arXiv subjects

Ahmet Kaplan

Publications and source records attributed to Ahmet Kaplan.

15 recordsLinked to original sources

arXiv2026

Safety-Gated Autoscaling: A Multi-Layered Defense Architecture for Kubernetes Vertical Resource Optimization

Kubernetes is the standard platform for orchestrating containerized applications, yet resource management remains difficult. To stay safe, engineers over-provision CPU and memory, leaving reserved but unused capacity that is the main source of wasted cost. The built-in Horizontal and Vertical Pod Autoscalers are reactive: they act only after a threshold is crossed, which causes lag, over-provisioning, and can mask software defects by granting a leaking workload more memory. Predictive autoscalers focus on improving forecasting accuracy or run inside proprietary infrastructure, and anomaly detection is used only to alert, never to block a harmful action. The Intelligent Cluster Optimizer is an open-source Kubernetes operator that right-sizes container workloads with safety as a first-class concern. Its central contribution is a five-layer safety pipeline where a memory-leak detector, based on linear regression with R^2 scoring, acts as a blocking gate: if a leak is detected the recommendation is rejected, so the optimizer never hides a bug by enlarging a broken container. The pipeline combines SLA monitoring, a circuit breaker, HPA/PDB conflict detection, and a policy engine, with rollback and dry-run mode for human approval. Recommendations are produced by percentile analysis and Holt-Winters forecasting, balanced through multi-objective Pareto optimization at the per-container level. We validated the system with 1118 automated tests at 80.3% coverage and a live deployment on Google Kubernetes Engine, where right-sizing produced estimated cost savings of 20--40% in what-if projections and the leak gate reached 83% detection accuracy.

cs.DC↗

arXiv2026

A multiverse-consensus pipeline for reproducible feature selection in untargeted LC-MS metabolomics

Background: Untargeted LC-MS metabolomics requires a long chain of preprocessing decisions, each with several equally defensible options. Analysts typically commit to one pipeline and report the resulting feature shortlist. How strongly that shortlist depends on choices that were never varied stays invisible. Results: We adapt multiverse analysis to untargeted metabolomics feature selection. We present an auditable, configuration-driven pipeline that (i) applies a ten-stage quality-control filter cascade in which every feature's fate is logged, and (ii) runs the downstream analysis as a multiverse over four contrasting preprocessing philosophies, each combined with four feature-ranking methods under bootstrap stability selection and label-permutation testing. Only features recurring across paths enter a tiered consensus. On a demonstration dataset of five breast-cancer cell lines (30,370 detected features), the four single pipelines individually returned shortlists of 4-20 features whose pairwise agreement was as low as Jaccard = 0.05. The multiverse consensus retained 15 features (>=2/4 paths), of which one recurred across all four, although two paths (sharing normalization and drift-correction methods) dominate the consensus. A pipeline-wide label-permutation test found no false discoveries in 50 null permutations. Conclusions: Reporting only preprocessing-robust features, with a complete kept/dropped audit trail, converts hidden analytical degrees of freedom into an explicit, inspectable output. We discuss scope and limitations, including single-batch design and the need for independent validation.

cs.LG↗

arXiv2026

Optimization Algorithms for Joint OFDM Waveform Design and RIS Configuration in 6G Networks: From Convex Relaxation to Foundation Models

Joint OFDM-RIS optimization for 6G is a mixed-integer nonlinear programming (MINLP) problem covering sum-rate maximization, energy efficiency, max-min fairness, and peak-to-average power ratio (PAPR)-constrained objectives. Seventy-eight joint OFDM-RIS optimization works published between 2021 and 2026 are surveyed. No standardized benchmark exists, and cross-paper comparisons remain infeasible. This survey classifies these works into four paradigms: (I) model-based convex relaxation, (II) heuristic and metaheuristic search, (III) deep reinforcement and unsupervised learning, and (IV) emerging methods including foundation models (FM), diffusion-based generative AI, and quantum optimization. A literature synthesis of self-reported benchmarks shows that ML-based methods (Paradigm~III) report 95-99\% of model-based spectral efficiency at 10^2-10^4 x faster per-inference runtime (method-pair dependent; literature values are self-reported and exclude ML pre-training cost). A companion tutorial benchmark at N=16, N=64, and N=128 reveals a critical scaling property: GPU-based neural network inference (DDQN, PPO, graph neural network (GNN), unsupervised DL) is N-invariant, with identical runtime at N=16 and N=128, while iterative solvers (AO+SCA, PSO) scale polynomially. Energy efficiency (P2) and PAPR-constrained (P4) benchmarks are deferred to future work with standardized power models and waveform generators. Six open challenges emerge from the synthesis: the cross-paradigm benchmark deficit, real-world hardware-constrained deployment, joint waveform-RIS optimization for doubly-dispersive channels, multi-objective PAPR trade-offs, LLM safety in live network control, and diminishing returns of standalone heuristics. We specify requirements for a standardized benchmark. This study serves as a roadmap for researchers and practitioners working on joint OFDM-RIS optimization in 6G networks.

