Window Size Research Articles

Enhanced least-cost path analysis for infrastructure planning: achieving a comprehensive search space with civil engineering structures

Least-cost path analysis (LCPA) is a widely recognized and practical algorithm for determining cost-effective paths between two points. This research presents an innovative LCPA designed to identify paths for infrastructure projects with slope threshold conditions (an interval of acceptable slopes). The algorithm incorporates potential DEM modifications through civil engineering structures, including cut-and-fill, tunnelling, and bridging, to include paths that otherwise exceed the maximum slope threshold. We conducted experiments of the developed LCPA on an area with complex topography, the Zagros Mountains in Iran, using three slope thresholds (5°, 8°, and 10°), with and without tunnelling and bridging. The results demonstrated the algorithm’s ability to identify paths with lower cost across all slope thresholds, with the inclusion of tunnelling and bridging leading to further cost reductions. A comparison with an LCPA based on an extended moving window approach highlighted the identification of paths with lower costs, even in the absence of tunnelling and bridging, across all slope thresholds and window sizes. The implementation of the developed LCPA in real-world scenarios is expected to significantly enhance transportation planning and infrastructure design processes.

Accurate and fast congestion feedback in MEC-enabled RDMA datacenters

Mobile edge computing (MEC) is a novel computing paradigm that pushes computation and storage resources to the edge of the network. The interconnection of edge servers forms small-scale data centers, enabling MEC to provide low-latency network services for mobile users. Nowadays, Remote Direct Memory Access (RDMA) has been widely deployed in such data centers to reduce CPU overhead and network latency. Plenty of congestion control mechanisms have been proposed for RDMA data centers, aiming to provide low-latency data delivery and high throughput network services. However, our fine-grained experimental analysis reveals that existing congestion control mechanisms still have performance limitations due to inappropriate congestion notifications and the long congestion feedback cycle. In this paper, we propose Mercury, which is an accurate and fast congestion feedback mechanism. Mercury comprises two key components: (1) the state-driven congestion detection and (2) the window-based congestion notification. Specifically, the state-driven congestion detection monitors the queue length and the number of packets received at the switch egress port when the PFC is triggered. It determines the states of egress ports and identifies flows that really contribute to congestion. Then, window-based congestion notification calculates the window sizes for congested flows and rapidly returns Congestion Notification Packets (CNPs) with the window information to the sender. It facilitates the rate adjustment of congested flows. Mercury is compatible with existing RDMA CC mechanisms and can be easily implemented in switches. We employ real-world data sets and conduct both micro-benchmark and large-scale simulations to evaluate the performance of Mercury. The results indicate that, thanks to the accurate and fast congestion feedback, Mercury achieves a reduction in the 99th tail flow completion time by up to 45.1%, 41.8%, 38.7%, 30.9%, and 37.9% compared with Timely, DCQCN, DCQCN+TCD, PACC, and HPCC, respectively.

Smarter Window Selection for Smarter Energy Consumption: The Case of the United Arab Emirates

The energy consumption levels of buildings in the United Arab Emirates (UAE) are among the highest in the world. One of the main reasons for this energy consumption is the need to cool buildings due to the hot climate of the UAE. As a large part of the heat accumulated inside buildings comes from windows, in this study, the effects of window size and direction in a typical building in the UAE on energy consumption and thermal performance are investigated through numerical modeling. The modeling process includes thermal conductivity, thermal convection, and solar radiation simulation. The energy performance of any building at any location can be obtained based on local weather data and the computational thermal characteristics of the building elements, such as its walls, roofs, windows, and doors. The study covered all different seasons of the year and different orientations for the windows, allowing the daily and yearly energy consumption associated with the windows to be obtained. Furthermore, the energy consumption was obtained for solar radiation and heat gain separately for both single- and double-glazed windows. It was found that north-facing windows consume significantly less annual energy (36% less), when compared with windows facing in the other three directions. Furthermore, the east- and west-facing windows consumed about 41% and 35% more daily cooling energy in August, when compared to north- and south-facing windows, respectively. The use of a window with a height equal to that of the wall can cause a clear greenhouse effect; hence, it is recommended to limit the window’s height to two-thirds of the wall height, which can save about one-third of the associated yearly cooling energy. This study should be considered as a general guideline, as the thermal performance of any specific building will be affected by its own thermal characteristics.

