Pattern Recognition Research Articles

Enhancing human computer interaction with coot optimization and deep learning for multi language identification

Human-Computer Interaction (HCI) is a multidisciplinary field focused on designing and utilizing computer technology, underlining the interaction interface between computers and humans. HCI aims to generate systems that allow consumers to relate to computers effectively, efficiently, and pleasantly. Multiple Spoken Language Identification (SLI) for HCI (MSLI for HCI) denotes the ability of a computer system to recognize and distinguish various spoken languages to enable more complete and handy interactions among consumers and technology. SLI utilizing deep learning (DL) involves using artificial neural networks (ANNs), a subset of DL models, to automatically detect and recognize the language spoken in an audio signal. DL techniques, particularly neural networks (NNs), have succeeded in various pattern detection tasks, including speech and language processing. This paper develops a novel Coot Optimizer Algorithm with a DL-Driven Multiple SLI and Detection (COADL-MSLID) technique for HCI applications. The COADL-MSLID approach aims to detect multiple spoken languages from the input audio regardless of gender, speaking style, and age. In the COADL-MSLID technique, the audio files are transformed into spectrogram images as a primary step. Besides, the COADL-MSLID technique employs the SqueezeNet model to produce feature vectors, and the COA is applied to the hyperparameter range of the SqueezeNet method. The COADL-MSLID technique exploits the SLID process’s convolutional autoencoder (CAE) model. To underline the importance of the COADL-MSLID technique, a series of experiments were conducted on the benchmark dataset. The experimentation validation of the COADL-MSLID technique exhibits a greater accuracy result of 98.33% over other techniques.

Testing the validity and reliability of the Korean nursing surveillance scale: a methodological study

BackgroundBecause of the importance of nursing surveillance, there is a need to develop a scale to measure nursing surveillance that reflects the roles of nurses in South Korea. This study aimed to develop a scale to measure surveillance by Korean nurses and to test its reliability and validity.MethodsIn the development phase, a literature review was conducted to verify the attributes of nursing surveillance, and preliminary items were developed based on the surveillance activities in the Nursing Intervention Classification (NIC) and the interviews of Korean nurses and modified through content validation and a pilot study. In the psychometric testing phase, two surveys were conducted with Korean nurses working in acute hospitals, using the preliminary scale in exploratory factor analysis (EFA, n = 220) and confirmatory factor analysis (CFA, n = 219). Data were analyzed through EFA, CFA, correlation, and reliability analyses to verify convergent validity, discriminant validity, criterion validity, and reliability. To verify the validity of the preliminary scale, the exploratory factor analysis and confirmatory factor analysis convergent validity, discriminant validity, criterion validity, and reliability were performed.ResultsIn the EFA, 16 items were grouped into four factors, accounting for 70.1% of the cumulative variance. In the CFA, the model exceeded the criteria for all fit indices (χ2 = 155.62 [df = 94, p < .001], CMIN = 1.65, SRMR = .048, RMSEA = .055, GFI = .921, NFI = .916, TLI = .955, CFI = .964) and was acceptable. The convergent validity, discriminant validity, criterion validity, and reliability were verified. The final Korean nursing surveillance scale consists of four factors: ‘anticipation of problems and decision-making’ with six items; ‘systematic assessment’ with five items; ‘recognition of patterns’ with three items; and ‘identification of the patient’s self-care and coping strategies’ with two items.ConclusionThe Korean nursing surveillance scale developed in this study comprised questions that included NIC’s surveillance activities and empirical data from Korean nurses; based on the attributes of nursing monitoring derived from concept analysis, its validity and reliability were verified. This study can provide precedent to motivate the development of nursing surveillance scales in other countries, and ultimately stimulate studies on nursing surveillance, which is essential for patient safety.

