Image Segmentation Using Membrane Computing: A Literature Survey

Traditionally, topics such as parallel computing, computer graphics, and artificial intelligence have been taught as stand-alone courses in the computing curriculum. Often these are elective courses, limiting the material to the subset of students choosing to take the course. Recently there has been movement to distribute topics across the curriculum in order to ensure that all graduates have been exposed to concepts such as parallel computing. This work describes one approach to threading topics from AI, graphics, and parallel processing into coursework starting early in a student's program without substantially altering the basic course objectives. This, in turn, allows the student to sample topics early enough to make informed decisions when selecting electives.

Hybrid clustering algorithm for an efficient brain tumor segmentation

Assalamu’alaikum Wr. Wb. and Greetings.I am pleased and honored to welcome you at the First International Conference on Computer Science and Applied Mathematic (ICCSAM 2018), which was held this year by AMIK and STIKOM Tunas Bangsa Pematangsiantar in collaboration with the Indonesian Computer and Information Professional Association (IPKIN), Indonesian Mathematical Society (INDOMS) and Bank Muamalat. As Chair of the Foundation, I would like to convey a greeting Welcome to Parapat City Lake Toba to presenters from various countries and especially those I respect for the presence of scientists in the field of Computer and Mathematical Sciences and industry practitioners in the 2018 ICCSAM event.I see that this activity is designed to enhance the exchange of knowledge and new discoveries in computer science and mathematics and related fields in industry. I hope that scientists in the field of computer science and mathematics and those who work in the industry can share knowledge and work together as a team that has mutual relations with each other. I am very pleased to say that the theme of this conference, “Advancing Computability Innovation” is very much in line with the objectives of AMIK and STIKOM conferences and missions, namely “to become a Science and Technology based Study Program that meets industrial needs and functions as a research center in Information Data Science. The conference was held in response to output and aoutcame which had a significant contribution in the field of computer science and mathematics as an inseparable unit of science towards the development of local and global industries. It is our happiness and honor to welcome distinguished professors present to convey their expertise at this conference.I hope this meeting will enable the development of productive dialogue between participants from various countries. They also provide invaluable opportunities for networking among participants, institutions and industries. I also hope that diversity in these fields can reveal more opportunities for researchers and practitioners from all over the world to start a lot of research related to the industry in the future.I would like to congratulate AMIK and STIKOM Tunas Bangsa for starting this conference with a synergistic contribution from dedicated partners namely the USU Faculty of Mathematics and Natural Sciences, USU’s Faculty of Computer and Information Technology, the Indonesian Computer and Informatics Professional Association (IPKIN), Indonesian Mathematical Society (INDOMS), Bank Muamalat, Malaysia Pahang University (UMP), University of Essex, United Kingdom, Ankara, Turkey and Institute of Applied Mathematics Middle East Technical University to all delegates for their full support, cooperation and contribution to the 2018 ICCSAM. I also want to thank the Organizing Committee for their perseverance and extraordinary efforts. Various sponsors are also rewarded for their contributions. I really hope that all participants will get a pleasant stay here at NIAGARA HOTEL and bring back unforgettable experiences and valuable knowledge from this conference.Thanks.H. Ahmad Ridwansyah Putra

All computing devices we currently use are parallel machines. This includes the whole range from portable devices to supercomputers. Until recently, parallel computing at the undergraduate level was considered an advanced elective topic in most computer science and engineering departments. If this continues, undergraduate students will not be competitive in the market. If they decide to go to graduate studies, they will be late in acquiring parallel computing skills.In this paper we discuss the challenges and insights in designing an undergraduate parallel computing course in computer science department. These insights stem from our experience in offering this course for six years, once per year.

Parallel computing finds its place in the world of computation long back since 1842 with the first ever design of Analytical Engine by English mathematician and computer pioneer Charles Babbage. It took lots of brainstorming by the great researchers like John Cocke, Daniel Slotnick, Gene Amdahl and the big organizations like IBM, Burroughs Corporation and Honeywell for the next century, to coin various laws and set a background for today's parallel computing platform. Since then, parallel computing has successfully replaced the notion of sequential computing in terms of instruction level, task level, thread level parallelism. From the use of SISD programs to MIMD programs, the evolution of parallelism in computing has been phenomenon. When a job is divided into several parts where each part is capable of running with others in parallel, then this not only increases the overall speed of execution of job, but also ascertains the optimal utilization of computer resources like memory, processor time and the like. On this basis, the computers can be categorized on hardware level at which they can support parallelism which include multi core/ many core computers, multi processor computers, clusters, grids and massively parallel supercomputers. With the concept of parallelization concepts like concurrency control, deadlocks, synchronization of tasks have been there. Lot of work is going on since years in addressing these concepts in virtue of parallel computing. This chapter is focusing on the history, background, types of parallel computing, the memory architectures, message passing, concurrency control, deadlocks and their possible solution in parallel computing.

