Biblio

Making use of spectrally diverse communications links to re-route traffic in response to dynamic environments to manage network bottlenecks has become essential in order to guarantee message delivery across heterogeneous networks. We propose an innovative, proactive Congestion Aware Intent-Based Routing (CONAIR) architecture that can select among available communication link resources based on quality of service (QoS) metrics to support continuous information exchange between networked participants. The CONAIR architecture utilizes a Network Controller (NC) and artificial intelligence (AI) to re-route traffic based on traffic priority, fundamental to increasing end user quality of experience (QoE) and mission effectiveness. The CONAIR architecture provides network behavior prediction, and can mitigate congestion prior to its occurrence unlike traditional static routing techniques, e.g. Open Shortest Path First (OSPF), which are prone to congestion due to infrequent routing table updates. Modeling and simulation (M&S) was performed on a multi-hop network in order to characterize the resiliency and scalability benefits of CONAIR over OSPF routing-based frameworks. Results demonstrate that for varying traffic profiles, packet loss and end-to-end latency is minimized.

In this paper, we investigate how to automatically persist versioned data structures in distributed settings (e.g. cloud + edge) using append-only storage. By doing so, we facilitate resiliency by enabling program state to survive program activations and termination, and program-level data structures and their version information to be accessed programmatically by multiple clients (for replay, provenance tracking, debugging, and coordination avoidance, and more). These features are useful in distributed, failure-prone contexts such as those for heterogeneous and pervasive Internet of Things (IoT) deployments. We prototype our approach within an open-source, distributed operating system for IoT. Our results show that it is possible to achieve algorithmic complexities similar to those of in-memory versioning but in a distributed setting.

As Edge deployments move closer towards the end devices, low latency communication among Edge aware applications is one of the key tenants of Edge service offerings. In order to simplify application development, service mesh architectures have emerged as the evolutionary architectural paradigms for taking care of bulk of application communication logic such as health checks, circuit breaking, secure communication, resiliency (among others), thereby decoupling application logic with communication infrastructure. The latency to throughput ratio needs to be measurable for high performant deployments at the Edge. Providing benchmark data for various edge deployments with Bare Metal and virtual machine-based scenarios, this paper digs into architectural complexities of deploying service mesh at edge environment, performance impact across north-south and east-west communications in and out of a service mesh leveraging popular open-source service mesh Istio/Envoy using a simple on-prem Kubernetes cluster. The performance results shared indicate performance impact of Kubernetes network stack with Envoy data plane. Microarchitecture analyses indicate bottlenecks in Linux based stacks from a CPU micro-architecture perspective and quantify the high impact of Linux's Iptables rule matching at scale. We conclude with the challenges in multiple areas of profiling and benchmarking requirement and a call to action for deploying a service mesh, in latency sensitive environments at Edge.

In many distributed learning setups such as federated learning, client nodes at the edge use individually collected data to compute the local gradients and send them to a central master server, and the master aggregates the received gradients and broadcasts the aggregation to all clients with which the clients can update the global model. As straggling communication links could severely affect the performance of distributed learning system, Prakash et al. proposed to utilize helper nodes and coding strategy to achieve resiliency against straggling client-to-helpers links. In this paper, we propose two coding schemes: repetition coding (RC) and MDS coding both of which enable the clients to update the global model in the presence of only helpers but without the master. Moreover, we characterize the uplink and downlink communication loads, and prove the tightness of uplink communication load. Theoretical tradeoff between uplink and downlink communication loads is established indicating that larger uplink communication load could reduce downlink communication load. Compared to Prakash's schemes which require a master to connect with helpers though noiseless links, our scheme can even reduce the communication load in the absence of master when the number of clients and helpers is relatively large compared to the number of straggling links.

Approximate computing emerged as a key alternative for trading off accuracy against energy efficiency and area reduction. Error-tolerant applications, such as multimedia processing, machine learning, and signal processing, can process the information with lower-than-standard accuracy at the circuit level while still fulfilling a good and acceptable service quality at the application level. Adaptive filtering-based systems have been demonstrating high resiliency against hardware errors due to their intrinsic self-healing characteristic. This paper investigates the design space exploration of arithmetic approximations in a Very Large-Scale Integration (VLSI) harmonic elimination (HE) hardware architecture based on Least Mean Square (LMS) adaptive filters. We evaluate the Pareto front of the area- and power versus quality curves by relaxing the arithmetic precision and by adopting both approximate multipliers (AxMs) in combination with approximate adders (AxAs). This paper explores the benefits and impacts of the Dynamic Range Unbiased (DRUM), Rounding-based Approximate (RoBA), and Leading one Bit-based Approximate (LoBA) multipliers in the power dissipation, circuit area, and quality of the VLSI HE architectures. Our results highlight the LoBA 0 as the most efficient AxM applied in the HE architecture. We combine the LoBA 0 with Copy and LOA AxAs with variations in the approximation level (L). Notably, LoBA 0 and LOA with \$L=6\$ resulted in savings of 43.7% in circuit area and 45.2% in power dissipation, compared to the exact HE, which uses multiplier and adder automatically selected by the logic synthesis tool. Finally, we demonstrate that the best hardware architecture found in our investigation successfully eliminates the contaminating spurious noise (i.e., 60 Hz and its harmonics) from the signal.