A global assemblage of tax haven clusters: profit shifting, tax dodging and money laundering

In this paper we explore a selection of tax haven clusters in the US and Europe as diverse but recognisable species of some fifty of the phenomena worldwide that have been seldom studied from an economic geography or spatial planning viewpoint. We treat the objects of study as being almost perfect expressions of the classical, canonical cluster configuration. They are: spatial agglomeration, untraded as well as market dependencies, small and medium-sized enterprise status, associative or agentic relationships, interaction with large firms inside or outside the cluster and knowledge acquisition, advisory, consultancy and knowledge translation services from research and innovation intermediaries - public and/or private. However, we think their characteristics demand further recognition of the interactive and often innovative communication networks by means of which these cluster incumbents interact globally. This is because they are set within a worldwide system that can be conceptualised as an exemplar of the well-known construct known as an ‘assemblage’ (Deleuze and Guattari, 2004a). Unlike more recent treatments from De Landa (2019) and others, we try to concentrate on the motive power of the ‘agentic’ impulses of ‘desire’ that motivate human action (e.g. regarding ‘God, Gold or Glory’ as commonly-rehearsed motivators for colonialism of various kinds). It has been more common to use ‘assemblage theory’ to analyse the interlocking ‘machinic’ elements of complex systems like power networks or laboratory interactions. To unlock the mysteries of system interlocking in our selected tax havens, which comprise Wilmington, Delaware (US), Ireland (EU) and Gibraltar (former EU, now British Overseas Territory) – post-Brexit - occupying a ‘quantum’ space ‘in which both the colonial and post-colonial find expression’ (Perera, 2021). Methodologically, we seek ‘pattern recognition’ to identify the lineaments that explain these clusters and the ‘agentic’ actors that motivate them.

Identifying High-Risk Patterns in Single-Vehicle, Single-Occupant Road Traffic Accidents: A Novel Pattern Recognition Approach

Despite various interventions in road safety work, fatal and severe road traffic accidents (RTAs) remain a significant challenge, leading to human suffering and economic costs. Understanding the multicausal nature of RTAs, where multiple conditions and factors interact, is crucial for developing effective prevention measures in road safety work. This study investigates the multivariate statistical analysis of co-occurring conditions in RTAs, focusing on single-vehicle accidents with single occupancy and personal injury on Austrian roads outside built-up areas from 2012 to 2019. The aim is to detect recurring combinations of accident-related variables, referred to as blackpatterns (BPs), using the Austrian RTA database. This study proposes Fisher’s exact test to estimate the relationship between an accident-related variable and fatal and severe RTAs (severe casualties). In terms of pattern recognition, this study develops the maximum combination value (MCV) of accident-related variables, a procedure to search through all possible combinations of variables to find the one that has the highest frequency. The accident investigation proceeds with the application of pattern recognition methods, including binomial logistic regression and a newly developed method, the PATTERMAX method, created to accurately detect and analyse variable-specific BPs in RTA data. Findings indicate significant BPs contributing to severe accidents. The combination of binomial logistic regression and the PATTERMAX method appears to be a promising approach to investigate severe accidents, providing both insights into detailed variable combinations and their impact on accident severity.

Efficient microplastic identification by hyperspectral imaging: A comparative study of spatial resolutions, spectral ranges and classification models to define an optimal analytical protocol

Microplastics (MPs) pollution is a global and challenging issue, necessitating the development of efficient analytical strategies for their detection to monitor their environmental impact.This study aims to define an optimal analytical protocol for characterizing MPs by hyperspectral imaging (HSI), comparing different setups based on spatial resolution, spectral range and classification models. The investigated MPs include polymers commonly found in the environment, such as polystyrene (PS), polypropylene (PP) and high-density polyethylene (HDPE), subdivided in three size classes (1000–2000 μm, 500–1000 μm, 250–500 μm). Furthermore, MP particles with diameters ranging from 30 to 250 μm were assessed to determine the limit of detection (LOD) in the different configurations. Hyperspectral images were acquired with two spatial resolutions, 150 and 30 μm/pixel, and two spectral ranges, 1000–1700 nm (NIR) and 1000–2500 nm (SWIR). Three classification models, Partial Least Square-Discriminant Analysis (PLS-DA), Error Correction Output Coding-Support Vector Machine (ECOC-SVM) and Neural Network Pattern Recognition (NNPR) were tested on the acquired images. The correctness of these models was evaluated by prediction maps and statistical parameters (Recall, Specificity and Accuracy). The results demonstrated that for MP particles larger than 250 μm, the optimal setup is a spatial resolution of 150 μm/pixel and a spectral range of 1000–1700 nm, utilizing a linear classification model like PLS-DA. This approach offers accurate predictions while being time- and cost-efficient. For MPs smaller than 250 μm, a higher spatial resolution of 30 μm/pixel with a spectral range of 1000–2500 nm and a non-linear classification method like ECOC-SVM is preferable. The LOD is 250 μm for the 150 μm/pixel resolution and ranges from 100 to 200 μm for the 30 μm/pixel resolution. These findings provide a valuable guide for selecting the appropriate HSI acquisition conditions and data processing methods to optimally characterize MPs of different sizes.

