Ketan Kotecha

Predicting stock and stock price index movement using Trend Deterministic Data Preparation and machine learning techniques

Four machine learning algorithms are used for prediction in stock markets.Focus is on data pre-processing to improve the prediction accuracy.Technical indicators are discretised by exploiting the inherent opinion.Prediction accuracy of algorithms increases when discrete data is used. This paper addresses problem of predicting direction of movement of stock and stock price index for Indian stock markets. The study compares four prediction models, Artificial Neural Network (ANN), Support Vector Machine (SVM), random forest and naive-Bayes with two approaches for input to these models. The first approach for input data involves computation of ten technical parameters using stock trading data (open, high, low & close prices) while the second approach focuses on representing these technical parameters as trend deterministic data. Accuracy of each of the prediction models for each of the two input approaches is evaluated. Evaluation is carried out on 10years of historical data from 2003 to 2012 of two stocks namely Reliance Industries and Infosys Ltd. and two stock price indices CNX Nifty and S&P Bombay Stock Exchange (BSE) Sensex. The experimental results suggest that for the first approach of input data where ten technical parameters are represented as continuous values, random forest outperforms other three prediction models on overall performance. Experimental results also show that the performance of all the prediction models improve when these technical parameters are represented as trend deterministic data.

Predicting stock market index using fusion of machine learning techniques

Two stage fusion model comprising three machine learning techniques is used.Emphasis is on adequacy of information given to prediction models.First stage provides future value of statistical parameters helping the later stage.Two stage fusion model helps in decreasing overall prediction error. The paper focuses on the task of predicting future values of stock market index. Two indices namely CNX Nifty and S&P Bombay Stock Exchange (BSE) Sensex from Indian stock markets are selected for experimental evaluation. Experiments are based on 10years of historical data of these two indices. The predictions are made for 1-10, 15 and 30days in advance. The paper proposes two stage fusion approach involving Support Vector Regression (SVR) in the first stage. The second stage of the fusion approach uses Artificial Neural Network (ANN), Random Forest (RF) and SVR resulting into SVR-ANN, SVR-RF and SVR-SVR fusion prediction models. The prediction performance of these hybrid models is compared with the single stage scenarios where ANN, RF and SVR are used single-handedly. Ten technical indicators are selected as the inputs to each of the prediction models.

Cluster Head Election for Energy and Delay Constraint Applications of Wireless Sensor Network

Designing of a multi-hop Wireless Sensor Network (WSN) depends upon the requirements of the underlying sensing application. The main objective of WSNs is to monitor physical phenomenon of interest in a given region of interest using sensors and provide collected data to sink. The WSN is made of a large number of energy, communication, and computational constraint nodes, to overcome energy constrains, replacing or recharging the batteries of the WSN nodes is an impossible task, once they are deployed in a hostile environment. Therefore, to keep the network alive as long as possible, communication between the WSN nodes must be done with load balancing. Time critical applications like forest fire detection, battle field monitoring demands reception of data by the sink with the bounded delay to avoid disasters. Hence, there is a need to design a protocol which enhances the network lifetime and provides information to the sink with a bounded delay. This paper will address this problem and solution. In this paper, a routing algorithm is proposed by introducing Energy Delay Index for Trade-off (EDIT) to optimize both objectives-energy and delay. The EDIT is used to select cluster heads and “next hop” by considering energy and/or delay requirements of a given application. Proposed approach is derived using two different aspects of distances between a node and the sink named Euclidean distance and Hop-count, and further prove using realistic parameters of radio to get data closest to the test bed implementation. The results aspire to give sufficient insights to others before doing test bed implementation.

Adaptive Scheduling Algorithm for Real-Time Multiprocessor Systems

EDF (Earliest Deadline First) has been proved to be optimal scheduling algorithm for single processor real-time system. It also performs well for multiprocessor system. Limitation of EDF is that its performance decreases exponentially when system becomes slightly overloaded. ACO (Ant Colony Optimization) based scheduling algorithm performs well in both underloaded and overloaded conditions. But its limitation is that it takes more time for execution compared to EDF. In this paper, an adaptive algorithm for multiprocessor real-time system is proposed, which is combination of both of these algorithms. The proposed algorithm along with EDF and ACO based algorithm is simulated for real-time multiprocessor system and the results are obtained. The performance is measured in terms of Success Ratio (SR) and Effective CPU Utilization (ECU). Execution Time taken by each scheduling algorithm is also measured. From analysis and experiments, it reveals that the proposed algorithm is fast as well as efficient in both underloaded and overloaded conditions for real-time multiprocessor systems.