Artificial intelligence (AI) is a rapidly evolving field that has seen tremendous growth in recent years. In this chapter, the authors provide an overview of current trends in AI and their applications in computer science. They also discuss the future directions of AI research and their potential impact on the field of computer science. They start by introducing the basic concepts of AI and its various subfields. Then, they present an overview of current trends in AI research, including machine learning, natural language processing, computer vision, and robotics. The authors discuss how these trends are applied in computer science, such as autonomous vehicles, fraud detection, and personalized medicine. Finally, they discuss the future directions of AI research, including the development of more explainable AI systems, the integration of AI with other emerging technologies, and the ethical considerations of AI.

Parallel dynamic process simulation of a distillation column on the BBN Butterfly Parallel Processor computer

Artificial Intelligence (AI) has become an increasingly important and popular topic not just within the field of Computer Science but also the world at large. One of the current challenges in the field of AI is multi-agent planning, of which Swarm Intelligence (SI) is a possible solution drawing from natural systems as an inspiration. While individual agents in a flock or swarm are mostly simplistic and similar in nature, together they can develop extremely complex and emergent behaviour. A very well-known implementation of Swarm Intelligence is “Boids”. Bird like objects first introduced by Craig Reynolds in 1987 that flock and move together based on the 3 core steering behaviours of Separation, Alignment, and Cohesion. However, even current work on boids tend to let individual agents be “reactive” in nature, giving instructions to themselves based on their current state and their observations of the environment around them. This project aims to study how adding an additional layer on top of traditional flocking behaviour, by making agents “socially aware” through actively sharing opinions with each other, will affect the dynamics of a flock.

There has been a recent emergence of many interesting and highly efficient hierarchical (multilevel) algorithms (e.g. multigrid, domain decomposition, wavelets, multilevel preconditioning, the fast multipole algorithms, etc.) for solving numerical problems in scientific computing. These algorithms derive their efficiency from using a hierarchical approach to capture the sharing of global information which is inherent in the physical processes being modelled. In addition to being computationally efficient, these algorithms also possess relatively high degrees of parallelism. I therefore argue that the architectures of parallel computers (especially massively parallel ones) should be designed to support hierarchical communication and synchronization needs of these algorithms. Hierarchical architectures are also more universal because they go beyond supporting a particular class of algorithms to supporting the underlying physical processes being modelled. Finally, I propose that algorithm designers take a critical look at traditional kernel algorithms and re-examine their cost-effectiveness in a massively parallel computing environment.

Sandia National Laboratories has developed massively parallel (MP) software that provides high absolute performance and nearly perfect parallel efficiencies. We have used this software on first- and second-generation 1K-processor hypercubes with more than thousand-fold parallel speedups and supercomputer performance. As we developed MP software, we made significant research advances in parallel numerical methods, such as parallel time stepping. The hardware diagnostic tools and parallel graphics algorithms that we have developed and provided to vendors can pinpoint hardware problems and visualize performance in thousand-processor ensembles. Our distributed-computing software will provide supercomputer performance from workstation networks. In collaboration with university and industry researchers in parallel computing, we have proven the concept of distributed parallel supercomputing with parallel computations on a network of VAX® computers. (VAX is a registered trademark of Digital Equipment Corporation.)

Congruences are ubiquitous in computer science, engineering, mathematics, and related areas. Developing techniques for finding (the number of) solutions of congruences is an important problem. But there are many scenarios in which we are interested in only a subset of the solutions; in other words, there are some restrictions. What do we know about these restricted congruences, their solutions, and applications? This book introduces the tools that are needed when working on restricted congruences and then systematically studies a variety of restricted congruences. Restricted Congruences in Computing defines several types of restricted congruence, obtains explicit formulae for the number of their solutions using a wide range of tools and techniques, and discusses their applications in cryptography, information security, information theory, coding theory, string theory, quantum field theory, parallel computing, artificial intelligence, computational biology, discrete mathematics, number theory, and more.This is the first book devoted to restricted congruences and their applications. It will be of interest to graduate students and researchers across computer science, electrical engineering, and mathematics.

Image segmentation has played an essential role in computer vision. The target detection model represented by YOLOv5 is widely used in image segmentation. However, YOLOv5 has performance bottlenecks such as object scale variation, object occlusion, computational volume, and speed when processing complex images. To solve these problems, an enhanced algorithm based on YOLOv5 is proposed. MobileViT is used as the backbone network of the YOLOv5 algorithm, and feature fusion and dilated convolution are added to the model. This method is validated on the COCO and PASCAL-VOC datasets. Experimental results show that it significantly reduces the processing time and achieves high segmentation quality with an accuracy of 95.32% on COCO and 96.02% on PASCAL-VOC. The improved model is 116 M, 52 M, and 76 M, smaller than U-Net, SegNet, and Mask R-CNN, respectively. This paper provides a new idea and method with which to solve the problems in the field of image segmentation, and the method has strong practicality and generalization value.

