Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “human detection”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records

Using artificial intelligence to detect human errors in nuclear power plants: A case in operation and maintenance

Human error (HE) is an important concern in safety-critical systems such as nuclear power plants (NPPs). HE has played a role in many accidents and outage incidents in NPPs. Despite the increased automation in NPPs, HE remains unavoidable. Hence, the need for HE detection is as important as HE prevention efforts. In NPPs, HE is rather rare. Hence, anomaly detection, a widely used machine learning technique for detecting rare anomalous instances, can be repurposed to detect potential HE. In this study, we develop an unsupervised anomaly detection technique based on generative adversarial networks (GANs) to detect anomalies in manually collected surveillance data in NPPs. More specifically, our GAN is trained to detect mismatches between automatically recorded sensor data and manually collected surveillance data, and hence, identify anomalous instances that can be attributed to HE. We test our GAN on both a real-world dataset and an external dataset obtained from a testbed, and we benchmark our results against state-of-the-art unsupervised anomaly detection algorithms, including one-class support vector machine and isolation forest. Our results show that the proposed GAN provides improved anomaly detection performance. Our study is promising for the future development of artificial intelligence based HE detection systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Statistical optimization of culture medium to produce recombinant viral protein by Escherichia coli host for diagnostic kit to detect human immunodeficiency virus (HIV) infection

The maximal production of recombinant HIV1 gp41 by E. coli was examined in optimal culture condition and medium compositions. The culture condition such as growth, initial medium pHs, IPTG concentrations, induction times, temperature (0.5 OD, 7.6, 0.75 mM, 4.6 h, 32 °C respectively), and yeast extract (7.51 g/l), tryptone (7.26 g/l), glucose (2.45 g/l), NaCl (20.40 g/l), betaine (10.41 mM) and ampicillin (71.23 μg/ml) was optimized using statistical experimental design and response surface method (RSM). One of the main popular methods to attain high cell density in fed-batch culture is by controlling the nutrient feeding, which is often necessary for high yield in protein (0.63–0.72 mg/l) and cell (1.7–2 g/l) of the desired product in four litter fermentations.

60 APPLIED LIFE SCIENCES↗

Detecting Humanity's Imprint on Rainfall Patterns: An S&TR Preprint

It's the perfect storm. At a time when global demand for water is rising rapidly due to population growth, urbanization, industrial activities, and expanded use of crop irrigation systems, climate change may be altering the timing, location, and amount of rain and snow that fall on large swaths of the planet. Computational models indicate that increases in global surface temperatures will redistribute rainfall in two ways. First, warmer air, which holds more water vapor, will intensify existing precipitation and drought conditions. That is, more rain will fall in wet areas, and evaporation will increase in drier areas. Second, shifts in atmospheric circulation patterns will push storm paths and subtropical dry zones toward the poles. Worldwide changes to rainfall patterns could magnify existing problems with water scarcity, food shortage, and possibly even political instabilities, thereby transforming an environmental concern into a global security issue. Confirming that the predicted changes are occurring and determining whether human-induced (anthropogenic) forces, such as greenhouse-gas emissions and ozone depletion, or naturally occurring fluctuations are causing the pattern shifts may help policy makers develop strategies for mitigating or adapting to the changes. However, extracting this information from global precipitation data can be challenging.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Integrating Symbolic and Statistical Methods for Testing Intelligent Systems Applications to Machine Learning and Computer Vision

Embedded intelligent systems ranging from tiny im- plantable biomedical devices to large swarms of autonomous un- manned aerial systems are becoming pervasive in our daily lives. While we depend on the flawless functioning of such intelligent systems, and often take their behavioral correctness and safety for granted, it is notoriously difficult to generate test cases that expose subtle errors in the implementations of machine learning algorithms. Hence, the validation of intelligent systems is usually achieved by studying their behavior on representative data sets, using methods such as cross-validation and bootstrapping.In this paper, we present a new testing methodology for studying the correctness of intelligent systems. Our approach uses symbolic decision procedures coupled with statistical hypothesis testing to. We also use our algorithm to analyze the robustness of a human detection algorithm built using the OpenCV open-source computer vision library. We show that the human detection implementation can fail to detect humans in perturbed video frames even when the perturbations are so small that the corresponding frames look identical to the naked eye.

