We develop a Learning Direct Optimization (LiDO) method for the refinement of a latent variable model that describes input image x. Our goal is to explain a single image x with an interpretable 3D computer graphics model having scene graph latent variables z (such as object appearance, camera position). Given a current estimate of z we can render a prediction of the image g(z), which can be compared to the image x. The standard way to proceed is then to measure the error E(x, g(z)) between the two, and use an optimizer to minimize the error. However, it is unknown which error measure E would be most effective for simultaneously addressing issues such as misaligned objects, occlusions, textures, etc. In contrast, the LiDO approach trains a Prediction Network to predict an update directly to correct z, rather than minimizing the error with respect to z. Experiments show that our LiDO method converges rapidly as it does not need to perform a search on the error landscape, produces better solutions than error-based competitors, and is able to handle the mismatch between the data and the fitted scene model. We apply LiDO to a realistic synthetic dataset, and show that the method also transfers to work well with real images.

In this paper, we focus on the task of small-footprint keyword spotting under the far-field scenario. Far-field environments are commonly encountered in real-life speech applications, and it causes serve degradation of performance due to room reverberation and various kinds of noises. Our baseline system is built on the convolutional neural network trained with pooled data of both far-field and close-talking speech. To cope with the distortions, we adopt the multi-task learning scheme with alignment loss to reduce the mismatch between the embedding features learned from different domains of data. Experimental results show that our proposed method maintains the performance on close-talking speech and achieves significant improvement on the far-field test set.

Showing items that do not match search query intent degrades customer experience in e-commerce. These mismatches result from counterfactual biases of the ranking algorithms toward noisy behavioral signals such as clicks and purchases in the search logs. Mitigating the problem requires a large labeled dataset, which is expensive and time-consuming to obtain. In this paper, we develop a deep, end-to-end model that learns to effectively classify mismatches and to generate hard mismatched examples to improve the classifier. We train the model end-to-end by introducing a latent variable into the cross-entropy loss that alternates between using the real and generated samples. This not only makes the classifier more robust but also boosts the overall ranking performance. Our model achieves a relative gain compared to baselines by over 26% in F-score, and over 17% in Area Under PR curve. On live search traffic, our model gains significant improvement in multiple countries.

Generative feature matching network (GFMN) is an approach for training implicit generative models for images by performing moment matching on features from pre-trained neural networks. In this paper, we present new GFMN formulations that are effective for sequential data. Our experimental results show the effectiveness of the proposed method, SeqGFMN, for three distinct generation tasks in English: unconditional text generation, class-conditional text generation, and unsupervised text style transfer. SeqGFMN is stable to train and outperforms various adversarial approaches for text generation and text style transfer.

Deep learning-based object detection and instance segmentation have achieved unprecedented progress. In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency. In particular, we consider three geometric factors, i.e., overlap area, normalized central point distance and aspect ratio, which are crucial for measuring bounding box regression in object detection and instance segmentation. The three geometric factors are then incorporated into CIoU loss for better distinguishing difficult regression cases. The training of deep models using CIoU loss results in consistent AP and AR improvements in comparison to widely adopted $ell_n$-norm loss and IoU-based loss. Furthermore, we propose Cluster-NMS, where NMS during inference is done by implicitly clustering detected boxes and usually requires less iterations. Cluster-NMS is very efficient due to its pure GPU implementation, , and geometric factors can be incorporated to improve both AP and AR. In the experiments, CIoU loss and Cluster-NMS have been applied to state-of-the-art instance segmentation (e.g., YOLACT), and object detection (e.g., YOLO v3, SSD and Faster R-CNN) models. Taking YOLACT on MS COCO as an example, our method achieves performance gains as +1.7 AP and +6.2 AR$_{100}$ for object detection, and +0.9 AP and +3.5 AR$_{100}$ for instance segmentation, with 27.1 FPS on one NVIDIA GTX 1080Ti GPU. All the source code and trained models are available at https://github.com/Zzh-tju/CIoU

Unsupervised learning of hidden representations has been one of the most vibrant research directions in machine learning in recent years. In this work we study the brain-like Bayesian Confidence Propagating Neural Network (BCPNN) model, recently extended to extract sparse distributed high-dimensional representations. The saliency and separability of the hidden representations when trained on MNIST dataset is studied using an external classifier, and compared with other unsupervised learning methods that include restricted Boltzmann machines and autoencoders.