Scheduling Algorithm for Real-Time Operating Systems Using ACO

The Ant Colony Optimization algorithms (ACO) are computational models inspired by the collective foraging behavior of ants. By looking at the strengths of ACO, they are the most appropriate for scheduling of tasks in soft real-time systems. In this paper, ACO based scheduling algorithm for real-time operating systems (RTOS) has been proposed. During simulation, results are obtained with periodic tasks, measured in terms of Success Ratio & Effective CPU Utilization and compared with Earliest Deadline First (EDF) algorithm in the same environment. It has been observed that the proposed algorithm is equally optimal during under loaded conditions and it performs better during overloaded conditions.

Efficient scheduling algorithms for real-time distributed systems

Dynamic scheduling has been always a challenging problem for real-time distributed systems. EDF (Earliest Deadline First) algorithm has been proved to be optimal scheduling algorithm for single processor real-time systems and it performs well for distributed systems also. In this paper, we have proposed scheduling algorithms for client/server distributed system with soft timing constraints. The algorithms are proposed with modifications in conventional EDF algorithm. The proposed algorithms are simulated; results are obtained and measured in terms of SR (Success Ratio) & ECU (Effective CPU Utilization). Finally the results are compared with EDF algorithm in the same environment. It has been observed that the proposed algorithms ares equally efficient during underloaded conditions and they perform much better during overloaded conditions.

Dynamic scheduling for real‐time distributed systems using ant colony optimization

Purpose – In client/server distributed systems, the server is often the bottleneck. Improving the server performance is thus crucial for improving the overall performance of distributed information systems. Real‐time system is required to complete its work and deliver its services on a timely basis. The purpose of this paper is to propose a new scheduling algorithm for real‐time distributed system (client/server model) to achieve the above‐mentioned goal.Design/methodology/approach – The ant colony optimization (ACO) algorithms are computational models inspired by the collective foraging behavior of ants. They provide inherent parallelism and robustness. Therefore, they are appropriate for scheduling of tasks in soft real‐time systems. During simulation, results are obtained with periodic tasks, measured in terms of success ratio and effective CPU utilization; and compared with results of earliest deadline first (EDF) algorithm in the same environment.Findings – Analysis and experiments show that the prop...

Alive Nodes Based Improved Low Energy Adaptive Clustering Hierarchy for Wireless Sensor Network

Energy efficiency is one of the important issues in the Wireless Sensor Networks (WSN). In this paper, a decentralized Alive Nodes based Low Energy Adaptive Clustering Hierarchy (AL-LEACH) is presented, that considers number of alive nodes in the network to elect the cluster heads. Alive nodes are used to dynamically compute weights of random numbers. Random number is one of the important parameters to elect cluster heads for the Low Energy Adaptive Clustering Hierarchy (LEACH) protocol. Extensive simulations are carried out to compare our proposed approach AL-LEACH with Low Energy Adaptive Clustering Hierarchy (LEACH), Low energy adaptive clustering hierarchy with Deterministic Cluster-Head Selection (LDCHS) and Advanced LEACH routing protocol for wireless micro sensor networks (ALEACH). Simulation results show that AL-LEACH improves the network life time and number of packets received by Base Station (BS) through balanced energy consumption of the network.

Comparative study of Distributed Intrusion Detection in Ad-hoc Networks

In recent years ad hoc networks are widely used because of mobility and open architecture nature. But new technology always comes with its own set of problems. Security of ad hoc network is an area of widespread research in recent years. Some unique characteristics of ad hoc network itself are an immense dilemma in the way of security. In this paper we have presented study about characteristics of ad hoc network, how they are problematic in ad hoc network security, attacks in ad hoc network and brief description of some existing intrusion detection system. We have also justified why distributed intrusion detection is better for ad hoc network with comparative study of existing intrusion detections in ad hoc network.

ACO Based Dynamic Scheduling Algorithm for Real-Time Multiprocessor Systems

The Ant Colony Optimization ACO algorithms are computational models inspired by the collective foraging behavior of ants. The ACO algorithms provide inherent parallelism, which is very useful in multiprocessor environments. They provide balance between exploration and exploitation along with robustness and simplicity of individual agent. In this paper, ACO based dynamic scheduling algorithm for homogeneous multiprocessor real-time systems is proposed. The results obtained during simulation are measured in terms of Success Ratio SR and Effective CPU Utilization ECU and compared with the results of Earliest Deadline First EDF algorithm in the same environment. It has been observed that the proposed algorithm is very efficient in underloaded conditions and it performs very well during overloaded conditions also. Moreover, the proposed algorithm can schedule some typical instances successfully which are not possible to schedule using EDF algorithm.