Algorithmically Optimized AVC Video Encoder with Parallel Processing of Data

A video encryption scheme combining with advanced video coding (AVC) is presented and analyzed in this paper, which is different from the ones used in MPEG1/2 video encryption. In the proposed scheme, the intra-prediction mode and motion vector difference are encrypted with the length-kept encryption algorithm (LKE) in order to keep the format compliance, and the residue data of the macroblocks are encrypted with the residue data encryption algorithm (RDE) in order to keep low cost. Additionally, a key distribution scheme is proposed to keep the robustness to transmission errors, which assigns sub-keys to different frames or slices independently. The encryption scheme's security, time efficiency and error robustness are analyzed in detail. Experimental results show that the encryption scheme keeps file format unchanged, is secure against replacement attacks, is efficient in computing, and is robust to some transmission errors. These properties make it a suitable choice for real-time applications, such as secure IPTV, secure videoconference or mobile/wireless multimedia, etc.

Multifrequency Spin Wave Device for Parallel Data Processing using Micro Structured Yttrium Iron Garnet Thin Films

Cloud computing is a technology in which the Cloud Service Providers (CSP) provide many virtual servers to the users to store their information in the cloud. The faults occurring on the assignment and dismission of the virtual machines, the processing cost in the allocation of resources must also be considered. The parallel processing of the information on the virtual machines must be done effectively and in an efficient manner. A variety of systems were developed to facilitate Many Task Computing (MTC). These systems aim to hide the issues of parallelism and fault tolerant and they are used in many applications. In this paper, we introduced Nephele, a data processing framework to exploit dynamic resource provisioning offered by IaaS clouds. The performance evaluation of the virtual machines has been evaluated and the allocation and deallocation of job tasks to the specific virtual machines has also been considered. A performance comparison with the well known data processing framework hadoop has been done. Thus this paper tells about the effective and efficient manner of processing the data by parallel processing and allocating the correct resources for the desired task. It also helps to reduce the cost of resource utilization by exploiting the dynamic resource utilization.

We apply optical parallel processing to operations for multiplication modulo, which is one of the key components of a factorization algorithm. With this method, optical phase modulation provides the results of modulo operations. We construct a prototype system based on a Michelson interferometer with a photodetector array. Mirrors are set at both object and reference arms to generate interference fringes. A mirror in the object arm is tilted slightly, whereas the reference arm is set perpendicular to the optical axis. The tilt angle is determined by parameters for the target modulo operations. The presented system can achieve massive data processing in parallel with only simple implementation. We present our experimental results to verify the usefulness of our method.

Cyber-physical applications need to process a lot of sensor data, for example, to analyze traffic patterns and structural soundness of critical infrastructures. Although the amount of sensor data to process is increasing fast, system support to efficiently store and analyze an extensive amount of sensor data largely lags behind. To efficiently store, retrieve, and process massive sensor data, we are developing a sensor data center (SDC) that supports spatio-temporal sensor data structures and parallel sensor data processing using clustered computational nodes composed of commodity hardware. The SDC sharply contrasts to most existing data centers that do not support spatio-temporal sensor data storage, retrieval, and processing. In this paper, we especially focus on the problem of potential load imbalance due to data access skews that adversely affects the timeliness of parallel sensor data processing. Specifically, we present an adaptive data replication method to address access skews in a SDC. In our performance evaluation performed in a preliminary version of a SDC, our adaptive approach substantially outperforms a baseline that does not support adaptive data replication.

With the increase in the number of mobile users, the need for new type of services and applications is also on the rise. Particularly, a growing area of interest is to provide location dependent services to the mobile users. In this paper, we present a system that supports distributed processing of location-dependent continuous queries on distributed mobile data in a mobile environment using mobile agents. We investigate a scenario in which both the querying unit and the object being queried (target object) are capable of movement and the mobile unit is equipped with more powerful capabilities, including the storage of a small database and the capacity of data processing. Since our system deals with continuous queries, we propose a shared incremental update mechanism, which caches the results of the previously evaluated queries and avoids redundant results thereby minimizing the data traffic in wireless environment. To further reduce the data transfer we share the cached data among different queries. Our system uses mobile agents for evaluating queries, which involves data from both the server and mobile unit, and it helps in parallel processing of data and it, can efficiently track the mobile units involved in the system. The conventional query processing method like join processing of data from mobile units and server is directly applied in the mobile environment.

Advanced Video Coding is recently announced and widely used, although the according protection means have not been developed thoroughly. In this paper, a selective encryption scheme is constructed on Advanced Video Coding. During AVC encoding, such sensitive data as intra-prediction mode, residue data, inter-prediction mode and motion vector are partially encrypted. This encryption scheme keeps secure against brute-force attack, replacement attack or known-plaintext attack, combines encryption process with compression process with low cost, and keeps the file format unchanged with some direct operations (such as displaying, time seeking, copying, cutting, etc.) supported. These properties make it suitable for secure video transmission.

With the rapid development of network technology, especially in the internet area, distributed computation and parallel processing of data are urgently needed. This paper studies the combination operation of the lattice-valued concept lattices to realize its distributed computation and parallel processing. The proposal of its corresponding combination algorithm is mainly according to the conjunction properties of incomparable attribute values. Firstly, we define a homotypic lattice-valued concept lattice and a combined concept lattice; secondly, we analyze some relations between the lattice-valued formal concepts under two conditions and prove the isomorphism of the combination theory; finally, we present the combination algorithm of multiple lattice-valued concept lattices and analyze the algorithm complexity and employ an example to show the application of this combination algorithm.

