SearcharxivSearch

arXiv subjects

Ishrat Jahan

Publications and source records attributed to Ishrat Jahan.

9 recordsLinked to original sources

An Automated Multimodal Glaucoma Detection Framework Using ViT and a Stacking-Based Ensemble

Glaucoma is a progressive eye disease that can lead to irreversible vision loss if not detected at an early stage. Conventional diagnostic procedures are often time-consuming and rely heavily on expert interpretation, limiting their scalability for large-scale screening. In this study, glaucoma detection is investigated under two evaluation settings: sample-wise, where individual samples are analyzed independently, and patient-wise, where data from each patient are aggregated for final prediction. An automated multimodal framework is proposed that integrates fundus images with clinical data. Under the sample-wise setting, detection is performed using fundus images and clinical features individually, as well as through their multimodal combination. Under the patient-wise setting, predictions are obtained by aggregating multiple fundus image representations with corresponding clinical information for each patient. Deep visual features are extracted using a Vision Transformer (ViT) architecture and classified using classical machine-learning models, with a stacking-based ensemble of the three best-performing classifiers employed to optimize performance. Experiments conducted on the publicly available PAPILA dataset demonstrate strong diagnostic performance, achieving 97.47% accuracy and a 97.50% F1-score for sample-wise multimodal classification, and 98.97% accuracy and F1-score for subject-wise detection. The proposed framework is further deployed as an end-to-end web-based platform to support automated glaucoma screening and clinical decision support.

cs.CV

Alignment-Aware and Reliability-Gated Multimodal Fusion for Unmanned Aerial Vehicle Detection Across Heterogeneous Thermal-Visual Sensors

Reliable unmanned aerial vehicle (UAV) detection is critical for autonomous airspace monitoring but remains challenging when integrating sensor streams that differ substantially in resolution, perspective, and field of view. Conventional fusion methods-such as wavelet-, Laplacian-, and decision-level approaches-often fail to preserve spatial correspondence across modalities and suffer from annotation of inconsistencies, limiting their robustness in real-world settings. This study introduces two fusion strategies, Registration-aware Guided Image Fusion (RGIF) and Reliability-Gated Modality-Attention Fusion (RGMAF), designed to overcome these limitations. RGIF employs Enhanced Correlation Coefficient (ECC)-based affine registration combined with guided filtering to maintain thermal saliency while enhancing structural detail. RGMAF integrates affine and optical-flow registration with a reliability-weighted attention mechanism that adaptively balances thermal contrast and visual sharpness. Experiments were conducted on the Multi-Sensor and Multi-View Fixed-Wing (MMFW)-UAV dataset comprising 147,417 annotated air-to-air frames collected from infrared, wide-angle, and zoom sensors. Among single-modality detectors, YOLOv10x demonstrated the most stable cross-domain performance and was selected as the detection backbone for evaluating fused imagery. RGIF improved the visual baseline by 2.13% mAP@50 (achieving 97.65%), while RGMAF attained the highest recall of 98.64%. These findings show that registration-aware and reliability-adaptive fusion provides a robust framework for integrating heterogeneous modalities, substantially enhancing UAV detection performance in multimodal environments.

cs.CV

Electrical and Thermal Performance Tuning of Spoof Plasmonic Interconnect

This work introduces an electromagnetic metastructure based interconnect design that could address the critical need for electrical bandwidth and heat dissipation in high-speed, chiplet integration. We leverage silicon as the substrate for its superior thermal properties, and to counteract its high dielectric constant that typically causes high mutual capacitance among interconnects, we've engineered a periodically corrugated, compact metallic structure enabling signal propagation via strongly confined spoof surface plasmon polaritons (SSPPs). By placing this engineered metal on a $50$ $μ$m oxide layer atop Si substrate, we achieved a low insertion loss of $0.015$ dB/cm and a $10$ dB reduction in crosstalk noise within $5$ GHz, resulting in a bandwidth $2.5\times$ as high as that of a standard microstriplines of the same footprint. Furthermore, a $5$ ns input pulse showed minimal distortion and a $0.13$ ns/cm propagation delay in our proposed interconnect. Critically, the thin oxide layer minimally impacted the heat dissipation of Si substrate, demonstrating a fourfold reduction in temperature compared to an FR4 substrate. These full-wave simulation-supported findings present a viable pathway for high-density, thermally efficient interconnects in advanced packaging.

physics.optics

Initiation of waves in BZ encapsulated vesicles using light - towards design of computing architectures

A gas free analogue of the Belousov-Zhabotinsky reaction catalysed by ferroin and encapsulated in phospholipid stabilised vesicles is reported. A reaction mixture which exhibits spontaneous oscillation and excitation transfer between vesicles was formulated. By adjusting the reagent concentrations a quiescent state with fewer spontaneous oscillations was achieved. Using relatively low power laser sources of specific wavelengths (green 532nm and blue 405nm) it was shown that waves could be reproducibly initiated within the BZ vesicles. Furthermore, despite the reduced excitability of the system overall the initiated waves exhibited vesicle to vesicle transfer. It was possible to manipulate single vesicles and design simple circuits based on a 2D validation of collision based circuits. Therefore, we conclude that this BZ system exhibits promise for computing applications based on 3D networks of vesicles.

