Search

Worldwide, it is forecasted that 131.5 million people will suffer from dementia by 2050, and the annual cost of care will increase from 818 billion USD in 2016 to 2 trillion USD by 2030, with burgeoning social consequences. Given a timely prediction of a dementia outcome in patients, appropriate mitigating interventions can be applied to reduce risk. However such prediction facilities need to be made available to wider populations, and these facilities cannot rely on specialised, costly and invasive testing (such as neuroimaging, cerebrospinal fluid collection, etc which constitute important instruments used in diagnosis), for interventions to have a meaningful quantitative impact. Hence an emerging need exists for the wider application of prognostic measures which can be deployed using lower cost data sources such as longitudinal records routinely collected by general practices. This paper proposes an efficient prediction modelling approach to the risk of dementia, using CPRD data collected from GP practices in UK, and based on machine learning in particular the Gradient Boosting Machines model combined with a survival model such as the Cox Proportional Hazard, encapsulated in a semi-supervised learning and model calibration methodology.

Femur fractures due to traumatic forces often require surgical intervention. Such surgeries require alignment of the femur in the presence of large muscular forces up to 500 N. Currently, orthopedic surgeons perform this alignment manually before fixation, leading to extra soft tissue damage and inaccurate alignment. One of the limitations of femoral fracture surgery is the limited vision and two-dimensional nature of X-ray images, which typically guide the surgeon in diagnosing the position of the femur. Other limitations include the lack of precise intraoperative planning and the process of trial-and-error alignment. To alleviate the issues discussed, we develop a marker-based approach for detecting the position of femur fragments using two X-ray images. The relative spatial position of the femur fragments plays a key role in guiding an innovative robotic system, named Robossis, for femur fracture alignment surgeries. Using the derived three-dimensional data, we simulate pre-programmed movements to visualize the proposed steps of the alignment method, while the bone fragments are attached to the robot. Ultimately, Robossis aims to improve the accuracy of femur alignment, which results in improved patient outcomes.

The GraphBLAS is a set of basic building blocks for constructing graph algorithms in terms of linear algebra. They are first and foremost defined mathematically with the goal that language bindings will be produced for a wide range of programming languages. We started with the C programming language and over the last four years have produced multiple versions of the GraphBLAS C API specification. In this paper, we describe our next version of the C GraphBLAS specification. It introduces a number of major changes including support for multithreading, import/export functionality, and functions that use the indices of matrix/vector elements. Since some of these changes introduce small backwards compatibility issues, this is a major release we call GraphBLAS 2.0.

Lidars are becoming common components for remote sensing in many emerging applications such as autonomous vehicle and facial recognition. To accurately visualize the point cloud for further data processing, metrics such as precision, sampling rate, and linearity are important. The concept of a sub-sampling pulsed-coherent lidar system [1] has demonstrated high precision and fast acquisition. The segmented time-of-flight (ToF) algorithm measures the phase shift of the carrier as fine ToF and counts the arrival time of the low-frequency mask’s envelope as intermediate and coarse ToF. Fig. 1(a) shows the down-conversion architecture in [1] using a simple LO generation which only uses dividers and a mixer to minimize the clock jitter. The performance based on the coherent detection, however, is limited by several factors. (1) The crosstalk between the reference clock and the echoed signal at the same frequency lowers the sensitivity and the linearity. Specifically, the reference leaks to the incoming signal path hence introducing an in-band spur. At the same time, the received signals with different power pull the clock phase and cause input-dependent phase shifts. (2) I/Q IF channels and two high-speed ADCs are required to reconstruct the mask’s envelope leading to high power consumption. Additionally, I/Q mismatch calibration process must be done prior to the normal acquisition. In this work, a local PLL synthesizes the LO to suppress the in-band reference leakage and crosstalk. A two-step down-conversion with digital down-mixing is implemented which improves the power efficiency and immunity to PVT variation without additional calibration. We also propose an inverter-based phase-invariant programmable gain amplifier (PI-PGA) that improves the linearity with a 40-dB tuning range. This calibration-free system achieves 6-μm precision and 30-μm INL Max with a 5-MSa/s sampling rate.

Graphs play a key role in data analytics. Graphs and the software systems used to work with them are highly diverse. Algorithms interact with hardware in different ways and which graph solution works best on a given platform changes with the structure of the graph. This makes it difficult to decide which graph programming framework is the best for a given situation. In this paper, we try to make sense of this diverse landscape. We evaluate five different frameworks for graph analytics: SuiteS-parse GraphBLAS, Galois, the NWGraph library, the Graph Kernel Collection, and GraphIt. We use the GAP Benchmark Suite to evaluate each framework. GAP consists of 30 tests: six graph algorithms (breadth-first search, single-source shortest path, PageRank, betweenness centrality, connected components, and triangle counting) on five graphs. The GAP Benchmark Suite includes high-performance reference implementations to provide a performance baseline for comparison. Our results show the relative strengths of each framework, but also serve as a case study for the challenges of establishing objective measures for comparing graph frameworks.

Triangles are the simplest non-trivial subgraphs and triangle counting is used in a number of different applications. The order in which vertices are processed in triangle counting strongly effects the amount of work that needs to be done (and thus the overall performance). Ordering vertices by degree has been shown to be one particularly effective ordering approach. However, for graphs with skewed degree distributions (such as power-law graphs), ordering by degree effects the distribution of work; parallelization must account for this distribution in order to balance work among workers. In this paper we provide an in-depth analysis of the ramifications of degree-based ordering on parallel triangle counting. We present approach for partitioning work in triangle counting, based on cyclic distribution and some surprisingly simple C++ implementations. Experimental results demonstrate the effectiveness of our approach, particularly for power-law (and social network) graphs.