Maintaining critical data and process availability is an important challenge of Industry 4.0. Given the variety of smart nodes, data and the access latency that can be tolerated by consumers in modern IoT-based industry, we propose a method for analyzing the resiliency of an IoT network. Due to the complexity of modern system structures, different components in the system can affect the system’s resiliency. Therefore, a fundamental problem is to propose methods to quantify the value of resilience contribution of a node in each system effectively. This paper aims to identify the most critical vertices of the network with respect to the latency constraint resiliency metric. Using important centrality metrics, we identify critical nodes in industrial IoT networks to analyze the degree of resiliency in the IoT environments. The results show that when nodes with the highest value of Closeness Centrality (CC) were disrupted Resiliency of Latency (RL) would have the lowest value. In other words, the results indicate the nodes with the high values for CC are most critical in an IoT network.

This paper presents a new framework for SATCOM jamming resiliency in the presence of a smart adversary jammer that can prioritize specific channels to attack with a non-uniform probability of distribution. We first develop a model and a defense action strategy based on a Markov decision process (MDP). We propose a greedy algorithm for the MDP-based defense algorithm's policy to optimize the expected user's immediate and future discounted rewards. Next, we remove the assumption that the user has specific information about the attacker's pattern and model. We develop a Q-learning algorithm-a reinforcement learning (RL) approach-to optimize the user's policy. We show that the Q-learning method provides an attractive defense strategy solution without explicit knowledge of the jammer's strategy. Computer simulation results show that the MDP-based defense strategies are very efficient; they offer a significant data rate advantage over the simple random hopping approach. Also, the proposed Q-learning performance can achieve close to the MDP approach without explicit knowledge of the jammer's strategy or attacking model.

Visual Question Answering (VQA) models have achieved significant success in recent times. Despite the success of VQA models, they are mostly black-box models providing no reasoning about the predicted answer, thus raising questions for their applicability in safety-critical such as autonomous systems and cyber-security. Current state of the art fail to better complex questions and thus are unable to exploit compositionality. To minimize the black-box effect of these models and also to make them better exploit compositionality, we propose a Dynamic Neural Network (DMN), which can understand a particular question and then dynamically assemble various relatively shallow deep learning modules from a pool of modules to form a network. We incorporate compositional temporal attention to these deep learning based modules to increase compositionality exploitation. This results in achieving better understanding of complex questions and also provides reasoning as to why the module predicts a particular answer. Experimental analysis on the two benchmark datasets, VQA2.0 and CLEVR, depicts that our model outperforms the previous approaches for Visual Question Answering task as well as provides better reasoning, thus making it reliable for mission critical applications like safety and security.

Recent projects regarding the exploration of the functions of microbiomes within communities brought about a plethora of new data. That specific field of study is called Metagenomics and one of its more advancing approach is the application of network analysis. The paper introduces NAMData which is a web-application tool for the network analysis of microbiome data. The system handles the compositionality and sparsity nature of microbiome data by applying taxa filtration, normalization, and zero treatment. Furthermore, compositionally aware correlation estimators were used to compute for the correlation between taxa and the system divides the network into the positive and negative correlation network. NAMData aims to capitalize on the unique network features namely network visualization, centrality scores, and community detection. The system enables researchers to include network analysis in their analysis pipelines even without any knowledge of programming. Biological concepts can be integrated with the network findings gathered from the system to either support existing facts or form new insights.