Jha, Sumit Kumar↗

Conducting polymer functionalized single-walled carbon nanotube based chemiresistive biosensor for the detection of human cardiac myoglobin

We report the fabrication of a single-walled carbon nanotube (SWNT) based ultrasensitive label-free chemiresistive biosensor for the detection of human cardiac biomarker, myoglobin (Ag-cMb). Poly(pyrrole-co-pyrrolepropylic acid) with pendant carboxyl groups was electrochemically deposited on electrophoretically aligned SWNT channel, as a conducting linker, for biomolecular immobilization of highly specific cardiac myoglobin antibody. The device was characterized by scanning electron microscopy, source-drain current-voltage (I-V), and charge-transfer characteristic studies. The device exhibited a linear response with a change in conductance in SWNT channel towards the target, Ag-cMb, over the concentration range of 1.0 to 1000 ng ml{sup −1} with a sensitivity of ∼118% per decade with high specificity.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Statistical Hypothesis Testing using CNN Features for Synthesis of Adversarial Counterexamples to Human and Object Detection Vision Systems

Validating the correctness of human detection vision systems is crucial for safety applications such as pedestrian collision avoidance in autonomous vehicles. The enormous space of possible inputs to such an intelligent system makes it difficult to design test cases for such systems. In this report, we present our tool MAYA that uses an error model derived from a convolutional neural network (CNN) to explore the space of images similar to a given input image, and then tests the correctness of a given human or object detection system on such perturbed images. We demonstrate the capability of our tool on the pre-trained Histogram-of-Oriented-Gradients (HOG) human detection algorithm implemented in the popular OpenCV toolset and the Caffe object detection system pre-trained on the ImageNet benchmark. Our tool may serve as a testing resource for the designers of intelligent human and object detection systems.

97 MATHEMATICS AND COMPUTING↗

Internship Presentation: Reactor System Facility Modification to Detect Compromised Human Machine Interfaces

This study presents a multi-layered Industrial Control System (ICS)/Operational Technology (OT) security architecture aimed at detecting and mitigating compromised Human Machine Interface (HMI) and Instrumentation & Control (I&C) systems within the Flowing Autoclave System (FAS) at Idaho National Laboratory (INL). The approach combines network security solutions, hash-based algorithms, and blockchain technologies to verify system integrity and provide an immutable record of network activity. This integrated three-pronged strategy enhances the detection of system compromises, enabling preemptive action before significant damage occurs.

21 - SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLAN↗

TU-FG-209-11: Validation of a Channelized Hotelling Observer to Optimize Chest Radiography Image Processing for Nodule Detection: A Human Observer Study

Purpose: To validate the use of a Channelized Hotelling Observer (CHO) model for guiding image processing parameter selection and enable improved nodule detection in digital chest radiography. Methods: In a previous study, an anthropomorphic chest phantom was imaged with and without PMMA simulated nodules using a GE Discovery XR656 digital radiography system. The impact of image processing parameters was then explored using a CHO with 10 Laguerre-Gauss channels. In this work, we validate the CHO’s trend in nodule detectability as a function of two processing parameters by conducting a signal-known-exactly, multi-reader-multi-case (MRMC) ROC observer study. Five naive readers scored confidence of nodule visualization in 384 images with 50% nodule prevalence. The image backgrounds were regions-of-interest extracted from 6 normal patient scans, and the digitally inserted simulated nodules were obtained from phantom data in previous work. Each patient image was processed with both a near-optimal and a worst-case parameter combination, as determined by the CHO for nodule detection. The same 192 ROIs were used for each image processing method, with 32 randomly selected lung ROIs per patient image. Finally, the MRMC data was analyzed using the freely available iMRMC software of Gallas et al. Results: The image processing parameters which were optimized for the CHO led to a statistically significant improvement (p=0.049) in human observer AUC from 0.78 to 0.86, relative to the image processing implementation which produced the lowest CHO performance. Conclusion: Differences in user-selectable image processing methods on a commercially available digital radiography system were shown to have a marked impact on performance of human observers in the task of lung nodule detection. Further, the effect of processing on humans was similar to the effect on CHO performance. Future work will expand this study to include a wider range of detection/classification tasks and more observers, including experienced chest radiologists.

