We Train AI, Why Not Humans, Too? An Exploration of Human-AI Team Training for Future Workplace Viability
Explore the source record for details and available documents.
SEARCH · Engineering Papers
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.
Explore the source record for details and available documents.
Medical Physicists are frequently involved in shipping radioactive materials or supervising those who do. Current U.S. Department of Transportation Hazardous Material Regulations, 49 CFR Parts 171 - 185, require hazmat employees to have documented training specified in 49 CFR 172 Subpart H. A hazmat employee is defined as an individual who: (1) loads, unloads or handles hazardous material; (2) manufactures, tests, reconditions, repairs, modifies, marks or otherwise represents containers, drums or packagings as qualified for use in the transportation of hazardous materials; (3) prepares hazardous materials for transportation; (4) is responsible for safety of transporting hazardous materials; or (5) operates a vehicle used to transport hazardous materials. Recurrent training is required at least once every three years. (The IATA two year training interval is not applicable and is generally misunderstood.) FAA has escalated inspection and enforcement. Facilities who ship radiopharmaceuticals to other laboratories, return radiopharmaceuticals or radioactive sources to suppliers, or otherwise ship radioactive materials have been cited for failure to provide and document the required training. The interrelationship of transportation regulations, 49 CFR, IATA, ICAO and other transportation regulations, which are frequently misunderstood, will be explained. The course will cover typical shipments by air and highway which are encountered in a medical institution. Items such as fissile materials, highway route controlled quantities, rail shipments, vessel shipments and such will be omitted; although specific questions may be addressed. A major objective of the course is to present the process of shipping radioactive material in a sequential and logical fashion. How radioactive materials for transportation purposes are defined by activity concentrations for exempt materials and activity limits for exempt consignments will be explained. Radioactive material shipments of excepted packages and Type A packages will be emphasized. The program is designed to meet the function specific DOT training requirements for shippers of medical radioactive materials. General awareness training and security awareness training can be obtained from two free DOT training CDs. Safety training and security awareness training is generally satisfied by the training required under the institution’s radioactive material license. For shippers of radioactive Yellow III labeled packages an in-depth written security plan and training are no longer required as of April 8, 2010. In general almost all shippers of medical radioactive material are now not required to have an in-depth security plan. Contents of general awareness training, security awareness training and in-depth security plans will be briefly outlined. It is the hazmat employer’s responsibility to ensure that each hazmat employee is properly trained. No third party can fulfill that requirement. It is the hazmat employer’s responsibility to determine the degree to which this course meets the employer’s requirements, including contents of the course and the examination. Participants will gain sufficient knowledge to prepare hazmat training programs for others in their institutions. A handout will be posted which should be printed out and brought to the course for reference during the presentation. The handout will also satisfy part of the training documentation required by DOT. A feature handout section is a composite table which provides A1, A2, RQ, Exempt Concentration, and Exempt Consignment values in a single table in both Becquerel and Curie units. Course attendance will be certified through the AAPM CEU documentation system. Learning Objectives: Understand the regulatory requirements for shipping radioactive materials. Understand the regulatory requirements for training of hazmat employees. Comprehend how to classify, package, mark, label, document, placard, and transport radioactive materials.
