Recency Factor Research Articles

Survey Inter-Reference Recency Based Page Replacement Policies to Cope with Weak Locality Workloads

Least recently used (LRU) makes bold assumption on recency factor only which made LRU miss behave with weak locality workloads. If the “frequency”, of each page reference is taken into consideration, it will perform better in the case where workload has weak locality. Frequency count leads to serious problem after a long duration of reference stream because it cannot cope with change in locality. Reuse distance or inter reference recency (IRR) of a block is equal to number of distinct pages accessed between recent consecutive or correlated access of that particular block. Many recent variations of LRU use IRR rather than recency such that LRU can be made friendly with weak locality workloads. This papers surveys LRU variants that use IRR to make page replacement decision.

Enhanced Service Discovery Protocol for MANET by Effective Cache Management

With the increasing pervasiveness of the mobile nodes, service discovery has become inevitable. In the resource constrained mobile nodes, caching is being used to reduce the access cost. The enhanced service discovery protocol presented in this paper is a combination of cache placement, cache discovery, cache consistency and replacement algorithms. The overheard service information is cached by the coordinator nodes of each geographical area to reduce the discovery delay. A light weight cache discovery algorithm that uses a minimum spanning tree is proposed. The cache consistency is maintained in a soft state. Cache replacement is done based on a weight value that is calculated using the recency, frequency and cost factors. An M/G/1/∞ non-preemptive queuing model is proposed to analyse the cache replacement performance. The extensive simulation results performed to demonstrate the effectiveness of the proposed enhanced service discovery protocol in terms of reduction in the service discovery delay and number of cache replacements. The replacement scheme proposed has increased the cache hit ratio.

A bi-objective mixed-model assembly line sequencing problem considering customer satisfaction and customer buying behaviour

ABSTRACTCustomer satisfaction and focusing on the most profitable customers are the key elements to achieving a sustainable competitive advantage in the current business environment. The mixed-model assembly line (MMAL) is an efficient type of manufacturing system that has been used increasingly over recent years to satisfy diverse customer demands. Product sequencing in an MMAL system has a huge effect on the performance of the firm in meeting customer demand and, therefore, on customer satisfaction. This study aims to address a sequencing problem with respect to recency, frequency and monetary factors. A two-stage framework is developed to achieve this goal. First, the prioritized orders based on the preference ranking organization method for enrichment of evaluations (PROMETHEE) are categorized into high-priority and normal-priority orders. Then, a bi-objective mathematical programming model is developed to determine the optimum sequence of products to minimize the total cost, as well as to maximize levels of customer satisfaction. After validation of the proposed model, owing to the NP-hard nature of this problem, two multi-objective metaheuristics are applied to tackle the second stage of this study. Several test problems are presented to evaluate the performance of these algorithms. The results show the superiority of one solution approach over the other.

Recency-based preferential attachment models

Preferential attachment models were shown to be very effective in predicting such important properties of real-world networks as the power-law degree distribution, small diameter, etc. Many different models are based on the idea of preferential attachment: LCD, Buckley-Osthus, Holme-Kim, fitness, random Apollonian network, and many others. Although preferential attachment models reflect some important properties of real-world networks, they do not allow to model the so-called recency property. Recency property reflects the fact that in many real networks nodes tend to connect to other nodes of similar age. This fact motivated us to introduce a new class of models – recency-based models. This class is a generalization of fitness models, which were suggested by Bianconi and Barabasi. Bianconi and Barabasi extended preferential attachment models with pages’ inherent quality or fitness of nodes. When a new node is added to the graph, it is joined to some already existing nodes that are chosen with probabilities proportional to the product of their fitness and incoming degree. We generalize fitness models by adding a recency factor to the attractiveness function. This means that pages are gaining incoming links according to their attractiveness, which is determined by the incoming degree of the page, its inherent popularity (some page-specific constant) and age (new pages are gaining new links more rapidly). We analyze different properties of recency-based models. For example, we show that some distributions of inherent popularity lead to the power-law degree distribution.

A Novel Approach to Enhance the Efficiency of Distributed Cooperative Caching in SWNETs

This project helps to improve Performance of Distributed Cooperative Caching by choosing appropriate object replacement algorithms in the Social wireless networks (SWNET). E-Object caching in such SWNETs are shown to be able to minimize the Object provisioning and maintenance cost which is based on the pricing and service dependences among different stakeholders including network communication service providers, Object providers (Server) and End users. Here we consider replacement of objects with respect to two dimensions. One is Frequency and another is Recency (freshness) factor of object requests. The efficiency of the algorithm lies in choosing which items to discard to make room for the new ones. So we use the concept of knapsack problem with respect to frequency and freshness of the objects. So nodes maintain their cache memories with more frequent and latest objects.

Memory factors in Rey AVLT: Implications for early staging of cognitive decline.

