Simple Network Design Research Articles

LUneXt: Simple and Efficient U-shaped Network Design for Medical Image Segmentation with Nonlinear Activation

Medical image segmentation has always been a challenging task. This paper proposes a new LUneXt medical image segmentation model based on the characteristics analysis of medical image data sets and testing of different nonlinear activation units. Both normalized activations for the original negative input image activation have good optimization capabilities for the tokenization module parameters proposed in the original UneXt model. Using different activation coefficients for different foreground and background areas has achieved better results. The experimental results of this paper on the Breast Ultrasound Images (BUSI) data set reached an intersection over union (IoU) value of 62.64%, a Dice value of 76.12%, and a single inference speed of 807.57[Formula: see text]ms. The experimental IoU value of the International Skin Imaging Collaboration (ISIC 2018) data set reached 82.95%, and the Dice value reached 90.50%. The single inference speed reached 842.58[Formula: see text]ms. The LUneXt model is more robust than other models. While improving model performance, it does not introduce higher computational complexity and does not have a major impact on the processing speed of a single image.

Vowel’s classification for stroke patients through rehabilitation performance via image-profiled sound data

In terms of medicine, a disorder is a disturbance of the mind or body's normal functioning. Communication issues may result from stroke because it damages the parts of the brain that control language. The capacity to talk, read, write, and comprehend speeches can all be affected after a stroke. The rehabilitation and treatment of patients generally take a long time and include constant medication, exercise, and rehabilitation training. However, most rehab facilities throughout the world still manually carry out this rehabilitation process. Machine learning and deep learning have been introduced to this medical field to aid rehabilitation using the new technology due to computer vision's impact on this field. A reliable Convolution Neural Network with a graphical user interface is introduced in this study to support and enhance rehabilitation efforts. The spectrogram in the image-profiled sound is used to provide the optimum outcome and accuracy. This project aims to develop a neural network that can distinguish vowels between a normal person's and stroke patients' voices. In this proposed paper's result, an intelligent Convolution Neural Network system for Malay language vowel detection with high-performance accuracy is demonstrated with maximum accuracy was 92.96% with 20 epoch numbers and 6 batch size. This outcome showed that the proposed method, even using a simple network design, is still competitive compared with other methods. The proposed method is ideal for training and validating vowel recognition accuracy especially for stroke patients.

Brain tumor segmentation using JGate-AttResUNet – A novel deep learning approach

Segmenting brain tumours in medical imaging is a crucial job. The ability to improve treatment options and boost patient survival rates depends on the early diagnosis of brain tumours. It is difficult and tedious task for segmenting the tumours for cancer diagnosis from a huge amount of MRI (Magnetic Resonance Imaging) images acquired in clinical practice. Therefore, automatic brain tumour segmentation techniques are needed. Deep learning algorithms for automatic tumor segmentation have lately grown in popularity as they produce cutting-edge results and are more effective than alternative techniques at solving this issue. Most of the recent researches used four MRI imaging modalities such as T1, T1c, T2, and FLAIR, because each delivers distinct and crucial characteristics relating to each area of the tumor. Even though several of the studies had better segmentation on the dataset utilized, they are having a most complicated network structure and they requires more training and testing time. As a result, a simple and novel JGate-AttResUNet network design is constructed in the proposed work to produce a robust and reliable brain tumour segmentation system. This method provides more effective and precise localization of tumor when compared with other models. For that J-Gate attention method is used to enhance the tumour localization. The experiments show that the suggested model generates competitive outcomes using the BRATS 2015 and 2019 dataset. For the BRATS 2015 and BRATS 2019 dataset, the designed model produces mean dice values of 0.896 and 0.913, respectively. The additional quantitative and qualitative assessments were discussed.

Aero Grade Epoxy Vitrimer towards Commercialization.

Traditional crosslinked aero grade epoxy resins have excellent thermal-mechanical properties and solvent resistance, but they cannot be remolded, recycled, or repaired. Vitrimers can be topologically rearranged via an associative exchange mechanism, endowing them with thermoplasticity. Introducing dynamic bonds into crosslinked networks to obtain more sustainable thermosets is currently an interesting research topic. While recent research into vitrimers has indicated many advantages over traditional thermosets, an important shortcoming has been identified: susceptibility to creep at service temperature due to the dynamic bonds present in the network. In addition, designing aero grade epoxy vitrimers (similar to RTM6 resin) still remains a challenge. Herein, low creep aero grade epoxy vitrimer with thermal and mechanical properties similar to those of aero grade epoxy resins and with the ability to be recyclable, repairable, and reprocessable, has been prepared. In this manuscript, we demonstrate that aero grade epoxy vitrimer with reduced creep can be easily designed by the introduction of a certain fraction of permanent crosslinks, without having a negative effect on the stress relaxation of the material. Subsequently, the mechanical and relaxation properties were investigated and compared with those of classical aero grade epoxy resin. A high Tg (175 °C) epoxy vitrimer was obtained which fulfilled all mechanical and thermal specifications of the aero sector. This work provides a simple network design to obtain aero grade epoxy resins with excellent creep resistance at elevated temperatures while being sustainable.