Granular computing-based time series anomaly pattern detection with semantic interpretation

Time series analysis may suffer from the “curse of dimensionality” due to its high-dimensionality characteristics. In terms of this issue, information granulation offers an effective vehicle to process time series at a higher level of abstraction. To take this advantage, this study conducts an interpretable time series anomaly pattern detection under the framework of granular computing, where each time series is granulated into a series of semantics according to its patterns and the anomaly ones are identified based on the obtained semantics. First, the time series is partitioned into a predefined number of segments and trend-based information granules are formed for the data points in each time interval. Guided by the principle of justifiable granularity, the granular results maintaining the main features of the original time series realize informative feature extraction and meaningful dimensionality reduction. Then, to realize semantic anomaly pattern detection, the Axiomatic Fuzzy Set (AFS) theory is generalized to construct and compute with semantic time series, and an AFS-based anomaly score is proposed to discover anomaly patterns. In the experiments, the proposed method is conducted on both UCR data sets and real-world time series, where the detected anomaly patterns are equipped with well-defined semantics.

Imaging approach for fungal sinusitis.

This article provides a comprehensive review of the computed tomography (CT) and magnetic resonance (MR) imaging findings of invasive fungal sinusitis with an emphasis on pattern recognition and approach to interpretation. Fungal sinusitis is categorized into invasive (acute, chronic, and granulomatous) and noninvasive forms (allergic fungal sinusitis and mycetoma). CT is superior for detecting bony erosion and hyperdense fungal elements, while MRI excels in evaluating soft tissue and mucosal involvement. Key radiologic signs such as bone destruction, sinus wall thickening, and 'black turbinate sign' aid in early diagnosis, especially in invasive cases. Early imaging signs can be subtle. Early detection is necessary, particularly in immunocompromised patients with acute invasive fungal sinusitis, where rapid intervention is critical. Pattern recognition and adequate interpretation of fungal sinusitis are possible using CT and MRI. Imaging can also help identify complications, aiding with reliable diagnosis and prompt intervention.

ADCMDES: Design of an augmented cross-domain collaborative recommendation model using novel distance metric and ensemble stratification

Collaborative recommendation involves leveraging information from one entity to suggest attributes of other entities through pattern analysis. These models are invaluable for understanding data behaviour’s impact on related entities. Researchers propose various pattern recognition and correlation models, employing distance metrics like Jaccard, Cosine, etc., to estimate correlations between user queries and recommendation datasets. However, these models become less efficient as dataset size increases due to exponential correlation estimation delays. To enhance scalability while retaining recommendation quality, a new approach is introduced: ADCMDES. This novel augmented cross-domain collaborative model employs a hybrid distance metric and ensemble stratification for dataset pruning. It operates semi-supervisedly, requiring information about the entities being collaborated upon. This data is used to cluster similar collaborative entities, producing a condensed cluster with greater relevancy to user queries. Utilizing word2vec, records are transformed into features for an ensemble classification engine. The resultant model categorizes user input, directing it to the most relevant cluster. Entries within this cluster are ranked using a hybrid metric amalgamating 18 distance measures, enhancing correlation between input queries and recommendations. In testing, ADCMDES exhibited 15% better accuracy, 8% better precision, 9% better recall, and 3% lower RMSE compared to standard models across datasets. While some delay is introduced due to ensemble classification and augmented feature pooling, this doesn't considerably affect long-term recommendation performance and can be mitigated through parallel processing and redundancy reduction techniques.

Identity Instrumentalized: Pattern Recognition as an Epistemology of Surveillance, 1960-66.

The emergence of new surveillance practices is not solely a matter of technological and political developments. It is also intertwined with the production of scientific knowledge. This article traces how scientists in the 1960s developed some of the earliest computerized facial recognition techniques while covertly sponsored by a U.S. intelligence agency. The article situates their project within approaches from the technical field of pattern recognition. It demonstrates how the scientists, especially amid unsteady patronage relationships, reinforced a key assumption: that recognizing identity could be reduced to classifying specific features within a set of existing examples. As their ambitions grew over six years, the scientists transformed human identity into a scientific object tailored to their recognition techniques. How this transformation occurred foregrounds the epistemic underpinnings of surveillance technologies.

