Arslan, Adem; Gül, Fatih

Background – Early identification of neurodevelopmental conditions during the pre-school years (ages 3–6) is critical for timely intervention, yet traditional questionnaire-based screeners suffer from low positive predictive value, late detection, and inequitable access. Artificial intelligence (AI) and machine-learning (ML) methods promise more objective, scalable identification, and two devices (Cognoa Canvas Dx, 2021; EarliPoint Evaluation, 2023) are already US Food and Drug Administration (FDA)-authorized. Recent reviews summarize the technical literature, but few address how deployed tools perform on clinical validity, equity, and real-world implementation, particularly outside high-income, English-speaking settings. Methods – Following Joanna Briggs Institute methodology and the PRISMA extension for scoping reviews (PRISMA-ScR), we searched seven databases (1 January 2020–15 June 2026) and charted primary validation studies of AI/ML developmental-screening tools for children aged 72 months or younger. We mapped tools by modality, diagnostic performance, regulatory status, geographic origin, and, as a structured analytic axis, demographic subgroup (equity) reporting and deployment readiness. Results – Sixteen primary AI-tool studies met inclusion, spanning eight modality classes (eye-tracking, multimodal questionnaire-plus-video, computer-vision home/clinical video, tablet/smartphone digital phenotyping, voice/acoustic ML, electronic-health-record risk prediction, questionnaire-based ML, and wearable sensors) and eight countries (USA, South Korea, Australia, Switzerland, France, Israel, China, Vietnam). Reported sensitivities ranged from approximately 75 to 99.2% and specificities from 78.9 to 95.5%. Only one tool demonstrated stable performance across sex, race, and ethnicity; subgroup-stratified validation was otherwise near-absent. No CE-marked autism-specific screening device was identified. Conclusions – The evidence base has broadened in modality and geography but remains autism-concentrated and equity-blind, with a wide gap between analytic accuracy and primary-care deployment. We propose equity validation, deployment-readiness reporting, and an implementation pathway for low-resource guidance-center settings as priorities.

Gökgöz, Baki; Aydin, Tolga; Gül, Fatih

The traditional Von Neumann computing architecture, which necessitates data transfer between external memory and the processor, incurs significant energy and time costs when running deep learning (DL) and machine learning (ML) architectures. The primary issue with the energy and time efficiency of this architecture stems from the frequent and intensive data transfers between memory and the processor. Therefore, memristive synaptic devices are utilized to overcome this energy and time inefficiency while performing cognitive tasks. The fundamental working principle of memristive devices is to reduce the need for data transfer by combining memory and processing in the same location, thereby significantly decreasing both energy consumption and the time required for operations. However, to achieve the desired level of efficiency in terms of energy and time consumption from neuromorphic systems, the performance of these systems needs to be further improved with respect to accuracy and test error rates for classification applications. Achieving high accuracy performance in such deep learning or machine learning models necessitates optimization processes not only at the hardware level but also at the algorithmic level. In this context, this paper presents a comprehensive examination and comparison of the frequently used SGD and its momentum variants for deep learning and machine learning applications in memristor-based neuromorphic computing systems. The study thoroughly investigates the performance of critical metrics such as the learning properties, energy efficiency, and accuracy rates of the nano-scale titanium dioxide (TiO2) based synaptic device. The experimental results for the MNIST dataset showed AdaDelta 89.48%, AdaGrad 79.00%, Adam 79.13%, AdaMax 79.68%, Momentum 88.55%, Nadam 81.20%, RMSprop 84.91% and SGD 89.47% accuracy. The experimental results for the CIFAR dataset showed AdaDelta 90.51%, AdaGrad 82.08%, Adam 83.10%, AdaMax 81.76%, Momentum 91.25%, Nadam 82.45%, RMSprop 88.11% and SGD 90.21% accuracy. 2024 The Authors. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Gökgöz, Baki; Gül, Fatih; Aydın, Tolga