60 APPLIED LIFE SCIENCES↗

Single-walled carbon nanotubes based chemiresistive genosensor for label-free detection of human rheumatic heart disease

A specific and ultrasensitive, label free single-walled carbon nanotubes (SWNTs) based chemiresistive genosensor was fabricated for the early detection of Streptococcus pyogenes infection in human causing rheumatic heart disease. The mga gene of S. pyogenes specific 24 mer ssDNA probe was covalently immobilized on SWNT through a molecular bilinker, 1-pyrenemethylamine, using carbodiimide coupling reaction. The sensor was characterized by the current-voltage (I-V) characteristic curve and scanning electron microscopy. The sensing performance of the sensor was studied with respect to changes in conductance in SWNT channel based on hybridization of the target S. pyogenes single stranded genomic DNA (ssG-DNA) to its complementary 24 mer ssDNA probe. The sensor shows negligible response to non-complementary Staphylococcus aureus ssG-DNA, confirming the specificity of the sensor only with S. pyogenes. The genosensor exhibited a linear response to S. pyogenes G-DNA from 1 to1000 ng ml{sup −1} with a limit of detection of 0.16 ng ml{sup −1}.

60 APPLIED LIFE SCIENCES↗

Uncertainty-Aware and Explainable Human Error Detection in the Operation of Nuclear Power Plants

The timely and accurate identification of incidents, such as human factor error, is important to restore nuclear power plants (NPPs) to a stable state. However, the identification of abnormal operating conditions is difficult because of the existence of multiple scenarios. In addition, to implement mitigation actions rapidly after an incident occurs, operators must accurately identify an incident by monitoring the trends of many variables. The mental burden posed by this can increase human error and cause failure in identifying incidents. Failure to identify incidents directly results in erroneous mitigation measures, which are detrimental to NPPs. In this study, we leverage uncertainty-aware models to identify such errors and thereby increase the chances of mitigating them. We use the data collected from a physical test bed. The goal is to identify both certain and accurate models. For this, the two main aspects of focus in this study are explainable artificial intelligence (XAI) and uncertainty quantification (UQ). While XAI elucidates the decision pathway, UQ evaluates decision reliability. Their integration paints a comprehensive picture, signifying that understanding decisions and their confidence should be interlinked. Thus, in this study we leverage UQ measures (e.g. entropy and mutual information) along with Shapley additive explanations to gain insights into the features contributing to both accuracy and uncertainty in error identification. Furthermore, our results show that uncertainty-aware models combined with XAI tools can explain the artificial intelligence–prescribed decisions, with the potential of better explaining errors for the operators.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Real-Time Fine Grained Occupancy Estimation Using Depth Sensors on ARM Embedded Platforms

Occupancy estimation is an important primitive for a wide range of applications including building energy efficiency, safety, and security. In this paper, we explore the potential of using depth sensors to detect, estimate, identify, and track occupants in buildings. While depth sensors have been widely used for human detection and gesture recognition, computer vision algorithms are typically run on a powerful computer like XBOX or Intel R CoreTM i7 processor. In this work, we develop a prototype system called FORK using off-the-shelf components that performs the entire depth data processing on a cheaper and low power ARM processor in real-time. As ARM processors are extremely weak in running computer vision algorithms, FORK is designed to detect humans and track them in a very efficient way by leveraging a novel lightweight model based approach instead of traditional approaches based on histogram of oriented gradients (HOG) features. Unlike other camera based approaches, FORK is much less privacy invasive (even if the sensor is compromised). Based on a complete implementation, real-world deployment, and extensive evaluation at realistic scenarios, we observe that FORK achieves over 99% accuracy in real-time (4-9 FPS) in occupancy estimation.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