Supraspan verbal list learning is widely used to assess dementia and related cognitive disorders where declarative memory deficits are a major clinical sign. While the overall learning rate is important for diagnosis, serial position patterns may give insight into more specific memory processes in patients with cognitive impairment. This study explored these patterns in a memory clinic clientele. One hundred eighty three participants took the Rey Auditory-Verbal Learning Test (RAVLT). The major groups were patients with Alzheimer's disease (AD), Vascular Dementia (VD), Mild Cognitive Impairment (MCI), and Subjective Cognitive Impairment (SCI) as well as healthy controls (HC). Raw scores for the five trials and five serial partitions were factor analysed. Three memory factors were found and interpreted as Primacy, Recency, and Resistance to Interference. AD and MCI patients had impaired scores in all factors. SCI patients were significantly impaired in the Resistance to Interference factor, and in the Recency factor at the first trial. The main conclusion is that serial position data from word list testing reflect specific memory capacities which vary with levels of cognitive impairment.

Individual differences in memory search and their relation to intelligence.

Attempts to understand why memory predicts intelligence have not fully leveraged state-of-the-art measures of recall dynamics. Using data from a multisession free recall study, we examine individual differences in measures of recall initiation and postinitiation transitions. We identify 4 sources of variation: a recency factor reflecting variation in the tendency to initiate recall from an item near the end of the list, a primacy factor reflecting a tendency to initiate from the beginning of the list, a temporal factor corresponding to transitions mediated by temporal associations, and a semantic factor corresponding to semantically mediated transitions. Together, these 4 factors account for 83% of the variability in overall recall accuracy, suggesting they provide a nearly complete picture of recall dynamics. We also show that these sources of variability account for over 80% of the variance shared between memory and intelligence. The temporal association factor was the most influential in predicting both recall accuracy and intelligence. We outline a theory of how controlled drift of temporal context may be critical across a range of cognitive activities.

Pronominal Anaphora Resolution in Punjabi Language

Anaphora Resolution is a process of finding referents in discourse. In computational linguistic, Anaphora resolution is complex and challenging task. This paper focuses on pronominal anaphora resolution. It is a subpart of anaphora resolution where pronouns are referred to noun referents. Including anaphora resolution into many applications like automatic summarization, opinion mining, machine translation, question answering systems etc. increase their accuracy by 10%. Related work in this field has been done in many languages. This paper focuses on resolving anaphora for Punjabi language. A model is proposed for resolving anaphora and an experiment is conducted to measure the accuracy of the system. The model uses two factors: Recency and Animistic knowledge. Recency factor works on the concept of Lappin Leass approach and for introducing animistic knowledge gazetteer method is used. The experiment is conducted on a Punjabi story containing more than 1000 words and result is drawn with the future directions.

Analysis of Anaphora Resolution System for English Language

Anaphora resolution is complex problem in linguistics and has attracted the attention of many researchers. It is the problem of identifying referents in the discourse. Anaphora Resolution plays an important role in Natural language processing task. This paper completely emphasis on pronominal anaphora resolution for English Language in which pronouns refers to the intended noun in discourse. In this paper two computational models are proposed for anaphora resolution. Resolution of anaphora is based on various factors among which these models use Recency factor and Animistic Knowledge. Recency factor is implemented by using Lappin Leass approach in first model and using Centering approach in second model. Information about animacy is obtained by Gazetteer method. The identification of animistic elements is employed to improve the accuracy of the system. This paper demonstrates experiment conducted by both the models on different data sets from different domains. A comparative result of both the model is summarized and conclusion is drawn for the best suitable model.

Comparative Performance Analysis of Two Anaphora Resolution Systems

Anaphora Resolution is the process of finding referents in the given discourse. Anaphora Resolution is one of the complex tasks of linguistics. This paper presents the performance analysis of two computational models that uses Gazetteer method for resolving anaphora in Hindi Language. In Gazetteer method different classes (Gazettes) of elements are created. These Gazettes are used to provide external knowledge to the system. The two models use Recency and Animistic factor for resolving anaphors. For Recency factor first model uses the concept of centering approach and second uses the concept of Lappin Leass approach. Gazetteers are used to provide Animistic knowledge. This paper presents the experimental results of both the models. These experiments are conducted on short Hindi stories, news articles and biography content from Wikipedia. The respective accuracy for both the model is analyzed and finally the conclusion is drawn for the best suitable model for Hindi Language.

Recency and Prior Probability (RPP) based Page Replacement Policy to Cope with Weak Locality Workloads having Probabilistic Pattern

Development of efficient block replacement policy is the topic of much research in operating system as well as database management systems. Among variety of page replacement algorithms Least Recently Used (LRU) algorithm is simple, flexible and has low overhead. LRU replaces page that is not accessed for longest time. But LRU makes bold assumption on recency factor only, which made LRU misbehave with weak locality workloads. This paper proposes a new Recency and Prior Probability (RPP) based page replacement policy for block replacement. The RPP combines recency and prior probability associated with the pages while selecting the victim frame from memory. If a page, to be used, has probability n times higher than another page, the page will get log(n) more chances to stay in the memory than lower probability pages. Hence with RPP, it is possible to prevent pages having higher probability of use from being replaced General Terms: Page Replacement, Memory Management, Operating System