Medical Physicists are frequently involved in shipping radioactive materials or supervising those who do. Current U.S. Department of Transportation Hazardous Material Regulations, 49 CFR Parts 171 - 185, require hazmat employees to have documented training specified in 49 CFR 172 Subpart H. A hazmat employee is defined as an individual who: (1) loads, unloads or handles hazardous material; (2) manufactures, tests, reconditions, repairs, modifies, marks or otherwise represents containers, drums or packagings as qualified for use in the transportation of hazardous materials; (3) prepares hazardous materials for transportation; (4) is responsible for safety of transporting hazardous materials; or (5) operates a vehicle used to transport hazardous materials. Recurrent training is required at least once every three years. (The IATA two-year training interval is not applicable and is generally misunderstood.) FAA has escalated inspection and enforcement. Facilities who ship radiopharmaceuticals to other laboratories, return radiopharmaceuticals or radioactive sources to suppliers, or otherwise ship radioactive materials have been cited for failure to provide and document the required training. The interrelationship of transportation regulations, 49 CFR, IATA, ICAO and other transportation regulations, which are frequently misunderstood, will be explained. The course will cover typical shipments by air and highway which are encountered in a medical institution. Items such as fissile materials, highway route controlled quantities, rail shipments, vessel shipments and such will be omitted; although specific questions may be addressed. A major objective of the course is to present the process of shipping radioactive material in a sequential and logical fashion. How radioactive materials for transportation purposes are defined by activity concentrations for exempt materials and activity limits for exempt consignments will be explained. Radioactive material shipments of excepted packages and Type A packages will be emphasized. The program is designed to meet the function specific DOT training requirements for shippers of medical radioactive materials. General awareness training and security awareness training can be obtained from two free DOT training CDs. Safety training and security awareness training is generally satisfied by the training required under the institution’s radioactive material license. For shippers of radioactive Yellow III labeled packages an in-depth written security plan and training are no longer required as of April 8, 2010. In general almost all shippers of medical radioactive material are now not required to have an in-depth security plan. Contents of general awareness training, security awareness training and in-depth security plans will be briefly outlined. It is the hazmat employer’s responsibility to ensure that each hazmat employee is properly trained. No third party can fulfill that requirement. It is the hazmat employer’s responsibility to determine the degree to which this course meets the employer’s requirements, including contents of the course and the examination. Participants will gain sufficient knowledge to prepare hazmat training programs for others in their institutions. A handout will be posted which should be printed out and brought to the course for reference during the presentation. The handout will also satisfy part of the training documentation required by DOT. A feature handout section is a composite table which provides A1, A2, RQ, Exempt Concentration, and Exempt Consignment values in a single table in both Becquerel and Curie units. Course attendance will be certified through the AAPM CEU documentation system. Learning Objectives: Understand the regulatory requirements for shipping radioactive materials. Understand the regulatory requirements for training of hazmat employees. Comprehend how to classify, package, mark, label, document, placard, and transport radioactive materials.
Trained, qualified, and designated staff at the Canadian Nuclear Safety Commission (CNSC) conduct inspections of licensed nuclear sites as a method of compliance verification. This paper will describe the unique and comprehensive qualification process for CNSC inspectors, known as the Inspector Training and Qualification Program (ITQP). The ITQP includes service-line-specific training that is unique to each inspection group within the CNSC, dependent on the facility/industry type. The training requirements specific to staff in the Wastes and Decommissioning Division and its impact on safety at waste management sites across Canada will be discussed. This paper will specifically identify the importance of CNSC inspector training and detail how the unique training program requirements enable the CNSC to better identify and encourage compliance among nuclear waste and decommissioning sites in Canada. CNSC inspectors are designated under section 29 of the Nuclear Safety and Control Act (NSCA), and the powers of inspectors are outlined in section 32 of the NSCA. Having trained, qualified, and designated inspectors is paramount for both the CNSC and the nuclear industry. For the CNSC, this ensures that staff in the field are aware of potential hazards and how to mitigate such hazards (if applicable), that staff understand the regulatory framework and how to measure compliance against it, and that staff consistently apply CNSC values across the nuclear industry. For the industry, this ensures that staff present at nuclear facilities are knowledgeable and professional, that inspections are conducted in a consistent manner, and that any compliance actions issued are measurable and defendable against the regulatory framework. The CNSC's ITQP incorporates both theoretical (in-class and online) and