Polybutadiene Vitrimers with Tunable Epoxy Ratios: Preparation and Properties.

Traditional crosslinked diene rubber has excellent thermal–mechanical properties and solvent resistance, yet it is incapable of being recycled via universal molding or injecting. Vitrimers, a new class of covalently crosslinked polymer networks, can be topologically rearranged with the associative exchange mechanism, endowing them with thermoplasticity. Introducing the concept of vitrimers into crosslinked networks for the recycling of rubbers is currently an attractive research topic. However, designing tailored rubber vitrimers still remains a challenge. Herein, polybutadiene (PB) vitrimers with different structures were prepared via partial epoxidation of double bonds and ring-opening esterification reactions. Their mechanical and relaxation properties were investigated. It was found that the increasing crosslinking density can increase tensile strength and activation energy for altering the network topology. The influence of side-group effects on their relaxation properties shows that an increase in the number of epoxy groups on the polybutadiene chain can increase the chance of an effective exchange of disulfide units. This work provides a simple network design which can tune vitrimer properties via altering the crosslinking density and side-group effects.

Artificial intelligence-based radiotherapy machine parameter optimization using reinforcement learning.

To develop and evaluate a volumetric modulated arc therapy (VMAT) machine parameter optimization (MPO) approach based on deep-Q reinforcement learning (RL) capable of finding an optimal machine control policy using previous prostate cancer patient CT scans and contours, and applying the policy to new cases to rapidly produce deliverable VMAT plans in a simplified beam model. A convolutional deep-Q network was employed to control the dose rate and multileaf collimator of a C-arm linear accelerator model using the current dose distribution and machine parameter state as input. A Q-value was defined as the discounted cumulative cost based on dose objectives, and experience-replay RL was performed to determine a policy to minimize the Q-value. A two-dimensional network design was employed which optimized each opposing leaf pair independently while monitoring the corresponding dose plane blocked by those leaves. This RL approach was applied to CT and contours from 40 retrospective prostate cancer patients. The dataset was split into training (15 patients) and validation (5 patients) groups to optimize the network, and its performance was tested in an independent cohort of 20 patients by comparing RL-based dose distributions to conformal arcs and clinical intensity modulated radiotherapy (IMRT) delivering a prescription dose of 78Gy in 40 fractions. Mean±SD execution time of the RL VMAT optimization was 1.5±0.2s per slice. In the test cohort, mean±SD (P-value) planning target volume (PTV), bladder, and rectum dose were 80.5±2.0Gy (P<0.001), 44.2±14.6Gy (P<0.001), and 43.7±11.1Gy (P<0.001) for RL VMAT compared to 81.6±1.1Gy, 51.6±12.9Gy, and 36.0±12.3Gy for clinical IMRT. RL was applied to VMAT MPO using clinical patient contours without independently optimized treatment plans for training and achieved comparable target and normal tissue dose to clinical plans despite the application of a relatively simple network design originally developed for video-game control. These results suggest that extending a RL approach to a full three-dimensional beam model could enable rapid artificial intelligence-based optimization of deliverable treatment plans, reducing the time required for radiotherapy planning without requiring previous plans for training.

A Few-Shot Modulation Recognition Method Based on Pseudo-Label Semi-Supervised Learning

In order to solve the problem of insufficient labeled samples in modulation recognition, this paper proposes a few-shot modulation recognition algorithm based on pseudo-label semi-supervised learning (pseudo-label algorithm). First of all, high quality artificial feature, excellent classifier and data-labeling method are used to build efficient pseudo label system, and then the pseudo label system is combined with signal classification method based on the deep learning to realize the modulation classification under the condition of a small number of labeled samples and a large number of unlabeled samples. The simulation results show that the pseudo-label algorithm can improve the model recognition performance by 5%-10% when the six kinds of digital signals are classified and identified and its SNR is greater than 5 dB. At the same time, the algorithm has a simple network design and is of great application value.

