Design Guidelines for Cooperative UAV-supported Services and Applications

Internet of Things (IoT) systems have advanced greatly in the past few years, especially with the support of Machine Learning (ML) and Artificial Intelligence (AI) solutions. Numerous AI-supported IoT devices are playing a significant role in providing complex and user-specific smart city services. Given the multitude of heterogeneous wireless networks, the plethora of computer and storage architectures and paradigms, and the abundance of mobile and vehicular IoT devices, true smart city experiences are only attainable through a cooperative intelligent and secure IoT framework. This article provides an extensive study on different cooperative systems and envisions a cooperative solution that supports the integration and collaboration among both centralized and distributed systems, in which intelligent AI-supported IoT devices such as smart UAVs provide support in the data collection, processing and service provisioning process. Moreover, secure and collaborative decentralized solutions such as Blockchain are considered in the service provisioning process to enable enhanced privacy and authentication features for IoT applications. As such, user-specific complex services and applications within smart city environments will be delivered and made available in a timely, secure, and efficient manner.

Beyond Relevance Ranking: A General Graph Matching Framework for Utility-Oriented Learning to Rank

Learning to rank from logged user feedback, such as clicks or purchases, is a central component of many real-world information systems. Different from human-annotated relevance labels, the user feedback is always noisy and biased. Many existing learning to rank methods infer the underlying relevance of query–item pairs based on different assumptions of examination, and still optimize a relevance based objective. Such methods rely heavily on the correct estimation of examination, which is often difficult to achieve in practice. In this work, we propose a general framework U-rank+ for learning to rank with logged user feedback from the perspective of graph matching. We systematically analyze the biases in user feedback, including examination bias and selection bias. Then, we take both biases into consideration for unbiased utility estimation that directly based on user feedback, instead of relevance. In order to maximize the estimated utility in an efficient manner, we design two different solvers based on Sinkhorn and LambdaLoss for U-rank+ . The former is based on a standard graph matching algorithm, and the latter is inspired by the traditional method of learning to rank. Both of the algorithms have good theoretical properties to optimize the unbiased utility objective while the latter is proved to be empirically more effective and efficient in practice. Our framework U-rank+ can deal with a general utility function and can be used in a widespread of applications including web search, recommendation, and online advertising. Semi-synthetic experiments on three benchmark learning to rank datasets demonstrate the effectiveness of U-rank+ . Furthermore, our proposed framework has been deployed on two different scenarios of a mainstream App store, where the online A/B testing shows that U-rank+ achieves an average improvement of 19.2% on click-through rate and 20.8% improvement on conversion rate in recommendation scenario, and 5.12% on platform revenue in online advertising scenario over the production baselines.

Comparative study to realize an automatic speaker recognition system

In this research, we present an automatic speaker recognition system based on adaptive orthogonal transformations. To obtain the informative features with a minimum dimension from the input signals, we created an adaptive operator, which helped to identify the speaker’s voice in a fast and efficient manner. We test the efficiency and the performance of our method by comparing it with another approach, mel-frequency cepstral coefficients (MFCCs), which is widely used by researchers as their feature extraction method. The experimental results show the importance of creating the adaptive operator, which gives added value to the proposed approach. The performance of the system achieved 96.8% accuracy using Fourier transform as a compression method and 98.1% using Correlation as a compression method.

An Energy-Efficient DRAM Cache Architecture for Mobile Platforms With PCM-Based Main Memory

A long battery life is a first-class design objective for mobile devices, and main memory accounts for a major portion of total energy consumption. Moreover, the energy consumption from memory is expected to increase further with ever-growing demands for bandwidth and capacity. A hybrid memory system with both DRAM and PCM can be an attractive solution to provide additional capacity and reduce standby energy. Although providing much greater density than DRAM, PCM has longer access latency and limited write endurance to make it challenging to architect it for main memory. To address this challenge, this article introduces CAMP, a novel DRAM c ache a rchitecture for m obile platforms with P CM-based main memory. A DRAM cache in this environment is required to filter most of the writes to PCM to increase its lifetime, and deliver highest efficiency even for a relatively small-sized DRAM cache that mobile platforms can afford. To address this CAMP divides DRAM space into two regions: a page cache for exploiting spatial locality in a bandwidth-efficient manner and a dirty block buffer for maximally filtering writes. CAMP improves the performance and energy-delay-product by 29.2% and 45.2%, respectively, over the baseline PCM-oblivious DRAM cache, while increasing PCM lifetime by 2.7×. And CAMP also improves the performance and energy-delay-product by 29.3% and 41.5%, respectively, over the state-of-the-art design with dirty block buffer, while increasing PCM lifetime by 2.5×.

