arXiv subjects

Ali Shakouri

Publications and source records attributed to Ali Shakouri.

At least 19 recordsLinked to original sources

arXiv2026

Instance camera focus prediction for crystal agglomeration classification

Agglomeration refers to the process of crystal clustering due to interparticle forces. Crystal agglomeration analysis from microscopic images is challenging due to the inherent limitations of two-dimensional imaging. Overlapping crystals may appear connected even when located at different depth layers. Because optical microscopes have a shallow depth of field, crystals that are in-focus and out-of-focus in the same image typically reside on different depth layers and do not constitute true agglomeration. To address this, we first quantified camera focus with an instance camera focus prediction network to predict 2 class focus level that aligns better with visual observations than traditional image processing focus measures. Then an instance segmentation model is combined with the predicted focus level for agglomeration classification. Our proposed method has a higher agglomeration classification and segmentation accuracy than the baseline models on ammonium perchlorate crystal and sugar crystal dataset.

cs.CV↗

arXiv2025

Confidence-aware agglomeration classification and segmentation of 2D microscopic food crystal images

Food crystal agglomeration is a phenomenon occurs during crystallization which traps water between crystals and affects food product quality. Manual annotation of agglomeration in 2D microscopic images is particularly difficult due to the transparency of water bonding and the limited perspective focusing on a single slide of the imaged sample. To address this challenge, we first propose a supervised baseline model to generate segmentation pseudo-labels for the coarsely labeled classification dataset. Next, an instance classification model that simultaneously performs pixel-wise segmentation is trained. Both models are used in the inference stage to combine their respective strengths in classification and segmentation. To preserve crystal properties, a post processing module is designed and included to both steps. Our method improves true positive agglomeration classification accuracy and size distribution predictions compared to other existing methods. Given the variability in confidence levels of manual annotations, our proposed method is evaluated under two confidence levels and successfully classifies potential agglomerated instances.

cs.CV↗

arXiv2025

Empowering Manufacturers with Privacy-Preserving AI Tools: A Case Study in Privacy-Preserving Machine Learning to Solve Real-World Problems

Small- and medium-sized manufacturers need innovative data tools but, because of competition and privacy concerns, often do not want to share their proprietary data with researchers who might be interested in helping. This paper introduces a privacy-preserving platform by which manufacturers may safely share their data with researchers through secure methods, so that those researchers then create innovative tools to solve the manufacturers' real-world problems, and then provide tools that execute solutions back onto the platform for others to use with privacy and confidentiality guarantees. We illustrate this problem through a particular use case which addresses an important problem in the large-scale manufacturing of food crystals, which is that quality control relies on image analysis tools. Previous to our research, food crystals in the images were manually counted, which required substantial and time-consuming human efforts, but we have developed and deployed a crystal analysis tool which makes this process both more rapid and accurate. The tool enables automatic characterization of the crystal size distribution and numbers from microscope images while the natural imperfections from the sample preparation are automatically removed; a machine learning model to count high resolution translucent crystals and agglomeration of crystals was also developed to aid in these efforts. The resulting algorithm was then packaged for real-world use on the factory floor via a web-based app secured through the originating privacy-preserving platform, allowing manufacturers to use it while keeping their proprietary data secure. After demonstrating this full process, future directions are also explored.

cs.CR↗

arXiv2024

Adversarial Domain Adaptation for Metal Cutting Sound Detection: Leveraging Abundant Lab Data for Scarce Industry Data

Cutting state monitoring in the milling process is crucial for improving manufacturing efficiency and tool life. Cutting sound detection using machine learning (ML) models, inspired by experienced machinists, can be employed as a cost-effective and non-intrusive monitoring method in a complex manufacturing environment. However, labeling industry data for training is costly and time-consuming. Moreover, industry data is often scarce. In this study, we propose a novel adversarial domain adaptation (DA) approach to leverage abundant lab data to learn from scarce industry data, both labeled, for training a cutting-sound detection model. Rather than adapting the features from separate domains directly, we project them first into two separate latent spaces that jointly work as the feature space for learning domain-independent representations. We also analyze two different mechanisms for adversarial learning where the discriminator works as an adversary and a critic in separate settings, enabling our model to learn expressive domain-invariant and domain-ingrained features, respectively. We collected cutting sound data from multiple sensors in different locations, prepared datasets from lab and industry domain, and evaluated our learning models on them. Experiments showed that our models outperformed the multi-layer perceptron based vanilla domain adaptation models in labeling tasks on the curated datasets, achieving near 92%, 82% and 85% accuracy respectively for three different sensors installed in industry settings.

