Mansaf Alam

Mohd Ashhad, Omar Ahmed, Sooraj K. Ambat et al.

Rising urban populations have led to a surge in vehicle use and made traffic monitoring and management indispensable. Acoustic traffic monitoring (ATM) offers a cost-effective and efficient alternative to more computationally expensive methods of monitoring traffic such as those involving computer vision technologies. In this paper, we present MVD and MVDA: two open datasets for the development of acoustic traffic monitoring and vehicle-type classification algorithms, which contain audio recordings of moving vehicles. The dataset contain four classes- Trucks, Cars, Motorbikes, and a No-vehicle class. Additionally, we propose a novel and efficient way to accurately classify these acoustic signals using cepstrum and spectrum based local and global audio features, and a multi-input neural network. Experimental results show that our methodology improves upon the established baselines of previous works and achieves an accuracy of 91.98% and 96.66% on MVD and MVDA Datasets, respectively. Finally, the proposed model was deployed through an Android application to make it accessible for testing and demonstrate its efficacy.

Preeti Agarwal, Mansaf Alam

Human Activity Recognition (HAR) using wearable and mobile sensors has gained momentum in last few years, in various fields, such as, healthcare, surveillance, education, entertainment. Nowadays, Edge Computing has emerged to reduce communication latency and network traffic.Edge devices are resource constrained devices and cannot support high computation. In literature, various models have been developed for HAR. In recent years, deep learning algorithms have shown high performance in HAR, but these algorithms require lot of computation making them inefficient to be deployed on edge devices. This paper, proposes a Lightweight Deep Learning Model for HAR requiring less computational power, making it suitable to be deployed on edge devices. The performance of proposed model is tested on the participants six daily activities data. Results show that the proposed model outperforms many of the existing machine learning and deep learning techniques.

Leena Khanna, Shailendra Narayan Singh, Mansaf Alam

Academic performance of any individual is dependent upon numerous aspects regarding the day to day life of the individual under consideration. Academic performance is measured in terms of the grade point average or GPA as it is called. Grade point average is dependent not only on the faculty but also on various psychological parameters including the study habits, social anxiety and allied. In this study, a detail analysis of numerous psychological factors impacting the grade point was carried and based upon various psychological factors the performance for the student in forth coming examination was forecasted.

Kashish A. Shakil, Farhana J. Zareen, Mansaf Alam et al.

Advancements in healthcare industry with new technology and population growth has given rise to security threat to our most personal data. The healthcare data management system consists of records in different formats such as text, numeric, pictures and videos leading to data which is big and unstructured. Also, hospitals have several branches at different locations throughout a country and overseas. In view of these requirements a cloud based healthcare management system can be an effective solution for efficient health care data management. One of the major concerns of a cloud based healthcare system is the security aspect. It includes theft to identity, tax fraudulence, insurance frauds, medical frauds and defamation of high profile patients. Hence, a secure data access and retrieval is needed in order to provide security of critical medical records in health care management system. Biometric authentication mechanism is suitable in this scenario since it overcomes the limitations of token theft and forgetting passwords in conventional token id-password mechanism used for providing security. It also has high accuracy rate for secure data access and retrieval. In this paper we propose BAMHealthCloud which is a cloud based system for management of healthcare data, it ensures security of data through biometric authentication. It has been developed after performing a detailed case study on healthcare sector in a developing country. Training of the signature samples for authentication purpose has been performed in parallel on hadoop MapReduce framework using Resilient Backpropagation neural network. From rigorous experiments it can be concluded that it achieves a speedup of 9x, Equal error rate (EER) of 0.12, sensitivity of 0.98 and specificity of 0.95 as compared to other approaches existing in literature.

Farhana Javed Zareen, Kashish Ara Shakil, Mansaf Alam et al.

With an exponential increase in number of users switching to mobile banking, various countries are adopting biometric solutions as security measures. The main reason for biometric technologies becoming more common in the everyday lives of consumers is because of the facility to easily capture biometric data in real time, using their mobile phones. Biometric technologies are providing the potential security framework to make banking more convenient and secure than it has ever been. At the same time, the exponential growth of enrollment in the biometric system produces massive amount of high dimensionality data that leads to degradation in the performance of the mobile banking systems. Therefore, in order to overcome the performance issues arising due to this data deluge, this paper aims to propose a distributed mobile biometric system based on a high performance cluster Cloud. High availability, better time efficiency and scalability are some of the added advantages of using the proposed system. In this paper a Cloud based mobile biometric authentication framework (BAMCloud) is proposed that uses dynamic signatures and performs authentication. It includes the steps involving data capture using any handheld mobile device, then storage, preprocessing and training the system in a distributed manner over Cloud. For this purpose we have implemented it using MapReduce on Hadoop platform and for training Levenberg-Marquardt backpropagation neural network has been used. Moreover, the methodology adopted is very novel as it achieves a speedup of 8.5x and a performance of 96.23%. Furthermore, the cost benefit analysis of the implemented system shows that the cost of implementation and execution of the system is lesser than the existing ones. The experiments demonstrate that the better performance is achieved by proposed framework as compared to the other methods used in the recent literature.

