Spread dynamics and the confinement policies of COVID-19 exhibit different patterns for different countries. Numerous factors affect such patterns within each country. Examining these factors, and analyzing the confinement practices allow government authorities to implement effective policies in the future. In addition, they help the authorities to distribute healthcare resources optimally without overwhelming their systems. In this empirical study, we use a clustering-based approach, Hierarchical Cluster Analysis (HCA) on time-series data to capture the spread patterns at various countries. We particularly investigate the confinement policies adopted by different countries and their impact on the spread patterns of COVID-19. We limit our investigation to the early period of the pandemic, because many governments tried to respond rapidly and aggressively in the beginning. Moreover, these governments adopted diverse confinement policies based on trial-and-error in the beginning of the pandemic. We found that implementations of the same confinement policies may exhibit different results in different countries. Specifically, lockdowns become less effective in densely populated regions, because of the reluctance to comply with social distancing measures. Lack of testing, contact tracing, and social awareness in some countries forestall people from self-isolation and maintaining social distance. Large labor camps with unhealthy living conditions also aid in high community transmissions in countries depending on foreign labor. Distrust in government policies and fake news instigate the spread in both developed and under-developed countries. Large social gatherings play a vital role in causing rapid outbreaks almost everywhere. An early and rapid response at the early period of the pandemic is necessary to contain the spread, yet it is not always sufficient.

Health insurance is one of the most important services that people depend on for paying the bills related to hospital and clinical services. This dependency on health insurance lures some healthcare service providers to commit insurance frauds which has become a grave concern. The majority of healthcare fraud is committed by a very small number of untrustworthy providers. Yet, such fraudulent actions damage the reputation of the health service providers and cost the system billions of dollars. In this article, we specifically focus on the fraudulent claim identification problem and develop different solution schemes to identify the fraudulent cases in healthcare claims with minimal data. We present a solution to the fraudulent claim identification problem that translates diagnoses and procedure code's relations into Bipartite Graphs with Fuzzy Edges (BiGFuzzE). We also investigate the extension ofBiGFuzzEusing vector representations of clinical codes instead of non-negative matrix factorization (NMF). Our experimental evaluations demonstrate significant outcomes.

Patients depend on health insurance provided by the government systems, private systems, or both to utilize the high-priced healthcare expenses. This dependency on health insurance draws some healthcare service providers to commit insurance frauds. Although the number of such service providers is small, it is reported that the insurance providers lose billions of dollars every year due to frauds. In this article, we formulate the fraud detection problem over a minimal, definitive claim data consisting of medical diagnosis and procedure codes. We present a solution to the fraudulent claim detection problem using a novel representation learning approach, which translates diagnosis and procedure codes into Mixtures of Clinical Codes (MCC). We also investigate extensions of MCC using Long Short Term Memory networks and Robust Principal Component Analysis. Our experimental results demonstrate promising outcomes in identifying fraudulent records.

Renewable energy resources are environment friendly but their integration as distributed energy resources (DERs) poses fundamental operational and governance challenges such as power system instability, reliability, power quality and protection. Protection is one of the major issues with integration of renewable energy with distribution system. Considering the high variability of generation from DERs, the current contribution from DERs are also highly dynamic and that can create bidirectional power flow, influence the protection relay operations and can introduce protection blinding to the existing protection relays. The present protection relays are unable to adjust with these dynamic changes as the fault current level varies with the DERs contributions, therefore relay pickup current settings are unable to match with the updated network conditions. Therefore, a secure protection for distribution network is a challenging issue with high penetration of DERs. This paper introduces an alternative protection scheme that can work irrespective of grid connected or islanded condition of distribution network and update its relay settings and pickup current based on the point of common coupling (PCC) information. This proposed scheme was tested in a 3-bus system and in IEEE 33-bus radial distribution network and was able to handle the protection blinding issue.