practical training, and is broken down into six categories: mandatory training for all new employees; core training; service-line-specific training; on-the-job training; CNSC regulations training; and, recommended additional training. This paper will discuss in detail the specific aspects of each of these categories, the importance of each category including the difference between knowledge and skills acquired in theoretical versus hands-on training, and how CNSC staff in designated inspector positions (inspectors-in-training) progress through the program. The complete list of core training and service-line-specific training for inspectors in the Wastes and Decommissioning Division, including re-qualification requirements, will be explored throughout the paper. It is further important that CNSC designated inspectors undergo continuous learning to ensure that their skills remain up to date, as well as to ensure that inspectors requalify at defined intervals to enable the maintenance of the core knowledge and skills with which the determination of the person's qualification was based. The steps involved in this requalification process, as well as the importance of continuous learning and the maintenance of skills and knowledge will be further discussed. (authors)
School inclusion is based on the need to adopt and implement a holistic view of education, training, and human development embodied in the idea of everyone, for everyone. In the context of Physical Education (PE), there are still several constraints to the realization of this universal desideratum. Among these, teacher training and qualification for the inclusion of students with Specific Health Needs (SHNs) stands out. That is, students with physical and mental health problems whose impact is significantly manifested in the learning process. Thus, the objective of this study was to identify the representations of PE teachers about their training to develop inclusive processes with students with SES. Participants in this study were 151 PE teachers from different regions and districts of Portugal (Algarve, Aveiro, Castelo Branco, Lisbon, Porto, and Viseu) who had 23.6 ± 8.1 years of teaching service. Teachers answered an online questionnaire, on the Google Forms platform, with open and closed questions about their education and training to develop inclusive processes in PE. The results indicate two significant dimensions: (1) initial training for teaching inclusive PE and (2) continuous training for inclusion. Regarding initial training, a large majority of the teachers under study, at the end of their initial training, did not have the essential skills to teach PE to students with SES. It was also identified that a large majority reported not having had any contact with students with SES throughout their training process for teaching. It was also recognized that this training was not adjusted to the development of intervention skills with students with SHN. Regarding continuous training, it was identified that attendance at this training increased their skills to teach PE to students with SHN. Workshops/actions/training courses are the main training models adopted. However, it is recognized that the training provided does not respond concretely to their training needs to intervene with students with SHN, since teachers essentially seek to improve intervention in the context of inclusive physical education. We conclude that teacher training for inclusion is not yet fully adjusted to the reality of the inclusive school paradigm. In this sense, in practical terms, the following are suggested: (1) the need for reinforcement in study plans with specific and long-term curricular units; (2) the introduction of real practice components in context; and (3) supervised pedagogical practice in diverse contexts.
The U.S. government has been assisting the Russian Federation (RF) Ministry of Defense (MOD) for many years with nuclear weapons transportation security (NWTS) through the provision of specialized guard escort railcars and cargo railcars with integrated physical security and communication systems, armored transport vehicles, and armored escort vehicles. As a natural continuation of the NWTS program, a partnership has been formed to construct a training center that will provide counterterrorism training to personnel in all branches of the RF MOD. The Abramovo Counterterrorism Training Center (ACTC) is a multinational, multiagency project with funding from Canada, RF and the U.S. Departments of Defense and Energy. ACTC will be a facility where MOD personnel can conduct basic through advanced training in various security measures to protect Category IA material against the threat of terrorist attack. The training will enhance defense-in-depth principles by integrating MOD guard force personnel into the overall physical protection systems and improving their overall response time and neutralization capabilities. The ACTC project includes infrastructure improvements, renovation of existing buildings, construction of new buildings, construction of new training facilities, and provision of training and other equipment. Classroom training will be conducted in a renovated training building. Basic and intermediate training will be conducted on three different security training areas where various obstacles and static training devices will be constructed. The central element of ACTC, where advanced training will be held, is the 'autodrome,' a 3 km road along which various terrorist events can be staged to challenge MOD personnel in realistic and dynamic nuclear weapons transportation scenarios. This paper will address the ACTC project elements and the vision for training development and integrating this training into actual nuclear weapons transportation operations.