Assessment of Communication Resource Allocation by the Transmission Control Protocol for the Target Virtual Connection under Competitive Conditions

The mathematical framework presented in this article focuses on the controlled-transmission protocol’s asynchronous process of bandwidth allocation for the target virtual connection implemented under competition for communication resources. The studied process is formalized as a two-dimensional discrete Markovian chain, taking into account the distributions of queue lengths of TCP data fragments from competing client nodes. Such a chain describes the dynamics of filling the stack of transmitted but unacknowledged data fragments of the investigated end device. Distributions of the chain states were found for various ratios of the target virtual-connection bandwidth, transmission-protocol parameters, and communication-channel characteristics. Analytical dependencies for computing the performance of the target virtual connection for different operating modes were obtained. The results of experiments conducted based on the obtained analytical constructions showed that the performance of the virtual connection with a selective repeat mode is mainly determined by the data-loss intensity, the queue size distribution in transit nodes, and the ratio between the protocol window size and the route length.

Narrowband Internet of Things via Low Earth Orbit Satellite Networks: An Efficient Coverage Enhancement Mechanism Based on Stochastic Geometry Approach.

With the development of IoT technology and 5G massive machine-type communication, the 3GPP standardization body considered as viable the integration of Narrowband Internet of Things (NB-IoT) in low Earth orbit (LEO) satellite-based architectures. However, the presence of the LEO satellite channel comes up with new challenges for the NB-IoT random access procedures and coverage enhancement mechanism. In this paper, an Adaptive Coverage Enhancement (ACE) method is proposed to meet the requirement of random access parameter configurations for diverse applications. Based on stochastic geometry theory, an expression of random access channel (RACH) success probability is derived for LEO satellite-based NB-IoT networks. On the basis of a power consumption model of the NB-IoT terminal, a multi-objective optimization problem is formulated to trade-off RACH success probability and power consumption. To solve this multi-objective optimization problem, we employ the Non-dominated Sorting Genetic Algorithms-II (NSGA-II) method to obtain the Pareto-front solution set. According to different application requirements, we also design a random access parameter configuration method to minimize the power consumption under the constraints of RACH success probability requirements. Simulation results show that the maximum number of repetitions and back-off window size have a great influence on the system performance and their value ranges should be set within [4, 18] and [0, 2048]. The power consumption of coverage enhancement with ACE is about 58% lower than that of the 3GPP proposed model. All this research together provides good reference for the scale deployment of NB-IoT in LEO satellite networks.

A New Technique for Urban and Rural Settlement Boundary Extraction Based on Spectral–Topographic–Radar Polarization Features and Its Application in Xining, China

Highly accurate data on urban and rural settlement (URS) are essential for urban planning and decision-making in response to climate and environmental changes. This study developed an optimal random forest classification model for URSs based on spectral–topographic–radar polarization features using Landsat 8, NASA DEM, and Sentinel-1 SAR as the remote-sensing data sources. An optimal urban and rural settlement boundary (URSB) extraction technique based on morphological and pixel-level statistical methods was established to link discontinuous URSs and improve the accuracy of URSB extraction. An optimal random forest classification model for URSs was developed, as well as a technique to optimize URSB, using the Google Earth Engine (GEE) platform. The URSB of Xining, China, in 2020 was then extracted at a spatial resolution of 30 m, achieving an overall accuracy and Kappa coefficient of 96.21% and 0.92, respectively. Compared to using a single spectral feature, these corresponding metrics improved by 16.21% and 0.35, respectively. This research also demonstrated that the newly constructed Blue Roof Index (BRI), with enhanced blue roof features, is highly indicative of URSs and that the URSB was best extracted when the window size of the structural elements was 13 × 13. These results can be used to provide technical support for obtaining highly accurate information on URSs.

