This paper introduces a heuristic solver based on neural networks and deep learning for the knapsack problem. The solver is inspired by mechanisms and strategies used by both algorithmic solvers and humans. The neural model of the solver is based on introducing several biases in the architecture. We introduce a stored memory of vectors that holds up items representations and their relationship to the capacity of the knapsack and a module that allows the solver to access all the previous outputs it generated. The solver is trained and tested on synthetic datasets that represent a variety of

This article proposes a new problem which is called the Stochastic Travelling Advisor Problem (STAP) in network optimization, and it is defined for an advisory group who wants to choose a subset of candidate workplaces comprising the most profitable route within the time limit of day working hours. A nonlinear binary mathematical model is formulated and a real application case study in the occupational health and safety field is presented. The problem has a stochastic nature in travelling and advising times since the deterministic models are not appropriate for such real-life problems. The

In a vehicular communications environment, the need for information sharing, entertainment, and multimedia will increase, leading to congestion of backhaul networks. The major challenge of this network is latency and resource limitations. Proactive caching can be obtained from local caches rather than from remote servers, which can avoid long delays resulting from limited backhaul capacity and resources. Therefore, proactive caching reduces latency and improves the quality of services. Determining which files should be cached in memory is a critical issue. The paper proposes various placement

In this paper, we investigate the performance of an ALOHA random access wireless network consisting of nodes with and without RF energy harvesting capability. We develop and analyze a Markov model for the system when nodes with RF energy harvesting capability are infinitely backlogged. Our results indicate that the network throughput is improved when the conventional nodes are underloaded. On the contrary, when all types of nodes have finite backlogs, we numerically demonstrate that the network throughput and delay are improved when the overall system is overloaded. We show that there exists a

In this paper we study the problem of tag identification in multi-reader RFID systems. In particular, we propose a novel solution to the reader-to-reader collisions and tag collisions in multi-reader systems, using the concept of bit tracking [1]. Towards this objective, we propose the multi-reader RFID tag identification using bit tracking (MRTI-BT) algorithm which allows concurrent tag identification, by neighboring RFID readers, as opposed to time-consuming scheduling. First, MRTI-BT identifies tags exclusive to different RFIDs, concurrently. Second, the concept of bit tracking and the

This paper develops a novel framework for sharing secret keys using the Automatic Repeat reQuest (ARQ) protocol. We first characterize the underlying information theoretic limits, under different assumptions on the channel spatial and temporal correlation function. Our analysis reveals a novel role of dumb antennas in overcoming the negative impact of spatial correlation on the achievable secrecy rates. We further develop an adaptive rate allocation policy, which achieves higher secrecy rates in temporally correlated channels, and explicit constructions for ARQ secrecy coding that enjoy low

Indoor localization has recently attended an increase in interest due to the potential for a wide range of services. In this paper, indoor high-precision positioning and motion prediction algorithms are proposed by using light fidelity (LI-FI) system with angular diversity receiver (ADR). The positioning algorithm uses to estimate the location of an object in the room. Furthermore, the prediction algorithm applies to predict the motion of that object. The simulation results show that the average root mean squares error of the positioning algorithm is about 0.6 cm, and the standard deviation