We describe a (time) cost model for the (call-by-value) λ-calculus based on a natural presentation of its game semantics: the cost of computing a finite approximant to the denotation of a term (its evaluation tree) is the size of its smallest derivation in the semantics. This measure has an optimality property enabling compositional reasoning about cost bounds: for any term A, context C[\_] and approximants a and c to the trees of A and C[A], the cost of computing c from C[A] is no more than the cost of computing a from A and c from C[a].Although the natural semantics on which it is based is nondeterministic, our cost model is reasonable: we describe a deterministic algorithm for recognizing evaluation tree approximants which satisfies it (up to a constant factor overhead) on a Random Access Machine. This requires an implementation of the λv-calculus on the RAM which is completely lazy: compositionality of costs entails that work done to evaluate any part of a term cannot be duplicated. This is achieved by a novel implementation of graph reduction for nameless explicit substitutions, to which we compile the λv-calculus via a series of linear cost reductions.

In this conceptual work, we present Deep Convolutional Gaussian Mixture Models (DCGMMs): a new formulation of deep hierarchical Gaussian Mixture Models (GMMs) that is particularly suitable for describing and generating images. Vanilla (i.e., flat) GMMs require a very large number of components to describe images well, leading to long training times and memory issues. DCGMMs avoid this by a stacked architecture of multiple GMM layers, linked by convolution and pooling operations. This allows to exploit the compositionality of images in a similar way as deep CNNs do. DCGMMs can be trained end-to-end by Stochastic Gradient Descent. This sets them apart from vanilla GMMs which are trained by Expectation-Maximization, requiring a prior k-means initialization which is infeasible in a layered structure. For generating sharp images with DCGMMs, we introduce a new gradient-based technique for sampling through non-invertible operations like convolution and pooling. Based on the MNIST and FashionMNIST datasets, we validate the DCGMMs model by demonstrating its superiority over flat GMMs for clustering, sampling and outlier detection.

While language learning in infants and toddlers progresses somewhat seamlessly, in artificial systems the grounding of language in knowledge structures that are learned from sensorimotor experiences remains a hard challenge. Here we introduce LEARNA, which learns event-characterizing abstractions to resolve natural language ambiguity. LEARNA develops knowledge structures from simulated sensorimotor experiences. Given a possibly ambiguous descriptive utterance, the learned knowledge structures enable LEARNA to infer environmental scenes, and events unfolding within, which essentially constitute plausible imaginations of the utterance’s content. Similar event-predictive structures may help in developing artificial systems that can generate and comprehend descriptions of scenes and events.

A kitchen underpinned by the Internet of Things (IoT) requires the management of complex procedural processes. This is due to the fact that when supporting an end-user in the preparation of even only one dish, various devices may need to coordinate with each other. Additionally, it is challenging— yet desirable—to enable an end-user to program their kitchen devices according to their preferred behaviour and to allow them to visualise and track their cooking workflows. In this paper, we compared two semantic representations, namely, Behaviour Trees and the DX-MAN model. We analysed these representations based on their suitability for a range of end-users (i.e., novice to experienced). The methodology required the analysis of smart kitchen user requirements, from which we inferred that the main architectural requirements for IoT cooking workflows are variability and compositionality. Guided by the user requirements, we examined various scenarios and analysed workflow complexity and feasibility for each representation. On the one hand, we found that execution complexity tends to be higher on Behaviour Trees. However, due to their fallback node, they provide more transparency on how to recover from unprecedented circumstances. On the other hand, parameter complexity tends to be somewhat higher for the DX-MAN model. Nevertheless, the DX-MAN model can be favourable due to its compositionality aspect and the ease of visualisation it can offer.

Neural Module Network (NMN) exhibits strong interpretability and compositionality thanks to its handcrafted neural modules with explicit multi-hop reasoning capability. However, most NMNs suffer from two critical draw-backs: 1) scalability: customized module for specific function renders it impractical when scaling up to a larger set of functions in complex tasks; 2) generalizability: rigid pre-defined module inventory makes it difficult to generalize to unseen functions in new tasks/domains. To design a more powerful NMN architecture for practical use, we propose Meta Module Network (MMN) centered on a novel meta module, which can take in function recipes and morph into diverse instance modules dynamically. The instance modules are then woven into an execution graph for complex visual reasoning, inheriting the strong explainability and compositionality of NMN. With such a flexible instantiation mechanism, the parameters of instance modules are inherited from the central meta module, retaining the same model complexity as the function set grows, which promises better scalability. Meanwhile, as functions are encoded into the embedding space, unseen functions can be readily represented based on its structural similarity with previously observed ones, which ensures better generalizability. Experiments on GQA and CLEVR datasets validate the superiority of MMN over state-of-the-art NMN designs. Synthetic experiments on held-out unseen functions from GQA dataset also demonstrate the strong generalizability of MMN. Our code and model are released in Github1.

