Diaa Badawi

Diaa Badawi

Auto-generated profile, based on publicly available information

Diaa Badawi

Department of Electrical and Computer Engineering, University of Illinois at Chicago, Chicago, IL, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 May 2020 in Sensors
Verified
Journal Article
Open access
PDF file
HPHongyi Pan
Hongyi Pan
DBDiaa Badawi
Diaa Badawi
Ahmet Enis CetinAhmet Enis Cetin
Ahmet Enis Cetin
In this paper, we propose a deep convolutional neural network for camera based wildfire detection. We train the neural network via transfer learning and use window based analysis strategy to increase the fire detection rate. To achieve computational efficiency, we calculate frequency response of the kernels in convolutional and dense layers and eliminate those filters with low energy impulse response. Moreover, to reduce the storage for edge devices, we compare the convolutional kernels in Fourier domain and discard similar filters using the cosine similarity measure in the frequency domain. We test the performance of the neural network with a variety of wildfire video clips and the pruned system performs as good as the regular network in daytime wild fire detection, and it also works well on some night wild fire video clips.

27 February 2020 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Closed access
DBDiaa Badawi
Diaa Badawi
HPHongyi Pan
Hongyi Pan
SCSinan Cem Cetin
Sinan Cem Cetin
Ahmet Enis CetinAhmet Enis Cetin
Ahmet Enis Cetin
In this article, we present a computationally efficient algorithm to detect Volatile Organic Compounds (VOC) leaking out of components used in chemical processes in petrochemical refineries and chemical plants. A leaking VOC plume from a damaged component appears as a dynamic dark cloud in infrared videos. We describe a two-stage deep neural network structure, taking advantage of both spatial and temporal structure of the dynamic texture regions created by the leaking VOC plume. We first detect moving pixels which are darker then their neighboring pixels. We extract one-dimensional (1-D) signals representing the temporal history of such pixels from video and feed the 1-D signals to a 1-D convolutional neural network. If those pixels are near the edge of a VOC plume, their 1-D temporal signals exhibit high-frequency behavior. The neural network generates high probability estimates for such pixels. If 1-D neural network generates high confidence values, final decision is reached using a deep convolutional neural network (CNN) which processes image frames. The overall structure is computationally efficient because the spatio-temporal CNN does not process all of the image frames of the captured video. Experimental results are presented.

2 April 2021 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
SNShamma Nasrin
Shamma Nasrin
DBDiaa Badawi
Diaa Badawi
Ahmet Enis CetinAhmet Enis Cetin
Ahmet Enis Cetin
WGWilfred Gomes
Wilfred Gomes
ATAmit Ranjan Trivedi
Amit Ranjan Trivedi
We propose a co-design approach for compute-in-memory inference for deep neural networks (DNN). We use multiplication-free function approximators based on l 1 norm along with a co-adapted processing array and compute flow. Using the approach, we overcame many deficiencies in the current art of in-SRAM DNN processing such as the need for digital-to-analog converters (DACs) at each operating SRAM row/column, the need for high precision analog-to-digital converters (ADCs), limited support for multi-bit precision weights, and limited vector-scale parallelism. Our co-adapted implementation seamlessly extends to multi-bit precision weights, it doesn't require DACs, and it easily extends to higher vector-scale parallelism. We also propose an SRAM-immersed successive approximation ADC (SA-ADC), where we exploit the parasitic capacitance of bit lines of SRAM array as a capacitive DAC. Since the dominant area overhead in SA-ADC comes due to its capacitive DAC, by exploiting the intrinsic parasitic of SRAM array, our approach allows low area implementation of within-SRAM SA-ADC. Our 8×62 SRAM macro, which requires a 5-bit ADC, achieves ~105 tera operations per second per Watt (TOPS/W) with 8-bit input/weight processing at 45 nm CMOS. Our 8×30 SRAM macro, which requires a 4-bit ADC, achieves ~84 TOPS/W. SRAM macros that require lower ADC precision are more tolerant of process variability, however, have lower TOPS/W as well. We evaluated the accuracy and performance of our proposed network for MNIST, CIFAR10, and CIFAR100 datasets. We chose a network configuration which adaptively mixes multiplication-free and regular operators. The network configurations utilize the multiplication-free operator for more than 85% operations from the total. The selected configurations are 98.6% accurate for MNIST, 90.2% for CIFAR10, and 66.9% for CIFAR100. Since most of the operations in the considered configurations are based on proposed SRAM macros, our compute-in-memory's efficiency benefits broadly translate to the system-level.

