Māori, an indigenous person of Aotearoa/New Zealand, has long used computing technologies for cultural resilience, linguistic survival, social revitalisation and resistance, and economic sustainability. Individuals have used various technologies, hapū, subtribe, iwi, tribe, academic institutes, innovators, activists, communities, industry leaders, computer scientists, programmers, historians, geographers, translators, linguists and te reo Māori, the Māori language teachers as a mechanism to connect Māori to their language, whakapapa, genealogy, whānau, family, and mātauranga, knowledge, culture and identity (T.T. Keegan and Sciascia 2018; Whaanga, Keegan, and Apperley 2017; Whaanga, Mato, and Keegan 2021). In this paper, we highlight some of the ICT initiatives Māori have undertaken and highlighted some of the real successes that we have had over the past three decades, from Te Wahapū, translations of the Microsoft and Google, to the Niupepa, Māori Newspaper collection, to some of the work that is currently being done in the areas of xR which encompasses augmented reality (AR), virtual reality (VR), and mixed reality (MR), machine learning techniques, text-to-speech and speech-to-text conversion, and social media platforms.

This paper deals with the capability of the orthogonal chirp division multiplexing (OCDM) modulation scheme to cope with multi-numerology concept in the context of next generations of communications. The OCDM-based multi-numerology transceiver is introduced, and the inter-numerology interference (INI) is analytically derived. The case of filtered-OCDM is considered as well, allowing to both reduce the INI and to shape the power spectrum of the composite signal (i.e. the signal composed of unitary signals configured with different numerologies) according to strong constraints of low out-of-band emissions. The simulations results show the inherent robustness of OCDM against INI as the interference is spread over all subcarriers, whereas it is concentrated in particular subcarriers in OFDM. It results that the (filtered)-OCDM waveform largely outperforms the orthogonal frequency division multiplexing (OFDM) in term of bit error rate (BER) performance, without need for a guard-band between numerologies.

There is an inherent need for the field of Artificial General Intelligence to begin incorporating principles of non-local science in their approach to knowledge representation for the pursuit towards general intelligence. Prevailing theories and concepts are unable to approach a proper implementation of Artificial General Intelligence due to the adoption of concepts that are considered outdated in current scientific terms when it comes to describing time and space. Current scientific progress has increasingly viewed the universe as whole and non-local. The Bhagavata Purana provides a robust framework to encompass various spatial and non-spatial as well as temporal features of reality required to describe non-local sciences. This research attempts to assess the extent towards which the Bhagavata Purana can reconcile the various issues in contemporary scientific theory within the context of data science. Through review of Newton's Principia Mathematica, Immanuel Kant's Critique of Pure Reason, various academic papers regarding topics of space and time, various reference frames used in the prevailing theories of time and space for perceiving reality is compared to the Bhagavata Purana. It aims to define a suitable methodology to describe general intelligence in the field of data science. The research concludes with a recommendation for further research through the implementation of an AGI prototype using a universal database that allows multiple domain knowledge representation in various data models. This is novel research as it aims to create a new ontological schema of time that is able to solve the prevailing issue of developing a truly dynamic time ontology for Artificial General Intelligence in Decision Support Systems by providing an internal intuition of time for machines.

The future electric grid is supported by a vast number of smart inverters interfacing with distributed energy resources at the edge. These inverters’ dynamics are typically characterized as impedances, which are crucial for ensuring grid stability and resiliency. However, the physical implementation of these inverters may change significantly from inverters to inverters and may be kept confidential. Existing analytical impedance models require a complete and precise understanding of system parameters. They can hardly capture the complete electrical behaviors when the inverters are performing complex functions. Online impedance measurements for many inverters across multiple operating points are not scalable. To address these issues, we present InvNet, a machine learning framework to systematically evaluate the effectiveness of data-driven methods for modeling inverter impedance patterns across a wide operation range, even with limited impedance data. Leveraging transfer learning, the InvNet can extrapolate from physics-based models to real-world ones and from one inverter to another with very limited data. This framework demonstrates machine  learning as a powerful tool for modeling and analyzing black-box characteristics of grid-tied inverter systems that cannot be accurately described by traditional analytical methods, such as inverters under model predictive control. Comprehensive evaluations were conducted to verify the effectiveness of the InvNet in various scenarios. All data and models were open-sourced.