cs.LG↗

arXiv2024

Efficient Microscopic Image Instance Segmentation for Food Crystal Quality Control

This paper is directed towards the food crystal quality control area for manufacturing, focusing on efficiently predicting food crystal counts and size distributions. Previously, manufacturers used the manual counting method on microscopic images of food liquid products, which requires substantial human effort and suffers from inconsistency issues. Food crystal segmentation is a challenging problem due to the diverse shapes of crystals and their surrounding hard mimics. To address this challenge, we propose an efficient instance segmentation method based on object detection. Experimental results show that the predicted crystal counting accuracy of our method is comparable with existing segmentation methods, while being five times faster. Based on our experiments, we also define objective criteria for separating hard mimics and food crystals, which could benefit manual annotation tasks on similar dataset.

cs.CV↗

arXiv2024

Enhanced Imaging of Electronic Hot Spots Using Quantum Squeezed Light

Detecting electronic hot spots is important for understanding the heat dissipation and thermal management of electronic and semiconductor devices. Optical thermoreflective imaging is being used to perform precise temporal and spatial imaging of heat on wires and semiconductor materials. We apply quantum squeezed light to perform thermoreflective imaging on micro-wires, surpassing the shot-noise limit of classical approaches. We obtain a far-field temperature sensing accuracy of 42 mK after 50 ms of averaging and show that a $256\times256$ pixel image can be constructed with such sensitivity in 10 minutes. We can further obtain single-shot temperature sensing of 1.6 K after only 10 $\mathrm{\mu s}$ of averaging enabling dynamical study of heat dissipation. Not only do the quantum images provide accurate spatio-temporal information about heat distribution, but the measure of quantum correlation provides additional information, inaccessible by classical techniques, that can lead to a better understanding of the dynamics. We apply the technique to both Al and Nb microwires and discuss the applications of the technique in studying electron dynamics at low temperatures.

quant-ph↗

arXiv2023

An Open Dataset of Sensor Data from Soil Sensors and Weather Stations at Production Farms

Weather and soil conditions are particularly important when it comes to farming activities. Study of these factors and their role in nutrient and nitrate absorption rates can lead to useful insights with benefits for both the crop yield and the protection of the environment through the more controlled use of fertilizers and chemicals. There is a paucity of public data from rural, agricultural sensor networks. This is partly due to the unique challenges faced during the deployment and maintenance of IoT networks in rural agricultural areas. As part of a 5-year project called WHIN we have been deploying and collecting sensor data from production and experimental agricultural farms in and around Purdue University in Indiana. Here we release a dataset comprising soil sensor data from a representative sample of 3 nodes across 3 production farms, each for 5 months. We correlate this data with the weather data and draw some insights about the absorption of rain in the soil. We provide the dataset at: https://purduewhin.ecn.purdue.edu/dataset2021.

cs.CY↗

arXiv2022

A Gate-All-Around Single-Channel In2O3 Nanoribbon FET with Near 20 mA/μm Drain Current

In this work, we demonstrate atomic-layer-deposited (ALD) single-channel indium oxide (In2O3) gate-all-around (GAA) nanoribbon FETs in a back-end-of-line (BEOL) compatible process. A maximum on-state current (ION) of 19.3 mA/μm (near 20 mA/μm) is achieved in an In2O3 GAA nanoribbon FET with a channel thickness (TIO) of 3.1 nm, channel length (Lch) of 40 nm, channel width (Wch) of 30 nm and dielectric HfO2 of 5 nm. The record high drain current obtained from an In2O3 FET is about one order of magnitude higher than any conventional single-channel semiconductor FETs. This extraordinary drain current and its related on-state performance demonstrate ALD In2O3 is a promising oxide semiconductor channel with great opportunities in BEOL compatible monolithic 3D integration.

