Jyotsna Kumar Mandal

Uttam Kr. Mondal, Shamayita Pal, AmitRanjan Dutta et al.

Steganography is a process that hides secrete message or secrete hologram or secrete video or secrete image whose mere presence within the source data should be undetectable and use for transmitting secret information over public media. Visual cryptography is a cryptographic technique in which no cryptographic computation is needed at the decryption end and the decryption is performed by the human visual system (HVS). In this paper, both Steganography and visual cryptography have been selected to provide more secure data transmission over the public media with less hazard of computation. This technique generates shares with less space overhead as well as without increasing the computational complexity compared to existing techniques and may provide better security. It is also easy to implement like other techniques of visual cryptography. Finally, experimental results are given to establish the security criteria.

Debarpita Santra, Jyotsna Kumar Mandal, Swapan Kumar Basu et al.

Aiming at developing a medical expert system for low back pain management, the paper proposes an efficient knowledge representation scheme using frame data structures, and also derives a reliable resolution logic through Bayesian Network. When a patient comes to the intended expert system for diagnosis, the proposed inference engine outputs a number of probable diseases in sorted order, with each disease being associated with a numeric measure to indicate its possibility of occurrence. When two or more diseases in the list have the same or closer possibility of occurrence, Bayesian Network is used for conflict resolution. The proposed scheme has been validated with cases of empirically selected thirty patients. Considering the expected value 0.75 as level of acceptance, the proposed system offers the diagnostic inference with the standard deviation of 0.029. The computational value of Chi-Squared test has been obtained as 11.08 with 12 degree of freedom, implying that the derived results from the designed system conform the homogeneity with the expected outcomes. Prior to any clinical investigations on the selected low back pain patients, the accuracy level (average) of 73.89% has been achieved by the proposed system, which is quite close to the expected clinical accuracy level of 75%.

Debarpita Santra, Swapan Kumar Basu, Jyotsna Kumar Mandal et al.

The aim of medical knowledge representation is to capture the detailed domain knowledge in a clinically efficient manner and to offer a reliable resolution with the acquired knowledge. The knowledge base to be used by a medical expert system should allow incremental growth with inclusion of updated knowledge over the time. As knowledge are gathered from a variety of knowledge sources by different knowledge engineers, the problem of redundancy is an important concern here due to increased processing time of knowledge and occupancy of large computational storage to accommodate all the gathered knowledge. Also there may exist many inconsistent knowledge in the knowledge base. In this paper, we have proposed a rough set based lattice structure for knowledge representation in medical expert systems which overcomes the problem of redundancy and inconsistency in knowledge and offers computational efficiency with respect to both time and space. We have also generated an optimal set of decision rules that would be used directly by the inference engine. The reliability of each rule has been measured using a new metric called credibility factor, and the certainty and coverage factors of a decision rule have been re-defined. With a set of decisions rules arranged in descending order according to their reliability measures, the medical expert system will consider the highly reliable and certain rules at first, then it would search for the possible and uncertain rules at later stage, if recommended by physicians. The proposed knowledge representation technique has been illustrated using an example from the domain of low back pain. The proposed scheme ensures completeness, consistency, integrity, non-redundancy, and ease of access.

Manas Paul, Jyotsna Kumar Mandal

In this paper, we propose a session based bit level symmetric key cryptographic technique and it is termed as Spiral Matrix Based Bit Orientation Technique (SMBBOT). SMBBOT consider the input plain text as binary bit stream. During encryption this stream is chopped into manageable sized blocks with variable lengths. Bits of these blocks are taken from MSB to LSB to fit into a square matrix of suitable order following the concept of Spiral matrix. This square matrix splits into 2x2 sub-matrices. Bits are taken column-wise from all 2x2 sub-matrices to form the encrypted binary string. Cipher text is generated from this encrypted binary string. Combination of values of block length and no. of blocks of a session generates the session key for SMBBOT. For decryption the cipher text is considered as binary bit string. Processing the session key information, this binary string is broken down into predefined blocks. Bits of these blocks are taken from MSB to LSB to fit column-wise into 2x2 square matrices. Using these sub-matrices a single square matrix with suitable order is formed. The decrypted binary string is formed after taking the bits from the square matrix following the reverse concept of Spiral Matrix. The plain text is regenerated from decrypted binary string. A comparison of SMBBOT with existing and industrially accepted TDES and AES has been done.

Arindam Sarkar, J. K. Mandal

In this paper, a multilayer perceptron guided key generation for encryption/decryption (MLPKG) has been proposed through recursive replacement using mutated character code generation for wireless communication of data/information. Multilayer perceptron transmitting systems at both ends accept an identical input vector, generate an output bit and the network are trained based on the output bit which is used to form a protected variable length secret-key. For each session, different hidden layer of multilayer neural network is selected randomly and weights or hidden units of this selected hidden layer help to form a secret session key. The plain text is encrypted using mutated character code table. Intermediate cipher text is yet again encrypted through recursive replacement technique to from next intermediate encrypted text which is again encrypted to form the final cipher text through chaining, cascaded xoring of multilayer perceptron generated session key. If size of the final block of intermediate cipher text is less than the size of the key then this block is kept unaltered. Receiver will use identical multilayer perceptron generated session key for performing deciphering process for getting the recursive replacement encrypted cipher text and then mutated character code table is used for decoding. Parametric tests have been done and results are compared in terms of Chi-Square test, response time in transmission with some existing classical techniques, which shows comparable results for the proposed technique.

J. K. Mandal, Debashis Das

In a gray scale image the pixel value ranges from 0 to 255. But when we use pixel-value differencing (pvd) method as image steganographic scheme, the pixel values in the stego-image may exceed gray scale range. An adaptive steganography based on modified pixel-value differencing through management of pixel values within the range of gray scale has been proposed in this paper. PVD method is used and check whether the pixel value exceeds the range on embedding. Positions where the pixel exceeds boundary has been marked and a delicate handle is used to keep the value within the range. From the experimental it is seen that the results obtained in proposed method provides with identical payload and visual fidelity of stego-image compared to the pvd method.

J. K. Mandal

Image steganography is art of hiding information onto the cover image. In this proposal a transformed domain based gray scale image authentication/data hiding technique using Z transform (ZT) termed as FDSZT, has been proposed. ZTransform is applied on 2x2 masks of the source image in row major order to transform original sub image (cover image) block to its corresponding frequency domain. One bit of the hidden image is embedded in each mask of the source image onto the fourth LSB of transformed coefficient based on median value of the mask. A delicate handle has also been performed as post embedding operation for proper decoding. Stego sub image is obtained through a reverse transform as final step of embedding in a mask. During the process of embedding, dimension of the hidden image followed by the content of the message/hidden image are embedded. Reverse process is followed during decoding. High PSNR obtained for various images conform the quality of invisible watermark of FDSZT.

Uttam Kr. Mondal, J. K. Mandal

Providing security to audio songs for maintaining its intellectual property right (IPR) is one of chanllenging fields in commercial world especially in creative industry. In this paper, an effective approach has been incorporated to fabricate authentication of audio song through application of message digest method with alternation of coefficients of harmonics in multi-stages of higher frequency domain without affecting its audible quality. Decomposing constituent frequency components of song signal using Fourier transform with generating secret code via applying message digest followed by alternating coefficients of specific harmonics in multi-stages generates a secret code and this unique code is utilized to detect the originality of the song. A comparative study has been made with similar existing techniques and experimental results are also supported with mathematical formula based on Microsoft WAVE (".wav") stereo sound file.