Janardan Misra

Artificial neural networks in hardware: A survey of two decades of progress

This article presents a comprehensive overview of the hardware realizations of artificial neural network (ANN) models, known as hardware neural networks (HNN), appearing in academic studies as prototypes as well as in commercial use. HNN research has witnessed a steady progress for more than last two decades, though commercial adoption of the technology has been relatively slower. We study the overall progress in the field across all major ANN models, hardware design approaches, and applications. We outline underlying design approaches for mapping an ANN model onto a compact, reliable, and energy efficient hardware entailing computation and communication and survey a wide range of illustrative examples. Chip design approaches (digital, analog, hybrid, and FPGA based) at neuronal level and as neurochips realizing complete ANN models are studied. We specifically discuss, in detail, neuromorphic designs including spiking neural network hardware, cellular neural network implementations, reconfigurable FPGA based implementations, in particular, for stochastic ANN models, and optical implementations. Parallel digital implementations employing bit-slice, systolic, and SIMD architectures, implementations for associative neural memories, and RAM based implementations are also outlined. We trace the recent trends and explore potential future research directions.

Binary Arithmetic for DNA Computers

We propose a (recursive) DNA algorithm for adding two binary numbers which require O(log n) bio-steps using only O(n) different type of DNA strands, where n is the size of the binary string representing the largest of the two numbers. The salient feature of our technique is that the input strands and the output strands have exactly the same structure which makes it fully procedural unlike most methods proposed so far. Logical operations of binary numbers can easily be performed by our method and hence can be used for cryptographic purpose.

Software Clustering: Unifying Syntactic and Semantic Features

Software clustering is an important technique for extracting high level component architecture from the underlying source code. One of the limitations of the existing approaches is that most of the proposed techniques use only similar types of features for estimating distance between source code elements. Therefore, in cases, where the selected features are poorly present in the source code, these techniques may not produce good quality results in absence of adequate inputs to work on. In this paper we propose an approach to overcome this limitation. Proposed approach uses a combination of multiple types of features together and applies automated weighing on the extracted features to enhance their information quality and to reduce noise. We define a way to estimate distance between code elements in terms of combination of multiple types of features. Weighted graph partitioning with a multi-objective global modularity criterion is used to select the clusters as architectural components. We describe methods for automated labeling of the extracted components and for generating inter-component interactions. We further discuss how the suggested approach extends to clustering at multiple hierarchical levels, to application portfolios, and even for improving precision for the feature location problem.

Increasing Anonymity in Bitcoin

Bitcoin prevents double-spending using the blockchain, a public ledger kept with every client. Every single transaction till date is present in this ledger. Due to this, true anonymity is not present in bitcoin. We present a method to enhance anonymity in bitcoin-type cryptocurrencies. In the blockchain, each block holds a list of transactions linking the sending and receiving addresses. In our modified protocol the transactions (and blocks) do not contain any such links. Using this, we obtain a far higher degree of anonymity. Our method uses a new primitive known as composite signatures. Our security is based on the hardness of the Computation Diffie-Hellman assumption in bilinear maps.

Terminological inconsistency analysis of natural language requirements

Context: Terminological inconsistencies owing to errors in usage of terms in requirements specifications could result into subtle yet critical problems in interpreting and applying these specifications into various phases of SDLC.Objective: In this paper, we consider special class of terminological inconsistencies arising from term-aliasing, wherein multiple terms spread across a corpus of natural language text requirements may be referring to the same entity. Identification of such alias entity-terms is a difficult problem for manual analysis as well as for developing tool support.Method: We consider the case of syntactic as well as semantic aliasing and propose a systematic approach for identifying these. Identification of syntactic aliasing involves automated generation of patterns for identifying syntactic variances of terms including abbreviations and introduced-aliases. Identification of semantic aliasing involves extracting multidimensional features (linguistic, statistical, and locational) from given requirement text to estimate semantic relatedness among terms. Based upon the estimated relatedness and standard language database based refinement, clusters of potential semantic aliases are generated. Results of these analyses with user refinement lead to generation of entity-term alias glossary and unification of term usage across requirements.Results: A prototype tool was developed to assess the effectiveness of the proposed approach for an automated analysis of term-aliasing in the requirements given as plain English language text. Experimental results suggest that approach is effective in identifying syntactic as well as semantic aliases, however, when aiming for higher recall on larger corpus, user selection is necessary to eliminate false positives.Conclusion: This proposed approach reduces the time-consuming and error-prone task of identifying multiple terms which might be referring to the same entity to a process of tool assisted identification of such term-aliases.