Autonomous driving systems have attracted a significant amount of interest recently, and many industry leaders, such as Google, Uber, Tesla, and Mobileye, have invested a large amount of capital and engineering power on developing such systems. Building autonomous driving systems is particularly challenging due to stringent performance requirements in terms of both making the safe operational decisions and finishing processing at real-time. Despite the recent advancements in technology, such systems are still largely under experimentation and architecting end-to-end autonomous driving systems remains an open research question. To investigate this question, we first present and formalize the design constraints for building an autonomous driving system in terms of performance, predictability, storage, thermal and power. We then build an end-to-end autonomous driving system using state-of-the-art award-winning algorithms to understand the design trade-offs for building such systems. In our real-system characterization, we identify three computational bottlenecks, which conventional multicore CPUs are incapable of processing under the identified design constraints. To meet these constraints, we accelerate these algorithms using three accelerator platforms including GPUs, FPGAs, and ASICs, which can reduce the tail latency of the system by 169x, 10x, and 93x respectively. With accelerator-based designs, we are able to build an end-to-end autonomous driving system that meets all the design constraints, and explore the trade-offs among performance, power and the higher accuracy enabled by higher resolution cameras.

The simple question "Was this review helpful to you?" increases an estimated $2.7B revenue to Amazon.com annually 1. In this paper, we propose a solution to the problem of electronic product review accumulation using helpfulness prediction. The popularity of e-commerce and online retailers such as Amazon, eBay, Yelp, and TripAdvisor are largely relying on the presence of product reviews to attract more customers. The major issue for the user submitted reviews is to quantify and evaluate the actual effectiveness by combining all the reviews under a particular product. With the varying size of reviews for each product, it is quite cumbersome for the customers to get hold of the overall helpfulness.Therefore, we propose a feature extraction technique that can quantify and measure helpfulness for each product based on user submitted reviews.

Interactive service providers have strict requirements on high-percentile (tail) latency to meet user expectations. If providers meet tail latency targets with less energy, they increase profits, because energy is a significant operating expense. Unfortunately, optimizing tail latency and energy are typically conflicting goals. Our work resolves this conflict by exploiting servers with per-core Dynamic Voltage and Frequency Scaling (DVFS) and Asymmetric Multicore Processors (AMPs). We introduce the Adaptive Slow-to-Fast scheduling framework, which matches the heterogeneity of the workload --- a mix of short and long requests --- to the heterogeneity of the hardware --- cores running at different speeds. The scheduler prioritizes long requests to faster cores by exploiting the insight that long requests reveal themselves. We use control theory to design threshold-based scheduling policies that use individual request progress, load, competition, and latency targets to optimize performance and energy. We configure our framework to optimize Energy Efficiency for a given Tail Latency (EETL) for both DVFS and AMP. In this framework, each request self-schedules, starting on a slow core and then migrating itself to faster cores. At high load, when a desired AMP core speed s is not available for a request but a faster core is, the longest request on an s core type migrates early to make room for the other request. Compared to per-core DVFS systems, EETL for AMPs delivers the same tail latency, reduces energy by 18% to 50%, and improves capacity (throughput) by 32% to 82%. We demonstrate that our framework effectively exploits dynamic DVFS and static AMP heterogeneity to reduce provisioning and operational costs for interactive services.

Accurate prediction of wind power is of vital importance for demand management. In this paper, we adopt a cluster-based ensemble framework to predict wind power. Natural groups/clusters exist in datasets and learning algorithms benefit from group/cluster wise learning — a philosophy that is not well explored for wind power prediction. The research presented in this paper investigates this philosophy to predict wind power by using an ensemble of regression models on natural clusters within wind data. We have conducted a series of experiments on a large number of locations across Australia and analyzed the existence of clusters within wind data, suitability of linear and nonlinear regression models for the proposed framework, and how well the cluster-based ensemble performs against the situation when no clustering is done. Experimental results demonstrate prediction improvement as high as 17.94% through the usage of the cluster-based ensemble regression algorithm.

Cache capacity and memory bandwidth play critical roles in application performance, particularly for data-intensive applications from domains that include machine learning, numerical analysis, and data mining. Many of these applications are also tolerant to imprecise inputs and have loose constraints on the quality of output, making them ideal candidates for approximate computing. This paper introduces a novel approximate computing technique that decouples the format of data in the memory hierarchy from the format of data in the compute subsystem to significantly reduce the cost of storing and moving bits throughout the memory hierarchy and improve application performance. This asymmetric compute-memory extension to conventional architectures, ACME, adds two new instruction classes to the ISA - load-concise and store-concise - along with three small functional units to the micro-architecture to support these instructions. ACME does not affect exact execution of applications and comes into play only when concise memory operations are used. Through detailed experimentation we find that ACME is very effective at trading result accuracy for improved application performance. Our results show that ACME achieves a 1.3x speedup (up to 1.8x) while maintaining 99% accuracy, or a 1.1x speedup while maintaining 99.999% accuracy. Moreover, our approach incurs negligible area and power overheads, adding just 0.005% area and 0.1% power to a conventional modern architecture.