2 September 2022 in IEEE Sensors Journal
Verified
Journal Article
Closed access
DBDiaa Badawi
Diaa Badawi
IBIshaan Bassi
Ishaan Bassi
SOSule Ozev
Sule Ozev
Ahmet Enis CetinAhmet Enis Cetin
Ahmet Enis Cetin
In this article, we address the problem of estimating the location of gas leak sources using sparse unreliable spatio-temporal chemical sensor data. We pose the task of estimating the underlying gas signal and predicting the source location as an inverse problem. For this purpose, we develop a novel deep-learning projection-based framework. We incorporate traditional projection-onto-convex-sets (POCS) iteration in the structure of the deep model to obtain a regularized solution that conforms to our prior knowledge on the spatio-temporal structure of the gas concentration distribution.We use Discrete Cosine Transform (DCT) layers to model the smooth nature of the gas plume signal. In the DCT domain, we project the feature maps onto a low-pass region, whose boundary is determined during training using the backpropagation algorithm. This operation is equivalent to projecting onto a convex set. Furthermore, these projection operations are embedded in the non-linear structure of a convolutional neural network. We address two different types of data: Methane-propane leak from industrial plants and isopropyl alcohol (isopropanol) vapor leak in an indoor environment. Experimental results are presented. Our results show that we can obtain a smooth estimate of the underlying gas signal while obtaining a good source location prediction with high accuracy.

23 September 2022 in IEEE Sensors Letters
Verified
Journal Article
Open access
HPHongyi Pan
Hongyi Pan
DBDiaa Badawi
Diaa Badawi
IBIshaan Bassi
Ishaan Bassi
SOSule Ozev
Sule Ozev
Ahmet Enis CetinAhmet Enis Cetin
Ahmet Enis Cetin
We propose a kernel-PCA-based method to detect anomaly in chemical sensors. We use temporal signals produced by chemical sensors to form vectors to perform the principal component analysis (PCA). We estimate the kernel-covariance matrix of the sensor data and compute the eigenvector corresponding to the largest eigenvalue of the covariance matrix. The anomaly can be detected by comparing the difference between the actual sensor data and the reconstructed data from the dominant eigenvector. In this letter, we introduce a new multiplication-free kernel, which is related to the $\ell _{1}$ -norm for the anomaly detection task. The $\ell _{1}$ -kernel PCA is not only computationally efficient but also energy-efficient because it does not require any actual multiplications during the kernel covariance matrix computation. Our experimental results show that our kernel-PCA method achieves a higher area under curvature score (0.7483) than the baseline regular PCA method (0.7366).

27 May 2021 in IEEE Sensors Journal
Verified
Journal Article
Closed access
DBDiaa Badawi
Diaa Badawi
AAAgamyrat Agambayev
Agamyrat Agambayev
SOSule Ozev
Sule Ozev
Ahmet Enis CetinAhmet Enis Cetin
Ahmet Enis Cetin
In this paper, we propose a computationally efficient deep learning framework to address the issue of sensitivity drift compensation for chemical sensors. The framework estimates the underlying drift signal from sensor measurements by means of a deep neural network with a multiplication-free Hadamard transform based layer. In addition, we propose an additive neural network which can be efficiently implemented in real-time on low-cost processors. The temporal additive neural network structure performs only one multiplication per “convolution” operation. Both the regular network and the additive network can have Hadamard transform based layers that implement orthogonal transforms over feature maps and perform soft-thresholding operations in the transform domain to eliminate noise. We also investigate the use of the Discrete Cosine Transform (DCT) and compare it with the Hadamard transform. We present experimental results demonstrating that the Hadamard transform outperforms the DCT.