Search

Severe to profound Sensorineural Hearing Loss is a challenging medical problem, particularly if this condition is associated with an inner ear anomaly. This case series studies the prevalence of inner ear anomalies among 76 consecutive prospective cochlear implant candidates who presented to our tertiary care hospital over 2 years. Inner ear anomalies were identified in 11 cases with a prevalence rate of 14%. Narrow Internal Auditory Canal (IAC) is the most common inner ear anomaly (5) followed by Mondini (3) and Globular vestibule (3). Combined CT and MRI play an important role in the preoperative assessment of inner ear anomalies which may affect not only the decision to perform the Implant procedure and the prognosis but also the choice of implant and surgical technique. [ABSTRACT FROM AUTHOR]

In modern power systems, accurate and timely detection of faults is crucial for ensuring system stability and reliability. The presence of high resistance in fault path curtails current and causes conventional distance relays to malfunction. These methods often require two-end measurements for accurate assessment of fault resistance necessitates an expensive communication channel. This paper proposes an innovative approach to enhance transmission line protection through an adaptive artificial neural network (ANN)-based relay system. The relay system integrates three ANN units: the fault detection unit, fault classification unit, and fault location unit, each tailored to detect, classify, and locate faults, respectively. By utilizing single-end measurements and employing discrete Fourier transform for feature extraction, the proposed algorithm efficiently diagnoses various fault conditions, including high resistance faults. Additionally, the algorithm dynamically updates its characteristics based on the estimated fault resistance (using one cycle post-fault data and the status of each ANN unit) in real-time, ensuring adaptability to changing system conditions, especially when the fault resistance falls beyond the scope of the training data. Simulation results on a 400-kV, 50-Hz transmission system demonstrate the robustness and effectiveness of the proposed approach in accurately identifying fault events under varying fault parameters, while also accounting for arcing faults and transducer errors. The suitability of the proposed method for real-time operations has been validated using OPAL-RT digital simulator. The adaptability of the proposed method for higher order systems is verified by performing a test case on the modified WSCC 9-bus system. The results support the adaptability and effectiveness of the proposed relaying algorithm in securing the transmission line under various conditions, including high resistance faults. [ABSTRACT FROM AUTHOR]

The growing popularity of convolutional neural networks (CNNs) along with their complexity has led to the search for efficient computational platforms suitable for them. Resistive random-access memory (ReRAM)-based architectures offer a promising alternative to commonly used GPU-based platforms for training CNNs. However, due to their low-precision storage capability, these architectures cannot support all types of CNN layers and suffer from accuracy loss of the learned model. In addition, ReRAM behavior varies with temperature. High temperature reduces noise margin and introduces additional noise. This makes training of CNNs challenging as outputs can be misinterpreted at higher operating temperatures leading to accuracy loss. In this work, we propose an M3D-enabled heterogeneous architecture: AccuReD, that combines ReRAM arrays with GPU cores, to address these challenges and achieve high accuracy CNN training. AccuReD supports all types of CNN layers and achieve near-GPU accuracy even with low-precision and nonideal behavior of ReRAMs. In addition, to reduce temperature, we present a performance–thermal-aware mapping policy that maps CNN layers to the computing elements of AccuReD. Experimental evaluation indicates that AccuReD does not lose accuracy while accelerating CNN training by 12 × on an average compared to conventional GPU-only platforms. [ABSTRACT FROM AUTHOR]

