Search for: All records

Real-time object detection is essential for AI-based intelligent traffic management. However, growing complexities of deep learning models for object detection cause increased latency and resource requirements. To tackle the challenge, we introduce a new approach, named AROD (Adaptive Real-Time Object Detection), that infers the pixel motion speed in continuous traffic video frames and skips redundant frames when the pixel velocity is low. Thereby, AROD aims to significantly enhance the efficiency and scalability, sustaining the accuracy of object detection. Our evaluation using real-world traffic videos reveals that our method for pixel velocity inference via lightweight deep learning reduces the RMSE (Root Mean Square Error) by up to two orders of magnitude compared to state-of-the-art approaches. AROD improves the frame processing rate of YOLOv5, SSD, and EfficientDet by approximately 32-61\%, 110-174\%, and 120-213\%, respectively. AROD considerably enhances scalability by supporting real-time object detection for up to three concurrent traffic video streams on a commodity machine. Moreover, AROD demonstrates its generalizability by supporting competitive accuracy in object detection for a separate traffic video that was fully hidden during training. 

Intelligent mobile image sensing powered by deep learning analyzes images captured by cameras from mobile devices, such as smartphones or smartwatches. It supports numerous mobile applications, such as image classification, face recognition, and camera scene detection. Unfortunately, mobile devices often lack the resources necessary for deep learning, leading to increased inference latency and rapid battery consumption. Moreover, the inference accuracy may decline over time due to potential data drift. To address these issues, we introduce a new cost-efficient framework, called Corun, designed to simultaneously handle multiple inference queries and continual model retraining/fine-tuning of a pre-trained model on a single commodity GPU in an edge server to significantly improve the inference throughput, upholding the inference accuracy. The scheduling method of Corun undertakes offline profiling to find the maximum number of concurrent inferences that can be executed along with a retraining job on a single GPU without incurring an out-of-memory error or significantly increasing the latency. Our evaluation verifies the cost-effectiveness of Corun. The inference throughput provided by Corun scales with the number of concurrent inference queries. However, the latency of inference queries and the length of a retraining epoch increase at substantially lower rates. By concurrently processing multiple inference and retraining tasks on one GPU instead of using a separate GPU for each task, Corun could reduce the number of GPUs and cost required to deploy mobile image sensing applications based on deep learning at the edge. 

Abstract Phytophthora cinnamomi, which causes the disease root rot, is an oomycete pathogen that is damaging to woody plants, including many horticulturally important groups, such as Rhododendron. Infecting the root of plants, Phytophthora cinnamomi inhibits water uptake, leading to root damage, wilting, and increased rates of plant mortality. Some observations suggest that P. cinnamomi infection corresponds to changes in leaf coloration, though whether this indicates a plant stress response or plant damage is generally unknown. We used leaf color analysis to test for differences in leaf discoloration between plants inoculated with the pathogen and control plants. We demonstrate a significant link between leaf discoloration in Rhododendron species and Phytophthora cinnamomi inoculation. This method was most useful when mortality was not exceptionally high, and analyzers must consider mortality as well as leaf damage in quantifying effects of the pathogen. Plants with leaf discoloration were 3.3 times more likely to die 2 weeks from our leaf census than plants with no leaf discoloration (P =0.005). This method is particularly inexpensive to implement, making it a valuable alternative to multi-spectral or hyperspectral imaging, especially in contexts such as horticulture and citizen science, where the high speed and low-cost nature of this technique might prove valuable. Species used in this study: root rot disease pathogen (Phytophthora cinnamomi Rands); Rhododendron atlanticum (Ashe) Rehder; Rhododendron brachycarpum D.Don ex G.Don; Rhododendron kiusianum Makino; Rhododendron maximum L.; Rhododendron minus Michx.; Rhododendron calendulaceum (Michx.) Torr.; Rhododendron kaempferi Planch.; Rhododendron keiskei Miq. Chemicals used in this study: Fosal Select Aliette/aluminum phosphite. 

We present ExLi, a tool for automatically generating inline tests, which were recently proposed for statement-level code validation. ExLi is the first tool to support retrofitting inline tests to existing codebases, towards increasing adoption of this type of tests. ExLi first extracts inline tests from unit tests that validate methods that enclose the target statement under test. Then, ExLi uses a coverage-then-mutants based approach to minimize the set of initially generated inline tests, while preserving their fault-detection capability. ExLi works for Java, and we use it to generate inline tests for 645 target statements in 31 open-source projects. ExLi reduces the initially generated 27,415 inline tests to 873. ExLi improves the fault-detection capability of unit test suites from which inline tests are generated: the final set of inline tests kills up to 24.4% more mutants on target statements than developer written and automatically generated unit tests. ExLi is open sourced at https://github.com/EngineeringSoftware/exli and a video demo is available at https://youtu.be/qaEB4qDeds4. 