The prevalence of artificial intelligence applications using artificial neural network architectures for functions such as natural language processing, text prediction, object detection, speech, and image recognition has significantly increased in today's world. The computational functions performed by artificial neural networks in classical applications require intensive and large-scale data movement between memory and processing units. Various software and hardware efforts are being made to perform these operations more efficiently. Despite these efforts, latency in data traffic and the substantial amount of energy consumed in data processing emerge as bottleneck disadvantages of the Von Neumann architecture. To overcome this bottleneck problem, it is necessary to develop hardware units specific to artificial intelligence applications. For this purpose, neuro-inspired computing chips are believed to provide an effective approach by designing and integrating a set of features inspired by neurobiological systems at the hardware level to address the problems arising in artificial intelligence applications. The most notable among these approaches is memristor-based neuromorphic computing systems. Memristors are seen as promising devices for hardware-level improvement in terms of speed and energy because they possess non-volatile memory and exhibit analog behavior. They enable effective storage and processing of synaptic weights, offering solutions for hardware-level development. Taking into account these advantages of memristors, this study examines the research conducted on artificial neural networks and hardware that can directly perform deep learning functions and mimic the biological brain, which is different from classical systems in today's context.

Gül, F.

Memristor-based resistive random access memory (RRAM) devices are very good competitors for next generation non-volatile crossbar memory applications. The sneak paths problem is one of the main constraints in fabricating crossbar memory devices. The one diode-one resistor (1D1R) structure design is effective for suppressing the sneak paths problem. Suitable circuit models are needed to simulate semiconductor structures.Ageneral circuit model for memristor-based one diode-one resistor structures is proposed in this work. The Simulation Program with Integrated Circuit Emphasis (SPICE) environment was used to simulate the designed circuit. Well-known mathematical models such as those of Strukov, Biolek, Joglekar, Prodromakis and Zha were used to simulate the memristor component of the circuit. The current-voltage characteristics were obtained for different mathematical models. All results were compatible with the expected characteristics. The best fit characteristics were acquired using the Zha and Strukov models.

Gul, Fatih

A metal-oxide-semiconductor (MOS)-based circuit model that emulates a TiO2 memristor is proposed in this study. First, a TiO2 (10-nm active layer thickness)-based memristor device was fabricated. The structural properties of the device were confirmed via energy dispersive X-ray spectroscopy. The memristive characteristics of the device were resolved by applying a time-dependent voltage. The typical pinched hysteresis memristive loops of the current-voltage curves were obtained. After physical implementation and characterization of the device, a circuit model was implemented using only four MOS transistors to emulate the fabricated TiO2 memristor. In addition to emulating the fabricated memristor, the proposed circuit model is suitable for use in general memristor-based applications. No active element or circuit blocks were used in the circuit to achieve memristive characteristics. The simulation and experimental results are in good agreement; moreover, the circuit is very simple compared to those presented in previous studies in the literature and it was able to emulate the fabricated memristor. All simulations were completed using 180 nm TSMC CMOS process parameters.

Gül, Fatih

Resistive random access memories (RRAMs) are favorable contenders in the race towards future technologies. Moreover, the desirable properties of memristor-based RRAM devices make them very good competitors in this field. The sneak paths problem poses one of the main difficulties in the construction of crossbar memory devices. This problem can be effectively suppressed by applying the 1diode-1resistor (1D1R) design structure. The Schottky diode has many advantages compared to the PN junction diode. The low-power (∼1 µW) ZnO active-layered thin-film (60 nm thick) one Schottky diode-one memristor device fabricated in this study included a top Ag electrode and a bottom Al electrode. The material makeup of the device was confirmed via energy dispersive X-ray spectroscopy (EDAX). The memristive and Schottky diode characteristics of the Ag/ZnO/Al device were resolved by measuring the time-dependent voltage/current. The characteristic pinched hysteresis memristive loops were observed at the first quadrant of the current-voltage plane, whereas the diode curves were seen at the third quadrant. Using the current-voltage curves, the height of the Schottky barrier, ideality factor and threshold voltage of the Schottky diode were found to be 0.68 eV, 3.75 and 0.49 V, respectively. After physical implementation and characterization of the one diode-one memristor device, its anti-crosstalk characteristics were investigated. Taking into account the 10% read margin, the maximum crossbar size was found to be 87.