Predictive analytics using the time-series data collected from various types of sensors is a fundamental task that enables diverse mobile and Internet of Things applications including smart health. Deep-learning-based solutions are increasingly employed to solve such tasks because of their ability to directly process raw sensor data to achieve high accuracy as opposed to using human-engineered features. However, there are no principled studies on analyzing deep models for multivariate time-series data in adversarial settings. In this article, we propose a novel framework referred as a multivariate time-series adversarial lens (MTS-AdLens) to analyze deep models for wearable and mobile sensing systems through the adversarial lens in a realistic setting. We make three main contributions toward this goal. First, we introduce highly effective black-box attacks that expose significant vulnerabilities of deep models for multivariate time-series input space. Specifically, we show that deep models are vulnerable to attacks on limited channels. Second, inspired by our vulnerability analysis, we propose a novel technique to improve the robustness of the model. Third, we perform comprehensive experiments on data collected from real tasks to validate all our claims. Our results show the effectiveness of MTS-AdLens in identifying the vulnerabilities of deep models and in improving their robustness to realistic attacks. [ABSTRACT FROM AUTHOR]

Safe deployment of time-series classifiers for real-world applications relies on the ability to detect the data that is not generated from the same distribution as training data. This task is referred to as out-of-distribution (OOD) detection. We consider the novel problem of OOD detection for the time-series domain. We discuss the unique challenges posed by time-series data and explain why prior methods from the image domain will perform poorly. Motivated by these challenges, this article proposes a novel Seasonal Ratio Scoring (SRS) approach. SRS consists of three key algorithmic steps. First, each input is decomposed into class-wise semantic component and remainder. Second, this decomposition is employed to estimate the class-wise conditional likelihoods of the input and remainder using deep generative models. The seasonal ratio score is computed from these estimates. Third, a threshold interval is identified from the in-distribution data to detect OOD examples. Experiments on diverse real-world benchmarks demonstrate that the SRS method is well-suited for time-series OOD detection when compared to baseline methods. [ABSTRACT FROM AUTHOR]

Tight collaboration between manycore system designers and machine-learning experts is necessary to create a data-driven manycore design framework that integrates both learning and expert knowledge. Such a framework will be necessary to address the rising complexity of designing large-scale manycore systems and machine-learning techniques. [ABSTRACT FROM AUTHOR]

Recent progress in Internet of Things (IoT) platforms has allowed us to collect large amounts of sensing data. However, there are significant challenges in converting this large-scale sensing data into decisions for real-world applications. Motivated by applications like health monitoring and intervention and home automation we consider a novel problem called Activity Prediction, where the goal is to predict future activity occurrence times from sensor data. In this paper, we make three main contributions. First, we formulate and solve the activity prediction problem in the framework of imitation learning and reduce it to a simple regression learning problem. This approach allows us to leverage powerful regression learners that can reason about the relational structure of the problem with negligible computational overhead. Second, we present several metrics to evaluate activity predictors in the context of real-world applications. Third, we evaluate our approach using real sensor data collected from 24 smart home testbeds. We also embed the learned predictor into a mobile-device-based activity prompter and evaluate the app for nine participants living in smart homes. Our results indicate that our activity predictor performs better than the baseline methods, and offers a simple approach for predicting activities from sensor data. [ABSTRACT FROM PUBLISHER]

A 3-D network-on-chip (NoC) enables the design of high performance and low power many-core chips. Existing 3-D NoCs are inadequate for meeting the ever-increasing performance requirements of many-core processors since they are simple extensions of regular 2-D architectures and they do not fully exploit the advantages provided by 3-D integration. Moreover, the anticipated performance gain of a 3-D NoC-enabled many-core chip may be compromised due to the potential failures of through-silicon-vias that are predominantly used as vertical interconnects in a 3-D IC. To address these problems, we propose a machine-learning-inspired predictive design methodology for energy-efficient and reliable many-core architectures enabled by 3-D integration. We demonstrate that a small-world network-based 3-D NoC (3-D SWNoC) performs significantly better than its 3-D MESH-based counterparts. On average, the 3-D SWNoC shows 35% energy-delay-product improvement over 3-D MESH for the PARSEC and SPLASH2 benchmarks considered in this paper. To improve the reliability of 3-D NoC, we propose a computationally efficient spare-vertical link (sVL) allocation algorithm based on a state-space search formulation. Our results show that the proposed sVL allocation algorithm can significantly improve the reliability as well as the lifetime of 3-D SWNoC. [ABSTRACT FROM AUTHOR]