Objective: Non-invasive human machine interfaces (HMIs) have high potential in medical, entertainment, and industrial applications. Traditionally, surface electromyography (sEMG) has been used to track muscular activity and infer motor intention. Ultrasound (US) has received increasing attention as an alternative to sEMG-based HMIs. Here, we developed a portable US armband system with 24 channels and a multiple receiver approach, and compared it with existing sEMG- and US-based HMIs on movement intention decoding. Methods: US and motion capture data was recorded while participants performed wrist and hand movements of four degrees of freedom (DoFs) and their combinations. A linear regression model was used to offline predict hand kinematics from the US (or sEMG, for comparison) features. The method was further validated in real-time for a 3-DoF target reaching task. Results: In the offline analysis, the wearable US system achieved an average  R2of 0.94 in the prediction of four DoFs of the wrist and hand while sEMG reached a performance of R2  = 0.60. In online control, the participants achieved an average 93% completion rate of the targets. Conclusion: When tailored for HMIs, the proposed US A-mode system and processing pipeline can successfully regress hand kinematics both in offline and online settings with performances comparable or superior to previously published interfaces. Significance: Wearable US technology may provide a new generation of HMIs that use muscular deformation to estimate limb movements. The wearable US system  allowed for robust proportional and simultaneous control over multiple DoFs in both offline and online settings.

Most two way relay network (TWRN) half-duplex channel estimation algorithms have been developed for single path channels, except for those in frequency domain OFDM systems. We derive a novel time-domain, blind Maximum A posteriori Probability (MAP) estimation method for multipath estimation in TWRN OFDM systems. Since a TWRN half-duplex system is a cascade of two/more bidirectional transmission systems, there are multiple forward and reverse, individual, as well as composite/cascade (of two individual) channels (unlike only one channel in traditional transmission). The situation is further complicated in the case of multipath channels. Additionally, TWRN systems suffer from having noise components at different nodes, including colored (non-white) at the receiver terminal node. Thus most recent research works concentrate on the easier task of estimating single-path (flat frequency) channels, that too by pilot-based, and sometimes, even by suboptimal least squares (LS) methods. However, in this paper, forward, composite/individual mulipath channel estimators developed are semiblind (for enhanced spectral efficiency), and which turn out to be nonlinear. Moreover, an unique “Factor Analysis Alternating Maximization” method (used in psychometrics and some Machine Learning (MLe) applications, but not in signal processing, communication/TWRN systems), is used, in a novel manner, to overcome the colored noise problem, allowing one to derive novel, closed-form, analytical expressions for reverse individual channel h estimation, (with its convergence provided), which is unavailable in existing literature. Non-trivial Cramer Rao bounds have also been derived for these novel multipath channel estimators. Comprehensive simulation results show the novel forward, reverse, composite and individual channel estimation methods perform much better than the existing ones.

Automatic Number Plate Recognition (ANPR) systems were created in order to address the challenges created due to rise in the volume, velocity and density of automobile vehicles. Most modern ANPR systems heavily depend on image processing techniques like contouring and gray-scaling to segment the license plate and use optical character recognition to extract the number from the manipulated image of the number plate. The major advantage of such systems is that they require less computational power and are quite cost-effective. But these systems process the complete images rather than just the region of interest. The more modern ANPR systems rely on object detection algorithms to overcome this challenge and process only the area of interest from the image. But these systems are not suitable for real-time applications due to high computational overhead and high processing time. To overcome the limitations of the existing ANPR systems, we propose an intelligent ANPR is a system for detecting and extracting number plate details from images or sequences of images of vehicles. The proposed deep learning model is based on an improved version of the You Only Look Once (YOLOv4) algorithm. The performance evaluation demonstrates that our model is able to recognize the number plates with an accuracy of above 95% under varied conditions such as high-speed moving vehicles, varying lighting, and vehicle dense area on Indian roads. The system is robust enough to detect the number plates of fast moving vehicles (speed≤ 80km/hr) as well as vehicles in highly traffic dense areas.

This paper gives a direct Visual Odometry (VO) of RGB-D cameras by using features conducted with low-order  Gaussian derivative functions such as Gaussian gradient operator. By using the feature metrics locally, it improves further possibilities for sampling more reliable points from scenarios that are lack of structure or texture and is beneficial to continuous tracking. The proposed approach reaches relatively acceptable performance with a globally heuristic framework built on the general coarse-to-fine and inverse compositional estimation. Experimental results are conducted on a group of TUM datasets for validating the proposed approach.

