Mehrdad Valipour

Learn More
Concept elicitation is centric for machine knowledge extraction and representation in cognitive robot learning. This paper presents a supervised methodology for machine concept elicitation from informal counterparts described in natural languages. The collective opinions of a given concept in ten selected dictionaries are quantitatively analyzed and(More)
Channel optimized multiple description (MD) vector quantization with symbol-based turbo codes are proposed, where the decoder exploits both nonuniformity of descriptions and their dependencies. The joint source channel coding strategy is devised by setting an entropy constraint for quantizer design, which together with the MD index assignment (IA), control(More)
Quantizer design for lossy compression with mismatched side information (SI) at the decoder is investigated. The statistical dependency between the source and SI is assumed to be a function of a random variable, dependency variable (DV). According to the available information about the DV, three design methods are proposed; namely, minimax solution, Average(More)
In this paper, a proper solution for a capacity-limited lossy wireless sensor network subject to packet loss as a problem has been presented by considering multiple sinks and correlated sources. At first, a joint optimization problem with two objectives, rate allocation and transmission structure, is introduced and solved. Also in the lossy network, a(More)
Multiple descriptions (MD) with symbol-based turbo (SBT) codes are proposed, where the decoder exploits both non-uniformity of descriptions and their dependencies. A distortion-power adaptive system is obtained by setting an entropy constraint for quantizer design, which together with the MD index assignment (IA), control the level of redundancy at the MD(More)
In this paper, a scheme based on 1-D nested lattice quantization followed by multi-level distributed arithmetic coding (MLDAC) as the Slepian-Wolf (SW) code is proposed for the lossy source coding of continuous sources. This system can be employed in distributed video and image coding applications. The output of the quantizer is first converted to binary,(More)
Multiple descriptions (MD) with symbol−based turbo (SBT) codes are proposed, where the decoder exploits both non−uniformity of descriptions and their dependencies. A distortion−power adaptive system is obtained by setting an entropy constraint for quantizer design, which together with the MD index assignment (IA), control the level of redundancy at the MD(More)
In this paper, a turbo-based distributed joint source-channel coding scheme, for efficient compression and communication of two dependent sources with time memory over noisy channels, is presented. Specifically, we consider the asymmetric case for two binary sources, where one of the sources is available at the decoder as side information. The problem is of(More)