Hypertension is a potentially unsafe health ailment, which can be indicated directly from the Blood pressure (BP). Hypertension always leads to other health complications. Continuous monitoring of BP is very important; however, cuff-based BP measurements are discrete and uncomfortable to the user. To address this need, a cuff-less, continuous and a non-invasive BP measurement system is proposed using Photoplethysmogram (PPG) signal and demographic features using machine learning (ML) algorithms. PPG signals were acquired from 219 subjects, which undergo pre-processing and feature extraction steps. Time, frequency and time-frequency domain features were extracted from the PPG and their derivative signals. Feature selection techniques were used to reduce the computational complexity and to decrease the chance of over-fitting the ML algorithms. The features were then used to train and evaluate ML algorithms. The best regression models were selected for Systolic BP (SBP) and Diastolic BP (DBP) estimation individually. Gaussian Process Regression (GPR) along with ReliefF feature selection algorithm outperforms other algorithms in estimating SBP and DBP with a root-mean-square error (RMSE) of 6.74 and 3.59 respectively. This ML model can be implemented in hardware systems to continuously monitor BP and avoid any critical health conditions due to sudden changes.

Reinforcement learning methods have been used to compute dialog policies from language-based interaction experiences. Efficiency is of particular importance in dialog policy learning, because of the considerable cost of interacting with people, and the very poor user experience from low-quality conversations. Aiming at improving the efficiency of dialog policy learning, we develop algorithm LHUA (Learning with Hindsight, User modeling, and Adaptation) that, for the first time, enables dialog agents to adaptively learn with hindsight from both simulated and real users. Simulation and hindsight provide the dialog agent with more experience and more (positive) reinforcements respectively. Experimental results suggest that, in success rate and policy quality, LHUA outperforms competitive baselines from the literature, including its no-simulation, no-adaptation, and no-hindsight counterparts.

Automated person re-identification in a multi-camera surveillance setup is very important for effective tracking and monitoring crowd movement. In the recent years, few deep learning based re-identification approaches have been developed which are quite accurate but time-intensive, and hence not very suitable for practical purposes. In this paper, we propose an efficient hierarchical re-identification approach in which color histogram based comparison is first employed to find the closest matches in the gallery set, and next deep feature based comparison is carried out using Siamese network. Reduction in search space after the first level of matching helps in achieving a fast response time as well as improving the accuracy of prediction by the Siamese network by eliminating vastly dissimilar elements. A silhouette part-based feature extraction scheme is adopted in each level of hierarchy to preserve the relative locations of the different body structures and make the appearance descriptors more discriminating in nature. The proposed approach has been evaluated on five public data sets and also a new data set captured by our team in our laboratory. Results reveal that it outperforms most state-of-the-art approaches in terms of overall accuracy.

Learning-based techniques are increasingly effective at controlling complex systems using data-driven models. However, most work done so far has focused on learning individual tasks or control laws. Hence, it is still a largely unaddressed research question how multiple tasks can be learned efficiently and simultaneously on the same system. In particular, no efficient state space exploration schemes have been designed for multi-task control settings. Using this research gap as our main motivation, we present an algorithm that approximates the smallest data set that needs to be collected in order to achieve high control performance for multiple learning-based control laws. We describe system uncertainty using a probabilistic Gaussian process model, which allows us to quantify the impact of potentially collected data on each learning-based controller. We then determine the optimal measurement locations by solving a stochastic optimization problem approximately. We show that, under reasonable assumptions, the approximate solution converges towards that of the exact problem. Additionally, we provide a numerical illustration of the proposed algorithm.

