Explore the vast range of titles available.

Motor imagery (MI) based brain-computer interface systems (BCIs) are highly in need for a large number of real-time applications such as hands and touch-free text entry system, movement of a wheelchair, movement of a cursor, prosthetic arm movement, virtual reality systems, etc. In recent years, sparse representation-based classification (SRC) is a growing technique and has been a successful technique on classifying MI-based Electroencephalography (EEG) signals. To further boost the proficiency of SRC technique, in this paper, a weighted SRC (WSRC) has been proposed for classifying MI signals. In WSRC approach, a weighted dictionary has been constructed according to the dissimilarity information between a test data and training samples. Then for the given test data, the sparse coefficients are computed over the weighted dictionary using l0-minimization problem. The sparse solution obtained using WSRC gives discriminative information and as a consequence, WSRC proves to be superior for MI-based EEG classification. The experimental results substantiate that WSRC is more efficient and accurate than SRC.

Fingerprint-based user identification and authentication are now used in many applications, but achieving absolute accuracy (eliminating false matches) still remains an issue. One of the reasons behind this issue is inappropriate image alignment prior to the feature extraction. In this paper, a robust Singular Value Decomposition (SVD) based fingerprint alignment method is proposed which automatically aligns the segmented and rotated image within the angular range − 900 to 900. Further, it overcomes the limitations of the existing fingerprint alignment methods as it neither depends on the quality of the image nor requires any reference image. The effectiveness of the approach has been tested with the standard fingerprint image databases FVC2002 (DB1, DB2, DB3, and DB4), FVC2004 (DB1, DB2, DB3, and DB4) and captured sensor images in an uncontrolled environment. The proposed approach was found to be efficient both in terms of accuracy and computational time. Also, it worked well for both database images and captured sensor images.

The digital repository of research articles is increasing at a rapid rate and hence searching the right paper becoming a tedious task for researchers. A research paper recommendation system is advocated to help researchers in this context. In the process of designing such a system, proper representation of articles, more specifically, feature identification and extraction are two essential tasks. The existing approaches mainly consider direct features which are readily available from research articles. However, there are certain features which are not readily available from a paper, but may greatly influence the performance of recommendation systems. This paper proposes four indirect features: keyword diversification, text complexity, citation analysis over time, and scientific quality measurement to represent a research article. The keyword diversification measures the uniqueness of the keywords of a paper which helps variation in recommendation. The text complexity measurement helps to provide a paper by matching the user’s understandability level. The citation analysis over time decides the relevancy of a paper. The scientific quality measurement helps to measure the scientific values of papers. Formal definitions of the proposed indirect features, schemes to extract the feature values given a research article, and metrics to measure them quantitatively are discussed in this paper. To substantiate the efficacy of the proposed features, a number of experiments have been carried out. The experimental results reveal that the proposed indirect features uniquely define a research article than the direct features. Given a research paper, extraction of feature vector is computationally fast and thus feasible to filter a large corpus of papers in real time. More significantly, indirect features are matchable with user’s profile features, thus satisfying an important criterion in collaborative filtering.

This work is on biometric data indexing for large-scale identification systems with a focus on different biometrics data indexing methods. It provides state-of-the-art coverage including different biometric traits, together with the pros and cons for each. Discussion of different multimodal fusion strategies are also included.

To avail cloud services; namely, Software as a Service (SaaS), Platform as a Service (PaaS), Infrastructure as a Service (IaaS), ...etc. via insecure channel, it is necessary to establish a symmetric key between end user and remote Cloud Service Server (CSS). In such a provision, both the end parties demand proper auditing so that resources are legitimately used and privacies are maintained. To achieve this, there is a need for a robust authentication mechanism. Towards the solution, a number of single server authenticated key agreement protocols have been reported recently. However, they are vulnerable to many security threats, such as identity compromization, impersonation, man-in-the-middle, replay, byzantine, offline dictionary and privileged-insider attacks. In addition to this, most of the existing protocols adopt the single server-based authentication strategy, which are prone to single point of vulnerability and single point of failure issues. This work proposes an efficient password-based two-server authentication and key exchange protocol addressing the major limitations in the existing protocols. The formal verification of the proposed protocol using Automated Validation of Internet Security Protocols and Applications (AVISPA) proofs that it is provably secure. The informal security analysis substantiates that the proposed scheme has successfully addressed the existing issues. The performance study contemplates that the overhead of the protocol is reasonable and comparable with those of other schemes. The proposed protocol can be considered as a robust authentication protocol for a secure access to the cloud services.

