Booming telemedicine applications makes it deemed necessary to provide security services for such applications. The algorithms proposed in this field can be grouped into three classes: watermarking‐based algorithms, crypto‐based algorithms and hybrid algorithms. In this study, the authors propose two crypto‐based algorithms capable of providing confidentiality, authenticity and integrity services to medical images exchanged in telemedicine applications. Strong cryptographic functions with internally generated symmetric keys and hash codes are used. The advanced encryption standard‐Galois counter mode is used with the whirlpool hash function to provide confidentiality and authenticity, and the elliptic curve digital signature algorithm is used to provide authenticity and integrity. The proposed algorithms are based on the digital imaging and communication in medicine (DICOM) standard; however, unlike the standard, the algorithms provide confidentiality, authenticity and integrity for the header data, as well as for the pixel data of the DICOM images. Effectiveness of the proposed algorithms is evaluated and demonstrated through extensive experimentation using a benchmark set of DICOM images.

The convolutional coding is a very popular channel coding technique for the major reason of mitigating the probability of having many retransmissions because of difficult (noisy) communication channels. Sequential decoding is a type of convolutional codes that becomes of interest in wireless communication since it affords a decoding time that can be adaptive to channel state. In this study, the authors propose an improved queuing model, using discrete-time semi-Markov chain, which represents a modified packet retransmission policy over previously proposed queuing model. The authors queuing model mainly describes the behaviour of the buffer, which belongs to intermediate hops, when sequential decoding is implemented and concerns also about packets being transmitted over erroneous channels. The authors aim after conducting queuing analysis to find a real mathematical form for the average buffer occupancy as a network performance metric. Although the improved queuing model when incorporating the new policy for retransmission is very complicated, we are finally able to derive an expression for that performance metric considering practical assumptions. They further illustrate how the modified queuing model has a better impact on the end-to-end delay of messages, being transmitted without any extra buffering requirements needed, than the other relevant proposed queuing model. They conduct a simulation study using computer programming with the same assumptions used for queuing analysis to validate their analytical explanations and results. Furthermore, they validate the correctness of their closed-form expression through comparing its results with those obtained from expression related to a queuing model which discarded employing any retransmission policy.

In a distributed shared memory (DSM) multiprocessor, the processors cooperate in solving a parallel application by accessing the shared memory. The latency of a memory access depends on several factors, including the distance to the nearest valid data copy, data sharing conditions, and traffic of other processors. To provide a better understanding of DSM performance and to support application tuning and compiler development for DSM systems, this paper extends microbenchmarking techniques to characterize the important aspects of a DSM system. We present an experiment-based methodology for characterizing the memory, communication, scheduling, and synchronization performance, and apply it to the Convex SPP1000. We present carefully designed microbenchmarks to characterize the performance of the local and remote memory, producer-consumer communication involving two or more processors, and the effects on performance when multiple processors contend for utilization of the distributed memory and the interconnection network.