Satellite rainfall bias correction incorporating effects on simulated crop water requirements

ABSTRACT Satellite rainfall estimates (SRE) offer spatial-temporal rainfall representations in regions with limited ground-based gauge rainfall measurements. However, differences exist between SRE and gauge measured rainfall, which needs assessment and reduction. This study presents a method to correct errors in SRE to make their use in agro-hydrological applications and models meaningful. The main scientific objective is the determination of effective window sizes for SRE bias correction. To conclude on effective window sizes, the crop water requirement satisfaction index (WRSI) for gauged rainfall, uncorrected SRE and bias corrected SRE were estimated and propagation effects of SRE errors on respective WRSI estimates were assessed. WRSI indicates how much of the crop water needs are satisfied by rainfall. The Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS) SRE was bias corrected using gauged rainfall data from 20 stations in the Lake Victoria basin of Kenya from 2012 to 2018. The results show that the error in WRSI can serve to determine effective window sizes for SRE bias correction rather than using SRE bias error itself. This proposed correction method resulted in improved estimates of WRSI.

Identifying soil groups and selecting a high-accuracy classification method based on multi-textural features with optimal window sizes using remote sensing images

Determining the spatial distribution of soil groups accurately is crucial for managing soil resources. However, limitations persist in the mapping of soil groups using multi-textural features derived from remote sensing images. Identification of the optimal window size for multi-textural feature extraction and the most effective classification method for soil group recognition using remote sensing multi-textural features remains unresolved. In this study, we investigated soil groups in a representative area of the Jiaodong Peninsula. We extracted the mean and entropy texture parameters for various window sizes (3 × 3 to 25 × 25 in odd increments) from Landsat 8 images to determine the optimal sizes for multi-textural feature extraction. The efficacy of identifying soil groups via textural features was analyzed using maximum likelihood classification (MLC), support vector machine (SVM), artificial neural network (ANN), and random forest (RF) methods to ascertain the most suitable classification approach. The results indicate that the optimal window sizes were 19 × 19 for the mean parameter and 23 × 23 for the entropy parameter. The SVM method outperformed the MLC, ANN, and RF methods in terms of the classification accuracy. Notably, the SVM classification method reached a peak accuracy of 71.61% when combining multi-textural features with the optimal windows. This demonstrates the feasibility of different soil groups using multi-textural information from remote sensing images. These findings have notable implications in guiding digital soil mapping using multi-textural features.

Decentralized Scheduling for Data-Parallel Tasks in the Cloud

For latency-sensitive data processing applications in the cloud, concurrent data-parallel tasks need to be scheduled and processed quickly. A data-parallel task usually consists of a set of sub-tasks, generating a set of flows that are collectively referred to as coflows . The state-of-the-art schedulers collect coflow information in the cloud to optimize coflow-level performance. However, most of the coflows, classified as small coflows because they consist of only short flows, have been largely overlooked. This paper presents OptaX , a decentralized network scheduling service that collaboratively schedules data-parallel tasks’ small coflows. OptaX adopts a cross-layer, COTS (commercial off-the-shelf) switch-compatible design that leverages the sendbuffer information in the kernel to adaptively optimize flow scheduling in the network. Specifically, OptaX (i) monitors the system calls (syscalls) in the hosts to obtain their sendbuffer footprints, and (ii) recognizes small coflows and assigns high priorities to their flows. OptaX transfers these flows in a FIFO manner by adjusting TCP’s two attributes: window size and round-trip time. We have implemented OptaX as a Linux kernel module. The evaluation shows that OptaX is at least 2.2 × faster than fair sharing and 1.2 × faster than only assigning small coflows with the highest priority. We further apply OptaX to improve the small I/O performance of Ursa , a distributed block storage system that provides virtual disks where small I/O is dominant. URSA with OptaX achieves significant improvement compared to the original URSA for small I/O latency.