An important goal in reinforcement learning is to create agents that can quickly adapt to new goals while avoiding situations that might cause damage to themselves or their environments. One way agents learn is through exploration mechanisms, which are needed to discover new policies. However, in deep reinforcement learning, exploration is normally done by injecting noise in the action space. While performing well in many domains, this setup has the inherent risk that the noisy actions performed by the agent lead to unsafe states in the environment. Here we introduce a novel approach called Meta-Learned Instinctual Networks (MLIN) that allows agents to safely learn during their lifetime while avoiding potentially hazardous states. At the core of the approach is a plastic network trained through reinforcement learning and an evolved "instinctual" network, which does not change during the agent's lifetime but can modulate the noisy output of the plastic network. We test our idea on a simple 2D navigation task with no-go zones, in which the agent has to learn to approach new targets during deployment. MLIN outperforms standard meta-trained networks and allows agents to learn to navigate to new targets without colliding with any of the no-go zones. These results suggest that meta-learning augmented with an instinctual network is a promising new approach for safe AI, which may enable progress in this area on a variety of different domains.

Water quality has a direct impact on industry, agriculture, and public health. Algae species are common indicators of water quality. It is because algal communities are sensitive to changes in their habitats, giving valuable knowledge on variations in water quality. However, water quality analysis requires professional inspection of algal detection and classification under microscopes, which is very time-consuming and tedious. In this paper, we propose a novel multi-target deep learning framework for algal detection and classification. Extensive experiments were carried out on a large-scale colored microscopic algal dataset. Experimental results demonstrate that the proposed method leads to the promising performance on algal detection, class identification and genus identification.

Bayesian predictive coding is a putative neuromorphic method for acquiring higher-level neural representations to account for sensory input. Although originating in the neuroscience community, there are also efforts in the machine learning community to study these models. This paper reviews some of the more well known models. Our review analyzes module connectivity and patterns of information transfer, seeking to find general principles used across the models. We also survey some recent attempts to cast these models within a deep learning framework. A defining feature of Bayesian predictive coding is that it uses top-down, reconstructive mechanisms to predict incoming sensory inputs or their lower-level representations. Discrepancies between the predicted and the actual inputs, known as prediction errors, then give rise to future learning that refines and improves the predictive accuracy of learned higher-level representations. Predictive coding models intended to describe computations in the neocortex emerged prior to the development of deep learning and used a communication structure between modules that we name the Rao-Ballard protocol. This protocol was derived from a Bayesian generative model with some rather strong statistical assumptions. The RB protocol provides a rubric to assess the fidelity of deep learning models that claim to implement predictive coding.

Recently, the outbreak of Coronavirus Disease 2019 (COVID-19) has spread rapidly across the world. Due to the large number of affected patients and heavy labor for doctors, computer-aided diagnosis with machine learning algorithm is urgently needed, and could largely reduce the efforts of clinicians and accelerate the diagnosis process. Chest computed tomography (CT) has been recognized as an informative tool for diagnosis of the disease. In this study, we propose to conduct the diagnosis of COVID-19 with a series of features extracted from CT images. To fully explore multiple features describing CT images from different views, a unified latent representation is learned which can completely encode information from different aspects of features and is endowed with promising class structure for separability. Specifically, the completeness is guaranteed with a group of backward neural networks (each for one type of features), while by using class labels the representation is enforced to be compact within COVID-19/community-acquired pneumonia (CAP) and also a large margin is guaranteed between different types of pneumonia. In this way, our model can well avoid overfitting compared to the case of directly projecting highdimensional features into classes. Extensive experimental results show that the proposed method outperforms all comparison methods, and rather stable performances are observed when varying the numbers of training data.

Segmentation is a prerequisite yet challenging task for medical image analysis. In this paper, we introduce a novel deeply supervised active learning approach for finger bones segmentation. The proposed architecture is fine-tuned in an iterative and incremental learning manner. In each step, the deep supervision mechanism guides the learning process of hidden layers and selects samples to be labeled. Extensive experiments demonstrated that our method achieves competitive segmentation results using less labeled samples as compared with full annotation.

