Dynamic feature selection for spam filtering using support vector machine

Spam is commonly defined as unsolicited email messages and the goal of spam filtering is to differentiate spam from legitimate email. Much work have been done to filter spam from legitimate emails using machine learning algorithm and substantial performance has been achieved with some amount of false positive (FP) tradeoffs. In this paper, architecture of spam filtering has been proposed based on support vector machine (SVM,) which will get better accuracy by reducing FP problems. In this architecture an innovative technique for feature selection called dynamic feature selection (DFS) has been proposed which is enhanced the overall performance of the architecture with reduction of FP problems. The experimental result shows that the proposed technique gives better performance compare to similar existing techniques.

Portfolio selection under higher moments using fuzzy multi-objective linear programming

Since asset returns have been recognized as not normally distributed, the avenue of research regarding portfolio higher moments soon emerged. To account for uncertainty and vagueness of portfolio returns as well as of higher moment risks, we proposed a new portfolio selection model employing fuzzy sets in this paper. A fuzzy multi-objective linear programming (MOLP) for portfolio optimization is formulated using marginal impacts of assets on portfolio higher moments, which are modelled by trapezoidal fuzzy numbers. Through a consistent centroid-based ranking of fuzzy numbers, the fuzzy MOLP is transformed into an MOLP that is then solved by the maximin method. By taking portfolio higher moments into account, the approach enables investors to optimize not only the normal risk (variance) but also the asymmetric risk (skewness) and the risk of fat-tails (kurtosis). An illustrative example demonstrates the efficiency of the proposed methodology comparing to previous portfolio optimization models.

Selection of the right risk measures for portfolio allocation

 An optimisation framework is proposed to enable investors to select the right risk measures in portfolio selection. Verification is deployed by performing experiments in developed markets (e.g., the US stock market), emerging markets (e.g., the South Korean stock market) and global investments. A preselection procedure dealing with large datasets is also introduced to eliminate stocks that have low diversification potential before running the portfolio optimisation model. Portfolios are evaluated by four performance indices, i.e., the Sortino ratio, the Sharpe ratio, the Stutzer performance index, and the Omega measure. Experimental results demonstrate that high performance and also well-diversified portfolios are obtained if modified value-at-risk, variance, or semi-variance is concerned whereas emphasising only skewness, kurtosis or higher moments in general produces low performance and poorly diversified portfolios. In addition, the preselection applied to large datasets results in portfolios that have not only high performance but also high diversification degree.

Dynamic access point association using software defined networking

Previous attempts in addressing Access Point (AP) association at overlapping zone of IEEE 802.11 networks have shown some issues. They work passively and estimate load from different network metrics such as frame delay, packet loss, number of users etc. that may not always true. Further the user behaviour is selfish i.e. illegitimate user consume high network resources. This adversely affect existing or new users which in turn motivates them to change locations. To alleviate these issues, we propose the use of a Software Defined Networking (SDN) enabled client side (wireless end user) solution. In this paper, we start by proposing a dynamic AP selection algorithm/framework in wireless user device. The device receive network resource related statistics from SDN Controller and guide the client device to associate itself with the best selected AP. We justify that the use of SDN discourage users to act selfishly. Further, a mathematical modelling of the proposed scheme is derived using Fuzzy membership function and the simulation is carried out. Results obtained from simulation necessitates to implement SDN enabled client side methods.

Architecture of adaptive spam filtering based on machine learning algorithms

Spam is commonly defined as unsolicited email messages and the goal of spam filtering is to distinguish between spam and legitimate email messages. Much work has been done to filter spam from legitimate emails using machine learning algorithm and substantial performance has been achieved with some amount of false positive (FP) tradeoffs. In the case of spam detection FP problem is unacceptable sometimes. In this paper, an adaptive spam filtering model has been proposed based on Machine learning (ML) algorithms which will get better accuracy by reducing FP problems. This model consists of individual and combined filtering approach from existing well known ML algorithms. The proposed model considers both individual and collective output and analyzes them by an analyzer. A dynamic feature selection (DFS) technique also proposed in this paper for getting better accuracy.

Spam filtering using classification algorithms

This thesis proposes an innovative adaptive multi-classifier spam filtering model, with a grey-list analyser and a dynamic feature selection method, to overcome false-positive problems in email classification. It also presents additional techniques to minimize the added complexity. Empirical evidence indicates the success of this model over existing approaches.

Analyst coverage and financing decisions

We provide evidence that analyst coverage affects security issuance. First, firms covered by fewer analysts are less likely to issue equity as opposed to debt. They issue equity less frequently, but when they do so, it is in larger amounts. Moreover, these firms depend more on favorable market conditions for their equity issuance decisions. Finally, debt ratios of less covered firms are more affected by Baker and Wurgler’s(2002) “external finance-weighted” average market-to-book ratio. These results are consistent with market timing behavior associated with information asymmetry, as well as behavior implied by dynamic adverse selection models of equity issuance.

Microhabitat selection by sea turtles in a dynamic thermal marine environment

1Reproductive fitness is often compromised at the margins of a species’ range due to sub-optimal conditions.2Set against this backdrop, the Mediterranean's largest loggerhead sea turtle (Caretta caretta) rookery at Zakynthos (Greece) presents a conundrum, being at a very high latitude for this species, yet hosting a high concentration of nesting.3We used visual surveys combined with global positioning system (GPS) tracking to show that at the start of the breeding season, individuals showed microhabitat selection, with females residing in transient patches of warm water. As the sea warmed in the summer, this selection was no longer evident.4As loggerhead turtles are ectothermic, this early season warm-water selection presumably speeds up egg maturation rates before oviposition, thereby allowing more clutches to be incubated when sand conditions are optimal during the summer.5Active selection of warm waters may allow turtles to initiate nesting at an earlier date.

Dynamic cloud service selection using an adaptive learning mechanism in multi-cloud computing

Cloud service selection in a multi-cloud computing environment is receiving more and more attentions. There is an abundance of emerging cloud service resources that makes it hard for users to select the better services for their applications in a changing multi-cloud environment, especially for online real time applications. To assist users to efficiently select their preferred cloud services, a cloud service selection model adopting the cloud service brokers is given, and based on this model, a dynamic cloud service selection strategy named DCS is put forward. In the process of selecting services, each cloud service broker manages some clustered cloud services, and performs the DCS strategy whose core is an adaptive learning mechanism that comprises the incentive, forgetting and degenerate functions. The mechanism is devised to dynamically optimize the cloud service selection and to return the best service result to the user. Correspondingly, a set of dynamic cloud service selection algorithms are presented in this paper to implement our mechanism. The results of the simulation experiments show that our strategy has better overall performance and efficiency in acquiring high quality service solutions at a lower computing cost than existing relevant approaches.

Dynamic reconfiguration of multi-agent systems based on autonomy oriented computing

Dynamic reconfiguration has been listed as one of the key challenges in support of agent adaptation to environments, which has attracted much attention of researchers world wide. To tackle this tough problem, an agent-based dynamic reconfiguration model (ADRM) is proposed from the autonomy-oriented computing (AOC) point of view. The ERA (environment-reactive rules-agents) algorithm used in AOC is improved to support the organization formation behavior, which is essential in dynamic reconfiguration. To test the efficiency of this model and the effectiveness of different reactive behaviors, the performance of this model was investigated under different selection probabilities.