Millimeter-Wave Downlink Coverage Extension Strategies

Traditionally, the uplink and downlink in a cellular network are associated with the same base station and the same frequency band since it promotes simpler network design, maintenance, and operation because of reduced complexity. However, when deploying millimeter-wave (mmWave) spectrum, network coverage has limitations hinging on the nature of the mmWave propagation characteristics relative to the traditional sub 6 GHz frequency bands. In this article, we present a method for an extension of the mmWave downlink coverage by demonstrating the benefits of decoupling the reverse and forward link frequencies and by leveraging macro-type radio deployment heights to maximize the line-of-sight coverage. The accompanying link budget analysis and coverage simulations quantify the benefit of the coverage extension methodology to be as much as 6.8 dB while extending possible coverage range distance to greater than 2 km.

Analysis of BGP Multihomed Link Utilization Effect on Internet Services (http, ftp and email)

internet services and network performance represented in end-to-end delay and jitter are studied with respect to different link utilization. Internet users will access the internet services through simulated internet network contains number of BGP routers and Multihomed links. Both link utilization effect on the different internet services and the inability of BGP to automatically redistribute the traffic over available Multihomed Links will be highlighted.This paper also introduce a simple network design which is very close to the real internet environment and covers internet users section , ISPs section and enterprise section which represents offered internet services hoping that this model give a hand in the BGP and internet services researches. KeywordsMultihomed; HTTP; FTP; Email; OPNET.

Efficient algorithms for a simple network design problem

AbstractWe consider the following simple network design problem. The input consists of n weighted nodes, and the output is an edge‐weighted connected network such that the total weight of the edges incident to a node is at least the given weight of the node. We aim to design the cheapest connected network; that is, the reachability of the network should be guaranteed, and the network is better if its total weight is less. In this article, we first show an efficient algorithm that produces an optimal network with minimum weight. The algorithm runs in linear time, and the resulting network contains at most n edges, where n is the number of nodes. To construct a connected network, at least n ‐ 1 edges are required. However, the algorithm sometimes outputs n edges. Next, we aim to minimize not only the weight but also the number of edges. That is, for given n weighted nodes, we aim to design a cheapest tree. Then, the problem becomes \documentclass{article}\usepackage{mathrsfs, amsmath, amssymb}\pagestyle{empty}\begin{document}\begin{align*}\mathcal{N}\mathcal{P}\end{align*} \end{document} ‐complete. We also propose efficient approximation algorithms for constructing a cheapest tree. © 2013 Wiley Periodicals, Inc. NETWORKS, 2013

Design Techniques to Facilitate Processor Power Delivery in 3-D Processor-DRAM Integrated Systems

As a promising option to address the memory wall problem, 3-D processor-DRAM integration has recently received many attentions. Since DRAM dies should be stacked between the processor die and package substrate, we have to fabricate a large number of through-DRAM through-silicon vias (TSVs) to connect the processor die and package for power and input/output (I/O) signal delivery. Although such through-DRAM TSVs will inevitably interfere with DRAM design and induce non-negligible power consumption overhead, little prior research has been done to study how to allocate these through-DRAM TSVs on the DRAM dies and analyze their impacts. To address this open issue, this paper first presents a through-DRAM TSV allocation strategy that well fits to the regular DRAM architecture. Meanwhile, due to the longer path between power/ground pads and processor die, power delivery integrity issue may become more serious in such 3-D processor-DRAM integrated systems. Decoupling capacitor insertion is the most popular method to deal with power delivery integrity issue in high-performance integrated circuits. This paper further proposes to use 3-D stacked DRAM dies to provide decoupling capacitors for the processor die. This can well leverage the superior capacitor fabrication ability of DRAM to reduce the area penalty of decoupling capacitor insertion on the processor die. For its practical implementation, a simple uniform decoupling capacitor network design strategy is presented. To demonstrate through-DRAM TSV allocation and decoupling capacitor insertion strategy and evaluate involved tradeoffs, circuit SPICE simulations and computer system simulations are carried out to quantitatively demonstrate the effectiveness and investigate various design tradeoffs.