Purpose: Precise prediction of respiratory motion is a prerequisite for real-time motion compensation techniques such as beam, dynamic couch, or dynamic multileaf collimator tracking. Collection of tumor motion data to train the prediction model is required for most algorithms. To avoid exposure of patients to additional dose from imaging during this procedure, the feasibility of training a linear respiratory motion prediction model with an external surrogate signal is investigated and its performance benchmarked against training the model with tumor positions directly. Methods: The authors implement a lung tumor motion prediction algorithm based on linear ridge regression that is suitable to overcome system latencies up to about 300 ms. Its performance is investigated on a data set of 91 patient breathing trajectories recorded from fiducial marker tracking during radiotherapy delivery to the lung of ten patients. The expected 3D geometric error is quantified as a function of predictor lookahead time, signal sampling frequency and history vector length. Additionally, adaptive model retraining is evaluated, i.e., repeatedly updating the prediction model after initial training. Training length for this is gradually increased with incoming (internal) data availability. To assess practical feasibility model calculation times as well as various minimum data lengths for retraining are evaluated. Relative performance of model training with external surrogate motion data versus tumor motion data is evaluated. However, an internal–external motion correlation model is not utilized, i.e., prediction is solely driven by internal motion in both cases. Results: Similar prediction performance was achieved for training the model with external surrogate data versus internal (tumor motion) data. Adaptive model retraining can substantially boost performance in the case of external surrogate training while it has little impact for training with internal motion data. A minimum adaptive retraining data length of 8 s and history vector length of 3 s achieve maximal performance. Sampling frequency appears to have little impact on performance confirming previously published work. By using the linear predictor, a relative geometric 3D error reduction of about 50% was achieved (using adaptive retraining, a history vector length of 3 s and with results averaged over all investigated lookahead times and signal sampling frequencies). The absolute mean error could be reduced from (2.0 ± 1.6) mm when using no prediction at all to (0.9 ± 0.8) mm and (1.0 ± 0.9) mm when using the predictor trained with internal tumor motion training data and external surrogate motion training data, respectively (for a typical lookahead time of 250 ms and sampling frequency of 15 Hz). Conclusions: A linear prediction model can reduce latency induced tracking errors by an average of about 50% in real-time image guided radiotherapy systems with system latencies of up to 300 ms. Training a linear model for lung tumor motion prediction with an external surrogate signal alone is feasible and results in similar performance as training with (internal) tumor motion. Particularly for scenarios where motion data are extracted from fluoroscopic imaging with ionizing radiation, this may alleviate the need for additional imaging dose during the collection of model training data.
Plans for the conversion of the Chinese origin miniature neutron source reactors (MNSRs) to low-enriched uranium (LEU), and the return of the high- enriched uranium (HEU) core to China, were initiated in February 2011 when an international MNSR Working Group (WG) was established to coordinate these activities. Based on a Ghana Atomic Energy Commission (GAEC) decision, the MNSR core at the GHARR-1 facility was selected for pilot shipment. Working on the preparation of the HEU MNSR materials’ removal from the GHARR-1 facility as a training tool, a mock-up MNSR vessel was built for operator training. Experiencing the usefulness of the mock-up vessel in operator training in the Ghana case has since been developed further into a full-scale training facility, named the International MNSR Training Center (IMTC), which is now available for training operators from MNSR operating countries. The main objective of this Book is to document the IMTC as a full-scale MNSR training facility in operator training for HEU MNSR core discharge and packaging. The goal is to describe the IMTC in its full complexity — that is: (1) to present the IMTC’s buildings with its internal and outer areas; (2) to provide a full listing of the installed equipment, as well as a functional description, available at the IMTC site; (3) to introduce the training materials, tutorials, and training program; and (4) to present the training sessions and Dry-run demonstration of the recently completed NIRR-1 operator training, with their experiences and lessons-learned included. This Book serves as a kind of user manual for the IMTC, which contains all of the information to launch training courses at the site at any time. The target audience for this Book is the MNSR community, especially MNSR operators and regulators who are facing HEU-LEU core conversion and HEU material transportation, who require operator training to carry out their jobs safely and professionally.
There is a great deal of debate concerning the benefits of working memory (WM) training and whether that training can transfer to other tasks. Although a consistent finding is that WM training programs elicit a short-term near-transfer effect (i.e., improvement in WM skills), results are inconsistent when considering persistence of such improvement and far transfer effects. In this study, we compared three groups of participants: a group that received WM training, a group that received training on how to use a mental imagery memory strategy, and a control group that received no training. Although the WM training group improved on the trained task, their posttraining performance on nontrained WM tasks did not differ from that of the other two groups. In addition, although the imagery training group’s performance on a recognition memory task increased after training, the WM training group’s performance on the task decreased after training. Participants’ descriptions of the strategies they used to remember the studied items indicated that WM training may lead people to adopt memory strategies that are less effective for other types of memory tasks. Our results indicate that WM training may have unintended consequences for other types of memory performance.