LEADD: Lamarckian evolutionary algorithm for de novo drug design

Given an objective function that predicts key properties of a molecule, goal-directed de novo molecular design is a useful tool to identify molecules that maximize or minimize said objective function. Nonetheless, a common drawback of these methods is that they tend to design synthetically unfeasible molecules. In this paper we describe a Lamarckian evolutionary algorithm for de novo drug design (LEADD). LEADD attempts to strike a balance between optimization power, synthetic accessibility of designed molecules and computational efficiency. To increase the likelihood of designing synthetically accessible molecules, LEADD represents molecules as graphs of molecular fragments, and limits the bonds that can be formed between them through knowledge-based pairwise atom type compatibility rules. A reference library of drug-like molecules is used to extract fragments, fragment preferences and compatibility rules. A novel set of genetic operators that enforce these rules in a computationally efficient manner is presented. To sample chemical space more efficiently we also explore a Lamarckian evolutionary mechanism that adapts the reproductive behavior of molecules. LEADD has been compared to both standard virtual screening and a comparable evolutionary algorithm using a standardized benchmark suite and was shown to be able to identify fitter molecules more efficiently. Moreover, the designed molecules are predicted to be easier to synthesize than those designed by other evolutionary algorithms. Graphical Abstract

Strategic Environmental Assessment of Land Transportation: An Application of DEA with Undesirable Output Approach

The efficiency of land transportation contributes significantly to determining a country’s economic and environmental sustainability. The examination of land transportation efficiency encompasses performance and environmental efficiency to improve system performance and citizen satisfaction. Evaluating the efficiency of land transportation is a vital process to improve operation efficiency, decrease investment costs, save energy, reduce greenhouse gas emissions, and enhance environmental protection. There are many methods for measuring transportation efficiency, but few papers have used the input and output data to evaluate the ecological efficiency of land transportation. This research focuses on evaluating the environmental efficiency for land transportation by using the data envelopment analysis (DEA) method with undesirable output to handle unwanted data. By using this, the paper aims to measure the performance of land transportation in 25 Organization for Economic Co-operation and Development (OECD) countries in the period of 2015–2019, considered as 25 decision-making units (DMUs) in the model. For identifying the ranking of DMUs, four inputs (infrastructure investment and maintenance, length of transport routes, labor force, and energy consumption) are considered. At the same time, the outputs consist of freight transport and passenger transport as desirable outputs and carbon dioxide emission (CO2) as an undesirable output. The proposed model effectively determines the environment-efficient DMUs in a very time-efficient manner. Managerial implications of the study provide further insight into the investigated measures and offer recommendations for improving the environmental efficiency of land transportation in OECD countries.

Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning

Reinforcement learning (RL) methods usually treat reward functions as black boxes. As such, these methods must extensively interact with the environment in order to discover rewards and optimal policies. In most RL applications, however, users have to program the reward function and, hence, there is the opportunity to make the reward function visible – to show the reward function’s code to the RL agent so it can exploit the function’s internal structure to learn optimal policies in a more sample efficient manner. In this paper, we show how to accomplish this idea in two steps. First, we propose reward machines, a type of finite state machine that supports the specification of reward functions while exposing reward function structure. We then describe different methodologies to exploit this structure to support learning, including automated reward shaping, task decomposition, and counterfactual reasoning with off-policy learning. Experiments on tabular and continuous domains, across different tasks and RL agents, show the benefits of exploiting reward structure with respect to sample efficiency and the quality of resultant policies. Finally, by virtue of being a form of finite state machine, reward machines have the expressive power of a regular language and as such support loops, sequences and conditionals, as well as the expression of temporally extended properties typical of linear temporal logic and non-Markovian reward specification.