Assistive robots enable people with disabilities to conduct everyday tasks on their own. However, these tasks can be complex, containing both coarse reaching motions and fine-grained manipulation. For example, when eating, not only does one need to move to the correct food item, but they must also precisely manipulate the food in different ways (e.g., cutting, stabbing, scooping). Shared autonomy methods make robot teleoperation safer and more precise by arbitrating user inputs with robot controls. However, these works have focused mainly on the high-level task of reaching a goal from a discrete set, while largely ignoring manipulation of objects at that goal. Meanwhile, dimensionality reduction techniques for teleoperation map useful high-dimensional robot actions into an intuitive low-dimensional controller, but it is unclear if these methods can achieve the requisite precision for tasks like eating. Our insight is that---by combining intuitive embeddings from learned latent actions with robotic assistance from shared autonomy---we can enable precise assistive manipulation. In this work, we adopt learned latent actions for shared autonomy by proposing a new model structure that changes the meaning of the human's input based on the robot's confidence of the goal. We show convergence bounds on the robot's distance to the most likely goal, and develop a training procedure to learn a controller that is able to move between goals even in the presence of shared autonomy. We evaluate our method in simulations and an eating user study.

We investigate learnability of possibilistic theories from entailments in light of Angluin's exact learning model. We consider cases in which only membership, only equivalence, and both kinds of queries can be posed by the learner. We then show that, for a large class of problems, polynomial time learnability results for classical logic can be transferred to the respective possibilistic extension. In particular, it follows from our results that the possibilistic extension of propositional Horn theories is exactly learnable in polynomial time. As polynomial time learnability in the exact model is transferable to the classical probably approximately correct model extended with membership queries, our work also establishes such results in this model.

Smart meters enable remote and automatic electricity, water and gas consumption reading and are being widely deployed in developed countries. Nonetheless, there is still a huge number of non-smart meters in operation. Image-based Automatic Meter Reading (AMR) focuses on dealing with this type of meter readings. We estimate that the Energy Company of Paran'a (Copel), in Brazil, performs more than 850,000 readings of dial meters per month. Those meters are the focus of this work. Our main contributions are: (i) a public real-world dial meter dataset (shared upon request) called UFPR-ADMR; (ii) a deep learning-based recognition baseline on the proposed dataset; and (iii) a detailed error analysis of the main issues present in AMR for dial meters. To the best of our knowledge, this is the first work to introduce deep learning approaches to multi-dial meter reading, and perform experiments on unconstrained images. We achieved a 100.0% F1-score on the dial detection stage with both Faster R-CNN and YOLO, while the recognition rates reached 93.6% for dials and 75.25% for meters using Faster R-CNN (ResNext-101).

Narrowband internet-of-things (NB-IoT) is a competitive 5G technology for massive machine-type communication scenarios, but meanwhile introduces narrowband interference (NBI) to existing broadband transmission such as the long term evolution (LTE) systems in enhanced mobile broadband (eMBB) scenarios. In order to facilitate the harmonic and fair coexistence in wireless heterogeneous networks, it is important to eliminate NB-IoT interference to LTE systems. In this paper, a novel sparse machine learning based framework and a sparse combinatorial optimization problem is formulated for accurate NBI recovery, which can be efficiently solved using the proposed iterative sparse learning algorithm called sparse cross-entropy minimization (SCEM). To further improve the recovery accuracy and convergence rate, regularization is introduced to the loss function in the enhanced algorithm called regularized SCEM. Moreover, exploiting the spatial correlation of NBI, the framework is extended to multiple-input multiple-output systems. Simulation results demonstrate that the proposed methods are effective in eliminating NB-IoT interference to LTE systems, and significantly outperform the state-of-the-art methods.

Recently, the Edge Computing paradigm has gained significant popularity both in industry and academia. Researchers now increasingly target to improve performance and reduce energy consumption of such devices. Some recent efforts focus on using emerging RRAM technologies for improving energy efficiency, thanks to their no leakage property and high integration density. As the complexity and dynamism of applications supported by such devices escalate, it has become difficult to maintain ideal performance by static RRAM controllers. Machine Learning provides a promising solution for this, and hence, this work focuses on extending such controllers to allow dynamic parameter updates. In this work we propose an Adaptive RRAM Variability-Aware Controller, AVAC, which periodically updates Wait Buffer and batch sizes using on-the-fly learning models and gradient ascent. AVAC allows Edge devices to adapt to different applications and their stages, to improve computation performance and reduce energy consumption. Simulations demonstrate that the proposed model can provide up to 29% increase in performance and 19% decrease in energy, compared to static controllers, using traces of real-life healthcare applications on a Raspberry-Pi based Edge deployment.

