Mini Batch Research Articles

Implementation of Parallel Optimization Algorithms for NLP: Mini-batch SGD, SGD with Momentum, AdaGrad Adam

Abstract. With the rapid development of machine learning technology, optimization algorithms and optimizers have become key to the development of related technologies contemporarily. Models need the help of optimizers to meet other performance indicators while saving computing resources. This research focuses on comparisons between optimizers, in the context of text sentiment classification tasks. The optimizers mainly compared in this article are mini batch SGD, momentum SGD, Adagrad and Adam. Through comparative experiments, it was found that SGD and its variants have a high dependence on the initial learning rate setting, while the performance of Adagrad and Adam is relatively balanced. Although the training time of Adagrad is shorter than that of Adam, its principal formula has flaws, which are not reflected in this task. The conclusions drawn in this article through comparison can point out the advantages and disadvantages of each optimizer, and can help realize better optimizers in subsequent research.

A comparative study of hot tensile deformation behavior of 6016 aluminum alloy under LSTM neural network and Arrhenius model

Abstract The isothermal tensile test of 6016-T6 aluminum alloy was carried out on Gleeble-3500 at the temperature range of 400 °C–550 °C and the strain rate range of 0.01–10 s−1. The results show that the thermal deformation mechanism of 6016-T6 is dynamic recovery and dynamic recrystallization. In this paper, the phenomenological Arrhenius constitutive model and the data-driven WOA-LSTM constitutive model for predicting the hot tensile deformation behavior of 6016-T6 aluminum alloy were studied in contrast. The whale optimization algorithm was used to optimize the hyperparameters of LSTM neural network to improve the prediction accuracy of flow stress. The optimization results show that the optimal hidden layer node, maximum training period, initial learning rate and mini batch size of WOA-LSTM are 46, 260, 0.0248 and 16, respectively. In addition, the influence of the number of hidden layers on the results of the network was discussed. The appropriate hidden layer of the network was determined to be 2. The result show that the prediction accuracy of WOA-LSTM constitutive model is better than the Arrhenius constitutive model. The mean absolute error and correlation coefficient are 0.9348% and 0.99952, respectively. Among them, in this study, the Arrhenius constitutive model has low precision and only has high precision within a single temperature range.

Resource allocation scheduling scheme for task migration and offloading in 6G Cybertwin internet of vehicles based on DRL

AbstractAs vehicular technology advances, intelligent vehicles generate numerous computation‐intensive tasks, challenging the computational resources of both the vehicles and the Internet of Vehicles (IoV). Traditional IoV struggles with fixed network structures and limited scalability, unable to meet the growing computational demands and next‐generation mobile communication technologies. In congested areas, near‐end Mobile Edge Computing (MEC) resources are often overtaxed, while far‐end MEC servers are underused, resulting in poor service quality. A novel network framework utilizing sixth‐generation mobile communication (6G) and digital twin technologies, combined with task migration, promises to alleviate these inefficiencies. To address these challenges, a task migration and re‐offloading model based on task attribute classification is introduced, employing a hybrid deep reinforcement learning (DRL) algorithm—Dueling Double Q Network DDPG (QDPG). This algorithm merges the strengths of the Deep Deterministic Policy Gradient (DDPG) and the Dueling Double Deep Q‐Network (D3QN), effectively handling continuous and discrete action domains to optimize task migration and re‐offloading in IoV. The inclusion of the Mini Batch K‐Means algorithm enhances learning efficiency and optimization in the DRL algorithm. Experimental results show that QDPG significantly boosts task efficiency and computational performance, providing a robust solution for resource allocation in IoV.