Expanding Sparse Radar Depth Based on Joint Bilateral Filter for Radar-Guided Monocular Depth Estimation.

Radar data can provide additional depth information for monocular depth estimation. It provides a cost-effective solution and is robust in various weather conditions, particularly when compared with lidar. Given the sparse and limited vertical field of view of radar signals, existing methods employ either a vertical extension of radar points or the training of a preprocessing neural network to extend sparse radar points under lidar supervision. In this work, we present a novel radar expansion technique inspired by the joint bilateral filter, tailored for radar-guided monocular depth estimation. Our approach is motivated by the synergy of spatial and range kernels within the joint bilateral filter. Unlike traditional methods that assign a weighted average of nearby pixels to the current pixel, we expand sparse radar points by calculating a confidence score based on the values of spatial and range kernels. Additionally, we propose the use of a range-aware window size for radar expansion instead of a fixed window size in the image plane. Our proposed method effectively increases the number of radar points from an average of 39 points in a raw radar frame to an average of 100 K points. Notably, the expanded radar exhibits fewer intrinsic errors when compared with raw radar and previous methodologies. To validate our approach, we assess our proposed depth estimation model on the nuScenes dataset. Comparative evaluations with existing radar-guided depth estimation models demonstrate its state-of-the-art performance.

FE-FAIR: Feature-Enhanced Fused Attention for Image Super-Resolution

Transformers have performed better than traditional convolutional neural networks (CNNs) for image super-resolution (SR) reconstruction in recent years. Currently, shifted window multi-head self-attention based on the swin transformer is a typical method. Specifically, the multi-head self-attention is used to extract local features in each window, and then a shifted window strategy is used to discover information interaction between different windows. However, this information interaction method needs to be more efficient and include some global feature information, which limits the model’s performance to a certain extent. Furthermore, optimizing the utilization of shallow features, which exhibit significant energy reserves and invaluable low-frequency information, is critical for advancing the efficacy of super-resolution techniques. In order to solve the above issues, we propose the feature-enhanced fused attention (FE-FAIR) method for image super-resolution. Specifically, we design the multi-scale feature extraction module (MSFE) as a shallow feature extraction layer to extract rich low-frequency information from different scales. In addition, we propose the fused attention block (FAB), which introduces channel attention in the form of residual connection based on shifted window self-attention, effectively achieving the fusion of global and local features. Simultaneously, we also discuss other methods to enhance the performance of the FE-FAIR method, such as optimizing the loss function, increasing the window size, and using pre-training strategies. Compared with state-of-the-art SR methods, our proposed method demonstrates better performance. For instance, FE-FAIR outperforms SwinIR by over 0.9 dB when evaluated on the Urban100 (×4) dataset.

Multi-sensor fusion based optimized deep convolutional neural network for boxing punch activity recognition

Recent advancements in deep learning have significantly enhanced the recognition of player activities in sports by enabling automatic feature extraction. In our proposed work, we focus on recognizing six distinct punches in the context of boxing. We incorporate the sliding window technique during the pre-processing stage to transform the time-series data obtained from Inertial Measurement Unit (IMU) sensors in a boxing punch activity recognition system. Our approach influences a sensor fusion-based Deep Convolutional Neural Network (DCNN) classification model to identify various boxing punches accurately, achieving an impressive F1 score. The system demonstrates proficiency in distinguishing similar activities, such as jab and hook punches where the existing systems made misclassifications due to subtle variations in arm flexion that differentiate the two. Through experimentation, we identify an optimal window size for boxing punch activity recognition, which falls within the range of 15–20 frames (equivalent to 0.15–0.25 s). This window size selection results in a notable reduction in inference time. To evaluate our proposed model, we conduct comparisons with a standard DCNN and an optimized DCNN model. Our proposed optimized DCNN model demonstrates enhanced recognition accuracy, achieving an impressive 99%, coupled with an improved F1 score of 87%. Furthermore, the model displays a remarkable reduction in inference time, clocking in at less than 1 ms. Overall, our research contributes to the field of sports-related player activity recognition by employing the power of deep learning. By expertly combining these techniques, we achieve remarkable accuracy, precision, and efficiency in recognizing various boxing punches.

MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application

Multi-view stereo plays an important role in 3D reconstruction but suffers from low reconstruction efficiency and has difficulties reconstructing areas with low or repeated textures. To address this, we propose MVP-Stereo, a novel multi-view parallel patchmatch stereo method. MVP-Stereo employs two key techniques. First, MVP-Stereo utilizes multi-view dilated ZNCC to handle low texture and repeated texture by dynamically adjusting the matching window size based on image variance and using a portion of pixels to calculate matching costs without increasing computational complexity. Second, MVP-Stereo leverages multi-scale parallel patchmatch to reconstruct the depth map for each image in a highly efficient manner, which is implemented by CUDA with random initialization, multi-scale parallel spatial propagation, random refinement, and the coarse-to-fine strategy. Experiments on the Strecha dataset, the ETH3D benchmark, and the UAV dataset demonstrate that MVP-Stereo can achieve competitive reconstruction quality compared to state-of-the-art methods with the highest reconstruction efficiency. For example, MVP-Stereo outperforms COLMAP in reconstruction quality by around 30% of reconstruction time, and achieves around 90% of the quality of ACMMP and SD-MVS in only around 20% of the time. In summary, MVP-Stereo can efficiently reconstruct high-quality point clouds and meet the requirements of several photogrammetric applications, such as emergency relief, infrastructure inspection, and environmental monitoring.

StresSense: Real-Time detection of stress-displaying behaviors

BackgroundWrist-worn gadgets like smartphones are ideal for unobtrusively gathering user data, in various fields such as health and fitness monitoring, communication, and productivity enhancement. They seamlessly integrate into users' daily lives, providing valuable insights and features without the need for constant attention or disruption. In sensitive domains like mental health, these devices provide user-friendly, privacy-protected means of diagnosis and treatment, offering a secure and cost-effective avenue for seeking help. ObjectivesThis study addresses the limitations of traditional mental health assessment techniques, such as intrusive sensing and subjective self-reporting, by harnessing the unobtrusive data collection capabilities of smartphones. Equipped with accelerometers and other sensors, these devices offer a novel approach to mental health research. Our objective was to develop methods for real-time detection of stress and boredom behavior markers using smart devices and machine learning algorithms. MethodologyBy leveraging data from accelerometers (A), gyroscopes (G), and magnetometers (M), we compiled a dataset indicative of stress-related behaviors and trained various machine-learning models for predictive accuracy. The methodology involved collecting data from motion sensors (A, G, and M) on the dominant arm's wrist-worn smartphone, followed by data preprocessing, transformation from time series format, and training a Deep Neural Network (DNN) model for activity recognition. FindingsRemarkably, the DNN achieved an accuracy of 93.50% on test data, outperforming traditional and ensemble machine learning methods across different window sizes, and demonstrated real-time accuracy of 77.78%, validating its practical application. ConclusionIn conclusion, this research presents a novel dataset for detecting stress and boredom behaviors using smartphones, reducing reliance on costly devices and offering a more objective assessment. It also proposes a DNN-based method for wrist-worn devices to accurately identify complex activities associated with stress and boredom, with benefits in terms of privacy and user convenience. This advancement represents a significant contribution to the field of mental health research, providing a less intrusive and more user-friendly approach to monitoring mental well-being.