physics.app-ph↗

arXiv2020

Context-Aware Collaborative-Intelligence with Spatio-Temporal In-Sensor-Analytics in a Large-Area IoT Testbed

Decades of continuous scaling has reduced the energy of unit computing to virtually zero, while energy-efficient communication has remained the primary bottleneck in achieving fully energy-autonomous IoT nodes. This paper presents and analyzes the trade-offs between the energies required for communication and computation in a wireless sensor network, deployed in a mesh architecture over a 2400-acre university campus, and is targeted towards multi-sensor measurement of temperature, humidity and water nitrate concentration for smart agriculture. Several scenarios involving In-Sensor-Analytics (ISA), Collaborative Intelligence (CI) and Context-Aware-Switching (CAS) of the cluster-head during CI has been considered. A real-time co-optimization algorithm has been developed for minimizing the energy consumption in the network, hence maximizing the overall battery lifetime of individual nodes. Measurement results show that the proposed ISA consumes ~467X lower energy as compared to traditional Bluetooth Low Energy (BLE) communication, and ~69,500X lower energy as compared with Long Range (LoRa) communication. When the ISA is implemented in conjunction with LoRa, the lifetime of the node increases from a mere 4.3 hours to 66.6 days with a 230 mAh coin cell battery, while preserving more than 98% of the total information. The CI and CAS algorithms help in extending the worst-case node lifetime by an additional 50%, thereby exhibiting an overall network lifetime of ~104 days, which is >90% of the theoretical limits as posed by the leakage currents present in the system, while effectively transferring information sampled every second. A web-based monitoring system was developed to archive the measured data in a continuous manner, and to report anomalies in the measured data.

cs.NI↗

arXiv2020

Hybrid Low-Power Wide-Area Mesh Network for IoT Applications

The recent advancement of the Internet of Things (IoT) enables the possibility of data collection from diverse environments using IoT devices. However, despite the rapid advancement of low-power communication technologies, the deployment of IoT networks still faces many challenges. In this paper, we propose a hybrid, low-power, wide-area network (LPWAN) structure that can achieve wide-area communication coverage and low power consumption on IoT devices by utilizing both sub-GHz long-range radio and 2.4 GHz short-range radio. Specifically, we constructed a low-power mesh network with LoRa, a physical-layer standard that can provide long-range (kilometers) point-to-point communication using custom time-division multiple access (TDMA). Furthermore, we extended the capabilities of the mesh network by enabling ANT, an ultra-low-power, short-range communication protocol to satisfy data collection in dense device deployments. Third, we demonstrate the performance of the hybrid network with two real-world deployments at the Purdue University campus and at the university-owned farm. The results suggest that both networks have superior advantages in terms of cost, coverage, and power consumption vis-à-vis other IoT solutions, like LoRaWAN.

cs.NI↗

arXiv2019

Relativistic stable processes in quasi-ballistic heat conduction in thin film semiconductors

In this article, we show how relativistic alpha stable processes can be used to explain quasi-ballistic heat conduction in semiconductors. This is a method that can fit experimental results of ultrafast laser heating in alloys. It also provides a connection to a rich literature on Feynman-Kac formalism and random processes that transition from a stable Lévy process on short time and length scales to the Brownian motion at larger scales. This transition was captured by a heuristic truncated Lévy distribution in earlier papers. The rigorous Feynman-Kac approach is used to derive sharp bounds for the transition kernel. Future directions are briefly discussed.

cond-mat.mes-hall↗

arXiv2019

Homogenous $In_{x}Ga_{1-x}N$ alloys on ZnO substrates: A new approach for high performance thermoelectric materials