We consider a framework for structured prediction based on search in the space of complete structured outputs. Given a structured input, an output is produced by running a timebounded search procedure guided by a learned cost function, and then returning the least cost output uncovered during the search. This framework can be instantiated for a wide range of search spaces and search procedures, and easily incorporates arbitrary structuredprediction loss functions. In this paper, we make two main technical contributions. First, we describe a novel approach to automatically defining an effective search space over structured outputs, which is able to leverage the availability of powerful classification learning algorithms. In particular, we define the limited-discrepancy search space and relate the quality of that space to the quality of learned classifiers. We also define a sparse version of the search space to improve the efficiency of our overall approach. Second, we give a generic cost function learning approach that is applicable to a wide range of search procedures. The key idea is to learn a cost function that attempts to mimic the behavior of conducting searches guided by the true loss function. Our experiments on six benchmark domains show that a small amount of search in limited discrepancy search space is often sufficient for significantly improving on state-of-the-art structured-prediction performance. We also demonstrate significant speed improvements for our approach using sparse search spaces with little or no loss in accuracy. [ABSTRACT FROM AUTHOR]

Processing-in-memory (PIM) is a promising technique to accelerate deep learning (DL) workloads. Emerging DL workloads (e.g., ResNet with 152 layers) consist of millions of parameters, which increase the area and fabrication cost of monolithic PIM accelerators. The fabrication cost challenge can be addressed by 2.5-D systems integrating multiple PIM chiplets connected through a network-on-package (NoP). However, server-scale scenarios simultaneously execute multiple compute-heavy DL workloads, leading to significant interchiplet data volume. State-of-the-art NoP architectures proposed in the literature do not consider the nature of DL workloads. In this article, we propose a novel server scale 2.5-D manycore architecture called SWAP that accounts for the traffic characteristics of DL applications. Comprehensive experimental evaluations with different system sizes as well as diverse emerging DL workloads demonstrate that SWAP achieves significant performance and energy consumption improvements with much lower fabrication cost than state-of-the-art NoP topologies. [ABSTRACT FROM AUTHOR]

Abstract: A series of novel phosphorylated derivatives of galanthamine 6–11 and 12–17 were synthesized in two step process with high yields. In the first step galanthamine 1 was reacted with bis (2-chloroethyl) phosphoramidic dichloride 2/4-nitrophenyl phosphorodichloridate 3 in presence of triethylamine (TEA) in dry tetrahydrofuran (THF) yielded the intermediates 4/5. They were further reacted with various compounds like 2-aminoethanol, ethyleneglycol, ethylenediamine, 2-aminoethanethiol, 2-hydroxyethanethiol, monopotassium dihydrogenphosphate to obtain the title compounds 6–11 and 12–17. The title compounds showed promising antimicrobial, antioxidant activities and was greatly influenced by the presence of different bioactive groups. [Copyright &y& Elsevier]

• Incorrect heat treatment of UNS N07718 will result in grain boundary precipitates and contribute to premature failures in Oil & Gas Production environments. • Laves phases dramatically reduces the room temperature ductility and ultimate tensile strength of UNS NO7718. • Compliance of technical requirements of UNS N07718 as outlined in API 6ACRA shall be mandatory for UNS N07718 material performance. High pressure/high-temperature (HP/HT) Oil & Gas wells in sour service are currently installed with UNS N07718 tubing hangers. Failure of UNS N07718 tubing hanger was recently discovered in one of the sour wells after more than ten years in service. Tubing hanger failures will result in significant production deferment and workover costs. The objective of this study is to present the failure mode of the tubing hanger and its implications on existing wells installed with similar material. All exposures due to well intervention activities like (integrity tests, fracking, coiled tubing operations, etc.) have been analyzed to determine the cause of failure. Microstructural investigations through optical and scanning electron microscope (SEM) analysis revealed several detrimental metallurgical phases, e.g., acicular, laves phases, which are present in the material and has contributed to the failure of the tubing hanger. The material was found to not meet current requirements as noted in API 6A CRA and the precursor API 6A 718 specifications. [ABSTRACT FROM AUTHOR]