cs.AI↗

arXiv2026

Patient-Level Elbow Abnormality Detection: Leakage-Aware Evaluation of Learned Preprocessing, Calibration, and Triage-Oriented Operating Points

In this study, we examine learned preprocessing pipelines in the context of triage-oriented orthopedic abnormality detection task using elbow radiographs from MURA dataset. The evaluation focuses on patient-level detection of musculoskeletal abnormalities under a leakage-aware protocol. We compare multiple preprocessing pipelines, with and without a lightweight DnCNN module as a learned preprocessing component, to assess their impact on discrimination and calibration. Performance is assessed using discrimination metrics (AUROC, PR-AUC), calibration measures (ECE, Brier score), and validation-selected operating point analysis targeting high specificity. Results show that differences across preprocessing strategies are modest and configuration-dependent, with no consistent discrimination advantage over the raw-input DenseNet121 baseline. The raw and diverse inputs combined with the DnCNN front-end showed reduced ECE and Brier score, while CLAHE combined with DnCNN did not improve calibration. Overall, the results suggest that under patient-level evaluation, preprocessing gains are modest and configuration-dependent; the raw-input DenseNet121 baseline remains competitive throughout, and no tested preprocessing strategy produced a consistent discrimination advantage across all metrics.

cs.CV↗

arXiv2026

GovAI-Pipe: A Layered AI Governance Pipeline for Citizen-Facing AI in Turkey's e-Government Gateway

Turkey's e-Government Gateway (e-Devlet) serves over 68 million registered users with more than 9,200 government services, and is increasingly integrating artificial intelligence into citizen-facing applications such as chatbot assistants and eligibility assessments. However, no structured technical governance infrastructure currently connects high-level AI policy frameworks, such as the EU AI Act, OECD AI Principles, and Turkey's own National AI Strategy, to the operational reality of deploying AI within a centralized e-government platform. We propose GovAI-Pipe, a four-layer governance pipeline designed using Design Science Research methodology that maps the AI model lifecycle to governance checkpoints: (1) pre-deployment validation for bias testing, explainability, and privacy impact assessment; (2) deployment governance for risk-tier classification and approval workflows; (3) runtime monitoring for drift detection, fairness tracking, and human-in-the-loop escalation; and (4) post-incident governance for audit trails, rollback, and citizen redress. Each layer is anchored to specific provisions of the EU AI Act, the GDPR data protection framework, and the National AI Strategy. We demonstrate the framework through two high-risk e-Devlet use cases, showing how GovAI-Pipe operationalizes governance principles as auditable, technical pipeline components.

cs.AI↗

arXiv2026

Experimental Study of Interference Suppression for Backscatter Communication in Distributed MIMO

Bistatic backscatter communication requires strong illumination of a backscatter device (BD), while a spatially separated reader detects the weak modulated reflection. In practice, the resulting direct link interference (DLI) at the reader can dominate the received backscattered signal and limit detection performance. This paper experimentally investigates transmit beamforming that jointly maximizes BD illumination and suppresses DLI at the reader in a distributed multiple-input multiple-output setup. We compare phase-only maximum ratio transmission (PO-MRT) with the proposed direct-link suppression (DLS) scheme, which enforces a spatial null at the reader under per-antenna power constraints. Measurements using a phase-coherent 42-element ceiling array at 920 MHz show that DLS reduces the DLI at the target reader and improves the signal-to-interference ratio by up to 31 dB compared to PO-MRT.

eess.SP↗

arXiv2026

Auto-Unrolled Proximal Gradient Descent: An AutoML Approach to Interpretable Waveform Optimization

This study explores the combination of automated machine learning (AutoML) with model-based deep unfolding (DU) for optimizing wireless beamforming and waveforms. We convert the iterative proximal gradient descent (PGD) algorithm into a deep neural network, wherein the parameters of each layer are learned instead of being predetermined. Additionally, we enhance the architecture by incorporating a hybrid layer that performs a learnable linear gradient transformation prior to the proximal projection. By utilizing AutoGluon with a tree-structured parzen estimator (TPE) for hyperparameter optimization (HPO) across an expanded search space, which includes network depth, step-size initialization, optimizer, learning rate scheduler, layer type, and post-gradient activation, the proposed auto-unrolled PGD (Auto-PGD) achieves 98.8% of the spectral efficiency of a traditional 200-iteration PGD solver using only five unrolled layers, while requiring only 100 training samples. We also address a gradient normalization issue to ensure consistent performance during training and evaluation, and we illustrate per-layer sum-rate logging as a tool for transparency. These contributions highlight a notable reduction in the amount of training data and inference cost required, while maintaining high interpretability compared to conventional black-box architectures.