A restricted Boltzmann machine (RBM) is a generative model that could be used in effectively balancing a cybersecurity dataset because the synthetic data a RBM generates follows the probability distribution of the training data. RBM training can be performed using contrastive divergence (CD) and quantum annealing (QA). QA-based RBM training is fundamentally different from CD and requires samples from a quantum computer. We present a real-world application that uses a quantum computer. Specifically, we train a RBM using QA for cybersecurity applications. The D-Wave 2000Q has been used to implement QA. RBMs are trained on the ISCX data, which is a benchmark dataset for cybersecurity. For comparison, RBMs are also trained using CD. CD is a commonly used method for RBM training. Our analysis of the ISCX data shows that the dataset is imbalanced. We present two different schemes to balance the training dataset before feeding it to a classifier. The first scheme is based on the undersampling of benign instances. The imbalanced training dataset is divided into five sub-datasets that are trained separately. A majority voting is then performed to get the result. Our results show the majority vote increases the classification accuracy up from 90.24% to 95.68%, in the case of CD. For the case of QA, the classification accuracy increases from 74.14% to 80.04%. In the second scheme, a RBM is used to generate synthetic data to balance the training dataset. We show that both QA and CD-trained RBM can be used to generate useful synthetic data. Balanced training data is used to evaluate several classifiers. Among the classifiers investigated, K-Nearest Neighbor (KNN) and Neural Network (NN) perform better than other classifiers. They both show an accuracy of 93%. Our results show a proof-of-concept that a QA-based RBM can be trained on a 64-bit binary dataset. The illustrative example suggests the possibility to migrate many practical classification problems to QA-based techniques. Further, we show that synthetic data generated from a RBM can be used to balance the original dataset.
The GKTC was created at the Kyiv Institute of Nuclear Research as a result of collaborative efforts between the United States and Ukraine. The GKTC has been designated by the Ukrainian Government to provide the MPC&A training and methodological assistance to nuclear facilities and nuclear specialists. In 2010 the GKTC has conducted the planned assessment of training needs of Ukrainian MPC&A specialists. The objective of this work is to acquire the detailed information about the number of MPC&A specialists and guard personnel, who in the coming years should receive the further advanced training. As a result of the performed training needs evaluation the GKTC has determined that in the coming years a number of new training courses need to be developed. Some training courses are already in the process of development. Also taking into account the specific of activity on the guarding of nuclear facilities, GKTC has begun to develop the specialized training courses for the guarding unit personnel. The evaluation of needs of training of Ukrainian specialists on the physical protection shows that without the technical base of learning is not possible to satisfy the needs of Ukrainian facilities, in particular, the need for further training of specialists who maintains physical protection technical means, provides vulnerability assessment and testing of technical means. To increase the training effectiveness and create the basis for specialized training courses holding the GKTC is now working on the construction of an Interior (non-classified) Physical Protection Training Site. The objective of this site is to simulate the actual conditions of the nuclear facility PP system including the complex of engineering and technical means that will help the GKTC training course participants to consolidate the knowledge and gain the practical skills in the work with PP system engineering and technical means for more effective performance of their official duties. This paper briefly describes the practical efforts applied to the provision of physical protection specialists advanced training in Ukraine and real results on the way to implement such efforts in 2011-2012.
In May 1973 the University of New Mexico conducted the first nationwide criticality safety training and education week-long short course for nuclear criticality safety engineers. Subsequent to that course, the Los Alamos Critical Experiments Facility (LACEF) developed very successful 'hands-on' subcritical and critical training programs for operators, supervisors, and engineering staff. Since the inception of the US Department of Energy (DOE) Nuclear Criticality Technology and Safety Project (NCT&SP) in 1983, the DOE has stimulated contractor facilities and laboratories to collaborate in the furthering of nuclear criticality as a discipline. That effort included the education and training of nuclear criticality safety engineers (NCSEs). In 1985 a textbook was written that established a path toward formalizing education and training for NCSEs. Though the NCT&SP went through a brief hiatus from 1990 to 1992, other DOE-supported programs were evolving to the benefit of NCSE training and education. In 1993 the DOE established a Nuclear Criticality Safety Program (NCSP) and undertook a comprehensive development effort to expand the extant LACEF 'hands-on' course specifically for the education and training of NCSEs. That successful education and training was interrupted in 2006 for the closing of the LACEF and the accompanying movement of materials and critical experiment machines to the Nevada Test Site. Prior to that closing, the Lawrence Livermore National Laboratory (LLNL) was commissioned by the US DOE NCSP to establish an independent hands-on NCSE subcritical education and training course. The course provided an interim transition for the establishment of a reinvigorated and expanded two-week NCSE education and training program in 2011. The 2011 piloted two-week course was coordinated by the Oak Ridge National Laboratory (ORNL) and jointly conducted by the Los Alamos National Laboratory (LANL) classroom education and facility training, the Sandia National Laboratory (SNL) hands-on criticality experiments training, and the US DOE National Criticality Experiment Research Center (NCERC) hands-on criticality experiments training that is jointly supported by LLNL and LANL and located at the Nevada National Security Site (NNSS) This paper provides the description of the bases, content, and conduct of the piloted, and future US DOE NCSP Criticality Safety Engineer Training and Education Project.