Data-driven bio-integrated design method encoded by biocomputational real-time feedback loop and deep semi-supervised learning (DSSL)

Today, under the imperatives of synthetic biology (Synbio), material-based design strategies are conceived as biofactories that can recapitulate the functionalities of living systems for developing building materials with controllable structural features. These strategies include biofabrication techniques such as vitro-culturing, Fabrication Information Modeling (FIM), growth parametrization, machinery systems, and genetic programming articulated bioproducts as the construction material for low-carbon buildings. However, these biophysical systems need interactive development by data-oriented models and decision-maker tools that can mine, measure, and re-configure the complexity in biological systems through monitoring and controlling in a higher integration toward systemic decision-making solutions. This research presents a real-time feedback loop as the bio-integrated design method for design and fabrication of Gluconacebacter Xylinus (GX) Bacterial Cellulose (BC) with Transfer Learning (TL) and Deep Semi-Supervised Learning (DSSL) through TensorFlow and Keras Python libraries. The loop started by mining datasets from BC growth via the VGG16 pre-trained model. In this stage, the loop can learn the material behavior over the growth process and attribute features to a measured BC thickness. Based on this attribution, the loop can drive real-time classifying of input datasets to thickness-based classes and guide the Region of Interests (ROIs) to a user-designed thickness till the captured features are fitted to the user-input class features. The training results over 8640 images show a 0.001 learning rate, an average loss of 0.18 (540 total steps), an accuracy of 0.706, and a precision of 0.752 for the feature extractor model. For the classifier, a 0.15 average loss (3375 total steps), an accuracy of 0.829, and a precision of 0.712 demonstrate the models' efficiency in pattern recognition and classification. Also, the loop operation persistently exhibits a more than 50% precision rate, displaying the loop's high performance in achieving user-designed 3D shapes. This research aims to a transformative shift in bio-integrated design based on feedback loops as the foundational step towards intelligent bio-digital design platforms. Also, this ground can break designing with biological systems based on desired tasks for the new generation of designers called biodesigners.

THE ROLE OF GEOSPATIAL ARTIFICIAL INTELLIGENCE (GEOAI) IN SMART BUILT ENVIRONMENT MAPPING: AUTOMATIC OBJECT DETECTION OF RASTER TOPOGRAPHIC MAPS IN MALAYSIA

Smart built environment mapping is integrating Geospatial Artificial Intelligence (GeoAI) to enable advanced analysis, pattern recognition, and decision-making processes. This shift in understanding, planning, designing, and managing the built environment is paving the way for a smarter, more sustainable future. This commentary explores the current role of AI in enhancing technology use within the geospatial field, focusing specifically on the application of GeoAI in mapping the built environment. Additionally, the paper presents a selection of case studies related to the implementation of AI in developing automatic vectorization, particularly for geospatial mapping in built environments. This research demonstrates the effectiveness of using Convolutional Neural Network (CNN) models for sorting objects in scanned, old topographic maps of the built environment. The findings of this study are valuable for making informed decisions, devising effective strategies, and identifying opportunities for further research and exploration within the dynamic field of GeoAI in smart built environment mapping and applications.

Analyzing convolutional neural networks and linear regression models for wind speed forecasting in sustainable energy provision

Wind energy's significance lies in its contribution to electricity production. Accurate wind speed prediction is crucial for precisely forecasting electricity generation, enhancing its overall importance. For the wind speed prediction two methods are developed in this paper that are the Linear Regression Method and Convolutional Neural Networks (CNNs). Linear regression makes a linear relation between input and output which are used to predict continuous outcomes. The second proposed leverage hierarchical feature extraction through convolutional layers, enabling them to excel at tasks like pattern recognition by capturing spatial patterns and hierarchies of information. Hyperparameter tuning is applied on both the models to minimize the errors. Then both the model’s performances are compared under different error matrices including MAE, RMSE, MSE and MAPE. The observations indicate that both the Linear Regression Model and CNN models are capable of forecasting wind speed However, the Linear Regression Model after Hyperparameter tuning performs better in terms of the calculated errors.