High performance thermoelectric materials for wide-range temperature applications still remains a challenge. In this study, we have produced high-quality homogeneous $In_{0.32}Ga_{0.68}N$ on ZnO substrates, with no phase separation at high Indium content, using metal organic chemical vapor deposition for thermoelectric applications. A record high room temperature figure of merit zT is obtained of 0.86, which is five times larger than that of SiGe, the current state of the art high temperature thermoelectric material. These materials are shown to have a nearly perfect doping concentration to maximize zT regardless of the scattering mechanism. This almost one order of magnitude increase in zT is due to large electrical conductivities from oxygen co-doping as well as low thermal conductivities from alloy scattering. The maximum power factor reached was $77.98x10^{-4} W/mK^{2}$ at 300K for $In_{0.32}Ga_{0.68}N$ alloys at a carrier concentration $~6.25x10^{20} cm^{-3}$. This work indicates that $In_{x}Ga_{1-x}N$ alloys have great potential for thermoelectric applications especially at a high temperature range.

cond-mat.mtrl-sci↗

arXiv2018

Ultrafast Chemical Imaging by Widefield Photothermal Sensing of Infrared Absorption

Infrared (IR) imaging has become a viable tool for visualizing various chemical bonds in a specimen. The performance, however, is limited in terms of spatial resolution and imaging speed. Here, instead of measuring the loss of the IR beam, we utilize a pulsed visible light for a high-throughput, widefield sensing of the transient photothermal effect induced by absorption of single mid-IR pulses. To extract such transient signals, we built a virtual lock-in camera synchronized to the visible probe and IR light pulses with precisely-controlled delays, allowing sub-microsecond temporal resolution determined by the probe pulse width. Our widefield photothermal sensing (WPS) microscope enabled chemical imaging at a speed up to 1250 frames per second, with high spectral fidelity, and offering sub-micron spatial resolution. With the capability of imaging living cells and nanometer-scale polymer films, WPS microscopy opens a new way for high-throughput characterization of biological and material specimens.

physics.optics↗

arXiv2018

Steep-slope Hysteresis-free Negative Capacitance MoS2 Transistors

The so-called Boltzmann Tyranny defines the fundamental thermionic limit of the subthreshold slope (SS) of a metal-oxide-semiconductor field-effect transistor (MOSFET) at 60 mV/dec at room temperature and, therefore, precludes the lowering of the supply voltage and the overall power consumption. Adding a ferroelectric negative capacitor to the gate stack of a MOSFET may offer a promising solution to bypassing this fundamental barrier. Meanwhile, two-dimensional (2D) semiconductors, such as atomically thin transition metal dichalcogenides (TMDs) due to their low dielectric constant, and ease of integration in a junctionless transistor topology, offer enhanced electrostatic control of the channel. Here, we combine these two advantages and demonstrate for the first time a molybdenum disulfide (MoS2) 2D steep slope transistor with a ferroelectric hafnium zirconium oxide layer (HZO) in the gate dielectric stack. This device exhibits excellent performance in both on- and off-states, with maximum drain current of 510 μA/μm, sub-thermionic subthreshold slope and is essentially hysteresis-free. Negative differential resistance (NDR) was observed at room temperature in the MoS2 negative capacitance field-effect-transistors (NC-FETs) as the result of negative capacitance due to the negative drain-induced-barrier-lowering (DIBL). High on-current induced self-heating effect was also observed and studied.

cond-mat.mes-hall↗

arXiv2017

Thermodynamic Studies of \b{eta}-Ga2O3 Nanomembrane Field-Effect Transistors on a Sapphire Substrate

The self-heating effect is a severe issue for high-power semiconductor devices, which degrades the electron mobility and saturation velocity, and also affects the device reliability. On applying an ultrafast and high-resolution thermoreflectance imaging technique, the direct self-heating effect and surface temperature increase phenomenon are observed on novel top-gate \b{eta}-Ga2O3 on insulator field-effect transistors. Here, we demonstrate that by utilizing a higher thermal conductivity sapphire substrate rather than a SiO2/Si substrate, the temperature rise above room temperature of \b{eta}-Ga2O3 on the insulator field-effect transistor can be reduced by a factor of 3 and thereby the self-heating effect is significantly reduced. Both thermoreflectance characterization and simulation verify that the thermal resistance on the sapphire substrate is less than 1/3 of that on the SiO2/Si substrate. Therefore, maximum drain current density of 535 mA/mm is achieved on the sapphire substrate, which is 70% higher than that on the SiO2/Si substrate due to reduced self-heating. Integration of \b{eta}-Ga2O3 channel on a higher thermal conductivity substrate opens a new route to address the low thermal conductivity issue of \b{eta}-Ga2O3 for power electronics applications.