Animal recognition is the need of the hour specially in a country like India. This paper provides the details of the safari system which is implemented with ease and in the best possible way. It involves the usage of efficient algorithms and technologies available to us. We have kept in mind the accuracy, cost and skill required for the implementation of the project in the course of conceptualization as well as formulation of code. We have used the YOLO V3 object detection algorithm to identify the animals. The Firebase stores the change in data as an object appears in front of the camera. This triggers the app and data are sent to the nearest found applications i.e., the safari van in use.

This paper introduces a concept of possibility that may be applied to real-world events that are viewed as having prerequisites that must be satisfied in order for the event to occur and/or constraints that may impede or prevent the event’s occurrence. The core idea is to compute the possibility of the event as a function of the probabilities that the prerequisites are satisfied and the constraints are not, and where this function computes possibility values of logical combinations of prerequisites and constraints according to the principles of fuzzy logic. Thus, this notion of possibility is a hybrid of fuzzy logic and probability theory. It has the advantage that it provides an objective procedure for determining the possibility of an event insofar as the probabilities of the prerequisites and constraints may be determined by statistical samplings. This version of possibility would appropriately be applied to problems of planning. When there are multiple plans available for achieving a goal, this theory can be used to determine which plan is most possible, i.e., easiest or most feasible to complete. It is speculated that this model of reasoning more correctly captures normal human reasoning about plans. This may be contrasted with the pure use of probability theory, which can be used to determine which plan is most likely to succeed, but is not typically employed by humans in their everyday decision making.

Line shunts are usually ignored by various power flow (PF) models in distribution system analysis, planning and optimization. However, “charging effects” from line shunts of underground/submarine power cables would cause non-negligible model errors for these commonly used PF models. In this brief, we propose a modified linear Distflow model (LinDist) with line shunts (LinDistS) to address relevant model errors. The strength of the proposed model not only lies in a straightforward structure like LinDist, but also maintaining the linearity after further considering three-phase unbalanced systems. The linearization error of voltage component is theoretically analyzed. Case studies show that compared with non-linear and linear models, LinDistS achieves the descent calculation accuracy and efficiency in large scale distribution systems.

Grasping is the most basic and important function of robots. However, the grasping performance of existing manipulators is far inferior to that of human hands. Human hands are able to evaluate the degree of incipient slip on contact surface based on tactile information during grasping process and thus regulate grasping force. As a result, humans can use the smallest possible grasping force while ensuring successful grasping, which maximizes the performance of their hands and avoids damaging the grasped object as much as possible. The existing incipient slip degree evaluation methods have certain shortcomings. So this paper proposes a novel method which can be applied to complex contact conditions where the incipient slip degree is not unidirectional and torque exists. Also, there are no restrictions on the material parameters and surface topography of the grasped object, and no need to obtain any information about it in advance. We construct a grasping force control strategy for parallel grippers based on this evaluation method, with the goal of enabling the gripper to achieve the similar grasping performance of human hands. The grasping strategy is verified in simulations and actual experiments, and the difference between the controlled force and minimum grasping force is demonstrated

We present a Boolean algebra based algorithm to extract if-then classification rules from supervised learning feedforward neural networks to solve the black-box problem of the decision process of the neural networks. This algorithm is called the BAB-G rule extraction algorithm, which stands for Boolean Algebra Based for General inputs. According to the concept of discretizing continuous hidden neuron activation values, we present the BAB-G rule extraction algorithm, which can be applied to three-layer feedforward neural networks with discrete, continuous, or mixed inputs. The antecedent parts of the if-then rules obtained from this algorithm are slanting hyperplanes. During the rule extraction procedure, redundant hidden neurons can be removed without affecting the functionality of the neural networks. Some empirical results on the data sets from the UCI repository of machine learning database are given for comparing our rule extraction algorithm and C5.0 decision tree algorithm. For these datasets, statistical hypothesis tests show that the rules obtained from our algorithm achieve the same classification accuracy as the neural networks. Moreover, our rules are better than the C5.0 decision tree both on comprehensibility and on accuracy for these datasets.