Monitoring and zoning soybean maturity using UAV remote sensing

Timely and accurate determination of the maturity status during the soybean harvest period is crucial for devising strategic harvesting plans, significantly enhancing the intelligent management of soybean production and minimizing losses. To explore the maturation dynamics of soybeans and pinpoint the precise maturity stage for optimal harvesting, we collected Unmanned Aerial Vehicle (UAV) remote sensing data, along with physical and chemical parameters, during the Beginning maturity(R7)-Full maturity(R8) stages from 2021 to 2022. We analyzed the variations in these parameters throughout the maturation period. Employing UAV multispectral technology and correlation analysis algorithms, we established a relationship between the spectral and physicochemical parameters during the maturation period, which led to the formulation of a soybean maturity evaluation index. Furthermore, we incorporated the concept of precision management zoning. In line with actual field production requirements, this index, combined with real-time moisture content, established a standard for grading soybean maturity. Additionally, our study examined the impact of spatial scale on maturity assessments by conducting a theoretical analysis of regionalized variables and analyzing the spatial correlations and variability of soybean maturity across different field plots. We determined the optimal theoretical model for various sampling distances, thereby establishing feasible zoning ranges. Comparative analysis of zoning algorithms, including Hierarchical Clustering (HC), K-Means, and its optimized versions K-Means++ and Mini Batch K-Means, was conducted using the partition performance index as the criterion. This analysis identified the most suitable algorithm for assessing soybean field maturity, which was subsequently verified through field tests. Results indicated that soybean leaf chlorophyll content and photosynthesis decreased sharply initially, then stabilized at a low rate. Water content in both soybean plants and seeds decreased rapidly before slowing, with plant dehydration rates exceeding those of the seeds. Green Normalized Difference Vegetation Index(GNDVI) showed a positive correlation with various physiological indicators, and soybean maturity was classified into three levels using the unit gridding management method, considering actual moisture content. Spatial correlation analysis of maturity variations in small and large test fields revealed Moran indices ranging from 0.78 to 0.95 and 0.70–0.90, respectively. Optimal detection ranges were determined to be 2.00–30.00 m for small fields and 2.00–67.00 m for large fields. The zoning categories for small and large fields were three and four, respectively. Comparative studies showed that the Mini Batch K-Means algorithm, an optimization of K-Means, achieved Calinski-Harabasz Index(CH) scores and silhouette coefficients of 10521.97, 109508.27, and 0.57, 0.54, respectively, indicating comparable zoning effectiveness to K-Means and K-Means++ and superiority over the HC algorithm. The zoning speeds were 12.50 s and 191.68 s, respectively, underscoring its efficiency in maturity zoning. Furthermore, zoning results corresponded well with actual soybean maturity. Terrain had little impact on soybean maturity, which was more susceptible to slope aspect. This study provides a theoretical foundation and practical guidelines for applying UAV remote sensing technology in determining soybean maturity and optimal harvesting periods, thereby reducing potential harvest losses.

Retraction Note: A novel multi-layer multi-spiking neural network for EEG signal classification using Mini Batch SGD

Retraction Note: A novel multi-layer multi-spiking neural network for EEG signal classification using Mini Batch SGD

Comparison of K-Means, Affinity Clustering, and Mini Batch K-Means Algorithms for Market Segmentation Analysis

Market segmentation is the process of dividing a market into homogeneous groups of buyers based on certain characteristics. Market segmentation is important for businesses to understand the needs and behaviors of their customers so that they can develop more effective marketing strategies.This study compares three clustering methods, namely K-Means Clustering, Affinity Propagation Clustering, and Mini Batch K-Means, in the context of market segmentation analysis. The data used is the marketing_campaign.csv dataset consisting of 29 columns and 2240 rows. Experiments were conducted to evaluate the performance of the three methods using the silhouette metric. The results of the experiments showed that Affinity Propagation produced the highest silhouette value of 0.5861, followed by K-Means with 0.4675, and Mini Batch K-Means with 0.4659. The finding indicates that Affinity Propagation can be a good choice for market segmentation analysis on that dataset. The results of this comparison provide insights into the strengths and weaknesses of each clustering method, helping users choose the approach that is most appropriate for their analytical goals. The study contributes to the practical understanding of the application of clustering techniques in the context of marketing.

Designing an AI purchasing requisition bundling generator

Following the design science methodology, a recommender system has been created with the research objective of finding a novel approach to the bundling problem in order to generate data-driven insights identifying cost potentials across an organization. In this study, a concept that has been implemented in business-to-business marketing at IBM is taken over to procurement in the automotive industry to provide decision support. Thereby, this work builds on information processing theory to utilize artificial intelligence technologies, i.e., natural language processing and supervised learning to augment the skills of buyers, whereby design principles were derived for information technology providers and procurement organizations in private and public settings worldwide. As a key finding, overall, Mini Batch K-means was the most performative model among the selected clustering algorithms. Furthermore, through actively making use of purchasing requisition data typically available in enterprise resource planning systems, the bundling generator artifact can lead to significant improvements in strategic planning and commodity management resulting in better utilization of buyer’s capacities, tender designs, and thus procurement’s value contribution in the transformation toward industry 4.0. The empirical study contributes to the literature on bundling and spend analysis, which has predominantly relied on historical data. By incorporating requisition data, which poses inherent challenges of precision and information-richness, this work expands this traditional approach with a forward-looking perspective.

