Avinash Chandra Pandey

Twitter sentiment analysis using hybrid cuckoo search method

A hybrid cuckoo search method (CSK) has been presented for Twitter sentiment analysis.CSK modifies the random initialization of population in cuckoo search (CS) by K-means to resolve the problem of random initialization.The proposed algorithm has outperformed five popular algorithms.The statistical analysis has been done to validate the performance of the proposed algorithm. Sentiment analysis is one of the prominent fields of data mining that deals with the identification and analysis of sentimental contents generally available at social media. Twitter is one of such social medias used by many users about some topics in the form of tweets. These tweets can be analyzed to find the viewpoints and sentiments of the users by using clustering-based methods. However, due to the subjective nature of the Twitter datasets, metaheuristic-based clustering methods outperforms the traditional methods for sentiment analysis. Therefore, this paper proposes a novel metaheuristic method (CSK) which is based on K-means and cuckoo search. The proposed method has been used to find the optimum cluster-heads from the sentimental contents of Twitter dataset. The efficacy of proposed method has been tested on different Twitter datasets and compared with particle swarm optimization, differential evolution, cuckoo search, improved cuckoo search, gauss-based cuckoo search, and two n-grams methods. Experimental results and statistical analysis validate that the proposed method outperforms the existing methods. The proposed method has theoretical implications for the future research to analyze the data generated through social networks/medias. This method has also very generalized practical implications for designing a system that can provide conclusive reviews on any social issues.

Outlier detection: A survey on techniques of WSNs involving event and error based outliers

In the recent few years, many wireless sensor networks have been distributed systematically in the real world to collect valuable raw sensed data. However, the crucial point of challenge is to extract high level knowledge from this raw sensed data. In the application of data analysis, a necessary preprocessing step is anomaly detection, also known as deviation detection or data cleansing. Outliers in wireless sensor networks (WSNs) are those measures that deviate from a defined pattern. Outlier detection can be used to remove noisy data, detect faulty nodes and discover interesting events. Numerous small and low cost nodes loaded with capabilities of integrated sensing and computation are involved in a WSN structure. Due to high density WSNs are exposed to faults and nasty attacks causing inaccurate and unreliable sensors reading, making Wireless sensor networks prone to outliers. This survey provides an outline of outlier detection techniques and approaches focusing on event and error based outliers.

Unsupervised data classification using modified cuckoo search method

Data clustering is one of the widely used data analysis methods which groups the unlabeled data into similar clusters. Classical data clustering methods under-performs to cluster multi-dimensional dataset such as micro arrays datasets. Therefore, this paper introduces a novel metaheuristic gauss-based cuckoo search clustering method to extend the capabilities of traditional clustering methods. The efficacy of proposed data clustering method has been tested on the three micro-array datasets. From the experimental results effectiveness of proposed method has been observed.

Implementing and Testing Priority Scheduler and Token Bucket Policer in Differentiated Service

Internet applications are growing rapidly. The requirement of QoS by these applications varies from very lenient to strict. Maintaining QoS is one of the most typical and challenging task in such scenario. Differentiated services architecture is very popular in such scenario. Differentiated Services is a practical method to implement traffic based service differentiation works on traffic aggregation, per hop behaviour forwarding. Differentiated services uses classifiers to categorize traffic in to flows, policies are defined to allocate the resources to flows and policers are used to shape the bursty traffic whereas schedulers are used to forward the traffic from various traffic queues.

Spam Detection Using Rating and Review Processing Method

In recent times, e-commerce sites have become an essential part of people lifestyle. Viewers give feedback and firsthand account of the online products, and these reviews thus play an important role in decision making of the other buyers. So, in order to increase or decrease sales of products, spam reviews are generated by the companies. Hence, there is a need to detect and filter the spam reviews to provide customers genuine reviews of the product. In this paper, a review processing method is proposed. Some parameters have been suggested to find the usefulness of reviews. These parameters show the variation of a particular review from other, thus increasing the probability of it being spam. This method introduced classifies the review as helpful or non-helpful depending on the score assigned to the review.

Spam Detection Using Ensemble Learning

In our daily life, we use email and SMS many times to communicate to each other, but due to the increase of spam email and SMS, it becomes a headache for both the sender and receiver. We need spam detection tool to detect the spam, and there are many spam detection tools available in the market but they are not up to the mark because they only emphasize on individual classifier or only one or two combination of classifier. In our research, we present different combinations of four different classifiers, namely “Gaussian Naive Bayes”, “Multinomial Naive Bayes”, “Bernoulli Naive Bayes”, and “Decision Tree”. We have used voting classifier, a type of ensemble learning to calculate the accuracy of different combinations of classifiers. Results show that use of voting classifier produces more accurate prediction than individual classifier. We had also created an android application to serve the purpose. The mobile application works on client–server principle. Basically, the mobile application acts as a client which sends the data clicked by a user from mobile to server. At the server, there is machine learning script which classifies the received data and sends the prediction back to the client.

Semi-supervised Spatiotemporal Classification and Trend Analysis of Satellite Images

Classification of satellite images can be used for land information extraction, i.e., land cover maps, forest maps, industrial maps, residential maps, flooded maps, etc. The classification can be performed using any of the two methods, namely supervised classification method and unsupervised method. However, supervised classification methods require extensive training with existing training datasets. For satellite images, it is difficult to generate training dataset for all the land cover types. Therefore, this paper proposes a novel semi-supervised classification method to classify satellite images. The efficiency of proposed method is tested on satellite images of Delhi and Himalayan regions. Experimental results validate that the proposed method outperforms the existing methods.

Unsupervised data classification using improved biogeography based optimization

Unsupervised data classification (data clustering) is one of the mostly used data analysis methods which groups the unlabeled data into identical clusters (groups). Classical clustering methods do not perform effectively while clustering high dimensional datasets viz micro array datasets. Therefore, a novel clustering method based on Biogeography based optimization is proposed to extend the capabilities of traditional clustering methods. Performance of proposed method has been tested on the four micro-array datasets. Experimental results validate the effectiveness of proposed method.

Traffic Shaping at Differentiated Services Enabled Edge Router Using Adaptive Packet Allocation to Router Input Queue

Differentiated Services provide Quality of Service within a domain by aggregation of flows. There are mainly four modules which work together in Differentiated Services Classifier, Meter, Marker, and Shaper/Dropper. When congestion increases at Differentiated Services enabled router, Quality of Service is maintained according to the priority of packets by dropping lower priority packets, providing high preference to high-priority packets. As the buffer space is limited in routers, at time of congestion buffer management plays a crucial role to provide Quality of Service. In this paper work is focused on allocating buffer to incoming traffic adaptively according to current availability of resource and priority required by packets. Here, we address congestion control issues at Differentiated Services enabled edge routers using dynamic allocation of virtual queues (precedence queues) to incoming traffic at edge router by shifting lower priority packets to higher priority queues (if under-utilized).