Proportional Fairness for Long-Term Evolution-Licensed Assisted Access (LTE-LAA) with Wi-Fi Coexistence in Unlicensed Spectrum

Long-Term Evaluation-Licensed Assisted Access (LTE-LAA) has good potential for fair coexistence with Wi-Fi in an unlicensed spectrum. Though the LTE-LAA utilizes the same listen before-talk technique as the distributed coordination function in IEEE 802.11, it utilizes completely different parameters and transmission durations. For this reason, a fair coexistence between LTE-LAA and Wi-Fi leaves an open question on how the LTE-LAA network should choose its parameters. To tackle this issue, an analytical framework considering the effects of varying important parameters, which are the different initial back-off window sizes, the numbers of sensing durations, the maximum back-off stages, the number of retransmissions and the transmission opportunities for LTE-LAA and Wi-Fi nodes on their performances has been developed. The node and network airtime performances are evaluated by using the current standard parameters setting to see how this setting affects the node and network airtime performances. From there, optimal settings of the initial backoff window size and number of sensing durations are applied by using the obtained node airtime equation that is derived from the Markov renewal process and evaluated as functions of system parameters. The optimum initial backoff window size and number of sensing durations of LTE-LAA are evaluated and verified by the calculation and simulation using MATLAB software. The analysis shows that LTE-LAA maintained unfair coexistence with Wi-Fi by using the current standard parameter setting as its initial back off window size or sensing duration. But in contrast, using the optimum initial backoff window size and number of sensing durations of LTE-LAA shows that they can maintain proportional fairness. It is unconcealed that the initial backoff window size tuning of LTE-LAA carries a high possibility of achieving fairness because it needs less system data and achieves a higher exactness result.

COVID-19 Detection From Respiratory Sounds With Hierarchical Spectrogram Transformers.

Monitoring of prevalent airborne diseases such as COVID-19 characteristically involves respiratory assessments. While auscultation is a mainstream method for preliminary screening of disease symptoms, its utility is hampered by the need for dedicated hospital visits. Remote monitoring based on recordings of respiratory sounds on portable devices is a promising alternative, which can assist in early assessment of COVID-19 that primarily affects the lower respiratory tract. In this study, we introduce a novel deep learning approach to distinguish patients with COVID-19 from healthy controls given audio recordings of cough or breathing sounds. The proposed approach leverages a novel hierarchical spectrogram transformer (HST) on spectrogram representations of respiratory sounds. HST embodies self-attention mechanisms over local windows in spectrograms, and window size is progressively grown over model stages to capture local to global context. HST is compared against state-of-the-art conventional and deep-learning baselines. Demonstrations on crowd-sourced multi-national datasets indicate that HST outperforms competing methods, achieving over 90% area under the receiver operating characteristic curve (AUC) in detecting COVID-19 cases.

Using capillary electrophoresis to identify Anopheline species in routine sampling sites.

In the Anopheles genus, various mosquito species are able to transmit the Plasmodium parasites responsible for malaria, while others are non-vectors. In an effort to better understand the biology of Anopheles species and to quantify transmission risk in an area, the identification of mosquito species collected in the field is an essential but problematic task. Morphological identification requires expertise and cannot be checked after processing samples in a destructive treatment, while sequencing of numerous samples is costly. Here, we introduce a method of Species identification via Simple Observation Coupled with Capillary Electrophoresis Technology (SOCCET). This molecular technique of species identification is based on precise determination of ITS2 length combined with a simple visual observation, the colour of mosquito hindleg tip. DNA extracted from field-collected Anopheles mosquitoes was amplified with universal Anopheles ITS2 primers and analysed with a capillary electrophoresis device, which precisely determines the size of the fragments. We defined windows of amplicon sizes combined with fifth hind tarsus colour, which allows discrimination of the major Anopheles species found in our collections. We validated our parameters via Sanger sequencing of ITS2 amplicons. Using the SOCCET method, we characterised the composition of Anopheles populations in five locations of French Guiana, where we detected a total of nine species. Anopheles braziliensis and Anopheles darlingi were detected in four locations each and represented 13 and 67% of our samples, respectively. The SOCCET method can be particularly useful when working with routine sampling sites with a moderate species diversity, that is, when the number of local species is too high to define species-specific primers but low enough to avoid individual ITS2 sequencing. This tool will be of interest to evaluate local malaria transmission risk and this approach may be further implemented for other mosquito genera.

