Trend-Adjusted Time Series Models with an Application to Gold Price Forecasting

Time series data play a critical role in various fields, including finance, healthcare, marketing, and engineering. A wide range of techniques (from classical statistical models to neural network-based approaches such as Long Short-Term Memory (LSTM)) have been employed to address time series forecasting challenges. In this paper, we reframe time series forecasting as a two-part task: (1) predicting the trend (directional movement) of the time series at the next time step, and (2) forecasting the quantitative value at the next time step. The trend can be predicted using a binary classifier, while quantitative values can be forecasted using models such as LSTM and Bidirectional Long Short-Term Memory (Bi-LSTM). Building on this reframing, we propose the Trend-Adjusted Time Series (TATS) model, which adjusts the forecasted values based on the predicted trend provided by the binary classifier. We validate the proposed approach through both theoretical analysis and empirical evaluation. The TATS model is applied to a volatile financial time series (the daily gold price) with the objective of forecasting the next days price. Experimental results demonstrate that TATS consistently outperforms standard LSTM and Bi-LSTM models by achieving significantly lower forecasting error. In addition, our results indicate that commonly used metrics such as MSE and MAE are insufficient for fully assessing time series model performance. Therefore, we also incorporate trend detection accuracy, which measures how effectively a model captures trends in a time series.

Adaptive grid-based decomposition for UAV-based coverage path planning in maritime search and rescue

Unmanned aerial vehicles (UAVs) are increasingly utilized in search and rescue (SAR) operations to enhance efficiency by enabling rescue teams to cover large search areas in a shorter time. Reducing coverage time directly increases the likelihood of finding the target quickly, thereby improving the chances of a successful SAR operation. In this context, UAVs require path planning to determine the optimal flight path that fully covers the search area in the least amount of time. A common approach involves decomposing the search area into a grid, where the UAV must visit all cells to achieve complete coverage. In this paper, we propose an Adaptive Grid-based Decomposition (AGD) algorithm that efficiently partitions polygonal search areas into grids with fewer cells. Additionally, we utilize a Mixed-Integer Programming (MIP) model, compatible with the AGD algorithm, to determine a flight path that ensures complete cell coverage while minimizing overall coverage time. Experimental results highlight the efficiency of the AGD algorithm in reducing coverage time (by up to 20%) across various scenarios.

An exact coverage path planning algorithm for UAV-based search and rescue operations

Unmanned aerial vehicles (UAVs) are increasingly utilized in global search and rescue efforts, enhancing operational efficiency. In these missions, a coordinated swarm of UAVs is deployed to efficiently cover expansive areas by capturing and analyzing aerial imagery and footage. Rapid coverage is paramount in these scenarios, as swift discovery can mean the difference between life and death for those in peril. This paper focuses on optimizing flight path planning for multiple UAVs in windy conditions to efficiently cover rectangular search areas in minimal time. We address this challenge by dividing the search area into a grid network and formulating it as a mixed-integer program (MIP). Our research introduces a precise lower bound for the objective function and an exact algorithm capable of finding either the optimal solution or a near-optimal solution with a constant absolute gap to optimality. Notably, as the problem complexity increases, our solution exhibits a diminishing relative optimality gap while maintaining negligible computational costs compared to the MIP approach.