nlin.PS

Sequential Voronoi diagram calculations using simple chemical reactions

In our recent paper [de Lacy Costello et al. 2010] we described the formation of complex tessellations of the plane arising from the various reactions of metal salts with potassium ferricyanide and ferrocyanide loaded gels. In addition to producing colourful tessellations these reactions are naturally computing generalised Voronoi diagrams of the plane. The reactions reported previously were capable of the calculation of three distinct Voronoi diagrams of the plane. As diffusion coupled with a chemical reaction is responsible for the calculation then this is achieved in parallel. Thus an increase in the complexity of the data input does not utilise additional computational resource. Additional benefits of these chemical reactions is that a permanent record of the Voronoi diagram calculation (in the form of precipitate free bisectors) is achieved, so there is no requirement for further processing to extract the calculation results. Previously it was assumed that the permanence of the results was also a potential drawback which limited reusability. This paper presents new data which shows that sequential Voronoi diagram calculations can be performed on the same chemical substrate. This is dependent on the reactivity of the original reagent and the cross reactivity of the secondary reagent with the primary product. We present the results from a number of binary combinations of metal salts on both potassium ferricyanide and potassium ferrocyanide substrates. We observe three distinct mechanisms whereby secondary sequential Voronoi diagrams can be calculated. In most cases the result was two interpenetrating permanent Voronoi diagrams. This is interesting from the perspective of mapping the capability of unconventional computing substrates. But also in the study of natural pattern formation per se.

nlin.PS

Time-dependent wave selection for information processing in excitable media

We demonstrate an improved technique for implementing logic circuits in light-sensitive chemical excitable media. The technique makes use of the constant-speed propagation of waves along defined channels in an excitable medium based on the Belousov-Zhabotinsky reaction, along with the mutual annihilation of colliding waves. What distinguishes this work from previous work in this area is that regions where channels meet at a junction can periodically alternate between permitting the propagation of waves and blocking them. These valve-like areas are used to select waves based on the length of time that it takes waves to propagate from one valve to another. In an experimental implementation, the channels which make up the circuit layout are projected by a digital projector connected to a computer. Excitable channels are projected as dark areas, unexcitable regions as light areas. Valves alternate between dark and light: every valve has the same period and phase, with a 50% duty cycle. This scheme can be used to make logic gates based on combinations of OR and AND-NOT operations, with few geometrical constraints. Because there are few geometrical constraints, compact circuits can be implemented. Experimental results from an implementation of a 4-bit input, 2-bit output integer square root circuit are given. This is the most complex logic circuit that has been implemented in BZ excitable media to date.

nlin.PS

Logical and Arithmetic Circuits in Belousov Zhabotinsky Encapsulated Discs

Excitation waves on a sub-excitable Belousov Zhabotinsky (BZ) substrate can be manipulated by chemical variations in the substrate and by interactions with other waves. Symbolic assignment and interpretation of wave dynamics can be used to perform logical and arithmetic computations. We present chemical analogs of elementary logic and arithmetic circuits created entirely from interconnected arrangements of individual BZ encapsulated cell like discs. Inter-disc wave migration is confined in carefully positioned connecting pores. This connection limits wave expansion and unifies the input-output characteristic of the discs. Circuit designs derived from numeric simulations are optically encoded onto a homogeneous photo-sensitive BZ substrate.

nlin.PS

Towards constructing one-bit binary adder in excitable chemical medium

Light-sensitive modification (ruthenium catalysed) of the Belousov-Zhabotinsky medium exhibits various regimes of excitability depending on the levels of illumination. For certain values of illumination the medium switches to a sub-excitable mode. An asymmetric perturbation of the medium leads to formation of a travelling localized excitation, a wave-fragment which moves along a predetermined trajectory, ideally preserving its shape and velocity. To implement collision-based computing with such wave-fragments we represent values of Boolean variables in presence/absence of a wave-fragment at specific sites of medium. When two wave-fragments collide they either annihilate, or form new wave-fragments. The trajectories of the wave-fragments after the collision represent a result of the computation, e.g. a simple logical gate. Wave-fragments in the sub-excitable medium are famously difficult to control. Therefore, we adopted a hybrid procedure in order to construct collision-based logical gates: we used channels, defined by lower levels illumination to subtly tune the shape of a propagating wave-fragment and allow the wave-fragments to collide at the junctions between channels. Using this methodology we were able to implement both in theoretical models (using the Oregonator) and in experiment two interaction-based logical gates and assemble the gates into a basic one-bit binary adder. We present the first ever experimental approach towards constructing arithmetical circuits in spatially-extended excitable chemical systems.

nlin.PS

Computational Modalities of Belousov-Zhabotinsky Encapsulated Vesicles

We present both simulated and partial empirical evidence for the computational utility of many connected vesicle analogs of an encapsulated non-linear chemical processing medium. By connecting small vesicles containing a solution of sub-excitable Belousov-Zhabotinsky (BZ) reaction, sustained and propagating wave fragments are modulated by both spatial geometry, network connectivity and their interaction with other waves. The processing ability is demonstrated through the creation of simple Boolean logic gates and then by the combination of those gates to create more complex circuits.

nlin.CG