Wide-area applications, such as electronic commerce, groupware, directory service etc., rely on distributed data management services which often employ data replication to meet availability and response time constraints imposed by the target domains. Since many of these applications can tolerate some staleness in the data they access, the constraints may be better met by exploiting relaxed data...

Typical social networking functionalities such as feed following are known to be hard to scale. Different from the popular approach that sacrifices consistency for scalability, in this paper we describe, implement, and evaluate a method that can simultaneously achieve scalability and consistency in feed following applications built on sharednothing distributed systems. Timing and client-side pr...

Data Caching improves data availability among the mobile nodes (MNs) that are connected together through unreliable wireless links. The MNs are often updating the cached data due to its dynamism. The query access rate of cached data is varied based on neighbor nodes requirements. The caching nodes must ensure the staleness of data with source. This paper proposes the novel Cluster Based Update ...

Emerging workloads, such as graph processing and machine learning are approximate because of the scale of data involved and the stochastic nature of the underlying algorithms. These algorithms are often distributed over multiple machines using bulk-synchronous processing (BSP) or other synchronous processing paradigms such as map-reduce. However, data parallel processing primitives such as repe...

Baked goods are among the most important sources of human food. They may suffer from a limited shelf life due to use of low-quality wheat. However, there are a number of novel dough preparation methods that can improve bread quality. The current study analyzed the effect of the yeast-salt method on the physicochemical and rheological properties of toast dough and bread. Baker’s yeast was used a...

The Internet of Things (IoT) brings internet connectivity to everyday devices. These devices generate a large volume information that needs be transmitted the nodes running IoT applications, where they are processed and used make some output decisions. On one hand, quality these decisions is typically affected by freshness received information, thus requesting frequent updates from other severe...

Software distributed shared memory (DSM) platforms on networks of workstations tolerate large network latencies by employing one of several weak memory consistency models. Data-race tolerant applications, such as Genetic Algorithms (GAs), Probabilistic Inference, etc., offer an additional degree of freedom to tolerate network latency: they do not synchronize shared memory references, and behave...

Information on the web and web services that are revised by stakeholders is growing incredibly. The presentation of this information has shifted from a representational model of web information with loosely clustered terminology to semi-formal terminology and even to formal ontology. Mediation (i.e., mapping) is required for systems and services to share information. Mappings are established be...

Asynchronous distributed machine learning solutions have proven very effective so far, but always assuming perfectly functioning workers. In practice, some of the workers can however exhibit Byzantine behavior, caused by hardware failures, software bugs, corrupt data, or even malicious attacks. We introduce Kardam, the first distributed asynchronous stochastic gradient descent (SGD) algorithm t...

The multitude of publications regarding overtraining syndrome (OTS or 'staleness') or the short-term 'over-reaching' and the severity of consequences for the athlete are in sharp contrast with the limited availability of valid diagnostic tools. Ergometric tests may reveal a decrement in sport-specific performance if they are maximal tests until exhaustion. Overtrained athletes usually present a...