Unsupervised Character Recognition with Graphene Memristive Synapses

Memristive devices being applied in neuromorphic computing are envisioned to significantly improve the power consumption and speed of future computing platforms. The materials used to fabricate such devices will play a significant role in their viability. Graphene is a promising material, with superb electrical properties and the ability to be produced sustainably. In this paper, we demonstrate that a fabricated graphene-pentacene memristive device can be used as synapses within Spiking Neural Networks (SNNs) to realise Spike Timing Dependent Plasticity (STDP) for unsupervised learning in an efficient manner. Specifically, we verify operation of two SNN architectures tasked for single digit (0-9) classification: (i) a simple single-layer network, where inputs are presented in 5x5 pixel resolution, and (ii) a larger network capable of classifying the Modified National Institute of Standards and Technology (MNIST) dataset, where inputs are presented in 28x28 pixel resolution. Final results demonstrate that for 100 output neurons, after one training epoch, a test set accuracy of up to 86% can be achieved, which is higher than prior art using the same number of output neurons. We attribute this performance improvement to homeostatic plasticity dynamics that we used to alter the threshold of neurons during training. Our work presents the first investigation of the use of green-fabricated graphene memristive devices to perform a complex pattern classification task. This can pave the way for future research in using graphene devices with memristive capabilities in neuromorphic computing architectures. In favour of reproducible research, we make our code and data publicly available https://anonymous.4open.science/r/c69ab2e2-b672-4ebd-b266-987ee1fd65e7.

Decision-Making Approach Based on Generalized Aggregation Operators with Complex Single-Valued Neutrosophic Hesitant Fuzzy Set Information

A strategic decision-making technique can help the decision maker to accomplish and analyze the information in an efficient manner. However, in our real life, an uncertainty will play a dominant role during the information collection phase. To handle such uncertainties in the data, we present a decision-making algorithm under the single-valued neutrosophic (SVN) environment. The SVN is a powerful way to deal the information in terms of three degrees, namely, “truth,” “falsity,” and “indeterminacy,” which all are considered independent. The main objective of this study is divided into three folds. In the first fold, we state the novel concept of complex SVN hesitant fuzzy (CSVNHF) set by incorporating the features of the SVN, complex numbers, and the hesitant element. The various fundamental and algebraic laws of the proposed CSVNHF set are described in details. The second fold is to state the various aggregation operators to obtain the aggregated values of the considered CSVNHF information. For this, we stated several generalized averaging operators, namely, CSVNHF generalized weighted averaging, ordered weighted average, and hybrid average. The various properties of these operators are also stated. Finally, we discuss a multiattribute decision-making (MADM) algorithm based on the proposed operators to address the problems under the CSVNHF environment. A numerical example is given to illustrate the work and compare the results with the existing studies’ results. Also, the sensitivity analysis and advantages of the stated algorithm are given in the work to verify and strengthen the study.

On a reduced-order model-based optimization of rotor electro-thermal anti-icing systems

Purpose Responsible for lift generation, the helicopter rotor is an essential component to protect against ice accretion. As rotorcraft present a smaller wing cross-section and a lower available onboard power compared to aircraft, electro-thermal heating pads are favored as they conform to the blades’ slender profile and limited volume. Their optimization is carried out here taking into account, for the first time, the highly three-dimensional (3D) nature of the flow and ice accretion, in contrast to the current state-of-the-art that is limited to two-dimensional (2D) airfoils. Design/methodology/approach Conjugate heat transfer simulation results are provided by the truly 3D finite element Navier–Stokes analysis package-ICE code, embedded in a proprietary rotorcraft simulation toolkit, with reduced-order modeling providing a time-efficient evaluation of the objective and constraint functions at every iteration. The proposed methodology optimizes heating pads extent and power usage and is versatile enough to address in a computationally efficient manner a wide variety of optimization formulations. Findings Low-error reduced-order modeling strategies are introduced to make the tackling of complex 3D geometries feasible in todays’ computers, with the developed framework applied to four problem formulations, demonstrating marked reductions to power consumption along with improved aerodynamics. Originality/value The present paper proposes a 3D framework for the optimization of electro-thermal rotorcraft ice protection systems, in hover and forward flight. The current state-of-the-art is limited to 2D airfoils.