Pattern recognition of drying lysozyme–glucose droplets using machine learning classifiers

Out-of-equilibrium processes, such as sessile droplet drying, often result in distinctive macroscopic residual patterns in systems containing molecules, proteins, and colloids. Protein–glucose mixtures are particularly effective models for studying the behavior of complex fluids containing biomolecules. This study investigates the drying patterns of lysozyme droplets with varying initial glucose concentrations. Without glucose, the crack patterns are chaotic and dispersed throughout the droplet. Interestingly, cracks predominantly form around the droplet edges at intermediate glucose concentrations, while the deposits become uniform and crack-free at high glucose concentrations. To understand and classify the unique patterns related to the initial compositional changes, we developed an automated pattern recognition pipeline. We used two methods for analyzing images captured throughout the drying process. The first method involved extracting statistical textural parameters from the images as quantitative features for machine learning classifiers. The second method utilized a neural network-based classifier to directly classify the images, achieving an accuracy of 97%. The results demonstrate the effectiveness of using images from the entire drying process, not just the final images, for pattern classification. This approach may be useful in gaining a fundamental understanding of unique crack pattern that emerge when glucose is added to a protein solution.

Enhancing Motor Imagery Classification in Brain–Computer Interfaces Using Deep Learning and Continuous Wavelet Transform

In brain–computer interface (BCI) systems, motor imagery (MI) electroencephalogram (EEG) is widely used to interpret the human brain. However, MI classification is challenging due to weak signals and a lack of high-quality data. While deep learning (DL) methods have shown significant success in pattern recognition, their application to MI-based BCI systems remains limited. To address these challenges, we propose a novel deep learning algorithm that leverages EEG signal features through a two-branch parallel convolutional neural network (CNN). Our approach incorporates different input signals, such as continuous wavelet transform, short-time Fourier transform, and common spatial patterns, and employs various classifiers, including support vector machines and decision trees, to enhance system performance. We evaluate our algorithm using the BCI Competition IV dataset 2B, comparing it with other state-of-the-art methods. Our results demonstrate that the proposed method excels in classification accuracy, offering improvements for MI-based BCI systems.

Research and Empirical Evidence of Machine Learning based Financial Statement Analysis Methods

This study presents a novel approach called FinAnalytix which merging machine learning’s prowess in pattern recognition with financial statement analysis. This integrated algorithm combines deep neural networks and recurrent neural networks for predictive accuracy in stock return analysis, alongside logistic regression and random forest models for robust fraud detection in financial statements. The empirical evidence demonstrates FinAnalytix effectiveness in identifying abnormal financial patterns and predicting market reactions to earnings announcements. The study utilizes extensive data from listed companies, ensuring a comprehensive and practical application. FinAnalytix represents a significant advancement in the field, providing a dual approach to financial analysis for enhancing investment strategies through accurate stock return forecasts and bolstering financial integrity by detecting fraudulent activities. The simulation of the study based on the financial data of 100 sample listed companies. This research not only bridges the gap between traditional financial analysis and modern machine learning techniques but also offers a powerful tool for investors and regulatory bodies in navigating the complex financial landscape.

Design of a differentiable L-1 norm for pattern recognition and machine learning

In various applications of pattern recognition, feature selection, and machine learning, L-1 norm is used as either an objective function or a regularizer. Mathematically, L-1 norm has unique characteristics that make it attractive in machine learning, feature selection, optimization, and regression. Computationally, however, L-1 norm presents a hurdle as it is non-differentiable, making the process of finding a solution difficult. Existing approach therefore relies on numerical approaches. In this work we designed an L-1 norm that is differentiable and, thus, has an analytical solution. The differentiable L-1 norm removes the absolute sign in the conventional definition and is everywhere differentiable. The new L-1 norm is almost everywhere linear, a desirable feature that is also present in the conventional L-1 norm. The only limitation of the new L-1 norm is that near zero, its behavior is not linear, hence we consider the new L-1 norm quasi-linear. Being differentiable, the new L-1 norm and its quasi-linear variation make them amenable to analytic solutions. Hence, it can facilitate the development and implementation of many algorithms involving L-1 norm. Our tests validate the capability of the new L-1 norm in various applications.