Mansaf Alam, Kishwar Sadaf

Giving user a simple and well organized web search result has been a topic of active information Retrieval (IR) research. Irrespective of how small or ambiguous a query is, a user always wants the desired result on the first display of an IR system. Clustering of an IR system result can render a way, which fulfills the actual information need of a user. In this paper, an approach to cluster an IR system result is presented.The approach is a combination of heuristics and k-means technique using cosine similarity. Our heuristic approach detects the initial value of k for creating initial centroids. This eliminates the problem of external specification of the value k, which may lead to unwanted result if wrongly specified. The centroids created in this way are more specific and meaningful in the context of web search result. Another advantage of the proposed method is the removal of the objective means function of k-means which makes cluster sizes same. The end result of the proposed approach consists of different clusters of documents having different sizes.

Mansaf Alam, Shuchi Sethi

Recent research shows that colluded malware in different VMs sharing a single physical host may use a resource as a channel to leak critical information. Covert channels employ time or storage characteristics to transmit confidential information to attackers leaving no trail.These channels were not meant for communication and hence control mechanisms do not exist. This means these remain undetected by traditional security measures employed in firewalls etc in a network. The comprehensive survey to address the issue highlights that accurate methods for fast detection in cloud are very expensive in terms of storage and processing. The proposed framework builds signature by extracting features which accurately classify the regular from covert traffic in cloud and estimates difference in distribution of data under analysis by means of scores. It then adds context to the signature and finally using machine learning (Support Vector Machines),a model is built and trained for deploying in cloud. The results show that the framework proposed is high in accuracy while being low cost and robust as it is tested after adding noise which is likely to exist in public cloud environments.

Mansaf Alam, Kishwar Sadaf

Clustering of web search result document has emerged as a promising tool for improving retrieval performance of an Information Retrieval (IR) system. Search results often plagued by problems like synonymy, polysemy, high volume etc. Clustering other than resolving these problems also provides the user the easiness to locate his/her desired information. In this paper, a method, called WSRDC-CSCC, is introduced to cluster web search result using cuckoo search meta-heuristic method and Consensus clustering. Cuckoo search provides a solid foundation for consensus clustering. As a local clustering function, k-means technique is used. The final number of cluster is not depended on this k. Consensus clustering finds the natural grouping of the objects. The proposed algorithm is compared to another clustering method which is based on cuckoo search and Bayesian Information Criterion. The experimental results show that proposed algorithm finds the actual number of clusters with great value of precision, recall and F-measure as compared to the other method

Kashish Ara Shakil, Shadma Anis, Mansaf Alam

Dengue is a life threatening disease prevalent in several developed as well as developing countries like India.In this paper we discuss various algorithm approaches of data mining that have been utilized for dengue disease prediction. Data mining is a well known technique used by health organizations for classification of diseases such as dengue, diabetes and cancer in bioinformatics research. In the proposed approach we have used WEKA with 10 cross validation to evaluate data and compare results. Weka has an extensive collection of different machine learning and data mining algorithms. In this paper we have firstly classified the dengue data set and then compared the different data mining techniques in weka through Explorer, knowledge flow and Experimenter interfaces. Furthermore in order to validate our approach we have used a dengue dataset with 108 instances but weka used 99 rows and 18 attributes to determine the prediction of disease and their accuracy using classifications of different algorithms to find out the best performance. The main objective of this paper is to classify data and assist the users in extracting useful information from data and easily identify a suitable algorithm for accurate predictive model from it. From the findings of this paper it can be concluded that Naïve Bayes and J48 are the best performance algorithms for classified accuracy because they achieved maximum accuracy= 100% with 99 correctly classified instances, maximum ROC = 1, had least mean absolute error and it took minimum time for building this model through Explorer and Knowledge flow results

Shuchi Sethi, Kashish Ara Shakil, Mansaf Alam

This work is focused on attacks on confidentiality that require time synchronization. This manuscript proposes a detection framework for covert channel perspective in cloud security. This problem is interpreted as a binary classification problem and the algorithm proposed is based on certain features that emerged after data analysis of Google cluster trace that forms base for analyzing attack free data. This approach can be generalized to study the flow of other systems and fault detection. The detection framework proposed does not make assumptions pertaining to data distribution as a whole making it suitable to meet cloud dynamism.

Khalid Raza, Mansaf Alam

Systems biology is an emerging interdisciplinary area of research that focuses on study of complex interactions in a biological system, such as gene regulatory networks. The discovery of gene regulatory networks leads to a wide range of applications, such as pathways related to a disease that can unveil in what way the disease acts and provide novel tentative drug targets. In addition, the development of biological models from discovered networks or pathways can help to predict the responses to disease and can be much useful for the novel drug development and treatments. The inference of regulatory networks from biological data is still in its infancy stage. This paper proposes a recurrent neural network (RNN) based gene regulatory network (GRN) model hybridized with generalized extended Kalman filter for weight update in backpropagation through time training algorithm. The RNN is a complex neural network that gives a better settlement between the biological closeness and mathematical flexibility to model GRN. The RNN is able to capture complex, non-linear and dynamic relationship among variables. Gene expression data are inherently noisy and Kalman filter performs well for estimation even in noisy data. Hence, non-linear version of Kalman filter, i.e., generalized extended Kalman filter has been applied for weight update during network training. The developed model has been applied on DNA SOS repair network, IRMA network, and two synthetic networks from DREAM Challenge. We compared our results with other state-of-the-art techniques that show superiority of our model. Further, 5% Gaussian noise has been added in the dataset and result of the proposed model shows negligible effect of noise on the results.