In-vitro and in-vivo imaging of MMP activity in cartilage and joint injury

Non-destructive detection of cartilage-degrading activities represents an advance in osteoarthritis (OA) research, with implications in studies of OA pathogenesis, progression, and intervention strategies. Matrix metalloproteinases (MMPs) are principal cartilage degrading enzymes that contribute to OA pathogenesis. MMPSense750 is an in-vivo fluorimetric imaging probe with the potential to continuously and non-invasively trace real-time MMP activities, but its use in OA-related research has not been reported. Our objective is to detect and characterize the early degradation activities shortly after cartilage or joint injury with MMPSense750. We determined the appropriate concentration, assay time, and linear range using various concentrations of recombinant MMPs as standards. We then quantified MMP activity from cartilage explants subjected to either mechanical injury or inflammatory cytokine treatment in-vitro. Finally, we performed in-vivo MMP imaging of a mouse model of post-traumatic OA. Our in-vitro results showed that the optimal assay time was highly dependent on the MMP enzyme. In cartilage explant culture media, mechanical impact or cytokine treatment increased MMP activity. Injured knees of mice showed significantly higher fluorescent signal than uninjured knees. We conclude that MMPSense750 detects human MMP activities and can be used for in-vitro study with cartilage, as well as in-vivo studies of knee injury, and can offering real-time insight into the degradative processes that occurring within the joint before structural changes become evident radiographically. - Highlights: • MMPSense750 is near-infrared fluorescent probe which can detect MMP activity. • MMPSense750 can detect human MMP-3, -9, and -13. • The reaction kinetics with MMPSense750 were different for the three MMPs. • MMPSense750 can visualized real time MMP activity in mouse injured knees. • MMPSense750 is convenient tool to evaluate real-time MMP activity non-invasively.

60 APPLIED LIFE SCIENCES↗

Characterizing Human Performance: Detecting Targets at High False Alarm Rates [Slides]

Analysts develop a “no threat” bias with high false alarms. If only shown alarms for actual attacks, may never actually see an alarm. We see this in the laboratory, but not often studied in applied environments. (TSA is an exception.) In this work, near-operational paradigms are useful, but difficult to construct well. Pilot testing is critical before engaging time-limited professionals. Experimental control is difficult to balance with operational realism. Grounding near-operational experiments in basic research paradigms has both advantages and disadvantages. Despite shortcomings in our second experiment, we now have a platform for experimental investigations into the human element of physical security systems.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Reactor System Facility Modification to Detect Compromised Human Machine Interfaces

This study focuses on a multi-layered Industrial Control System (ICS)/Operational Technology (OT) security architecture to aid in the discovery and mitigation of compromised Human Machine Interface (HMI)/Instrumentation & Control (I&C) based systems for modifying a prototypical reactor condition test facility called the Flowing Autoclave System (FAS) at Idaho National Laboratory (INL). This is achieved through a three-layered combination of network security solutions, hash-based algorithms, and blockchain technologies. Hash algorithms are mathematical functions used to generate a predetermined set of fixed-length values. They are widely used in computer security to verify the integrity of system information and data, both on a local network and the wider internet. Even small amounts of unauthorized system modification will cause the hash algorithm to output a set of characters that deviate significantly from its original value. Assisting secure hash functions, blockchain technology is a secure and distributed technology used to provide an immutable set of records replicated on all devices within a decentralized network. Blockchain offers a cost-effective solution to detect system compromise by providing a traceable breadcrumb trail of all network activity and data modification happening on a system. If both are used in conjunction with network monitoring tools, the integration of this three-pronged approach can become an asset in detecting suspected system compromises before any real damage can occur.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