Fast solution of wave propagation in periodic structures usually relies on simplified approaches, such as analytical methods, transmission line models, scattering matrix approaches, plane wave methods, etc. For complex multi-dimensional problems, computationally intensive direct numerical simulation (DNS) is always needed. This study demonstrates a fast and accurate simulation methodology enabled by a physics-based learning methodology, derived from proper orthogonal decomposition (POD) and Galerkin projection, for periodic quantum nanostructure and photonic crystals. POD is a projection-based method that generates optimal basis functions (or POD modes) via solution data collected from DNSs. This process trains the POD modes to adapt parametric variations of the system and offers the best least squares (LS) fit to the solution using the smallest number of modes. This is very different from other projection approaches, e.g., Fourier, Legendre, Bessel, Airy functions, etc., that adopt assumed basis functions selected for the problem based on the solution form. After generating the optimal POD modes, Galerkin projection of the wave equation onto each of the POD modes is performed to close the model and incorporate physical principles guided by the wave equation. Such a rigorous approach offers efficient simulations with high accuracy and exhibits the extrapolation ability in cases reasonably beyond the training bounds. The POD-Galerkin methodology is applied in this study to predict band structures and wave solutions for 2D periodic quantum-dot and photonic-lattice structures. The plane-wave approach is also included in a periodic quantum-dot structure to illustrate the superior performance of the POD-Galerkin methodology. The POD-Galerkin approach offers a 2-order computing speedup for both nanostructure and optical superlattices, compared to DNS, when solving both the wave solution and band structure. If the band structure is the only concern, a 4-order improvement in computational efficiency can be achieved. Fig. 1(a) shows the optical superlattice in a demonstration, where a unit cell includes 22 discs with diagonally symmetrical refractive indices and the background index n = 1. The POD modes for this case are trained by TE mode electric field data collected from DNSs with variation of diagonally symmetrical refractive indices. The LS error of the predicted electric field wave solution from the POD-Galerkin approach, shown in Fig. 1(b) compared to DNS, is below 1% with just 8 POD modes that offer a more than 4-order reduction in the degrees of freedom, compared to DNS. In addition, an extremely accurate prediction of band structure is illustrated in Fig. 1(c) with a maximum error below 0.1% in the entire Brillouin zone. 

A rigorous physics-informed learning methodology is proposed for predictions of wave solutions and band structures in electronic and optical superlattice structures. The methodology is enabled by proper orthogonal decomposition (POD) and Galerkin projection of the wave equation. The approach solves the wave eigenvalue problem in POD space constituted by a finite set of basis functions (or POD modes). The POD ensures that the generated modes are optimized and tailored to the parametric variations of the system. Galerkin projection however enforces physical principles in the methodology to further enhance the accuracy and efficiency of the developed model. It has been demonstrated that the POD-Galerkin methodology offers an approach with a reduction in degrees of freedom by 4 orders of magnitude, compared to direct numerical simulation (DNS). A computing speedup near 15,000 times over DNS can be achieved with high accuracy for either of the superlattice structures if only the band structure is calculated without the wave solution. If both wave function solution and band structure are needed, a 2-order reduction in computational time can be achieved with a relative least square error (LSE) near 1%. When the training is incomplete or the desired eigenstates are slightly beyond the training bounds, an accurate prediction with an LSE near 1%-2% still can be reached if more POD modes are included. This reveals its remarkable learning ability to reach correct solutions with the guidance of physical principles provided by Galerkin projection. 

An ensemble data-learning approach based on proper orthogonal decomposition (POD) and Galerkin projection (EnPOD-GP) is proposed for thermal simulations of multi-core CPUs to improve training efficiency and the model accuracy for a previously developed global POD-GP method (GPOD-GP). GPOD-GP generates one set of basis functions (or POD modes) to account for thermal behavior in response to variations in dynamic power maps (PMs) in the entire chip, which is computationally intensive to cover possible variations of all power sources. EnPOD-GP however acquires multiple sets of POD modes to significantly improve training efficiency and effectiveness, and its simulation accuracy is independent of any dynamic PM. Compared to finite element simulation, both GPOD-GP and EnPOD-GP offer a computational speedup over 3 orders of magnitude. For a processor with a small number of cores, GPOD-GP provides a more efficient approach. When high accuracy is desired and/or a processor with more cores is involved, EnPOD-GP is more preferable in terms of training effort and simulation accuracy and efficiency. Additionally, the error resulting from EnPOD-GP can be precisely predicted for any random spatiotemporal power excitation. 

Abstract Charge density waves are emergent quantum states that spontaneously reduce crystal symmetry, drive metal-insulator transitions, and precede superconductivity. In low-dimensions, distinct quantum states arise, however, thermal fluctuations and external disorder destroy long-range order. Here we stabilize ordered two-dimensional (2D) charge density waves through endotaxial synthesis of confined monolayers of 1T-TaS₂. Specifically, an ordered incommensurate charge density wave (oIC-CDW) is realized in 2D with dramatically enhanced amplitude and resistivity. By enhancing CDW order, the hexatic nature of charge density waves becomes observable. Upon heating via in-situ TEM, the CDW continuously melts in a reversible hexatic process wherein topological defects form in the charge density wave. From these results, new regimes of the CDW phase diagram for 1T-TaS₂are derived and consistent with the predicted emergence of vestigial quantum order. 

Power modeling is an essential building block for computer systems in support of energy optimization, energy profiling, and energy-aware application development. We introduce VESTA, a novel approach to modeling the power consumption of applications with one key insight: language runtime events are often correlated with a sustained level of power consumption. When compared with the established approach of power modeling based on hardware performance counters (HPCs), VESTA has the benefit of solely requiring application-scoped information and enabling a higher level of explainability, while achieving comparable or even higher precision. Through experiments performed on 37 real-world applications on the Java Virtual Machine (JVM), we find the power model built by VESTA is capable of predicting energy consumption with a mean absolute percentage error of 1.56%, while the monitoring of language runtime events incurs small performance and energy overhead.