Near-Optimal Network Design with Selfish Agents

We introduce a simple network design game that models how independent selfish agents can build or maintain a large network. In our game every agent has a specific connectivity requirement, i.e. each agent has a set of terminals and wants to build a network in which his terminals are connected. Possible edges in the network have costs and each agent's goal is to pay as little as possible. Determining whether or not a Nash equilibrium exists in this game is NP-complete. However, when the goal of each player is to connect a terminal to a common source, we prove that there is a Nash equilibrium on the optimal network, and give a polynomial time algorithm to find a $(1+\varepsilon)$-approximate Nash equilibrium on a nearly optimal network. Similarly, for the general connection game we prove that there is a 3-approximate Nash equilibrium on the optimal network, and give an algorithm to find a $(4.65+\varepsilon)$-approximate Nash equilibrium on a network that is close to optimal.

Non-Cooperative Tree Creation

In this paper we consider the connection game, a simple network design game with independent selfish agents that was introduced by Anshelevich et al. (Proc. 35th Ann. ACM Symp. Theo. Comp. (STOC), pp. 511–520, 2003). Our study concerns an important subclass of tree games, in which every feasible network is guaranteed to be connected. It generalizes the class of single-source games considered by Anshelevich et al. We focus on the existence, quality, and computability of pure-strategy exact and approximate Nash equilibria. For tree connection games, in which every player holds two terminals, we show that there is a Nash equilibrium as cheap as the optimum network. In contrast, for single-source games, in which every player has at most three terminals, the price of stability is at least k−2, and it is $\mathsf{NP}$-complete to decide the existence of a Nash equilibrium. Hence, we propose polynomial time algorithms for computing approximate Nash equilibria, which provide relaxed stability and cost efficiency guarantees. For the case of two terminals per player, there is an algorithm to find a (2+e,1.55)-approximate Nash equilibrium. It can be generalized to an algorithm to find a (3.1+e,1.55)-approximate Nash equilibrium for general tree connection games. This improves the guarantee of the only previous algorithm for the problem, which returns a (4.65+e,1.55)-approximate Nash equilibrium. Tightness results for the analysis of all algorithms are derived. Our algorithms use a novel iteration technique for trees that might be of independent interest.

Toward scalable admission control for VoIP networks

We present an overview of scalable admission control in IP networks. We introduce various approaches and discuss the mechanism and characteristics of each method. In particular, we argue that end-to-end measurement based admission control (EMBAC), which employs end-to-end on-demand probing, should be used for call admission control. Second, we consider use of EMBAC in VoIP networks. We present a new probability-based EMBAC scheme and show that its performance is close to the ideal method using virtual-trunk-based admission control. We also present a QoS allocation approach for selecting an admission threshold and dimensioning link capacities. A simple network design and evaluation results suggest that this QoS allocation approach is effective to adequately dimension a network, while satisfying end-to-end targets in terms of blocking probability and packet loss rate.

A Graph-Theoretic Game and Its Application to the k-Server Problem

This paper investigates a zero-sum game played on a weighted connected graph $G$ between two players, the tree player and the edge player. At each play, the tree player chooses a spanning tree $T$ and the edge player chooses an edge $e$. The payoff to the edge player is $cost(T,e)$, defined as follows: If $e$ lies in the tree $T$ then $cost(T,e)=0$; if $e$ does not lie in the tree then $cost(T,e) = cycle(T,e)/w(e)$, where $w(e)$ is the weight of edge $e$ and $cycle(T,e)$ is the weight of the unique cycle formed when edge $e$ is added to the tree $T$. The main result is that the value of the game on any $n$-vertex graph is bounded above by $\exp(O(\sqrt{\log n \log\log n}))$. It is conjectured that the value of the game is $O(\log n)$. The game arises in connection with the $k$-server problem on a road network; i.e., a metric space that can be represented as a multigraph $G$ in which each edge $e$ represents a road of length $w(e)$. It is shown that, if the value of the game on $G$ is $Val(G,w)$, then there is a randomized strategy that achieves a competitive ratio of $k(1 + Val(G,w))$ against any oblivious adversary. Thus, on any $n$-vertex road network, there is a randomized algorithm for the $k$-server problem that is $k\cdot\exp(O(\sqrt{\log n \log\log n}))$ competitive against oblivious adversaries. At the heart of the analysis of the game is an algorithm that provides an approximate solution for the simple network design problem. Specifically, for any $n$-vertex weighted, connected multigraph, the algorithm constructs a spanning tree $T$ such that the average, over all edges $e$, of $cost(T,e)$ is less than or equal to $\exp(O(\sqrt{\log n \log\log n}))$. This result has potential application to the design of communication networks. It also improves substantially known estimates concerning the existence of a sparse basis for the cycle space of a graph.