Entity Disambiguation in Natural Language Text Requirements

We consider the problem of terminological ambiguity in requirement specifications arising from term-aliasing, wherein multiple terms may be referring to the same entity in a corpus of natural language text requirements. We consider the case of syntactic as well as semantic aliasing. Syntactic alias identification involves automated generation of patterns for identifying syntactic variances of terms including abbreviations and introduced-aliases. Semantic alias identification includes extracting multi-dimensional features (linguistic, statistical, and locational) from given requirement text to estimate semantic relatedness between terms. Based upon the estimated relatedness and standard language database based refinement, clusters of potential semantic aliases are generated. Results of these analyses with user refinement should lead to generation of entity-term alias glossary and unification of term usage across requirements. We present experimental results assessing the effectiveness of the presented approach using a prototype tool for an automated analysis of term-aliasing in the requirements given as plain English language text.

Latent semantic centrality based automated requirements prioritization

This paper focuses on the problem of assigning relative priorities to requirements specified in the natural language. Proposed method includes processing plain text requirements specifications in order to extract multidimensional statistical features from the given requirement text to estimate latent semantic cohesion among the requirements as well as specific information contained within requirements. Using these estimates, latent semantic centrality and relative information specificity scores are derived for each requirement, which form the basis for assigning relative priorities to the requirements. We next extend this approach to clusters of requirements, where in requirements are clustered into semantically coherent groups and relative priorities are assigned to these groups of requirements. We further discuss a method for identifying semantically isolated requirements which might demand further analysis and elaboration by user. Suggested approach is specifically amenable to automated tool support as the case of prototype tool used in experiments to assess feasibility and effectiveness of the proposed approach demonstrates.

Topic cohesion preserving requirements clustering

This paper focuses on the problem of generating human interpretable clusters of semantically related plain-text requirements. Presented approach applies techniques from information retrieval, natural language processing, network analysis, and machine learning for identifying semantically central terms as themes and clustering requirements into semantically coherent groups together with meaningful explanatory themes associated with the clusters to assist in user comprehension of the clusters. Presented approach is generic in nature and can be used for other phases of SDLC (Software Development Life Cycle) including code-comprehension and architectural discovery. Suggested approach is particularly suitable for developing automated tool support for requirements management and analysis.

A reinforcement model for collaborative security and Its formal analysis

This paper presents a principled approach to one of the many little studied aspects of computer security which relate to human behavior. Advantages of involving users who usually have strong analytic ability to detect violations and threats but not primarily responsible for security have been well emphasized in the literature. In this work we propose a reinforcement framework for enabling collaborative monitoring of policy violations by the users. We define a payoff model to formalize the reinforcement framework. The model stipulates appropriate payoffs as reward, punishment, and community price according to reporting of genuine or false violations, non-reporting of the detected violations, and proactive reporting of vulnerabilities and threats by the users. We define probabilistic robustness property of the resulting system and constraints for economic feasibility of the payoffs. For estimating the parameters in the payoff model, system and user behaviors are modeled in terms of probabilistic finite state machines (PFSM) and likelihood of the success of the model is specified using Probabilistic Computation Tree Logic (PCTL). PRISM model checker based automated quantitative analysis elicits the process of the estimation of various parameters in the model using PFSMs and PCTL formulas.

A simplification of a real-time verification problem

We revisit the problem of real‐time verification with dense‐time dynamics using timeout and calendar‐based models and simplify this to a finite state verification problem. We introduce a specification formalism for these models and capture their behaviour in terms of semantics of timed transition systems. We discuss a technique, which reduces the problem of verification of qualitative temporal properties on infinite state space of a large fragment of these timeout and calender‐based transition systems into that on clock‐less finite state models through a two‐step process comprising of digitization and finitary reduction. This technique enables us to verify safety invariants for real‐time systems using finite state model checking avoiding the complexity of infinite state (bounded) model checking and scale up models without applying techniques from induction‐based proof methodology. In the same manner, we verify timeliness properties. Moreover, we can verify liveness for real‐time systems, which are not possible by using induction with infinite state model checkers. Copyright