cs.LG↗

arXiv2026

Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography

Advancements in medical imaging AI, particularly in 3D imaging, have been limited due to the scarcity of comprehensive datasets. We introduce CT-RATE, a public dataset that pairs 3D medical images with corresponding textual reports. CT-RATE comprises 25,692 non-contrast 3D chest CT scans from 21,304 unique patients. Each scan is accompanied by its corresponding radiology report. Leveraging CT-RATE, we develop CT-CLIP, a CT-focused contrastive language-image pretraining framework designed for broad applications without the need for task-specific training. We demonstrate how CT-CLIP can be used in multi-abnormality detection and case retrieval, and outperforms state-of-the-art fully supervised models across all key metrics. By combining CT-CLIP's vision encoder with a pretrained large language model, we create CT-CHAT, a vision-language foundational chat model for 3D chest CT volumes. Finetuned on over 2.7 million question-answer pairs derived from the CT-RATE dataset, CT-CHAT underscores the necessity for specialized methods in 3D medical imaging. Collectively, the open-source release of CT-RATE, CT-CLIP, and CT-CHAT not only addresses critical challenges in 3D medical imaging but also lays the groundwork for future innovations in medical AI and improved patient care.

cs.CV↗

arXiv2025

Joint Access Point Selection and Beamforming Design for Bistatic Backscatter Communication

Future Internet-of-Things networks are envisioned to use small and cheap sensor nodes with extremely low power consumption to avoid the extensive use of batteries. To provide connectivity to a massive number of these nodes, backscatter communication (BC) is emerging as an energy- and cost-efficient technology exploiting the reflection of radio frequency signals. However, challenges such as round-trip path loss and direct link interference (DLI) between the carrier emitter and the reader limit its performance. To tackle these limitations, this paper proposes a joint access point role selection and a novel beamforming technique for bistatic BC in a distributed multiple-input multiple-output setup. The proposed approach boosts the received backscattered energy while effectively mitigating DLI, thereby reducing the error probability. We also propose a channel estimation method tailored to operate under DLI conditions and propose a mismatch detector using estimated channel coefficients. Furthermore, we derive a closed-form expression for the probability of error for the detectors and model the quantization noise caused by DLI. Finally, comprehensive simulation results show that the proposed method with 1-bit analog-to-digital converters (ADCs) effectively mitigates DLI, reduces the quantization noise, and enhances backscattered signal energy, achieving performance comparable to the benchmark scenario with 8-bit ADCs.

eess.SP↗

arXiv2025

Analysis of Broad Beam Beamforming for Collocated and Distributed MIMO

Broad beam beamforming (BF) design in multiple-input multiple-output (MIMO) can be convenient for initial access, synchronization, and sensing capabilities in cellular networks by avoiding overheads of sweeping methods while making efficient use of resources. Phase-only BF is key for maximizing power efficiency across antennas. A successful method to produce broad beams is the phase-only dual-polarization BF (DPBF). However, its efficiency has not been proved in non-line-of-sight (NLoS). Therefore, this paper contributes by evaluating DPBF in collocated and distributed MIMO configurations under both line-of-sight (LoS) and NLoS channel conditions. We model the reflection coefficients for different materials in NLoS conditions and propose the use of orthogonal space-time block code to improve the coverage compared to the DPBF in collocated MIMO (C-MIMO). We further propose a DPBF method for distributed MIMO and show that it achieves better coverage than C-MIMO with DPBF.

eess.SP↗

arXiv2025

Physically Large Apertures for Wireless Power Transfer: Performance and Regulatory Aspects

Wireless power transfer (WPT) is a promising service for the Internet of Things, providing a cost-effective and sustainable solution to deploy so-called energy-neutral devices on a massive scale. The power received at the device side from a conventional transmit antenna with a physically small aperture decays rapidly with the distance. New opportunities arise from the transition from conventional far-field beamforming to near-field beam focusing. We argue that a physically large aperture, i.e., large with respect to the distance to the receiver, enables a power budget that remains practically independent of distance. Distance-dependent array gain patterns allow focusing the power density maximum precisely at the device location, while reducing the power density near the infrastructure. Physical aperture size is a key resource in enabling efficient yet regulatory-compliant WPT. We use real-world measurements to demonstrate that a regulatory-compliant system operating at sub-10GHz frequencies can increase the power received at the device into the milliwatt range. Our empirical demonstration shows that power-optimal near-field beam focusing inherently exploits multipath propagation, yielding both increased WPT efficiency and improved human exposure safety.