We provide a first look at GBTLX, a code generator that translates graph processing programs written using the GraphBLAS Template Library (GBTL) into high-performance C programs that match the performance of hand-tuned implementations. GBTLX refactors code written using GBTL into problems that capture the signature of algorithms and solvers that capture the semantics (input/output behavior of algorithms. Users provide classes that implement these two aspects using standard GBTL functions and encapsulate the targeted algorithm. GBTLX then performs a sequence of inspection, code generation, and high-performance execution. First, the user code is traced while running with the original GBTL. Then, the trace is used to define the semantics and signature of the algorithm to be produced in code generation. The SPIRAL system is used to generate high-performance C code that implements the user-specified algorithm, specializing the code for algorithm and hardware-dependent optimizations. Finally, the user-provided GBTL-based implementation is replaced by the SPIRAL generated C code. For triangle counting and k-truss enumeration, the resulting executables provide performance equivalent to hand-tuned implementations, while the source code is maintainable as it only uses the C++ GBTL library.

This paper describes two methods for creating improved probabilistic wind power forecasts through the use of turbine-level data. The first is a feature engineering approach whereby deterministic power forecasts from the turbine level are used as explanatory variables in a wind farm level forecasting model. The second is a novel bottom-up hierarchical approach where the wind farm forecast is inferred from the joint predictive distribution of the power output from individual turbines. Notably, the latter produces probabilistic forecasts that are coherent across both turbine and farm levels, which the former does not. The methods are tested at two utility scale wind farms and are shown to provide consistent improvements of up to 5%, in terms of continuous ranked probability score compared to the best performing state-of-the-art benchmark model. The bottom-up hierarchical approach provides greater improvement at the site characterized by a complex layout and terrain, while both approaches perform similarly at the second location. We show that there is a clear benefit in leveraging readily available turbine-level information for wind power forecasting.

This paper presents a cost-effective method using 3D printing technology to reduce the parasitic losses when probing a channel with a logic analyzer compared to traditional methods. The method is demonstrated on a 16 Gb/s PCIe Gen4 channel, taking advantage of the physically accessible SMT AC decoupling capacitors through a custom fixture to contact the signals of the high-speed serial (HSS) channel.Channel topology, length and transceiver compensation, and sophisticated equalization has increased link frequency dramatically at the cost of complexity. This renders traditional debug activities using an oscilloscope to be of very limited value in the characterization and verification of the link. The protocol-awareness of HSS links, including the use of retimers, makes the use of a logic analyzer necessary.While a logic analyzer fills the need for protocol analysis and timing data to debug link errors that would be undetected by traditional oscilloscope efforts, the fixturing to contact the signals introduces an electrical loading in the channel. As data rates continue to increase, the loading becomes increasingly severe. The commonly available probe connectors for logic analyzers are physically large, require substantial board real estate, and consume a notable percentage of channel margin due to its parasitic losses.With the proposed method, HSS channels can be analyzed during link operation and link training. Prototype parts can be analyzed and, with fore-thought and planning, even failure analysis of customer-failing parts can be investigated. The fixturing is affordable, compact, and configurable using 3D printing technology promising continued use as HSS data rates continue to increase.

The GraphBLAS emerged from an international effort to standardize linear-algebraic building blocks for computing on graphs and graph-structured data. The GraphBLAS is expressed as a C API and has paved the way for multiple implementations. The GraphBLAS C API, however, does not define how distributed-memory parallelism should be handled. This paper reviews various approaches for a GraphBLAS API for distributed computing. This work is guided by our experience with existing distributed memory libraries. Our goal for this paper is to highlight the pros and cons of different approaches rather than to advocate for one particular choice.

The GraphBLAS are building blocks for expressing graph algorithms in terms of linear algebra. Currently, the GraphBLAS are defined as a C API. Implementations of the GraphBLAS have exposed limitations in expressiveness and performance due to limitations in C. A move to $\mathrm {C}++$ should address many of these limitations while providing a simpler API. Furthermore, for methods based on user-defined types and operators, the performance should be significantly better. $\mathrm {C}++$ has grown into a pervasive programming language across many domains. We see a compelling argument to define a GraphBLAS $\mathrm {C}++$ API. This paper presents our roadmap for the development of a GraphBLAS $\mathrm {C}++$ API. Open issues are highlighted with the goal of fostering discussion and generating feedback within the GraphBLAS user community to guide us as we develop the GraphBLAS $\mathrm {C}++$ API.

Multiple magnetic resonance imaging (MRI) modalities are currently used for the diagnosis and characterization of temporal lobe epilepsy (TLE). The objective of this study is to assess the performance of individual and combination of multimodal MRI datasets to provide an accurate classification of TLE by employing a multi-channel deep neural network. Several multi-channel deep neural network models were trained, validated, and tested using brain structure metrics from structural MRI, MRI-based region of interest correlation features, and personal demographic and cognitive data (PDC). The results show that PDC individually offered the most accurate classification of TLE followed by the combination of PDC with MRI-based brain structure metrics. These findings demonstrate the potential of deep learning approaches such as mDNN models to combine multiple datasets for TLE classification.