Machine Learning: Advances and Clinical Translation (2026) · doi

  Continuous learning systems for cardiovascular risk prediction pose unresolved regulatory challenges due to their dynamic model update nature, but the paper does not specify what post-deployment monitoring mechanisms, performance drift detection thresholds, or adaptive regulatory approval processes FDA and EMA should implement for evolving machine learning medical devices.

• Breast cancer recurrence risk prediction based on MIL (2026) · doi

  Computational efficiency is claimed for the ConvNeXt-MIL-XGBoost pipeline during inference, but the paper does not provide quantitative metrics such as inference time per WSI, memory footprint, or scalability benchmarks on datasets with varying WSI resolutions and patch counts for clinical deployment in breast cancer screening.

• A Federated Learning Framework with Metaheuristic Optimization for Heart Disease Prediction (2026) · doi

  The framework was tested on data from only 3 hospitals (Table 8); evaluation across larger federated networks with 10+ geographically distributed healthcare institutions and varying degrees of statistical heterogeneity (non-IID data distributions) is needed to validate robustness claims.

• Latency-efficient edge intelligence in IoT networks using knowledge distillation (2026) · doi

  Energy consumption analysis (Figure 7, Equation 18) shows FEKD remains below 18 mJ at 400 tasks, but this evaluation is limited to homogeneous task distributions and does not explore energy efficiency under dynamic task arrivals, variable task complexity, or device heterogeneity-induced workload imbalance in edge intelligence systems.

• Lightweight and Explainable Neural Models for Multilingual Movie Script Certification (2026) · doi

  The lightweight model design (measured in MB file size via ONNX format) is intended for deployment efficiency, but latency benchmarks, memory consumption during inference on edge devices, and scalability testing on full-length scripts versus script excerpts are not documented. Comparative analysis with larger transformer models (BERT) on computational constraints is absent.

• Understanding the Dynamics of Trust and Engagement in E-Commerce Recommender Systems: Trends and Influences (2026) · doi

  Quantum computing applications using Quantum Approximate Optimization Algorithm (QAOA) for product recommendation optimization during high-pressure scenarios like flash sales are proposed but completely untested. Empirical validation is needed to demonstrate whether quantum optimization can actually outperform classical algorithms for large-scale e-commerce recommendation problems and handle real-time constraints.

• A Review on Daylighting Prediction by Using Artificial Neural Network Techniques (2026) · doi

  Most ANN daylighting prediction models are trained for specific building geometries and configurations; research on integrating geometric parameters (e.g., window size, overhang depth, room dimensions) into generalizable models that can transfer across new buildings with different geometric constraints remains insufficient.

• A general framework for Gaussian Splatting-based human-centric volumetric videos (2026) · doi

  The frame-by-frame independent Gaussian point cloud representation for dynamic volumetric videos ignores extensive geometric and appearance redundancy between frames, resulting in storage and transmission costs that grow linearly with sequence length, making application to long sequences or resource-constrained mobile/XR scenarios impractical without novel cross-frame correspondence mechanisms.

• Adaptive distribution network reconfiguration with renewable energy and EV integration using reverse-multiverse learning archimedes algorithm (2026) · doi

  The RMLAA algorithm was validated only on IEEE 33-bus and 69-bus test systems; validation on larger-scale distribution networks (>100 buses) with multiple microgrids and higher penetration levels of renewable energy sources and EV charging stations is needed to assess scalability and real-world applicability.

• Smart Prediction of Weather-Induced Flight Delays Applying Deep Learning (2026) · doi

  The system is deployed locally with SQLite and Flask but lacks cloud scalability testing. Deployment on AWS or Azure infrastructure with containerization (Docker/Kubernetes) should be evaluated to assess performance of the hybrid XGBoost-ANN model under high-throughput real-time flight delay prediction workloads.

• Deep Learning Based Fish Species and Freshness Detection Using Convolutional Neural Networks (2026) · doi

  The paper does not specify the computational requirements, inference latency, or energy consumption of the MobileNet model when deployed on Raspberry Pi hardware; real-time performance metrics for on-device deep learning inference in embedded systems need quantification.

• Cleansera: A Context-Aware, Algorithm-Centric Data Cleaning System with RAG-Enhanced Intelligence (2026) · doi

  Cleansera's cleaning pipeline includes seven sequential stages (Schema Validation, Duplicate Detection, Missing Value Treatment, Format Standardization, Outlier Handling, Semantic Validation, Quality Checkpoint), but the paper provides no empirical performance benchmarks or scalability analysis on datasets varying in size (from thousands to millions of records) or complexity (number of columns, data types, missing value percentages).

• Unified URL and QR Based Phishing Detection Framework (2026) · doi

  The system demonstrated 100+ hours continuous stability without crashes, but no evaluation of performance degradation under high-volume concurrent requests (e.g., scanning 1000+ URLs/QR codes simultaneously) or with emerging phishing techniques post-deployment is documented.

• Employee Performance Classification and Monitoring using Machine zearning Models (2026) · doi

  The system's stability was validated only with repeated testing sessions on an unspecified dataset size and employee population; scalability to corporate/educational deployments with hundreds of concurrent users and varying hardware configurations (different webcam quality, network bandwidth) remains untested.

• Real-Time Bank Transaction Fraud Detection Using Kafka and Machine Learning (2026) · doi

  The system's scalability using Kubernetes and Docker containerization for managing multiple Kafka brokers and database instances has been mentioned conceptually but lacks empirical validation; performance benchmarks under varying transaction volume loads and latency constraints are absent.

• A Comparative Analysis of Machine Learning and Deep Learning Approaches to Enhanced Fake News Detection (2026) · doi

  While the paper establishes performance benchmarks for machine learning and deep learning approaches to fake news detection, it does not address how these models should handle the scalability challenge of processing greater volumes of fake news in real-time deployment scenarios across social media platforms and online news sites.

• AI-Powered Resume Screening and Ranking System (2026) · doi

  The system's performance on large-scale applicant pools (beyond the datasets tested) and its computational efficiency with varying resume volumes are not documented. The paper lacks analysis of how processing time, memory usage, and ranking accuracy scale when the system processes thousands of resumes simultaneously for high-volume recruitment scenarios.