We propose a novel density-based learning technique assisted by real data to determine the appropriate Epsilon and to locate the HTC. We have also studied the correlation of anomalous BSs (ABs) in the data in the context of network planning. The algorithm, density-based network clustering (DNC), determines the ABs, identifies the HTC and the appropriate value of Epsilon by satisfying the MNOs’ requirements on the highest traffic density MB/km2 and the target deployment area in km2 . We use the k nearest neighbors (k-NN) as a benchmark to compare the appropriate value of Epsilon and other performance parameters.

A hardware neuron that can generate a broad class of activation functions is introduced. The requirements on the explicit form of activation functions within neural networks is not stringent. It is shown that the use of standard transistors can readily provide a variety of nonlinear transfer functions that can serve as activation functions. The similarities and differences of the hardware generated activation functions to commonly used mathematical activation functions are presented. A hardware neural network (HNN) based upon the neuron design is evaluated for pattern recognition. The accuracy and robustness of the HNN for the application is found to be comparable to its software counterpart even with moderate performance degradation due to perturbations to the inputs and component variability. This CMOS compatible neuron allows for HNN designs that are readily manufacturable leading to a practical, low-power platform for including HNNs into applications such as the Internet of Things (IoT) and systems-on-a- chip (SoC).

Reconfigurable intelligent surfaces (RISs) and millimeter-wave (mmWave) communications have been considered for providing wireless connectivity to mobile robots used in industrial plants and other indoor environments. However, the existing works have not sufficiently studied how the number and deployment locations of RISs should be optimized for serving a mobile robot. In this paper, we study RIS-assisted mmWave communications for a robot moving around fixed obstacles in an indoor industrial environment. For a fixed total number of reflecting elements, we formulate an optimization problem to minimize the transmission energy consumption of the access point (AP) while ensuring the robot’s received signal-to-noise ratio (SNR) above a threshold throughout its journey by jointly optimizing the number, positions and phase shifts of RISs and the beamforming vectors of the AP. To solve the formulated nonconvex optimization problem, we devise an iterative algorithm that decomposes it into two subproblems (i.e., optimizing the phase shifts of RISs and the beamforming vector of the AP, and optimizing the number and locations of RISs) and solves them alternately. Simulation results show that the proposed algorithm converges fast and can obtain the best number and locations of RISs that lead to a transmission energy consumption of the AP much lower than the benchmark schemes.

Reinforcement learning (RL) is currently used in various real-life applications. RL-based solutions have the potential to generically address problems, including the ones that are difficult to solve with heuristics and meta-heuristics and, in addition, the set of problems and issues where some intelligent or cognitive approach is required. However, reinforcement learning agents require a not straightforward design and have important design issues. RL agent design issues include the target problem modeling, state-space explosion, the training process, and agent efficiency. Research currently addresses these issues aiming to foster RL dissemination. A BAM model, in summary, allocates and shares resources with users. There are three basic BAM models and several hybrids that differ in how they allocate and share resources among users. This paper addresses the issue of an RL agent design and efficiency. The RL agent’s objective is to allocate and share resources among users. The paper investigates how a BAM model can contribute to the RL agent design and efficiency. The AllocTC-Sharing (ATCS) model is analytically described and simulated to evaluate how it mimics the RL agent operation and how the ATCS can offload computational tasks from the RL agent. The essential argument researched is whether algorithms integrated with the RL agent design and operation have the potential to facilitate agent design and optimize its execution. The ATCS analytical model and simulation presented demonstrate that a BAM model offloads agent tasks and assists the agent’s design and optimization.

Blockchain is a distributed ledger technology (DLT) to manage data in a decentralised way. During the last years, interoperability has become one of the main challenges within blockchain research as blockchains increasingly require integration between each other. Indeed, blockchains work by design in silos of information as interoperability is not a native feature. The main efforts in the field are focused on blockchains, such as Bitcoin and Ethereum. However, interoperability in DLT remains as an almost untouched area of work as they introduce additional requirements focusing on privacy and identity. Although there are some interoperability solutions for DLT, they are either high-level design proposals not providing concrete implementations or focus on interoperability issues between business applications and blockchain platforms. In this paper we propose a gateway-based platform-to-platform interoperability solution for DLT, which comprises a detailed solution design and a reference implementation. The proposal was assessed through the development of a social security case scenario and the evaluation through two interoperability frameworks. A reference implementation was built using two DLT: Hyperledger Fabric and Corda. The experimental results shows that it is possible to achieve technical interoperability between two heterogeneous DLT platforms using a gateway-based interoperability solution, relaxing decentralisation, data privacy, identity and authorisation management properties.