P. M. Rubesh Anand

Identity and access management for cloud web services

Cloud computing plays an important role in fulfilling the present day organizational requirements. The recent attraction of cloud web services due to its availability and cost effectiveness is achieved by different flexible service models like, IaaS, SaaS, PaaS and multi tenancy. The privacy and security risks associated with these service models are high. In order to minimize the risks in cloud web service, organizations require a strong, flexible, scalable and accountable Identity and Access Management (IAM) system. In this paper, we propose an integrated identity and attribute based access management system for cloud web services. The combination of authentication and attribute based access control provides improved security to the cloud web service.

Big data analytics for disaster response and recovery through sentiment analysis

Abstract Big data created by social media and mobile networks provide an exceptional opportunity to mine valuable insights from them. This information is harnessed by business entities to measure the level of customer satisfaction but its application in disaster response is still in its inflection point. Social networks are increasingly used for emergency communications and help related requests. During disaster situations, such emergency requests need to be mined from the pool of big data for providing timely help. Though government organizations and emergency responders work together through their respective national disaster response framework, the sentiment of the affected people during and after the disaster determines the success of the disaster response and recovery process. In this paper, we propose a big data driven approach for disaster response through sentiment analysis. The proposed model collects disaster data from social networks and categorize them according to the needs of the affected people. The categorized disaster data are classified through machine learning algorithm for analyzing the sentiment of the people. Various features like, parts of speech and lexicon are analyzed to identify the best classification strategy for disaster data. The results show that lexicon based approach is suitable for analyzing the needs of the people during disaster. The practical implication of the proposed methodology is the real-time categorization and classification of social media big data for disaster response and recovery. This analysis helps the emergency responders and rescue personnel to develop better strategies for effective information management of the rapidly changing disaster environment.

Encrypted token based authentication with adapted SAML technology for cloud web services

Abstract Web applications and cloud services are rapidly emerging as the inevitable technology for communication between organizations. Cloud-based solutions are currently deployed to provide improvement in the existing business processes and services. The major challenge involved in cloud is data security that is stored and transferred. Cloud infrastructure requires an extensive authentication mechanism to protect data as well as to ensure that the right person is accessing the right information. In this paper, token based fine grained authentication for cloud web services with the help of adapted Security Assertion Markup Language (SAML) technology is proposed. The entire set of communications between Identity Provider, Service Provider and Cloud Server is encrypted to enhance the security. The combination of SAML and single use access token based verification provides improved security to cloud web services. The proposed adapted SAML authentication mechanism ensures flexibility and scalability of the environment by the provision of adding multiple numbers of trusted sources and web services.

An empirical analysis and classification of crisis related tweets

The social media generates large volume of data through tweets and text messages during and after any disaster. The analysis and classification of the obtained data at the time of disaster is essential for conveying the information to the appropriate rescue personnel. In this paper, an automated text classification system is proposed in order to classify the data effectively. The classification of the tweets related to disaster is a challenging task as the texts are not correctly written or do not convey the exact meaning since people send the text messages in panic situations. A manual vocabulary has been created by considering the nature of the disaster data. The created vocabulary is used for splitting the tweets into various categories. In the categorized data, popular statistical feature selection methods like, term frequency, Chi Square are used in combination with Support Vector Machine (SVM) and Naïve Bayes algorithms to classify the data. The results reveal that SVM performs better than Multinomial and Bernoulli Naïve Bayes for all the classes of disaster related data.

Optimized gradient histogram preservation with block wise SURE shrinkage for noise free image restoration

The image noise removal and restoration techniques invariably employ the hybrid filter and genetic algorithm approaches for recovery of noise free images. However, the desired level of denoising is not met with these approaches. The usage of adaptive genetic algorithm recovers the quality of the restored image. In order to improve the image denoising performance, an innovative noise removal method named optimized gradient histogram preservation (OGHP) is proposed. Initially, the preprocessing is applied on the noise contaminated image. Subsequently, the preprocessed image is subjected to OGHP noise exclusion procedure and stein’s unbiased risk estimate shrinkage. The resulted noiseless images are passed through the image restoration procedure carried out by employing the proposed adaptive genetic algorithm. The performance evaluation of the proposed method compared with the existing techniques demonstrates the efficiency of the proposed technique in noise elimination and effective restoration of image.

Robust CHARM: an efficient data hosting scheme for cloud data storage system

Cloud computing is the recent evolving arena, which offers more benefits to cloud service providers and online users, compared to the traditional architecture. In this paper, an efficient data-hosting scheme with high availability for implementing over heterogeneous multi-cloud system is proposed. The proposed ROBUST CHARM (RCH) scheme is designed with data hosting, storage mode switching, speed mode and workload indicator modules. These modules process data with the support of heuristic and storage mode transition algorithm. The algorithm is proved efficient in identifying the apt cloud to store data. Storage transition is adopted by considering the cost and data access pattern of the data stored during any requirements. This evaluation enables efficient usage of cloud resources with high availability. The experimental results show that the proposed scheme works effectively without affecting the performance compared to the existing systems. The ability to utilize heterogeneous multi-cloud storage with the benefit of cost effectiveness is an added advantage to the cloud users.

A secure and reputation based recommendation framework for cloud services

The expanding applications of cloud computing has urged the researchers with strong requirements for developing trust management models. It is essential to create trust management system that is adoptable for improving the privacy of the consumers, enabling the service availability, providing security to both cloud service providers and consumers of cloud services. Due to the dynamic cloud environment and proliferation of cloud users, identification of malicious users who can harm the reputation of a cloud service is a difficult task. In this paper, a Secure and Reputation based Recommendation Framework for Cloud Services (SRRFCS) is proposed to provide Trust as a Service (TaaS). The proposed framework provides privacy ensured trust quantified system and enables protection against malicious users through a reliability model by comparing with other cloud services. The work also focuses on presenting an availability model for decentralization of trust management service. The applicability of the proposed system is studied using an experimental setup with the set of real time trust feedbacks over the cloud services. In the proposed system, the service selection and usage are considered for recommendation which provides the easy way to select the best cloud services compared to the existing Service-Level Agreement (SLA) and Lightweight Directory Access Protocol (LDAP) methodologies.

DRS tunable monopole antenna for dual band wireless LAN applications

Dielectric Resonator Antenna (DRA) plays a vital role in the wireless communication systems due to its support for wide impedance bandwidth and symmetrical radiation pattern. Dielectric Resonator Structures (DRS) combined with metallic structures reduce the antenna size at low frequency bands of operation. In this paper, a monopole antenna is designed to operate at 5.5 GHz and the antenna performance is identically shifted to 3.6 GHz by loading a cylindrical shape dielectric resonator structure over the monopole antenna. The DRS provides wider impedance bandwidth at lower resonant frequency with negligible dielectric losses. The dielectric resonating structure is designed using Bakelite with the dielectric constant (εr) of 4.8. The simulated monopole antenna with and without DRS is studied for its performance measures. The antenna performance is evaluated through fabrication of the DRS and monopole antenna. Dual band operation of the monopole antenna operating at 5.5 GHz and 3.6 GHz is achieved with the help of DRS. The designed and fabricated monopole antenna structure is suitable for wireless LAN applications.