Transfer learning is a highly successful approach to train deep neural networks for customized image recognition tasks. Transfer learning leverages deep learning models that are previously trained on massive datasets and re-trains the network for a novel image recognition dataset. Typically, the advantage of transfer learning has been measured in sample efficiency, but instead, we investigate the computational efficiency of transfer learning. A good pre-trained model provides features that can be used as input to a new classifier (usually the top layers of a neural network). We show that if a good pre-trained model is selected, that training a new classifier can be much more computationally efficient than training a deep neural network without transfer learning. The first step in transfer learning is to select a pre-trained model to use as a feed-forward network for generating features. Here this selection process either uses human intuition/convenience or a methodical but computationally intensive validation loop. Instead, we would prefer a method to select the pre-trained model that will produce the best transfer results for the least amount of computation. To this end, we provide a computationally efficient metric for the fit between a pre-trained model and a novel image recognition task. The better the fit, the less computation will be needed to re-train the pre-trained model for the novel task. As machine learning becomes ubiquitous, highly-accurate trained models will proliferate and computationally efficient transfer learning methods will enable rapid development of new image recognition models.
Post-training model compression can reduce the inference costs of deep neural networks, but uncompressed training still consumes enormous hardware resources and energy. To enable low-energy training on edge devices, it is highly desirable to directly train a compact neural network from scratch with a low memory cost. Low-rank tensor decomposition is an effective approach to reduce the memory and computing costs of large neural networks. However, directly training low-rank tensorized neural networks is a very challenging task because it is hard to determine a proper tensor rank a priori, and the tensor rank controls both model complexity and accuracy. Here, this paper presents a novel end-to-end framework for low-rank tensorized training. We first develop a Bayesian model that supports various low-rank tensor formats (e.g., CANDECOMP/PARAFAC, Tucker, tensor-train, and tensor-train matrix) and reduces neural network parameters with automatic rank determination during training. Then we develop a customized Bayesian solver to train large-scale tensorized neural networks. Our training methods shows orders-of-magnitude parameter reduction and little accuracy loss (or even better accuracy) in the experiments. On a very large deep learning recommendation system with over 4.2 ×10 9 model parameters, our method can reduce the parameter number to 1.6 ×10 5 automatically in the training process (i.e., by 2.6 ×10 4 times) while achieving almost the same accuracy. Code is available at https://github.com/colehawkins/bayesian-tensor-rank-determination.
Background: Despite the continued growth of Health Impact Assessment (HIA) in the US, there is little research on HIA capacity-building. A comprehensive study of longer-term training outcomes may reveal opportunities for improving capacity building activities and HIA practice. Methods: We conducted in-depth interviews with HIA trainees in the United States to assess their outcomes and needs. Using a training evaluation framework, we measured outcomes across a spectrum of reaction, learning, behavior and results. Results: From 2006 to 2012, four organizations trained over 2200 people in at least 75 in-person HIA trainings in 29 states. We interviewed 48 trainees, selected both randomly and purposefully. The mean duration between training and interview was 3.4 years. Trainees reported that their training objectives were met, especially when relevant case-studies were used. They established new collaborations at the trainings and maintained them. Training appeared to catalyze more holistic thinking and practice, including a range of HIA-related activities. Many trainees disseminated what they learned and engaged in components of HIA, even without dedicated funding. Going forward, trainees need assistance with quantitative methods, project management, community engagement, framing recommendations, and evaluation. Conclusions: The research revealed opportunities for a range of HIA stakeholders to refine and coordinate training resources, apply a competency framework and leverage complimentary workforce development efforts, and sensitize and build the capacity of communities. - Highlights: • We interviewed HIA trainees in the United States to assess longer-term outcomes. • Training appeared to catalyze a range of beneficial partnerships and activities. • Trainees reported outstanding needs for specific skills and competencies. • There are various opportunities to improve training and capacity-building.