eess.SP↗

arXiv2024

Reducing Dynamic Range in Bistatic Backscatter Communication via Beamforming Design

Considering the exponential growth of Internet-of-Things devices and the goals toward sustainable networks, the complexity should be focused on the infrastructure side. For a massive number of passive devices, backscatter communication (BC) is a promising technology that reduces cost and increases energy efficiency by enabling transmitting information by backscattering radio frequency signals. Two main limitations that restrict the performance of BC are the round-trip path loss effect and the direct link interference (DLI) from the carrier emitter (CE). To circumvent this, we propose a novel transmit beamforming design for a multiple antenna bistatic BC (BiBC) system that realizes both purposes: mitigation of the DLI and increasing the power towards the backscatter device (BD). Additionally, we provide a detector design and the performance is evaluated in terms of the probability of error, for which we also provide a closed-form expression. Finally, simulation results show the superiority of the proposed beamforming design in decreasing DLI over a benchmark scenario that considers maximum-ratio transmission.

eess.SP↗

arXiv2024

Access Point Selection for Bistatic Backscatter Communication in Cell-Free MIMO

Backscatter communication (BC) has emerged as a key technology to satisfy the increasing need for low-cost and green Internet-of-Things (IoT) connectivity, especially in large-scale deployments. Unlike the monostatic BC (MoBC), the bistatic BC (BiBC) has the possibility to decrease the round-trip path loss by having the carrier emitter (CE) and the reader in different locations. Therefore, this work investigates the BiBC in the context of cell-free multiple-input multiple-output (MIMO) networks by exploring the optimal selection of CE and reader among all access points, leveraging prior knowledge about the area where the backscatter device (BD) is located. First, a maximum a posteriori probability (MAP) detector to decode the BD information bits is derived. Then, the exact probability of error for this detector is obtained. In addition, an algorithm to select the best CE-reader pair for serving the specified area is proposed. Finally, simulation results show that the error performance of the BC is improved by the proposed algorithm compared to the benchmark scenario.

eess.SP↗

arXiv2023

Dynamic Range Improvement in Bistatic Backscatter Communication Using Distributed MIMO

Backscatter communication (BSC) is a promising solution for Internet-of-Things (IoT) connections due to its low-complexity, low-cost, and energy-efficient solution for sensors. There are several network infrastructure setups that can be used for BSC with IoT nodes/passive devices. One of them is a bistatic setup where there is a need for high dynamic range and high-resolution analog-to-digital converters at the reader side. In this paper, we investigate a bistatic BSC setup with multiple antennas. We propose a novel algorithm to suppress direct link interference between the carrier emitter (CE) and the reader using beamforming into the nullspace of the CE-reader direct link to decrease the dynamic range of the system and increase the detection performance of the backscatter device (BSD). Further, we derive a Neyman-Pearson (NP) test and an exact closed-form expression for its performance in the detection of the BSD. Finally, simulation results show that the dynamic range of the system is significantly decreased and the detection performance of the BSD is increased by the proposed algorithm compared to a system not using beamforming in the CE, which could then be used in a host of different practical fields such as agriculture, transportation, factories, hospitals, smart cities, and smart homes.

eess.SP↗

arXiv2023

Direct Link Interference Suppression for Bistatic Backscatter Communication in Distributed MIMO

Backscatter communication (BC) is a promising technique for future Internet-of-Things (IoT) owing to its low complexity, low cost, and potential for energy-efficient operation in sensor networks. There are several network infrastructure setups that can be used for BC with IoT nodes. One of them is the bistatic setup where typically there is a need for high dynamic range and high-resolution analog-to-digital converters at the reader. In this paper, we investigate a bistatic BC setup with multiple antennas. We propose a novel transmission scheme, which includes a protocol for channel estimation at the carrier emitter (CE) as well as a transmit beamformer construction that suppresses the direct link interference between the two ends of a bistatic link (namely CE and reader), and increases the detection performance of the backscatter device (BD) symbol. Further, we derive a generalized log-likelihood ratio test (GLRT) to detect the symbol/presence of the BD. We also provide an iterative algorithm to estimate the unknown parameters in the GLRT. Finally, simulation results show that the required dynamic range of the system is significantly decreased, and the detection performance of the BD symbol is increased, by the proposed algorithm compared to a system not using beamforming at the CE.

eess.SP↗