physics.app-ph↗

arXiv2017

\b{eta}-Ga2O3 on Insulator Field-effect Transistors with Drain Currents Exceeding 1.5 A/mm and Their Self-heating Effect

We have demonstrated that depletion/enhancement-mode b-Ga2O3 on insulator field-effect transistors can achieve a record high drain current density of 1.5/1.0 A/mm by utilizing a highly doped b-Ga2O3 nano-membrane as the channel. b-Ga2O3 on insulator field-effect transistor (GOOI FET) shows a high on/off ratio of 1010 and low subthreshold slope of 150 mV/dec even with 300 nm thick SiO2. The enhancement-mode GOOI FET is achieved through surface depletion. An ultra-fast, high resolution thermo-reflectance imaging technique is applied to study the self-heating effect by directly measuring the local surface temperature. High drain current, low Rc, and wide bandgap make the b-Ga2O3 on insulator field-effect transistor a promising candidate for future power electronics applications.

cond-mat.mes-hall↗

arXiv2016

Limitations of generalised grey phonon models for quasiballistic thermal transport in time-periodic regimes

Suitably superimposed grey-medium solutions of the Boltzmann transport equation (BTE) provide a simple yet accurate description of non-grey quasiballistic heat conduction in transient thermal grating experiments. Recent applications of similar strategies based on kinetic and McKelvey-Schockley-Landauer theory to time-periodic transport predicted notable conductivity suppression only at heating frequencies comparable to phonon scattering rates, in contrast to lengthscale criteria observed by several prior studies. Here we show that the frequency-integrated grey-medium approximation (FIGMA) is ill suited to tackle temporally periodic quasiballistic transport. Starting from first-principles phonon dispersions and scattering rates, we obtain semi-analytic 1D BTE solutions for semi-infinite structures subjected to sinusoidal surface heating and compare these to the approximate model counterparts. We find FIGMA-based approaches to overestimate the semiconductor surface temperature by up to one and characteristic heating frequencies for onset of quasiballistic effects by up to three orders of magnitude respectively. Our study reasserts that experimentally observed heating-frequency dependent apparent conductivities originate in the overlap of the characteristic length scale of the thermal gradient with phonon mean free paths.

cond-mat.mes-hall↗

arXiv2015

Nonlocality in microscale heat conduction

Thermal transport at short length and time scales inherently constitutes a nonlocal relation between heat flux and temperature gradient, but this is rarely addressed explicitly. Here, we present a formalism that enables detailed characterisation of the delocalisation effects in nondiffusive heat flow regimes. A convolution kernel $κ^{\ast}$, which we term the nonlocal thermal conductivity, fully embodies the spatiotemporal memory of the heat flux with respect to the temperature gradient. Under the relaxation time approximation, the Boltzmann transport equation formally obeys the postulated constitutive law and yields a generic expression for $κ^{\ast}$ in terms of the microscopic phonon properties. Subsequent synergy with stochastic frameworks captures the essential transport physics in compact models with easy to understand parameters. A fully analytical solution for $κ^{\ast}(x')$ in tempered Lévy transport with fractal dimension $α$ and diffusive recovery length $x_{\text{R}}$ reveals that nonlocality is physically important over distances $\sqrt{2-α} \,\,x_{\text{R}}$. This is not only relevant to quasiballistic heat conduction in semiconductor alloys but also applies to similar dynamics observed in other disciplines including hydrology and chemistry. We also discuss how the previously introduced effective thermal conductivity $κ_{\text{eff}}$ inferred phenomenologically by transient thermal grating and time domain thermoreflectance measurements relates to $κ^{\ast}$. Whereas effective conductivities depend on the experimental conditions, the nonlocal thermal conductivity forms an intrinsic material property. Experimental results indicate nonlocality lengths of 400$\,$nm in Si membranes and $\simeq 1\,μ$m in InGaAs and SiGe, in good agreement with typical median phonon mean free paths.

cond-mat.mes-hall↗