The authors report online parallel data processing in the GA.SP (gamma spectrometer) data acquisition system. A transputer network (TNET) has been built as a dedicated parallel machine for high-speed data processing and a nuclear experiment oriented parallel language (NEO) has been designed to support parallel programming on TNET. Event pipeline analyzing domain data structures and interactive communication with the program are characteristics of the NEO language. A multichain pipeline machine and its shell are also presented to show how to run the NEO program and to operate the TNET efficiently.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Neuroalgorithms and neuronetwork structures were analyzed, basic components of neuronetworks were defined and the principles of their development were chosen. It was shown that using the method of parallel vertical group data processing for the implementation of the neuronetworks basic components provides speed increase, reduce of hardware costs and increasing of the equipment use efficiency. Parallel vertical group codes converter, which provides time alignment of data receipt processes and bit sections formation, was developed. The methods and the structures of the components with parallel vertical group data processing for definition of maximum and minimum numbers in the arrays, calculation of the sum of differences squares and scalar product, which due to parallel processing of bit sections groups, provide speed increase, were developed. It was shown that use of the developed basic components for neuronetworks synthesis will provide reduction of time and development cost.

Neural-network quantum states (NQS) has emerged as a powerful application of quantum-inspired deep learning for variational Monte Carlo methods, offering a competitive alternative to existing techniques for identifying ground states of quantum problems. A significant advancement toward improving the practical scalability of NQS has been the incorporation of autoregressive models, most recently transformers, as variational ansätze. Transformers learn sequence information with greater expressiveness than recurrent models, but at the cost of increased time complexity with respect to sequence length. We explore the use of the retentive network (RetNet), a recurrent alternative to transformers, as an ansatz for solving electronic ground state problems in ab initio quantum chemistry. Unlike transformers, RetNets overcome this time complexity bottleneck by processing data in parallel during training, and recurrently during inference. We give a simple computational cost estimate of the RetNet and directly compare it with similar estimates for transformers, establishing a clear threshold ratio of problem-to-model size past which the RetNet’s time complexity outperforms that of the transformer. Though this efficiency comes at the expense of decreased expressiveness relative to the transformer, we overcome this gap through training strategies that leverage the autoregressive structure of the model—namely, variational neural annealing. Our findings support the RetNet as a means of improving the time complexity of NQS without sacrificing accuracy. We provide further evidence that the ablative improvements of neural annealing extend beyond the RetNet architecture, suggesting it would serve as an effective general training strategy for autoregressive NQS.

Internet of things is a rapidly growing industry, and there are more connected devices than humans. There are unlimited internet of things devices around us. The scope of these devices has increased manifold in recent years in different areas like healthcare, unmanned vehicles, automatic monitoring systems, and smart homes, etc. These connected devices produce lots of data that need to be processed to achieve the goal of automation in daily life. The cloud provides many centralized solutions to process data using powerful resources in real-time, but there could be latency issues due to increased network traffic. So a distributed solution is much needed to meet this growing demand of processing data in parallel. In this paper, we propose a distributed shared memory [18] abstraction for the internet of things that uses a graph-aware partitioning algorithm and uses smart message passing techniques to process data in distributed and parallel fashion [19].

This work aims to investigate the FPGA (Field-Programmable Gate Array) and GPU (Graphical Processing Unit) technology in image optimization research for an industrial frontier study. Using an experimental method, the research compared the efficiency of two technologies as implemented in some many image processing algorithms. NI CompactRIO platform for FPGA implementation and NVIDIA GeForce GTX 970 in GPU processing performed differently. As is well known, low-lag applications (camera synchronization, real-time data processing etc.) were very well suited for FPGAs. GPUs with architecture CUDA, on the other hand could be a thousand times faster than traditional CPUs in parallel data processing. Other challenges identified through analysis were FPGA design optimization and GPU resource wise utilization. The results give recommendation in terms of selecting technologies based on the features for image industrial processing applications

Abstract: This chapter explores the design and development of photonic processors for ultra-fast data processing in high-performance computing (HPC) environments. By leveraging light instead of electricity for computation, photonic processors offer significant advantages in terms of speed, bandwidth, and energy efficiency. The chapter covers advancements in photonic materials, device engineering, and optical interconnects that enable scalable photonic systems for real-world applications, including AI, machine learning, and quantum computing. Key topics include the integration of photonic processors with quantum communication networks, the role of photonic multiplexing in parallel data processing, and innovations such as all-optical neurons for neuromorphic computing. The chapter also addresses current challenges, including phase sensitivity and the development of photonic quantum gates, offering solutions for scaling photonic computing to meet the demands of HPC and quantum networks. Keywords: photonic processors, high-performance computing, ultra-fast data processing, optical interconnects, photonic materials, quantum communication, AI, machine learning, photonic multiplexing, neuromorphic computing, phase sensitivity, quantum gates, scalable systems.

Today, the complex large scale computing tasks can be performed by using the various multithreading architectures. Despite the multithreading mechanisms of modern programming languages are efficient, the reliable and accuracy of the application data processing is depending on the computational architecture. Therefore, parallel data processing are more complex than the sequential ones and requires additional work hard. The main problem of multithreading mechanisms is the non-centralized usage of these mechanisms. In this case, the code becomes dependent on particular programming techniques and it is difficult to modify the functions of application. The use of multithreading technique requires the study of the application architecture. This article describes an application architecture which can improve the design requirements of software products. The paper presents a class diagram «Computing Process subsystem» for the entire computing process of the application and a detailed analysis of the entities objects. In this article, the development of automated traffic scheduling system of subway will take into account as a real world application of the proposed computational architecture.