The C* Conference on Computer Science and Software Engineering (C3S2E) was established in 2008. C3S2E 2010 is the third annual meeting in the C3S2E conference series and is held in Montréal, Québec, Canada, during May 19-20, 2010. The conference aims to address the need of the academic community in computer science and software engineering. It brings together academics, government and industry professionals to discuss recent progress and challenges in a broad range of areas in the field of computer science and software engineering such as algorithms and theory, artificial intelligence, bioinformatics, computer architecture, computer graphics, computer security, computer vision, data mining, databases, image processing, information retrieval, machine learning, as well as software engineering. C3S2E 2010 also serves as a platform for theoreticians and practitioners to exchange their original research ideas on academic or application aspects of computing and engineering of software systems, present their new findings on theoretical or practical aspects of computer science and software engineering, share their experiences on integrating new technologies into products and applications, discuss their work on applying computing and software engineering to real-life situations, describe their development and operations of challenging computing related systems, and identify unsolved challenges. Although it is the third time C3S2E is held, this comprehensive conference has grown from a Canadian conference into an international conference. For C3S2E 2010, we continue to keep our tradition for inviting international experts in various areas of computer science and software engineering to join our team of international program committee. As a result, our Program Committee consists of professionals from different parts of the world including Australia, Canada, Germany, Hong Kong, Italy, Japan, Portugal, South Korea, Turkey, UAE, and UK. This committee has done an excellent job in finishing the single-blind review and on-line double-blind debate processes in record time. On average, about 90% of reviews were submitted by the due date and about 3.67 reviews were received for each paper. In terms of submissions, we have attracted many high-quality papers submitted by authors globally. The paper selection process was thorough and competitive. On average, each paper was refereed by at least three reviewers, and about 18% of submissions were accepted as full research papers. This year, we have an intensive program that spans over two days. In addition to research papers and student posters, we also include position papers, which allow authors to give their opinions and vision on exploring new concepts and research directions.

Part 1 Computers in control systems: historical development digital computer interfacing structure of a digital control loop interface units data representation and aliasing. Part 2 The z-transformation: definition of the z-transform z-transform properties inverse z-transform pulse of z-transfer functions of systems discrete approximations numerical integration pole-zero mapping modified z-transform multi-rate sampling systems analysis of multi-rate systems fast-slow multi-rate systems closed-loop multi-rate systems. Part 3 Analysis of sampled-data control systems z-transformation of systems stability in discrete systems time domain analysis root locus analysis frequency domain analysis. Part 4 Digital compensator design: continuous domain design digital design digital root locas design state feedback design digital PID control disign deadbeat response design optimal control design controller design in the presence of noise. Part 5 Real-time computer control systems: hardware requirements the digital computer and peripheral equipment the real-time clock interface units software aspects controller implementation programming languages system design co-ordination sampling rate selection and quantization errors computer/device communications interrupt handling multi-tasking and background/foreground. Part 6 Advances in computer control: artificial intelligence expert systems examples of expert systems knowledge based systems in control engineering conventional controller design methods manual control methods fuzzy sets and rule-based control basic fuzzy operations fuzzy relations fuzzy control algorithms parallel processing techniques parallel computers algorithms for parallel (MIMD) computers programming parallel computers performance of parallel computers parallel processing in control engineering matrix algebra numerical integration fault tolerance. Appendices: Table of laplace and z-transforms continuous second-order systems response specifications frequency response characteristics the transputer and occam occam overview transputer systems and occam configuration vibration control of a flexible cantilever system simulation modelling and state estimation controller design user interface solutions.

Medical image segmentation plays a crucial role in intelligent medical image processing systems, serving as the foundation for effective medical image analysis, particularly in assisting diagnosis and surgical planning. Over the past few years, UNet has achieved tremendous success in the field of image segmentation, with several UNet-based extension models widely applied in medical image segmentation tasks. However, the application of these models is limited to scenarios where large medical equipment can be deployed, such as hospitals. The significant computational costs associated with these segmentation models pose significant challenges when deploying them on portable devices with limited hardware resources. This hinders the realization of rapid and efficient image segmentation in Homelab. In this paper, we present a lightweight model, RGShuffleNet, specifically designed for resource-constrained mobile devices for medical image segmentation. To reduce parameters and computational complexity, we first propose Reshaped Group Convolution, a novel convolutional method for effectively restructuring dimensions of different feature groups. Modifying the feature structure enhances correlations between different groups. Additionally, we introduce the MSC-Shuffle block to facilitate information flow between different feature groups. Unlike traditional Shuffle operations that focus solely on channel correlation, the MSC-Shuffle block proposed in this paper enables information exchange between different groups in both channel and spatial dimensions, thereby achieving superior segmentation performance. Experimental evaluations on two cardiac ultrasound image datasets and one chest CT image dataset demonstrate that RGShuffleNet achieves performance superior to various other state-of-the-art methods while maintaining lower complexity. Finally, RGShuffleNet is deployed on portable devices. The source code of the project is available at https://github.com/Zemin-Cai/RGShuffleNet.