Resistive random-access memory (ReRAM)-based architectures can be used to accelerate convolutional neural network (CNN) training. However, existing architectures either do not support normalization at all or they support only a limited version of it. Moreover, it is common practice for CNNs to add normalization layers after every convolution layer. In this work, we show that while normalization layers are necessary to train deep CNNs, only a few such layers are sufficient for effective training. A large number of normalization layers do not improve prediction accuracy; it necessitates additional hardware and gives rise to performance bottlenecks. To address this problem, we propose DeepTrain, a heterogeneous architecture enabled by a Bayesian optimization (BO) methodology; together, they provide adequate hardware and software support for normalization operations. The proposed BO methodology determines the minimum number of normalization operations necessary for a given CNN. Experimental evaluation indicates that the BO-enabled DeepTrain architecture achieves up to $15\times $ speedup compared to a conventional GPU for training CNNs with no accuracy loss while utilizing only a few normalization layers. [ABSTRACT FROM AUTHOR]

The relationship between sinonasal disease and septal deviations is well known, albeit vaguely. There was no serious attempt to classify deviations except calling them mild deviations, gross deviations, spur, high deviations, etc. The airflow changes in these deviations, which lead to mucosal changes predisposing to polyps or infection have not been documented clearly. In this study we made a classification of septal deformities by modifying the classification described by Mladina in 1987. This classification has been applied to 100 consecutive cases who have been advised nasal surgery and 100 normal individuals who did not have any nasal symptoms. All patients had CT scan of PNS and their CT findings were studied in relation to the type of deviation. This paper presents an analysis of the incidence of various types of deviations in patients and controls and the relationship of different deformities to the sinus pathology. [ABSTRACT FROM AUTHOR]

Summary: Series compensation improves the power transfer capability and the stability of a transmission system. Inclusion of series compensating devices along with their protecting equipment introduces the problems to conventional protective relaying during power system faults. In this paper, a new protection strategy is proposed based on the instantaneous active and reactive power variations. The applicability of the proposed method to a series compensated transmission system is studied with numerous fault cases. Instantaneous power quantities are measured, and respective active and reactive power quantities are reproduced onto a two‐dimensional coordinated system with reactive power as ordinate and active power as abscissa. The locus of ordered pair of instantaneous power quantities (p(t), q(t)) forms a P‐Q trajectory. The quadrant in which the starting point of P‐Q trajectory (p0(t), q0(t)) lies is computed and taken as reference. This P‐Q portrait is analyzed to detect the fault depending on the condition that the operating point shifts its quadrant under fault condition. Fault will be classified based on the polarities of extracted powers. Classification tree is formed by a set of yes/no consequences to classify the fault. The proposed method is tested for different types of faults, at distinct locations and fault inceptions on 500‐kV, 50‐Hz test system. Results thus obtained show the potentiality of proposed strategy for the protection of series compensated transmission system concerning the speed, computational burden, and mathematical complexity. [ABSTRACT FROM AUTHOR]