The mission of the United States Department of Energy (DOE) National Nuclear Security Administrations (NNSA's) Global Threat Reduction Initiative (GTRI) is to identify, secure, recover and facilitate the disposition of vulnerable nuclear and high-risk radioactive materials around the world that pose a threat to the United States and the international community. The GTRI's unique mission to reduce and protect vulnerable nuclear and radiological materials located at civilian sites worldwide directly addresses recommendations of the 9/11 Commission1, and is a vital part of the President's National Security Strategy and the Global Initiative. The GTRI Remote Monitoring System (RMS) is a standalone security system that includes radiation and tamper alarms, and CCTV; which can be transmitted securely over the Internet to multiple on-site and off-site locations. Through our experiences during installation of the system at 162 sites, plus feedback received from Alarm Response Training course participants, site input to project teams and analysis of trouble calls; indications were that current system training was lacking and inconsistent. A survey was undertaken to gather information from RMS users across the nation, to evaluate the current level of training and determine what if any improvements needed to be made. Additional questions were focused on the operation of the RMS software. The training survey was initially sent electronically to 245 users at the RMS sites and achieved a 37.6% return rate. Analysis of the resulting data revealed that 34.6% of the respondents had not received training or were unsure if they had, despite the fact that vendor engineers provide training at installation of the system. Any training received was referred to as minimal, and brief, not documented, and nothing in writing. 63.7% of respondents said they were either not at all prepared or only somewhat prepared to use the RMS software required to effectively operate the system. As a result of this analysis, a formal training curriculum will be designed and implemented to include several blended learning delivery options. This training will be piloted at RMS sites; initial training will become a required element of RMS installation and refresher training will be considered for sustainability of operations.
Classification machine learning models require high-quality labeled datasets for training. Among the most useful datasets for photovoltaic array fault detection and diagnosis are module or string current-voltage (IV) curves. Unfortunately, such datasets are rarely collected due to the cost of high fidelity monitoring, and the data that is available is generally not ideal, often consisting of unbalanced classes, noisy data due to environmental conditions, and few samples. In this paper, we propose an alternate approach that utilizes physics-based simulations of string-level IV curves as a fully synthetic training corpus that is independent of the test dataset. In our example, the training corpus consists of baseline (no fault), partial soiling, and cell crack system modes. The training corpus is used to train a 1D convolutional neural network (CNN) for failure classification. The approach is validated by comparing the model’s ability to classify failures detected on a real, measured IV curve testing corpus obtained from laboratory and field experiments. Results obtained using a fully synthetic training dataset achieve identical accuracy to those obtained with use of a measured training dataset. When evaluating the measured data’s test split, a 100% accuracy was found both when using simulations or measured data as the training corpus. When evaluating all of the measured data, a 96% accuracy was found when using a fully synthetic training dataset. The use of physics-based modeling results as a training corpus for failure detection and classification has many advantages for implementation as each PV system is configured differently, and it would be nearly impossible to train using labeled measured data.
This study presents a principled empirical evaluation of image storage systems for training deep neural networks. We employ the Caffe deep learning framework to train neural network models for three different data sets, MNIST, CIFAR-10, and ImageNet. While training the models, we evaluate five different options to retrieve training image data: (1) PNG-formatted image files on local file system; (2) pushing pixel arrays from image files into a single HDF5 file on local file system; (3) in-memory arrays to hold the pixel arrays in Python and C++; (4) loading the training data into LevelDB, a log-structured merge tree based key-value storage; and (5) loading the training data into LMDB, a B+tree based key-value storage. The experimental results quantitatively highlight the disadvantage of using normal image files on local file systems to train deep neural networks and demonstrate reliable performance with key-value storage based storage systems. When training a model on the ImageNet dataset, the image file option was more than 17 times slower than the key-value storage option. Along with measurements on training time, this study provides in-depth analysis on the cause of performance advantages/disadvantages of each back-end to train deep neural networks. We envision the provided measurements and analysis will shed light on the optimal way to architect systems for training neural networks in a scalable manner.