Interactive services, such as Web search, recommendations, games, and finance, must respond quickly to satisfy customers. Achieving this goal requires optimizing tail (e.g., 99th+ percentile) latency. Although every server is multicore, parallelizing individual requests to reduce tail latency is challenging because (1) service demand is unknown when requests arrive; (2) blindly parallelizing all requests quickly oversubscribes hardware resources; and (3) parallelizing the numerous short requests will not improve tail latency. This paper introduces Few-to-Many (FM) incremental parallelization, which dynamically increases parallelism to reduce tail latency. FM uses request service demand profiles and hardware parallelism in an offline phase to compute a policy, represented as an interval table, which specifies when and how much software parallelism to add. At runtime, FM adds parallelism as specified by the interval table indexed by dynamic system load and request execution time progress. The longer a request executes, the more parallelism FM adds. We evaluate FM in Lucene, an open-source enterprise search engine, and in Bing, a commercial Web search engine. FM improves the 99th percentile response time up to 32% in Lucene and up to 26% in Bing, compared to prior state-of-the-art parallelization. Compared to running requests sequentially in Bing, FM improves tail latency by a factor of two. These results illustrate that incremental parallelism is a powerful tool for reducing tail latency.

We propose GreenPar, a scheduler for parallel high-perormance applications in datacenters partially powered by on-site generation of renewable ("green'') energy. GreenPar schedules the workload to maximize the green energy consumption and minimize the grid ("brown'') energy consumption, while respecting a performance service-level agreement (SLA). When green energy is available, GreenPar increases the resource allocations of active jobs to reduce runtimes. When using brown energy, GreenPar reduces resource allocations within the constraints imposed by the performance SLA to conserve energy. GreenPar makes its decisions based on the speedup profile of each job. We have implemented GreenPar in a real solar-powered datacenter. Our results show that GreenPar can increase the green energy consumption and reduce both the average job runtime and the brown energy consumption, compared to schedulers that are oblivious to on-site green energy.

This paper proposes a Simulated Annealing based Global Maximum Power Point Tracking (GMPPT) technique designed for photovoltaic (PV) systems which experience partial shading conditions (PSC). The proposed technique is compared with the common Perturb and Observe MPPT technique and the Particle Swarm Optimization approach to GMPPT. The performance is assessed by considering the time taken to converge and the number of cases where the technique converges to the GMPP Simulation results indicate the improve performance of the Simulated Annealing based GMPPT algorithm in tracking to the Global maxima in a multiple module system experiencing PSC.

In this paper, we propose GreenSlot, a parallel batch job scheduler for a datacenter powered by a photovoltaic solar array and the electrical grid (as a backup). GreenSlot predicts the amount of solar energy that will be available in the near future, and schedules the workload to maximize the green energy consumption while meeting the jobs' deadlines. If grid energy must be used to avoid deadline violations, the scheduler selects times when it is cheap. Our results for production scientific workloads demonstrate that Green-Slot can increase green energy consumption by up to 117% and decrease energy cost by up to 39%, compared to a conventional scheduler. Based on these positive results, we conclude that green datacenters and green-energy-aware scheduling can have a significant role in building a more sustainable IT ecosystem.

In a volunteer-based Grid, the system must be heterogeneous, and the computation capability of each node varies, and load distribution or load balancing is one of the most important issues in Grid. Some techniques have been proposed for dynamic load distribution which relocates jobs, by migrating running jobs keeping their execution states, from a high-loaded node to a lower-loaded node during execution. In this paper, we propose a dynamic load distribution between computation nodes using mobile threads which leads to lightweight, low-overhead job relocation. We present its effects using an example problem, parallel Prefix Span used in analysis of amino-acid sequences, whose computation cost is absolutely unpredictable.