The rising use of deep learning and other big-data algorithms has led to an increasing demand for hardware platforms that are computationally powerful, yet energy-efficient. Due to the amount of data parallelism in these algorithms, high-performance three-dimensional (3D) manycore platforms that incorporate both CPUs and GPUs present a promising direction. However, as systems use heterogeneity (e.g., a combination of CPUs, GPUs, and accelerators) to improve performance and efficiency, it becomes more pertinent to address the distinct and likely conflicting communication requirements (e.g., CPU memory access latency or GPU network throughput) that arise from such heterogeneity. Unfortunately, it is difficult to quickly explore the hardware design space and choose appropriate tradeoffs between these heterogeneous requirements. To address these challenges, we propose the design of a 3D Network-on-Chip (NoC) for heterogeneous manycore platforms that considers the appropriate design objectives for a 3D heterogeneous system and explores various tradeoffs using an efficient machine learning (ML)-based multi-objective optimization (MOO) technique. The proposed design space exploration considers the various requirements of its heterogeneous components and generates a set of 3D NoC architectures that efficiently trades off these design objectives. Our findings show that by jointly considering these requirements (latency, throughput, temperature, and energy), we can achieve 9.6 percent better Energy-Delay Product on average at nearly iso-temperature conditions when compared to a thermally-optimized design for 3D heterogeneous NoCs. More importantly, our results suggest that our 3D NoCs optimized for a few applications can be generalized for unknown applications as well. Our results show that these generalized 3D NoCs only incur a 1.8 percent (36-tile system) and 1.1 percent (64-tile system) average performance loss compared to application-specific NoCs. [ABSTRACT FROM AUTHOR]

Resistive random-access memory (ReRAM)-based manycore architectures enable acceleration of graph neural network (GNN) inference and training. GNNs exhibit characteristics of both DNNs and graph analytics. Hence, GNN training/inferencing on ReRAM-based manycore architectures give rise to both computation and on-chip communication challenges. In this work, we leverage model pruning and efficient graph storage to reduce the computation and communication bottlenecks associated with GNN training on ReRAM-based manycore accelerators. However, traditional pruning techniques are either targeted for inferencing only, or they are not crossbar-aware. In this work, we propose a GNN pruning technique called DietGNN. DietGNN is a crossbar-aware pruning technique that achieves high accuracy training and enables energy, area, and storage efficient computing on ReRAM-based manycore platforms. The DietGNN pruned model can be trained from scratch without any noticeable accuracy loss. Our experimental results show that when mapped on to a ReRAM-based manycore architecture, DietGNN can reduce the number of crossbars by over 90% and accelerate GNN training by ${\sim }{2}.{7}{\times }$ compared to its unpruned counterpart. In addition, DietGNN reduces energy consumption by more than ${\sim }{3}.{5}{\times }$ compared to the unpruned counterpart. [ABSTRACT FROM AUTHOR]

Abstract Planning with preferences has been employed extensively to quickly generate high-quality plans. However, it may be difficult for the human expert to supply this information without knowledge of the reasoning employed by the planner. We consider the problem of actively eliciting preferences from a human expert during the planning process. Specifically, we study this problem in the context of the Hierarchical Task Network (HTN) planning framework as it allows easy interaction with the human. We propose an approach where the planner identifies when and where expert guidance will be most useful and seeks expert's preferences accordingly to make better decisions. Our experimental results on several diverse planning domains show that the preferences gathered using the proposed approach improve the quality and speed of the planner, while reducing the burden on the human expert. [ABSTRACT FROM AUTHOR]

Deep neural networks have seen tremendous success for different modalities of data including images, videos, and speech. This success has led to their deployment in mobile and embedded systems for real-time applications. However, making repeated inferences using deep networks on embedded systems poses significant challenges due to constrained resources (e.g., energy and computing power). To address these challenges, we develop a principled co-design approach. Building on prior work, we develop a formalism referred as coarse-to-fine networks (C2F Nets) that allow us to employ classifiers of varying complexity to make predictions. We propose a principled optimization algorithm to automatically configure C2F Nets for a specified tradeoff between accuracy and energy consumption for inference. The key idea is to select a classifier on-the-fly whose complexity is proportional to the hardness of the input example: simple classifiers for easy inputs and complex classifiers for hard inputs. We perform comprehensive experimental evaluation using four different C2F Net architectures on multiple real-world image classification tasks. Our results show that optimized C2F Net can reduce the energy delay product by 27% to 60% with no loss in accuracy when compared to the baseline solution, where all predictions are made using the most complex classifier in C2F Net. [ABSTRACT FROM AUTHOR]