In this paper, we continue our prior work on using imitation learning (IL) and model free reinforcement learning (RL) to learn driving policies for autonomous driving in urban scenarios, by introducing a model based RL method to drive the autonomous vehicle in the Carla urban driving simulator. Although IL and model free RL methods have been proved to be capable of solving lots of challenging tasks, including playing video games, robots, and, in our prior work, urban driving, the low sample efficiency of such methods greatly limits their applications on actual autonomous driving. In this work, we developed a model based RL algorithm of guided policy search (GPS) for urban driving tasks. The algorithm iteratively learns a parameterized dynamic model to approximate the complex and interactive driving task, and optimizes the driving policy under the nonlinear approximate dynamic model. As a model based RL approach, when applied in urban autonomous driving, the GPS has the advantages of higher sample efficiency, better interpretability, and greater stability. We provide extensive experiments validating the effectiveness of the proposed method to learn robust driving policy for urban driving in Carla. We also compare the proposed method with other policy search and model free RL baselines, showing 100x better sample efficiency of the GPS based RL method, and also that the GPS based method can learn policies for harder tasks that the baseline methods can hardly learn.

Making changes to a program to optimize its performance is an unscalable task that relies entirely upon human intuition and experience. In addition, companies operating at large scale are at a stage where no single individual understands the code controlling its systems, and for this reason, making changes to improve performance can become intractably difficult. In this paper, a learning system is introduced that provides AI assistance for finding recommended changes to a program. Specifically, it is shown how the evaluative feedback, delayed-reward performance programming domain can be effectively formulated via the Monte Carlo tree search (MCTS) framework. It is then shown that established methods from computational games for using learning to expedite tree-search computation can be adapted to speed up computing recommended program alterations. Estimates of expected utility from MCTS trees built for previous problems are used to learn a sampling policy that remains effective across new problems, thus demonstrating transferability of optimization knowledge. This formulation is applied to the Apache Spark distributed computing environment, and a preliminary result is observed that the time required to build a search tree for finding recommendations is reduced by up to a factor of 10x.

Coronavirus disease 2019 (Covid-19) is highly contagious with limited treatment options. Early and accurate diagnosis of Covid-19 is crucial in reducing the spread of the disease and its accompanied mortality. Currently, detection by reverse transcriptase polymerase chain reaction (RT-PCR) is the gold standard of outpatient and inpatient detection of Covid-19. RT-PCR is a rapid method, however, its accuracy in detection is only ~70-75%. Another approved strategy is computed tomography (CT) imaging. CT imaging has a much higher sensitivity of ~80-98%, but similar accuracy of 70%. To enhance the accuracy of CT imaging detection, we developed an open-source set of algorithms called CovidCTNet that successfully differentiates Covid-19 from community-acquired pneumonia (CAP) and other lung diseases. CovidCTNet increases the accuracy of CT imaging detection to 90% compared to radiologists (70%). The model is designed to work with heterogeneous and small sample sizes independent of the CT imaging hardware. In order to facilitate the detection of Covid-19 globally and assist radiologists and physicians in the screening process, we are releasing all algorithms and parametric details in an open-source format. Open-source sharing of our CovidCTNet enables developers to rapidly improve and optimize services, while preserving user privacy and data ownership.

By Lauren McCauley Common Dreams In landmark agreement, California’s last remaining nuclear plant will be replaced by greenhouse-gas-free energy sources A plan to shutter the last remaining nuclear power plant in California and replace it with renewable energy is being … Continue reading →

[IMAGE-1] Part of being a music lover is also being a snob, and even though my mind has opened considerably as I've aged, I still remember all the genres I just couldn't give any time to when I was growing up. Southern rock was definitely verboten for much of my life.…

A computer-implemented method is provided for statistical data learning under privacy constraints. The method includes: receiving, by a processor, a plurality of pieces of statistical information relating to a statistical object and aggregating, by the processor, the plurality of pieces of statistical information so as to provide an estimation of the statistical object. Each piece of statistical information includes an uncertainty variable, the uncertainty variable being a value determined from a function having a predetermined mean. The number of pieces of statistical information aggregated is proportional to the reliability of the estimation of the statistical object.