Exploring the Possibility of Photoplethysmography-Based Human Activity Recognition Using Convolutional Neural Networks.

Various sensing modalities, including external and internal sensors, have been employed in research on human activity recognition (HAR). Among these, internal sensors, particularly wearable technologies, hold significant promise due to their lightweight nature and simplicity. Recently, HAR techniques leveraging wearable biometric signals, such as electrocardiography (ECG) and photoplethysmography (PPG), have been proposed using publicly available datasets. However, to facilitate broader practical applications, a more extensive analysis based on larger databases with cross-subject validation is required. In pursuit of this objective, we initially gathered PPG signals from 40 participants engaged in five common daily activities. Subsequently, we evaluated the feasibility of classifying these activities using deep learning architecture. The model's performance was assessed in terms of accuracy, precision, recall, and F-1 measure via cross-subject cross-validation (CV). The proposed method successfully distinguished the five activities considered, with an average test accuracy of 95.14%. Furthermore, we recommend an optimal window size based on a comprehensive evaluation of performance relative to the input signal length. These findings confirm the potential for practical HAR applications based on PPG and indicate its prospective extension to various domains, such as healthcare or fitness applications, by concurrently analyzing behavioral and health data through a single biometric signal.

IMPLEMENTATION OF THE BIDIRECTIONAL GATED RECURRENT UNIT ALGORITHM ON CONSUMER PRICE INDEX DATA IN INDONESIA

The Consumer Price Index (CPI) is the main index in measuring the inflation rate. Changes in the CPI from time to time reflect inflation and deflation, namely the higher the CPI value, the higher the inflation rate. This study aims to apply Birectional Gated Recurrent Unit (BiGRU) model to the CPI data in Indonesia. BiGRU comprises two GRU layers so it captures sequences that are ignored by the GRU. The research data is in the form of CPI data in Indonesia from January 2006 to December 2022 sourced from the website of the Central Bureau of Statistics totaling 204 data. The data is divided into training data and testing data. Training data was taken from January 2006 to July 2019 as many as 163 data. Data testing was taken from August 2019 to December 2022 as many as 41 data. Before the data is processed, a sliding window process is carried out by dividing the data into segments to reduce the error value. The window size value used is 10. In the sliding window process, the number of segments is 194 data segments. Based on the experiment results, it was concluded that the application of BiGRU to the CPI data was carried out in an experiment with 20 BiGRU architectures. BiGRU architecture was obtained which produced the lowest MAPE value, namely an architecture with two BiGRU layers having 256 neurons and 400 units, and one dense layer. In addition, the epochs used are 200 epochs, the ReLU activation function, and Adam optimization. The experimental results of the BiGRU architecture obtained a MAPE value of 0.24% which indicates that the architectural performance is very good.

Comparison of Wave Prediction and Performance Evaluation in Korea Waters based on Machine Learning

<i>Waves are a complex phenomenon in marine and coastal areas, and accurate wave prediction is essential for the safety and resource management of ships at sea. In this study, three types of machine learning techniques specialized in nonlinear data processing were used to predict the waves of Korea waters. An optimized algorithm for each area is presented for performance evaluation and comparison. The optimal parameters were determined by varying the window size, and the performance was evaluated by comparing the mean absolute error (MAE). All the models showed good results when the window size was 4 or 7 d, with the gated recurrent unit (GRU) performing well in all waters. The MAE results were within 0.161 m to 0.051 m for significant wave heights and 0.491 s to 0.272 s for periods. In addition, the GRU showed higher prediction accuracy for certain data with waves greater than 3 m or 8 s, which is likely due to the number of training parameters. When conducting marine and offshore research at new locations, the results presented in this study can help ensure safety and improve work efficiency. If additional wave-related data are obtained, more accurate wave predictions will be possible.</i>