In-hand manipulation is a fundamental ability for multi-fingered robotic hands that interact with their environments. Owing to the high dimensionality of robotic hands and intermittent contact dynamics, effectively programming a robotic hand for in-hand manipulations is still a challenging problem. To address this challenge, this work employs deep reinforcement learning (DRL) algorithm to learn in-hand manipulations for multi-fingered robotic hands. A reward-shaping method is proposed to assist the learning of in-hand manipulation. The synergy of robotic hand postures is analysed to build a low-dimensional hand posture space. Two additional rewards are designed based on both the analysis of hand synergies and its learning history. The two additional rewards cooperating with an extrinsic reward are used to assist the in-hand manipulation learning. Three value functions are trained jointly with respect to their reward functions. Then they cooperate to optimise a control policy for in-hand manipulation. The reward shaping not only improves the exploration efficiency of the DRL algorithm but also provides a way to incorporate domain knowledge. The performance of the proposed learning method is evaluated with object rotation tasks. Experimental results demonstrated that the proposed learning method enables multi-fingered robotic hands to learn in-hand manipulation effectively.

The main purpose of this study is to bring in a new extension of multi-objective optimisation on the basis of ratio analysis plus full multiplicative form (MULTIMOORA) in trapezoidal neutrosophic number (TrNN) environment. MULTIMOORA strategy provides high efficiency and effectiveness in problem-solving. The new MULTIMOORA strategy consists of three components. The components are ratio system approach, reference point approach, and full multiplicative form. To develop the proposed strategy, the authors find out three ranking order of alternatives using the three components. The final ranking order of the alternatives is based on dominance property. The study is original as it first develops the MULTIMOORA strategy in the TrNN environment, which they call TrNN- MULTIMOORA. They solve a realistic banking problem involving multi-attribute group decision making in the TrNN environment to reflect the applicability and proficiency of the developed strategy. They also present a comparison between the proposed strategy and the existing tomada de decisao interativa e multicritévio and VlseKriterijumska Optimizcija I Kaompromisno Resenje strategies.

Group decision making typically requires eliciting and coordinating the preferences of group members. In this study, the authors develop an overall framework of group consensus in context of hesitant fuzzy linguistic preference relations (HFLPRs). A new notion of distance measure between two HFLPRs is defined, based on which a consensual framework consists of two mechanisms, the automatic consensus reaching and the interactive consensus reaching is presented. Accordingly, they, respectively, design two algorithms to implement these mechanisms. Finally, a group decision problem of green supplier selection is provided to exemplify and verify both of the proposed methods, and a comparative analysis with some related approaches is performed.

Compared with conventional image sensors, event cameras have been attracting attention thanks to their potential in environments under fast motion and high dynamic range (HDR). To tackle the lost-track issue due to fast illumination changes under HDR scene such as tunnels, an object tracking framework has been presented based on event count images from an event camera. The framework contains an offline-trained detector and an online-trained tracker which complement each other: The detector benefits from pre-labelled data during training, but may have false or missing detections; the tracker provides persistent results for each initialised object but may suffer from drifting issues or even failures. Besides, process and measurement equations have been modelled, and a Kalman fusion scheme has been proposed to incorporate measurements from the detector and the tracker. Self-initialisation and track maintenance in the fusion scheme ensure autonomous real-time tracking without user intervene. With self-collected event data in urban driving scenarios, experiments have been conducted to show the performance of the proposed framework and the fusion scheme.

In recent years, hyper-complex deep networks (such as complex-valued and quaternion-valued neural networks – QVNNs) have received a renewed interest in the literature. They find applications in multiple fields, ranging from image reconstruction to 3D audio processing. Similar to their real-valued counterparts, quaternion neural networks require custom regularisation strategies to avoid overfitting. In addition, for many real-world applications and embedded implementations, there is the need of designing sufficiently compact networks, with few weights and neurons. However, the problem of regularising and/or sparsifying QVNNs has not been properly addressed in the literature as of now. In this study, the authors show how to address both problems by designing targeted regularisation strategies, which can minimise the number of connections and neurons of the network during training. To this end, they investigate two extensions of and structured regularisations to the quaternion domain. In the authors’ experimental evaluation, they show that these tailored strategies significantly outperform classical (real-valued) regularisation approaches, resulting in small networks especially suitable for low-power and real-time applications.

The unmanned warehouse dispatching system of the ‘goods to people’ model uses a structure mainly based on a handling robot, which saves considerable manpower and improves the efficiency of the warehouse picking operation. However, the optimal performance of the scheduling system algorithm has high requirements. This study uses a deep Q-network (DQN) algorithm in a deep reinforcement learning algorithm, which combines the Q-learning algorithm, an empirical playback mechanism, and the volume-based technology of productive neural networks to generate target Q-values to solve the problem of multi-robot path planning. The aim of the Q-learning algorithm in deep reinforcement learning is to address two shortcomings of the robot path-planning problem: slow convergence and excessive randomness. Preceding the start of the algorithmic process, prior knowledge and prior rules are used to improve the DQN algorithm. Simulation results show that the improved DQN algorithm converges faster than the classic deep reinforcement learning algorithm and can more quickly learn the solutions to path-planning problems. This improves the efficiency of multi-robot path planning.