Methods and arrangements for conducting a search using query logs. A query log is consulted and query rewrite rules are learned automatically based on data in the query log. The learning includes obtaining click-through data present in the query log.

A method of disposing nuclear waste in underground rock formations is presented. The method includes the steps of selecting a land area having a rock formation positioned there-below of a depth able to prevent radioactive material placed therein from reaching the surface and drilling a vertical wellbore from the surface, to a depth ranging between 5,000 feet and 25,000 feet, into the underground rock formation or repository. A plurality of horizontal laterals or horizontal wellbores, ranging in length from 500 feet to 40,000 feet, are drilled from the vertical wellbore into the underground rock formation or repository. Nuclear waste to be stored within these laterals is encapsulated in a special waste canister and these nuclear waste canisters are positioned within the horizontal laterals wherein they are sealed to prevent loss and leakage. Means are also provided by which these canisters are adapted to allow retrievability of the canisters from the wellbore at a later date and to return the waste to the surface for use after retrieval.

A method and device for limiting the degassing of tritiated waste issued from the nuclear industry are provided. The method reduces an amount of generated tritiated hydrogen (T2 or HT) and/or tritiated water (HTO or T2O) including at least one piece of tritiated waste from the nuclear industry. The method includes placing the package in contact with a mixture including manganese dioxide (MnO2) combined with a component that includes silver; and placing the package in contact with a molecular sieve.

A datapath extraction tool uses machine-learning models to selectively classify clusters of cells in an integrated circuit design as either datapath logic or non-datapath logic based on cluster features. A support vector machine and a neural network can be used to build compact and run-time efficient models. A cluster is classified as datapath if both the support vector machine and the neural network indicate that it is datapath-like. The cluster features may include automorphism generators for the cell clusters, or physical information based on the cell locations from a previous (e.g., global) placement, such as a ratio of a total cell area for a given cluster to a half-perimeter of a bounding box for the given cluster.

A handheld electronic device includes a reduced QWERTY keyboard and is enabled with a disambiguation routine that is operable to disambiguate text input. In addition to identifying and outputting representations of language objects that are stored in the memory and that correspond with a text input, the device is able to perform a spell check routine during input of a text entry and to learn and automatically correct mistakes typically made by the particular user.

Smoking cessation lighter is configured for lighting cigarettes for a smoker, and learning software is provided for monitoring smoking behavior of a smoker during a first data collection period and guiding a smoker's smoking cessation by directing the smoker when the smoker is to smoke a cigarette based on data collected during the first data collection period. The learning software monitors user behavior and collects data during use of the lighter by the smoker after the initial data collection period in order to analyze and further guide the smoker based on the smoker's cheating behavior, the smoker's behavior of lighting a cigarette for a friend, and the smoker's behavior of skipping use of the lighter at a time when the smoker has been directed to light a cigarette by the lighter.

A cochlear lead includes a plurality of electrodes configured to stimulate an auditory nerve from within a cochlea and a flexible body supporting the plurality of electrodes along a length of the flexible body. A stiffening element is slidably encapsulated within the flexible body and positioned such that the stiffening element plastically deforms upon insertion into a curved portion of the cochlea.

The present invention relates to the field of organic chemistry and in particular to organic free radicals used as polarizing agents in the technique of Dynamic Nuclear Polarization (DNP), which involves transferring the polarization of electron spins to the nuclei of a compound whose Nuclear Magnetic Resonance (NMR) is being observed. It concerns Dinitroxide-type Biradical polarizing agents characterized by a rigid linkage between the aminoxyl groups of said nitroxide units. This particular structure enables, at low temperatures and high fields, optimal transfer of polarization and optimal enhancement of NMR/MAS signals of the polarized nuclei of the compound studied.

