Daniel Berleant

Wei Dai, Daniel Berleant

Image quality is important, and can affect overall performance in image processing and computer vision as well as for numerous other reasons. Image quality assessment (IQA) is consequently a vital task in different applications from aerial photography interpretation to object detection to medical image analysis. In previous research, the BRISQUE algorithm and the PSNR algorithm were evaluated with high resolution (atleast 512x384 pixels), but relatively small image sets (no more than 4,744 images). However, scientists have not evaluated IQA algorithms on low resolution (no more than 32x32 pixels), multi-perturbation, big image sets (for example, tleast 60,000 different images not counting their perturbations). This study explores these two IQA algorithms through experimental investigation. We first chose two deep learning image sets, CIFAR-10 and MNIST. Then, we added 68 perturbations that add noise to the images in specific sequences and noise intensities. In addition, we tracked the performance outputs of the two IQA algorithms with singly and multiply noised images. After quantitatively analyzing experimental results, we report the limitations of the two IQAs with these noised CIFAR-10 and MNIST image sets. We also explain three potential root causes for performance degradation. These findings point out weaknesses of the two IQA algorithms. The research results provide guidance to scientists and engineers developing accurate, robust IQA algorithms. All source codes, related image sets, and figures are shared on the website (https://github.com/caperock/imagequality) to support future scientific and industrial projects.

Wei Dai, Daniel Berleant

Accuracies of deep learning (DL) classifiers are often unstable in that they may change significantly when retested on adversarial images, imperfect images, or perturbed images. This paper adds to the fundamental body of work on benchmarking the robustness of DL classifiers on defective images. To measure robust DL classifiers, previous research reported on single-factor corruption. We created comprehensive 69 benchmarking image sets, including a clean set, sets with single factor perturbations, and sets with two-factor perturbation conditions. The state-of-the-art two-factor perturbation includes (a) two digital perturbations (salt & pepper noise and Gaussian noise) applied in both sequences, and (b) one digital perturbation (salt & pepper noise) and a geometric perturbation (rotation) applied in both sequences. Previous research evaluating DL classifiers has often used top-1/top-5 accuracy. We innovate a new two-dimensional, statistical matrix to evaluating robustness of DL classifiers. Also, we introduce a new visualization tool, including minimum accuracy, maximum accuracy, mean accuracies, and coefficient of variation (CV), for benchmarking robustness of DL classifiers. Comparing with single factor corruption, we first report that using two-factor perturbed images improves both robustness and accuracy of DL classifiers. All source codes and related image sets are shared on the Website at http://cslinux.semo.edu/david/data to support future academic research and industry projects.

Venkat Kodali, Daniel Berleant

Understanding visual question answering is going to be crucial for numerous human activities. However, it presents major challenges at the heart of the artificial intelligence endeavor. This paper presents an update on the rapid advancements in visual question answering using images that have occurred in the last couple of years. Tremendous growth in research on improving visual question answering system architecture has been published recently, showing the importance of multimodal architectures. Several points on the benefits of visual question answering are mentioned in the review paper by Manmadhan et al. (2020), on which the present article builds, including subsequent updates in the field.

Venkat Kodali, Daniel Berleant

Superimposed text annotations have been under-investigated, yet are ubiquitous, useful and important, especially in medical images. Medical images also highlight the challenges posed by low resolution, noise and superimposed textual meta-information. Therefor we probed the impact of superimposing text onto medical images on VQA. Our results revealed that this textual meta-information can be added without severely degrading key measures of VQA performance. Our findings are significant because they validate the practice of superimposing text on images, even for medical images subjected to the VQA task using AI techniques. The work helps advance understanding of VQA in general and, in particular, in the domain of healthcare and medicine.