Over the past two decades, itemset mining techniques have become an integral part of pattern mining in large databases. We present a novel system for mining frequent and rare itemsets simultaneously with supports weighted by cardinality in transactional datasets. Based on our neural item embedding with additive compositionality, the original mining problems are approximately reduced to polynomial-time convex optimization, namely a series of vector subset selection problems in Euclidean space. The numbers of transactions and items are no longer exponential factors of the time complexity under such reduction, except only the Euclidean space dimension, which can be assigned arbitrarily for a trade-off between mining speed and result quality. The efficacy of our method reveals that additive compositionality can be represented by linear translation in the itemset vector space, which resembles the linguistic regularities in word embedding by similar neural modeling. Experiments show that our learned embedding can bring pattern itemsets with higher accuracy than sampling-based lossy mining techniques in most cases, and the scalability of our mining approach triumphs over several state-of-the-art distributed mining algorithms.

In this paper, we discuss the methodology of generalizing the optimal control law from learned component tasks to unlearned composite tasks on Multi-Agent Systems (MASs), by using the linearity composition principle of linearly solvable optimal control (LSOC) problems. The proposed approach achieves both the compositionality and optimality of control actions simultaneously within the cooperative MAS framework in both discrete and continuous-time in a sample-efficient manner, which reduces the burden of re-computation of the optimal control solutions for the new task on the MASs. We investigate the application of the proposed approach on the MAS with coordination between agents. The experiments show feasible results in investigated scenarios, including both discrete and continuous dynamical systems for task generalization without resampling.

There are two paradigms in language processing, as characterised by symbolic compositional and statistical distributional modelling, which may be regarded as based upon the principles of compositionality (or symbolic recursion) and of contextuality (or the distributional hypothesis), respectively. Starting with philosophy of language as in Frege and Wittgenstein, we elucidate the nature of language and language processing from interdisciplinary perspectives across different fields of science. At the same time, we shed new light on conceptual issues in language processing on the basis of recent advances in Transformer-based models such as BERT and GPT-3. We link linguistic cognition with mathematical cognition through these discussions, explicating symbol grounding/emergence problems shared by both of them. We also discuss whether animal cognition can develop recursive compositional information processing.

Generative Adversarial Networks (GANs) are machine learning methods that are used in many important and novel applications. For example, in imaging science, GANs are effectively utilized in generating image datasets, photographs of human faces, image and video captioning, image-to-image translation, text-to-image translation, video prediction, and 3D object generation to name a few. In this paper, we discuss how GANs can be used to create an artificial world. More specifically, we discuss how GANs help to describe an image utilizing image/video captioning methods and how to translate the image to a new image using image-to-image translation frameworks in a theme we desire. We articulate how GANs impact creating a customized world.

Nowadays, children, teens, and almost everyone around us tend to receive abundant and frequent advice regarding the usefulness of syllabification. Not only does it improve pronunciation, but it also makes it easier for us to read unfamiliar words in chunks of syllables rather than reading them all at once. Within this paper, we have designed, implemented, and presented a Turing machine-based syllable splitter. A Turing machine forms the theoretical basis for all modern computers and can be used to solve universal problems. On the other hand, a syllable splitter is used to hyphenate words into their corresponding syllables. We have proposed our work by illustrating the various states of the Turing machine, along with the rules it abides by, its machine specifications, and transition function. In addition to this, we have implemented a Graphical User Interface to stimulate our Turing machine to analyze our results better.

Evolutionary computation (EC) is a kind of advanced computational intelligence (CI) algorithm and advanced artificial intelligence (AI) algorithm. EC algorithms have been widely studied for solving optimization and scheduling problems in various real-world applications, which act as one of the Big Three in CI and AI, together with fuzzy systems and neural networks. Even though EC has been fast developed in recent years, there is an assumption that the algorithm designer can obtain the objective function of the optimization problem so that they can calculate the fitness values of the individuals to follow the “survival of the fittest” principle in natural selection. However, in a real-world application scenario, there is a kind of problem that the objective function is privacy so that the algorithm designer can not obtain the fitness values of the individuals directly. This is the privacy-preserving optimization problem (PPOP) where the assumption of available objective function does not check out. How to solve the PPOP is a new emerging frontier with seldom study but is also a challenging research topic in the EC community. This paper proposes a rank-based cryptographic function (RCF) to protect the fitness value information. Especially, the RCF is adopted by the algorithm user to encrypt the fitness values of all the individuals as rank so that the algorithm designer does not know the exact fitness information but only the rank information. Nevertheless, the RCF can protect the privacy of the algorithm user but still can provide sufficient information to the algorithm designer to drive the EC algorithm. We have applied the RCF privacy-preserving method to two typical EC algorithms including particle swarm optimization (PSO) and differential evolution (DE). Experimental results show that the RCF-based privacy-preserving PSO and DE can solve the PPOP without performance loss.