Recurrence analysis of 3D point clouds for the detection of surface anomalies in advanced manufacturing

Due to tool wear, machine malfunction, and other internal and external factors, surface anomalies are widely observed in diverse manufacturing processes, such as machining, stamping, and additive manufacturing. The detection of surface anomalies remains an important challenge for assuring the quality and reliability of manufacturing products. Conventional image-based approaches lack the ability to fully capture the 3-dimensional (3D) morphologies of surface defects, which hinder their applications in defect identification, characterization, and diagnosis. The emerging 3D sensing technologies, such as laser or structured-light scanning, enable the collection of point clouds, which embodies a comprehensive representation of defect-altered surface morphologies in 3D space. However, scanned point cloud data are unstructured and oftentimes contain large numbers of points, which pose significant challenges for the recognition of defective surface patterns. To address the challenges, this study develops a recurrence-based approach for the representation learning of 3D point clouds to detect surface defects in manufactured products. Specifically, with a scanned point cloud, key points are first extracted using a voxel-based sampling strategy, and each key point and its neighboring points form a localized sub-region. Then, a recurrence network is generated through a tailored approach, which considers both the morphology similarity and spatial closeness of sub-regions. For anomaly detection, a tensor-based one-class classification model is further deployed to distinguish abnormal surface patterns from normal ones. The developed methodology is experimentally evaluated through simulation and real-world case studies. Experimental results have demonstrated that the developed methodology outperforms benchmarks, highlighting its efficacy in the detection of surface anomalies.

On-line recognition of mixture control chart patterns using hybrid CNN and LSTM for auto-correlated processes

Statistical process control (SPC), designed to detect and identify process disturbances, is an effective quality control method for ensuring process stability. Owing to the growing automation of the industry, the manufacturing process can be autocorrelated. Engineer process control (EPC) is typically used to address autocorrelation. However, process disturbances can be offset by feedback compensation, making control chart patterns (CCPs) difficult to identify. Most studies on control chart pattern recognition (CCPR) techniques are based on a single abnormal control chart pattern (CCP). However, a mixture of CCPs can occur during real-world manufacturing processes. With the development of intelligent manufacturing systems, early detection of abnormal concurrent CCPs has become an important issue. In this study, a hybrid model combining a convolutional neural network (CNN) and long short-term memory (LSTM) in an online detection system was used to recognize the concurrent CCPR problem in SPC-EPC processes. The results showed that the average accuracy of the deep learning CNN-LSTM method was 99.83%, which was significantly better than that of the machine learning method. In addition, the running time of the CNN-LSTM model was shortened. In a comparison of online monitoring between the deep learning method and the machine learning method, the CNN-LSTM model for an online monitoring system identified abnormal concurrent patterns faster. Therefore, the proposed CNN-LSTM online monitoring scheme can be applied confidently and successfully to identify mixture CCPs in an SPC-EPC process.

S813 Artificial Intelligence as a Transforming Factor in Motility Disorders - Automatic Detection and Differentiation of Motility Patterns in High-Resolution Anorectal Manometry

S813 Artificial Intelligence as a Transforming Factor in Motility Disorders - Automatic Detection and Differentiation of Motility Patterns in High-Resolution Anorectal Manometry

Detection of Dominant Rainfall Patterns in Indonesian Regions Using Empirical Orthogonal Function (EOF) and Its Relation with ENSO and IOD Events

Several studies indicate that Indonesia’s position on the equator, where winds from the northern and southern hemispheres converge, leads to year-round rainfall in Indonesia. Previous studies have also shown the presence of monsoon winds over Indonesia, which causes rain in Indonesia to follow the Asian and Australian monsoon wind patterns. Recently, variations in rainfall patterns and intensity in Indonesia have been highly volatile and difficult to predict. This study uses gridded data analysis of ocean-atmospheric rainfall for 69 years (1948–2016) to detect monsoonal, equatorial, and local signals and relate them to ENSO and IOD events. Rainfall analysis reveals that the first mode accounts for 38.57%, the second 13.92%, and the third 8.93% of the total variance. These results show that these variants are very variable, both in space and time. Monsoonal patterns were detected in the southern region of Indonesia, equatorial patterns in northern Sumatra and western Kalimantan, while local patterns were detected in Maluku and the Maluku Islands. Furthermore, the monsoonal and local rainfall patterns are strongly correlated (&gt; 0.85) with local SST, but the equatorial rainfall pattern is weakly correlated (&lt; 0.5) with local SST. Note that the equatorial pattern is associated with the Inter Tropical Convergence Zone (ITCZ) phase. The varied vector correlation map illustrates the asymmetric fluctuations in sea surface temperature and the simultaneous existence of winds coming from the west from the Indian Ocean and winds coming from the east from the Pacific Ocean during the period of heavy precipitation.