Typically, people with severe motor disabilities have limited opportunities to socialize. Brain-Computer Interfaces (BCIs) can be seen as a hope of restoring freedom to immobilized individuals. Motor imagery (MI) signals recorded via electroencephalograms (EEGs) are the most convenient basis for designing BCIs as they provide a high degree of freedom. MI-based BCIs help motor disabled people to interact with any real-time BCI applications by performing a sequence of MI tasks. But, inter-subject variability, extracting user-specific features and increasing accuracy of the classifier are still a challenging task in MI-based BCIs. In this work, we propose an approach to overcome the above-mentioned issues. The proposed approach considers channel selection, band-pass filter based common spatial pattern, feature extraction, feature selection and modeling using Gaussian Naïve Bayes (GNB) classifier. Since the optimal features are selected by feature selection techniques, they help overcome inter-subject variability and improve performance of GNB classifier. To the best of our knowledge, the proposed methodology has not been used for MI-based BCI applications. The proposed approach has been validated using BCI competition III dataset IVa. The result of our approach has been compared with those of two classifiers; namely, Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM). The results prove that the proposed method provides an improved accuracy over LDA and SVM classifiers. The proposed method can be further developed to design reliable and real-time MI-based BCI applications.

The traditional digital data security mechanisms follow either cryptography or authentication. The primary point of contention with these mechanisms remains either memorizing or securely storing the user’s credentials. The proposed work addresses this critical issue by presenting a fingerprint biometric-based mechanism to protect users’ digitized documents. In our approach, biometric features are extracted from the user’s fingerprint captured with a fingerprint biometric sensor. The extracted features are then used to generate a unique code utilizing the convolution coding principle. This unique code is further used to generate a cryptographic key for encryption and decryption of the user’s document. A sedulous investigation to our approach which includes experimentation with a variety of standard fingerprint images as the database starkly reveals a staggering 95.12 % true positive and 0 % as false negative. Further, the advantages of our approach are that it generates a unique key for each user and eliminates the storage of any biometric template or key. In addition, it is faster and accurate enough to develop any robust data storage security system.

Polyurethanes, an important class of polymers, are used extensively for preparing various apparel, shoesoles, etc. This paper reports that polyurethanes could be prepared conveniently after blocking the precursor molecule toluene diisocyanate (TDI)with 4-bromo-1H-pyrazole to form blocked toluene diisocyanate (TDI). The blocked adducts were characterized by FTIR, NMR, thermogravimetric analysis (TGA), differential scanning calorimetry (DSC), and CHNS analysis. Particularly, spectroscopic analysis was used to confirm the complete blocking. The DSC thermogram showed that the blocked adducts deblock at 238 °C, regenerating TDI and blocking agent 4-bromopyrazole. At 238 °C, regenerated TDI reacted with polyolsof different molecular weights to form polyurethane under solvent-free conditions. The polyurethanes were further characterized by FTIR, NMR, thermogravimetric analysis, differential scanning calorimetry, and contact angle study. FTIR study shows that there is no peak at 2250–2270 cm −1 . So it confirms the absence of NCO peaks. Contact angle measurements of various polyurethanes showed the values in the ranges of 27–50 °C, indicating generally hydrophilic natures of samples. DSC thermogram indicates the presence of glass transition temperature of synthesized polyurethanes at − 30 to − 40 °C. Viscosity measurements of polyurethanes in chloroform at different temperatures indicated decrease in viscosity at higher temperature.

In the era of artificial intelligence, healthcare informatics holds significant promise for cardiovascular disease (CVD) analysis. This study employs three computational intelligence approaches to address CVD-related challenges comprehensively. At first, various statistical methods unveil relationships between heterogeneous risk factors and predicted outcomes, employing tests of significance to discern differences in risk factors between classes with and without CVD. In the second stage, a hybrid statistical approach incorporates feature selection, identifying critical risk factors, and employs Tri-fuzzy interval arithmetic for precise estimation. Finally, the proposed Gaussian Probabilistic Neural Network (Gaussian-PNN) predicts heart disease onset with maximum accuracy, providing a nuanced assessment of CVD probability for each patient using interval-based lower and upper bounds derived from Tri-Fuzzy numbers. Experimental validations affirm the efficacy of these contributions, highlighting the analysis of significant risk factors, interrelationship establishment, and the novel integration of crisp and fuzzy interval estimates, advancing heart disease diagnosis.

Presently, blockchain technology is used to secure electronic medical records (EMR) and an arrangement of multiple servers as off-chain storage is advocated to minimize the storage overhead of the medical blockchain. Therefore, an authorized access mechanism to the medical records stored on multiple servers needs a secure multi-server-based authentication system. However, existing blockchain-based systems for medical data storage do not consider an authentication system for a multi-server environment between patients and multiple medical servers. In this paper, a blockchain-based healthcare system is considered to ensure the scalability of the blockchain using off-chain storage. The blockchain contains the hash value of the medical data, while multiple servers are used as off-chain storage for storing the original data. A patient can access those servers in a single enrollment under a multi-server authentication system using fuzzy commitment and can share his or her healthcare data with an authorized healthcare service provider. Replay attacks are examined using formal security analysis, such as the AVISPA tool and the mutual authentication of the proposed protocol is examined using BAN logic. At the same time, a rigorous informal security analysis confirms that our scheme is secured against various known attacks. Moreover, we have investigated the transaction cost for block creation, and the proposed scheme is compared with the existing blockchain-based EMR systems. Again, the security functionality, computation cost, and communication cost of the proposed protocol are also compared with existing protocols.