Forecasting stock prices is complex and challenging. Uncovering correlations among stocks has proven to enhance stock price forecasting. However, existing correlation discovery methods, such as concept-based methods, are slow, inaccurate, and limited by their reliance on predefined concepts and manual analysis. In this paper, we propose COGRASP, a novel approach for stock price forecasting that constructs stock co-occurrence graphs automatically by analyzing rapidly updated sources such as reports, newspapers, and social media. Besides, we aggregate forecasts across multiple timescales (i.e., long-, medium-, and short-term) to capture multi-timescale trends fluctuations, thereby enhancing price forecasting accuracy. In experiments with real-world open-source stock market data, COGRASP outperforms state-of-the-art methods.

This article considers maximizing coverage quality in Internet of Things (IoT) networks using unmanned aerial vehicles (UAVs) to augment the link from solar-powered devices to a sink/gateway. Specifically, it aims to jointly optimize the assignment of UAVs to hovering points or a charging station, time in which devices monitor targets, and the amount of data transmitted by devices. These quantities are optimized over a given planning horizon using a mixed integer linear program (MILP). Further, this article presents a heuristic method named decoupled energy aware algorithm (DEAA) to optimize the said quantities. In addition, it outlines a model predictive control (MPC) approach that only requires current and historical energy arrivals information of devices. The simulation results showed that DEAA and MPC achieved 80.58% and 61.19% of the optimal results computed by MILP.

This article studies a coverage problem in Internet of things (IoT) networks using unmanned aerial vehicles (UAVs) supported by solar-powered charging platforms. The problem at hand is to determine an assignment of UAVs to either a charging station or a monitoring point over a planning horizon. A key constraint is$K$-coverage, where given a set of$\mathcal {M}$points,$K$of these points must be monitored by a UAV in each time slot. In this respect, the paper aims to design UAVs assignment solutions that yield the longest$K$-coverage lifetime. We formulate a novel mixed integer linear program (MILP) to jointly optimize UAVs assignments over a given planning horizon. The problem is challenging as the energy level of charging platforms and UAVs are coupled across time slots. Moreover, the formulated MILP requires non-causal energy arrivals information at charging platforms. To this end, we outline a model predictive control (MPC) and a Monte Carlo tree search (MCTS) based solution that use non-causal energy arrivals information. The simulation results show that MPC and MCTS achieve approximately 81.04% and 67.07% of the optimal results computed by MILP.

This article studies targets coverage in an energy harvesting (EH) Internet of Things (IoT) network. Specifically, it addresses the problem of activating subsets of EH sensor nodes to monitor targets, such as valuable assets or the ingresses and egresses of a building. A key requirement, so called complete targets coverage, is that all targets must be monitored by at least one sensor node at all times. To meet this requirement, we need to derive set covers, where each set cover is comprised of one or more sensor nodes that are activated simultaneously in each time slot. To this end, we show for the first time how the belief propagation message-passing framework can be used to derive these set covers. Advantageously, our approach does not require future energy arrivals information at devices. The results show that our message-passing approach is within 90% of the optimal coverage lifetime.