Wei Dai, Daniel Berleant

This paper adds to the fundamental body of work on benchmarking the robustness of deep learning (DL) classifiers. We innovate a new benchmarking methodology to evaluate robustness of DL classifiers. Also, we introduce a new four-quadrant statistical visualization tool, including minimum accuracy, maximum accuracy, mean accuracy, and coefficient of variation, for benchmarking robustness of DL classifiers. To measure robust DL classifiers, we created a comprehensive 69 benchmarking image set, including a clean set, sets with single factor perturbations, and sets with two-factor perturbation conditions. After collecting experimental results, we first report that using two-factor perturbed images improves both robustness and accuracy of DL classifiers. The two-factor perturbation includes (1) two digital perturbations (salt & pepper noise and Gaussian noise) applied in both sequences, and (2) one digital perturbation (salt & pepper noise) and a geometric perturbation (rotation) applied in both sequences. All source codes, related image sets, and preliminary data, figures are shared on a GitHub website to support future academic research and industry projects. The web resources locate at https://github.com/caperock/robustai

Wei Dai, Daniel Berleant

In the context of deep learning research, where model introductions continually occur, the need for effective and efficient evaluation remains paramount. Existing methods often emphasize accuracy metrics, overlooking stability. To address this, the paper introduces the Accuracy-Stability Index (ASI), a quantitative measure incorporating both accuracy and stability for assessing deep learning models. Experimental results demonstrate the application of ASI, and a 3D surface model is presented for visualizing ASI, mean accuracy, and coefficient of variation. This paper addresses the important issue of quantitative benchmarking metrics for deep learning models, providing a new approach for accurately evaluating accuracy and stability of deep learning models. The paper concludes with discussions on potential weaknesses and outlines future research directions.

Peng-Hung Tsai, Daniel Berleant, Richard S. Segall et al.

Quantitative technology forecasting uses quantitative methods to understand and project technological changes. It is a broad field encompassing many different techniques and has been applied to a vast range of technologies. A widely used approach in this field is trend extrapolation. Based on the publications available to us, there has been little or no attempt made to systematically review the empirical evidence on quantitative trend extrapolation techniques. This study attempts to close this gap by conducting a systematic review of technology forecasting literature addressing the application of quantitative trend extrapolation techniques. We identified 25 studies relevant to the objective of this research and classified the techniques used in the studies into different categories, among which growth curves and time series methods were shown to remain popular over the past decade, while newer methods, such as machine learning-based hybrid models, have emerged in recent years. As more effort and evidence are needed to determine if hybrid models are superior to traditional methods, we expect to see a growing trend in the development and application of hybrid models to technology forecasting.

Peng-Hung Tsai, Daniel Berleant

Forecasting technological advancement in complex domains such as space exploration presents significant challenges due to the intricate interaction of technical, economic, and policy-related factors. The field of technology forecasting has long relied on quantitative trend extrapolation techniques, such as growth curves (e.g., Moore's law) and time series models, to project technological progress. To assess the current state of these methods, we conducted an updated systematic literature review (SLR) that incorporates recent advances. This review highlights a growing trend toward machine learning-based hybrid models. Motivated by this review, we developed a forecasting model that combines long short-term memory (LSTM) neural networks with an augmentation of Moore's law to predict spacecraft lifetimes. Operational lifetime is an important engineering characteristic of spacecraft and a potential proxy for technological progress in space exploration. Lifetimes were modeled as depending on launch date and additional predictors. Our modeling analysis introduces a novel advance in the recently introduced Start Time End Time Integration (STETI) approach. STETI addresses a critical right censoring problem known to bias lifetime analyses: the more recent the launch dates, the shorter the lifetimes of the spacecraft that have failed and can thus contribute lifetime data. Longer-lived spacecraft are still operating and therefore do not contribute data. This systematically distorts putative lifetime versus launch date curves by biasing lifetime estimates for recent launch dates downward. STETI mitigates this distortion by interconverting between expressing lifetimes as functions of launch time and modeling them as functions of failure time. The results provide insights relevant to space mission planning and policy decision-making.

Wei Dai, Daniel Berleant

This paper surveys benchmarking principles, machine learning devices including GPUs, FPGAs, and ASICs, and deep learning software frameworks. It also reviews these technologies with respect to benchmarking from the perspectives of a 6-metric approach to frameworks and an 11-metric approach to hardware platforms. Because MLPerf is a benchmark organization working with industry and academia, and offering deep learning benchmarks that evaluate training and inference on deep learning hardware devices, the survey also mentions MLPerf benchmark results, benchmark metrics, datasets, deep learning frameworks and algorithms. We summarize seven benchmarking principles, differential characteristics of mainstream AI devices, and qualitative comparison of deep learning hardware and frameworks.