Various protocols have been proposed in the area of wireless sensor networks in order to achieve network-wide time synchronization. A large number of proposed protocols in the literature employ a message passing mechanism to make sensor node clocks tick in unison. In this paper, we first classify Message Passing based Time Synchronization (MPTS) protocols and then analyze them based on different metrics. The classification is based on the following three criteria: structure formation of the network affected by the synchronization protocol, frequency of synchronization process (synchronization interval), and synchronization message overhead. Proposed protocols are analyzed and evaluated from different perspectives based on available data. A comparison table of the reviewed protocols is presented according to the evaluation metrics. Finally, some potential methods will be proposed to improve the synchronization process.

The emergence of Wireless Sensor Networks (WSNs) applications such as localizing, tracking, surveillance, speedometers, and so on, synchronizing sensor motes' clocks is essential in WSNs. Thus, many time synchronization protocols are proposed in recent decade to get network wide synchronization. Each of those protocols strives to get a good precision in different ways. This paper aims to review some of the main protocols and classify them based on their scope, topology structure, and dynamicity then analyzes them based on three criteria of accuracy, robustness, and computation load. At the end a comparison is done for the reviewed protocols.

Since wireless sensor nodes are battery powered, the emphasis was on reducing the energy consumption of the sensor nodes. However, with the increase in real-time traffic requirements in wireless sensor nodes, network performance metrics are increasingly important. Nonetheless, most existing network performance studies were done via simulation, with few experimental studies performed on testbeds using ad hoc methodologies. This paper proposes a structured experimental methodology for evaluating the delay, throughput, and packet loss performance of wireless sensor networks, while addressing practical issues related to the use of an experimental approach. A global clock synchronization technique, in addition to insertion of timestamps in the network packets was proposed for more accurate measurement of the network delay. Several different physical topologies such as single cluster, chain, and cluster tree topologies were defined as standard test topologies. The EMLMAC protocol was used to demonstrate the viability of the proposed structured experimental methodology. Based on the proposed experimental approach, the measured throughput for EMLMAC for the single cluster two-hop and three-hop chain topologies differed by 1.02%, 6.75% and 13.91% respectively from the simulation results. This indicates that an experimental approach is essential for verifying the actual performance of a wireless sensor network.

The rapid digital transformation of the retail industry has generated large-scale, high-frequency data; yet many retailers still rely on siloed systems that decouple demand forecasting from operational inventory management. This separation often leads to structural inventory imbalances, including simultaneous stockouts and overstock situations. To address this, we propose a unified, data-driven framework that integrates advanced sales forecasting with a diagnostic inventory health system, bridging predictive analytics with diagnostic decision support for proactive inventory-risk assessment. Utilizing a real-world dataset of approximately 500,000 product–store–day records from a Chinese e-commerce company, we evaluate six forecasting models across statistical, machine learning, and Deep Learning (DL) architectures. Results indicate that DL models achieved the lowest RMSE and MAPE values, whereas RF and XGBoost produced more favorable MASE values. Forecasting performance varied by evaluation criterion, with no model consistently outperforming all others. However, LSTM achieved the lowest testing RMSE (0.3996) and MAPE (21.63%). Building upon these predictive outputs, we introduce an inventory health diagnosis framework based on empirically calibrated thresholds for the Inventory Turnover Ratio (ITR) and Excess Inventory Rate (EIR), with the thresholds calibrated on the training and calibration period and evaluated on an independent temporal validation period. Application of this framework to the independent diagnostic validation period shows that 61.1% of SKU–store observations were classified as Potential Risk or Critical, including 16.3% classified as Critical, indicating inventory misalignment requiring managerial attention. By providing an interpretable and scalable system for proactive risk detection, this research provides a practical framework to support retailers in transitioning from demand forecasting to inventory diagnostic decision support.