Obfuscation is rampant in both benign and malicious JavaScript (JS) codes. It generates an obscure and undetectable code that hinders comprehension and analysis. Therefore, accurate detection of JS codes that masquerade as innocuous scripts is vital. The existing deobfuscation methods assume that a specific tool can recover an original JS code entirely. For a multi-layer obfuscation, general tools realize a formatted JS code, but some sections remain encoded. For the detection of such codes, this study performs Deobfuscation, Unpacking, and Decoding (DUD-preprocessing) by function redefinition using a Virtual Machine (VM), a JS code editor, and a python int_to_str() function to facilitate feature learning by the FastText model. The learned feature vectors are passed to a classifier model that judges the maliciousness of a JS code. In performance evaluation, the authors use the Hynek Petrak's dataset for obfuscated malicious JS codes and the SRILAB dataset and the Majestic Million service top 10,000 websites for obfuscated benign JS codes. They then compare the performance to other models on the detection of DUD-preprocessed obfuscated malicious JS codes. Their experimental results show that the proposed approach enhances feature learning and provides improved accuracy in the detection of obfuscated malicious JS codes.

With the development of network services and location-based systems, many mobile applications begin to use users’ geographical location to provide better services. In terms of social networks, geographical location is actively shared by users. In some applications with recommendation services, before the geographical location recommendation is provided, the authors have to obtain user's permission. This kind of social network integrated with geographical location information is called location-based social networks (abbreviate for LBSNs). In the LBSN, each user has location information when he or she checked in hotels or feature spots. Based on this information, they can identify user's trajectory of movement behaviour and activity patterns. In general, if there is friendship between two users, their trajectories in reality are likely to be similar. In this study, according to user's geographical location information over a period of time, they explore whether there exists friendly relationship between two users based on trajectory similarity and the structure theory of graphs. In particular, they propose a new factor function and a factor graph model based on user's geographical location to predict the friendship between two users in the real LBSN.

This study proposed the concepts of a multi-valued interval neutrosophic linguistic soft set (MVINLSS) by integrating the concepts of multi-valued interval neutrosophic soft set and linguistic set. MVINLSS is presented as it can deal with ambiguous and uncertain information in decision making which is characterised by linguistic membership. This proposed set amalgamates quantitative assessment with the qualitative assessment which can solve complex problems with ambiguity, uncertainty, and inconsistency. It can be an effective tool to describe the real decision-makers’ opinions and reflect their hesitancy. Then, the authors propose the basic operational rules of MVINLSS. Moreover, they define a multi-valued interval neutrosophic linguistic soft weighted arithmetic averaging operator. This work proposed a multi-criteria decision-making (MCDM) method which considers different priority levels of criteria and the criteria values take the form of multi-valued interval neutrosophic linguistic soft numbers. Finally, the proposed MCDM method is applied to the knowledge management case, considering 11 criteria.

This study intends to present an innovative study for ranking the alternatives in multiple-criteria decision analysis (MCDA) problems under the interval-valued neutrosophic soft set (IVNSS) environment. In this study, to illustrate the notion of objective and subjective weight, the prospect decision theory (PDT) performs an imperative role in determining decision-making problems. PDT predicts human behaviour in terms of gains and losses and considers the expected utility relation to a reference point rather than complete outcomes. In the analysis of merged criteria weight and the prospect decision-making matrix, the authors get a new dimension level for ranking the array of alternatives. This manuscript provides an improved score function (SF) to convert the interval-valued membership grades of truth, indeterminacy and falsity into a mathematical and computational value. The advantage of this method is that it merges the objective and subjective weight during the proposed method. They propose an algorithm based on the SF to determine MCDA problems with IVNSSs. They illustrate a case study and provide various comparative analyses to show its significance over existing studies.

The medical health systems empowered by wireless body area networks (WBANs) are becoming a reliable technology with unmatched facilities for personalised health monitoring and managing real-time health issues. A WBAN is primarily composed of a miniature, and smart devices called sensors that are worn in, on, or around the human body. In recent years, research has been mainly centred towards the reduction of the energy consumption and stability of the network. The selection of the relay node is one of the foremost issues for balancing the energy consumption in WBAN. To overcome this issue, the authors propose a hybrid analytic hierarchy process–neutrosophic method for making the decision of the relay node selection, in which the analytic hierarchy process (AHP) technique calculates the weights for different criteria and forwards them to the neutrosophic technique which finds out the best alternative solution or choice which is closest to the ideal solution. A detailed analysis is carried out on multi-criteria decision-making techniques by comparing the proposed AHP–neutrosophic and AHP techniques taking into account various criteria and alternatives. The experimental outcomes of this research indicate a significant reduction in terms of energy consumption and enhanced overall network-stability.

Federated learning aims to collaboratively train a machine learning model with possibly geo-distributed workers, which is inherently communication constrained. To achieve communication efficiency, the conventional federated learning algorithms allow the worker to decrease the communication frequency by training the model locally for multiple times. Conventional federated learning architecture, inherited from the parameter server design, relies on highly centralised topologies and large nodes-to-server bandwidths, and convergence property relies on the stochastic gradient descent training in local, which usually causes the large end-to-end training latency in real-world federated learning scenarios. Thus, in this study, the authors propose the adaptive partial gradient aggregation method, a gradient partial level decentralised federated learning, to tackle this problem. In FedPGA, they propose a partial gradient exchange mechanism that makes full use of node-to-node bandwidth for speeding up the communication time. Besides, an adaptive model updating method further reduces the convergence rate by adaptive increasing the step size of the stable direction of gradient descent. The experimental results on various datasets demonstrate that the training time is reduced up to compared to baselines without accuracy degrade.