MTD method for better prediction of sea surface temperature

A class of incremental learning procedures known as the Modified Temporal Difference (MTD) method is introduced in this paper for fixed-step prediction problems which uses the functional features of Multilayer Perceptron. The method is applied for weekly prediction of the Sea Surface Temperature (SST) from oceanographic data. Temporal Difference (TD) methods suggest how each output of a temporal sequence must be changed, whereas a back-propagation algorithm decides which part(s) of a network to change in order to influence its output and reduce the overall error. In other words, TD methods and backpropagation address temporal credit and structural credit assignment issues, respectively. While the two methods address different sides of the same issues they are quite compatible and easily combined. A new scheme is formed by combining the advantage of back-propagation and TD methods catering to fixedstep problems and is named as the MTD method. The back-propagation algorithm is modified to propagate the temporal error. For prediction problems, the exponential recency has not been found suitable due to its large negative slope. In this paper a weighing scheme is introduced in which alterations are made to past predictions according to a newly proposed recency factor. The stochastic method, back-propagation algorithm, TD and MTD methods are applied to predict the SST values in the Arabian Sea, the Bay of Bengal and Central Indian Ocean and a comparative study is made. From the study it is observed that the proposed alternative recency factor in the MTD method leads to better prediction than the exponential recency.

TD(λ) learning without eligibility traces: a theoretical analysis

A common approach to learning from delayed rewards is to use temporal difference (TD) methods for predicting future reinforcement values. They are parameterized by a recency factor λ which determines whether and how the outcomes from several consecutive time steps contribute to a single prediction update. TD(λ > 0) has been found to usually yield noticeably faster learning than TD(0), but its standard eligibility traces implementation is associated with some well known deficiencies, in particular significantly increased computation expense. This article investigates theoretically two possible ways of implementing TD(λ) without eligibility traces, both proposed by prior work. One is the TTD procedure, which efficiently approximates the effects of eligibility traces by the use of truncated TD(λ) returns. The other is experience replay, which relies on replaying TD prediction updates backwards in time. We provide novel theoretical results related to the former and present an original analysis of the effects of two variations of the latter. The ultimate effect of these investigations is a unified view of the apparently different computational techniques. This contributes to the TD(λ) research in general, by highlighting interesting relationships between several TD-based algorithms and facilitating their further analysis.

Truncating temporal differences

Temporal difference (TD) methods constitute a class of methods for learning predictions in multi-step prediction problems, parameterized by a recency factor λ. Currently the most important applicat...

Truncating Temporal Differences: On the Efficient Implementation of TD(lambda) for Reinforcement Learning

Temporal difference (TD) methods constitute a class of methods for learning predictions in multi-step prediction problems, parameterized by a recency factor lambda. Currently the most important application of these methods is to temporal credit assignment in reinforcement learning. Well known reinforcement learning algorithms, such as AHC or Q-learning, may be viewed as instances of TD learning. This paper examines the issues of the efficient and general implementation of TD(lambda) for arbitrary lambda, for use with reinforcement learning algorithms optimizing the discounted sum of rewards. The traditional approach, based on eligibility traces, is argued to suffer from both inefficiency and lack of generality. The TTD (Truncated Temporal Differences) procedure is proposed as an alternative, that indeed only approximates TD(lambda), but requires very little computation per action and can be used with arbitrary function representation methods. The idea from which it is derived is fairly simple and not new, but probably unexplored so far. Encouraging experimental results are presented, suggesting that using lambda > 0 with the TTD procedure allows one to obtain a significant learning speedup at essentially the same cost as usual TD(0) learning.

Disparate Impact, Disparate Treatment, and the Displaced Homemaker

All marriages end. When a marriage ends because of death, the surviving spouse typically is a woman. Also typically, provisions for her continued support are inadequate. When a marriage ends in divorce, the female partner usually must find some way of supporting herself. Even when the marriage does not end, disability of a husband or inflation and familial needs sometimes make it imperative that a wife return to work. In all these cases, older women without recent experience in the labor force traditionally have found it difficult to qualify for any except the most menial jobs.' A federal district court recently decreed that use of a recency factor in evaluating a woman's qualifications for a position has a discriminatory impact on older women possibly constituting gender and age discrimination in the absence of other defenses to such claims.2

A factor Analytic Demonstration of two Memory Processes

A principal component solution and varimax rotation were obtained for eight studies using a serial position (SP) probe technique for studying short-term memory. The factor pattern which emerged showed the first and middle SPs to load on one factor, called the primacy factor, while the middle and last positions loaded on a second factor, called the recency factor. The results were consistent with the view that short-term memory is composed of two processes, primary memory and secondary memory. One study supported the notion that immature humans show a rehearsal deficit.

Primacy and Recency Factors in Animal Motor Learning

(1929). Primacy and Recency Factors in Animal Motor Learning. The Pedagogical Seminary and Journal of Genetic Psychology: Vol. 36, No. 2, pp. 240-256.

Pattern Versus Frequency and Recency Factors in Maze Learning: A Preliminary Study

Pattern Versus Frequency and Recency Factors in Maze Learning: A Preliminary Study

Learning When Frequency and Recency Factors Are Negative.

Learning When Frequency and Recency Factors Are Negative.