Babacan, Yunus; Yesil, Abdullah; Gul, Fatih

In this paper, a ZnO-based semiconductor thin film memristor (300 nm in thickness) device is fabricated using metallic top and bottom electrodes by direct-current reactive magnetron sputter. The memristive characteristics of the device were completed by time-dependent current-voltage (I-V-t) measurements, and the typical pinched hysteresis I-V loops of the memristor were observed. This paper is continued with the designing memristor emulator circuit, which has only four MOS transistors. The proposed circuit is suitable both for emulating the fabricated memristor and for using general memristor-based applications. Any circuit blocks such as a multiplier or active element are not used in the circuit to obtain memristive characteristics. All results of the proposed memristor emulator circuit are compatible with general characteristics of the fabricated semiconductor device. The MOSFET-based proposed memristor emulator circuit is laid out in the Analog Design Environment of Cadence Software using 180-nm TSMC CMOS process parameters and its layout area is 366 μm2. So as to show its performance, the dependences of the operating frequency and process corner as well as effects of radical temperature changes have been investigated in the simulation results section.

Gul, Fatih; Babacan, Yunus

A semiconductor memristor device based on a 300-nm ZnO thin film was fabricated by direct-current reactive sputter. The memristive behavior of this device was confirmed by time dependent current–voltage (I-V-t) measurements, and the distinctive pinched hysteresis I-V loops of the memristor were observed. Structural analysis of the ZnO memristor was carried out using both X-ray powder diffraction (XRD) and scanning electron microscopy (SEM). After physical implementation of the memristor, an operational transconductance amplifier (OTA) based memristor circuit was designed to emulate the ZnO-based semiconductor memristor for use in memristor-based circuit applications. All simulations were in good agreement with experimental results. In addition, a comparison of the proposed circuit with other memristor emulators was presented.

Gul, Fatih

A titanium dioxide (TiO2) based memristor device having an active layer thickness of 10 nm was fabricated using radio frequency (RF) reactive sputtering and its resistive switching characteristics and carrier transport mechanisms were investigated. Scanning electron microscopy (SEM) and X-ray photoelectron spectroscopy (XPS) were used to confirm the structural properties of the device. Measurement of the time-dependent current-voltage (I-V-t) was used to characterize resistive switching and memristive behavior. The characteristic pinched hysteresis I-V loops of the memristor were apparent. Bipolar and homogeneous resistive switching characteristics and a forming voltage of 2 V were detected in the device. The retention time exceeded 103 s and the endurance test was reasonably acceptable. In addition, the carrier transport mechanism of the device was revealed. The linear region of the low electric field demonstrated ohmic behavior, whereas the non-linear high electric field region was dominated by a Schottky emission carrier transport mechanism. A Poole-Frenkel emission mechanism acted as a secondary conduction mechanism. It was proposed that the Poole-Frenkel and Schottky emission mechanisms were associated with oxygen vacancies in the TiO2.

Gul, Fatih; Efeoglu, Hasan

In this study, a direct-current reactive sputtered AliZnO/Al-based memristor device was fabricated and its resistive switching (RS) characteristics investigated. The optical and structural properties were confirmed by using UV vis spectrophotometry and x-ray diffraction, respectively. The memristive and resistive switching characteristics were determined using time dependent current voltage (I-V-t) measurements. The typical pinched hysteresis I-V loops of a memristor were observed. In addition, the device showed forming-free, uniform and bipolar RS behavior. The low electric field region exhibited ohmic conduction, while the Schottky emission (SE) was found to be the dominant conduction mechanism in the high electric field region. A weak Poole-Frenkel (PF) emission also appeared. In conclusion, it was suggested that the SE and PF mechanisms were related to the oxygen vacancies in the ZnO. (C) 2016 Elsevier Ltd. All rights reserved.