In the Swarm Intelligence domain, the firefly algorithm(s) is the most significant algorithm applied in most all optimization areas. FA and variants are easily understood and implemented. FA is capable of solving different domain problems. For solving diverse range of engineering problems requires modified FA or Hybrid FA algorithms, but it is possible additional scope of improvement. In recent times swarm intelligence based intelligent optimization algorithms have been used for Research purposes. FA is one of most important intelligence Swarm algorithm that can be applied for the problems of Global optimization. FA algorithm is capable of achieving best results for complicated issues. In this research study we have discussed and different characteristics of FA and presented brief Review of FA. Along with other metahauristic algorithm we have discussed FA algorithm’s different variant like multi objective, and hybrid. The applications of firefly algorithm are bestowed. The aim of the paper is to give future direction for research in FA.

Numerical simulation of fluid flow is a significant research concern during the design process of a machine component that experiences fluid-structure interaction (FSI). State-of-the-art in traditional computational fluid dynamics (CFD) has made CFD reach a relative perfection level during the last couple of decades. However, the accuracy of CFD is highly dependent on mesh size; therefore, the computational cost depends on resolving the minor feature. The computational complexity grows even further when there are multiple physics and scales involved making the approach time-consuming. In contrast, machine learning (ML) has shown a highly encouraging capacity to forecast solutions for partial differential equations. A trained neural network has offered to make accurate approximations instantaneously compared with conventional simulation procedures. This study presents transient fluid flow prediction past a fully immersed body as an integral part of the ML-CFD project. MLCFD is a hybrid approach that involves initialising the CFD simulation domain with a solution forecasted by an ML model to achieve fast convergence in traditional CDF. Initial results are highly encouraging, and the entire time-based series of fluid patterns past the immersed structure is forecasted using a deep learning algorithm. Prepared results show a strong agreement compared with fluid flow simulation performed utilising CFD.

Application of computational intelligence methods in data analysis and optimization problems can allow feasible and optimal solutions of complicated engineering problems. This study demonstrates an intelligent analysis scheme for determination of optimal operating condition of an internal combustion engine. For this purpose, an artificial neural network learning model is used to represent engine behavior based on engine data, and a metaheuristic optimization method is implemented to figure out optimal operating states of the engine according to the neural network learning model. This data analysis scheme is used for adjustment of optimal engine speed and fuel rate parameters to provide a maximum torque under Nitrous oxide emission constraint. Harris hawks optimization method is implemented to solve the proposed optimization problem. The solution of this optimization problem addresses eco-friendly enhancement of vehicle performance. Results indicate that this computational intelligent analysis scheme can find optimal operating regimes of an engine.

Earlier around in year 1880’s, Industry 2.0 marked as change to the society caused by the invention of electricity. In today’s era, artificial intelligence plays a crucial role in defining the period of Industry 4.0. In this research study, we have presented Computational Intelligence based Machine Condition Monitoring system architecture for determination of developing faults in industrial machines. The goal is to increase efficiency of machines and reduce the cost. The architecture is fusion of machine sensitive sensors, cloud computing, artificial intelligence and databases, to develop an autonomous fault diagnostic system. To explain CI-MCMs, we have used neural networks on sensor data obtained from hydraulic system. The results obtained by neural network were compared with those obtained from traditional methods.

Pooling together samples and testing the resulting mixture is gaining considerable interest as a potential method to markedly increase the rate of testing for SARS-CoV-2, given the resource limited conditions. Such pooling can also be employed for carrying out large scale diagnostic testing of other infectious diseases, especially when the available resources are limited. Therefore, it has become important to design a user-friendly tool to assist clinicians and policy makers, to determine optimal testing pool and sub-pool sizes for their specific scenarios. We have developed such a tool; the calculator web application is available at https://riteshsingh.github.io/poolsize/. The algorithms employed are described and analyzed in this paper, and their application to other scientific fields is also discussed. We find that pooling always reduces the expected number of tests in all the conditions, at the cost of test sensitivity. The No sub-pooling optimal pool size calculator will be the most widely applicable one, because limitations of sample quantity will restrict sub-pooling in most conditions.