Turgay Temel

A novel signed higher-radix full-adder algorithm and implementation with current-mode multi-valued logic circuits

A higher-radix algebra for full-addition of two numbers is described and realised by combining multivalued logic min, max, literal and cyclic operators in terms disjoint terms. The latter operator is designed by using a current-mode threshold circuit while the other operator is realised by only voltage-mode switching circuits. The threshold circuit employed allows for much higher radices compared to architectures employing voltage-mode binary logic switching circuits as well as better mismatch properties compared to previous threshold circuits. Due to disjoint terms involved, multi-valued logic min and max operators can be replaced with ordinary transmission operation and addition, respectively. Resultant a single-digit, radix-8 full-adder and its 3-bit counterpart voltage-mode circuits are realised and compared. The algorithm is also exploited for a multi-digit case and its HSPICE simulation results are presented.

A Threshold Free Clustering Algorithm for Robust Unsupervised Classification

A new information-theoretic, unsupervised, subtractive clustering algorithm is proposed. The algorithm eliminates threshold constraint to detect possible cluster members. Cluster centers are formed with minimum entropy. Instead of using a fixed- threshold, a decision region is formed with the use of maximum mutual information. Cluster members are chosen with a relative-cost assigned in partitions of data set. The algorithm yields more reliably distributed cluster numbers in statistical sense, hence reducing further computation for validation, which is justified for a set of synthetic data.

A novel information-theoretic clustering algorithm for robust, unsupervised classification

A new information-theoretic, unsupervised, subtractive clustering algorithm is proposed. The algorithm eliminates threshold constraint to detect possible cluster members. Cluster centers are formed with minimum entropy. Instead of using a fixed-threshold, a decision region is formed with the use of maximum mutual information. Cluster members are chosen with a relative-cost assigned in partitions of data set. The algorithm yields more reliably distributed cluster numbers in statistical sense, hence reducing further computation for validation, which is justified for a set of synthetic data.