A spent fuel reprocessing method including the steps of partitioning U and Pu(III) in a solvent by solvent extraction and subsequently polishing the solvent in a neptunium rejection operation for removing Np therefrom. The solvent obtained from the neptunium rejection operation (the polished solvent or NpA solvent product) is then recycled to a U/Pu partitioning operation. The method enables a reduction in solvent feed and solvent effluent volumes.

The present invention relates to a process to dissolve plutonium or a plutonium alloy, by placing it in contact with an aqueous dissolution mixture, wherein said dissolution mixture comprises nitric acid, a carboxylic acid with complexing properties with respect to plutonium, and a compound comprising at least one —NH2 radical such as urea. The invention also relates to a process to convert plutonium or a plutonium alloy into plutonium oxide and to manufacture nuclear fuel from said oxide.The invention particularly applies to the dismantling of plutonium contained in nuclear weapons with a view to its use in civilian nuclear reactors, particularly in the form of MOX fuel.

This invention is provided for improvement of corrosion-resistant property of a crucible and for promotion of safety in a pyrochemical reprocessing method for the spent nuclear fuel. The spent nuclear fuel is dissolved in a molten salt placed in the crucible. In a pyrochemical reprocessing method, the nuclear fuel is deposited, and the crucible (2) is heated by induction heating. Cooling media (5, 6) are supplied to cool down, and a molten salt layer (7) is maintained by keeping balance between the heating and the cooling, and a solidified salt layer (8) is formed on inner wall surface of the crucible.

The invention provides a method of separating uranium from at least fission products in irradiated nuclear fuel, said method comprising reacting said irradiated nuclear fuel with a solution of ammonium fluoride in hydrogen fluoride fluorinating said reacted irradiated nuclear fuel to form a volatile uranium fluoride compound and separating said volatile uranium fluoride compound from involatile fission products. The invention thus provides a reprocessing scheme for irradiated nuclear fuel. The method is also capable of reacting, and breaking down Zircaloy cladding and stainless steel assembly components. Thus, whole fuel elements may be dissolved as one thereby simplifying procedures over conventional Purex processes.

A vol-oxidizer of spent nuclear fuel, the spent nuclear fuel is injected to a reaction portion, the reaction portion is connected to a driving portion and oxidizes the spent nuclear fuel by rotating and back-rotating the spent nuclear fuel. The oxidized powder of the spent nuclear fuel is gathered in a discharge portion located in a lower portion of the reaction portion. By providing minute powder particles for recycling and a post process of the spent nuclear fuel, even though a size of an apparatus is small, processing a large amount is possible. Time required for oxidation can be reduced, and the powder is readily discharged by gravity since the apparatus is vertically configured.

Disclosed is a separation and receiving apparatus for a spent nuclear fuel rod. The spent nuclear fuel rod is mounted and downwardly transferred by a pin. At this time, a blade peels the hull of the spent nuclear fuel rod. The hull and a pellet positioned therein are separated by a separator. The peeled hull and pellet are each received in respective receiving vessels. Accordingly, since the hull and pellet made of uranium oxide (UO2) may be automatically separated and received in each respective vessel, safety and automation may be guaranteed.

A method of repairing a nuclear fuel cell wall and tools useful for performing that repair are described. A repair tool may be used to align a jack near a region of a bent or distorted structural component of nuclear fuel cell and that jack may be used to apply a force to that structural component. Application of such a force may serve to bend the structural component of a nuclear fuel cell in a way to restore the structural component to its position before damage occurred. The repair tool includes a way of mounting that tool to a fuel cell, positioning elements to align the tool near a structural deformation or bent element and a jack that may be use to apply a force to at least one structural component in a fuel cell.

Illustrative embodiments provide a nuclear fission reactor, a vented nuclear fission fuel module, methods therefor and a vented nuclear fission fuel module system.

Compositions are provided that include nuclear fuel. Methods for treating nuclear fuel are provided which can include exposing the fuel to a carbonate-peroxide solution. Methods can also include exposing the fuel to an ammonium solution. Methods for acquiring molybdenum from a uranium comprising material are provided.

A method for design of a fuel assembly for nuclear reactors, including structural components made from zirconium alloy: the mean uniaxial tensile or compressive stress to which the components are subjected during the assembly life is calculated, the zirconium alloy of which the components are made is selected according to the following criteria: those components subjected to an axial or transverse compressive stress of between −10 et −20 MPa are made from an alloy with a content of Sn between Sn=(=0.025σ−0.25)% and Sn=−0.05σ%: those components subjected to such a stress of between 0 et −10 MPa are made from an alloy the Sn content of which is between Sn=traces and Sn=(0.05σ+1)%: those components subjected to such a stress of between 0 and +10 MPa are made from an alloy the Sn content of which is between Sn=0.05% and Sn=(0.07σ+1)%: and those components subjected to such a stress of between +10 and +20 MPa are made from an alloy the content of SN of which is between 0.05% and 1.70%. A fuel assembly made according to the method.

Compositions are provided that include nuclear fuel. Methods for treating nuclear fuel are provided which can include exposing the fuel to a carbonate-peroxide solution. Methods can also include exposing the fuel to an ammonium solution. Methods for acquiring molybdenum from a uranium comprising material are provided.

A storage rack arrangement (10) for the storage of nuclear fuel elements in a storage pool includes at least two storage racks (1.1-1.3) which each contain a plurality of vertical channels (9) arranged next to one another for the reception of the fuel elements, with positioning elements (6) being provided at the storage racks at the bottom. The storage racks are connected to one another at the top and the storage rack arrangement (10) additionally includes one or more base plates (2.1-2.3) which are provided with positioning members (8) which fit with the positioning elements (6) of the storage racks (1.1-1.3) and which, together with the positioning elements, position the storage racks with respect to the base plate or base plates (2.1-2.3) to prevent a displacement of the storage racks on the base plate or plates.

Illustrative embodiments provide a nuclear fission reactor, a vented nuclear fission fuel module, methods therefor and a vented nuclear fission fuel module system.

A method for measuring the neutron flux in the core of a nuclear reactor, the method including several steps recurrently performed at instants separated by a period, the method comprising at each given instant the following steps: acquiring a total signal by a cobalt neutron detector placed inside the core of the reactor; assessing a calibration factor representative of the delayed component of the total signal due to the presence of cobalt 60 in the neutron detector; assessing a corrected signal representative of the neutron flux at the detector from the total signal and from the calibration factor; assessing a slope representative of the time-dependent change of the calibration factor between the preceding instant and the given instant; the calibration factor at the given instant being assessed as a function of the calibration factor assessed at the preceding instant, of the slope, and of the time period separating the given instant from the preceding instant.

Disclosed embodiments include methods of assembling a vented nuclear fission fuel module. Given by way of non-limiting example and not of limitation, an illustrative method of assembling a vented nuclear fission fuel module includes receiving a nuclear fission fuel element capable of generating a gaseous fission product. A valve body is coupled to the nuclear fission fuel element, and the valve body defines a plenum therein for receiving the gaseous fission product. A valve is disposed in communication with the plenum for controllably venting the gaseous fission product from the plenum. A flexible diaphragm is coupled to the valve for moving the valve. A cap is mounted on the valve, and a manipulator extendable to the cap for manipulating the cap is received.

An arrangement to control the clearance of a sliding bearing is disclosed. A sliding bearing arrangement, of a direct driven wind turbine, comprises a bearing. The bearing comprises a first bearing shell and a second bearing shell, whereby the first bearing shell and the second bearing shell are arranged rotatable in respect to each other. A certain predetermined clearance is present between the first bearing shell and the second bearing shell, while the bearing is in rotation. A first circuit comprises a first fluid, while the first circuit is in thermal contact with the first bearing shell. A second circuit comprises a second fluid, while the second circuit is in thermal contact with the second bearing shell. The first circuit and the second circuit are coupled in a way that a difference in the temperature between the first bearing shell and the second bearing shell is compensated via the first and the second fluid, thus the clearance is kept within a predetermined range.