Deep learning model to identify potential occurrence of reduced LVEF in patients with implantable loop recorders

Abstract Background Early detection of left ventricular systolic dysfunction (LVSD) using minimally invasive electrocardiographic assessment in an ambulatory setting may be important considering the increasing economic burden of HF. Recently artificial intelligence (AI) algorithms have been reported to classify reduced ejection fraction using snapshot 12-lead ECG measurements, however the ability of AI to identify LVSD using only a single lead ambulatory ECG is unknown. Purpose We aimed to develop a convolution neural network (CNN) based deep learning algorithm using single lead ECG to predict ejection fraction less than 40% in ambulatory patients implanted with implantable loop recorders (ILRs). Methods We linked ILR patients with LVEF measurements from a de-identified database of aggregated electronic health record (EHR) data during the period of 2007-2021 to a manufacturer’s device database with ambulatory single lead ECGS. The routine ECG transmissions from the ILR devices were paired with LVEF measured within a week. The data was pre-processed to obtain the time-frequency components of ECG using wavelet transform. The wavelet coefficients were then used as input to train and validate a 2D-CNN model. An independent test dataset consisting of data from patient not included in training/validation dataset was used to assess the performance of CNN model to classify LVEF< = 40% using the metrics area under the curve (AUC), sensitivity and specificity. Results A total of 35,741 unique LVEF-ECG pairs collected from 2,249 ILR patients were used to train the model; an independent validation dataset consisted of 6,721 unique LVEF ECG pairs from 750 patients and independent test dataset consisted of 6,611 unique LVEF ECG pairs from 750 patients. In our CNN model, cross entropy was used as loss function and adaptive moment estimation (ADAM) was used as the optimizer. The initial learning rate was selected as 0.0001, epochs as 20 and mini batch size as 64. The threshold to delineate reduced ejection fraction (LVEF< = 40%) was set as 0.1 (Figure 1). The model yielded accuracy, sensitivity, specificity, AUC of 75%,70%, 76% and 0.8 respectively in the independent test set (Figure 2). Conclusion A deep learning algorithm applied to ambulatory single lead ECGs acquired by ILR can detect LVEF< = 40%. This continuous ambulatory AI-ECG monitoring may allow to identify longitudinal changes in LVEF post ILR implant via remote monitoring.Figure 1:Model output vs Actual EF rangeFigure 2:ROC

Pulse wave analysis as a tool for the evaluation of resuscitation therapy in septic shock

Objective. Pulse wave analysis (PWA) can provide insights into cardiovascular biomechanical properties. The use of PWA in critically ill patients, such as septic shock patients, is still limited, but it can provide complementary information on the cardiovascular effects of treatment when compared to standard indices outlined in international guidelines. Previous works have highlighted how sepsis induces severe cardiovascular derangement with altered arterial blood pressure waveform morphology and how resuscitation according to standard haemodynamic targets is not able to restore the physiological functioning of the cardiovascular system. The aim of this work is to test the effectiveness of PWA in characterizing arterial waveforms obtained from a swine experiment involving polymicrobial septic shock and resuscitation with different drugs. Methods. During the experiment, morphological aortic waveform features, such as indices related to the dicrotic notch and inflection point, were extracted by means of PWA techniques. Finally, all the PWA indices were used to compute a clustering classification (mini batch K-means) of the pigs according to the different phases of the experiment. This analysis aimed to test if PWA features alone could be used to distinguish between the different responses to the administered therapies. Results. The PWA indices highlighted different cardiovascular conditions of the pigs in response to different treatments, despite the mean haemodynamic values typically used to guide therapy administration being similar in all animals. The clustering algorithm was able to distinguish between the different phases of the experiment and the different responses of the animals based on the unique information derived from the aortic PWA. Conclusion. Even when used alone, PWA indices were highly informative when assessing therapy responses in cases of septic shock. Significance. A complex pathological condition like septic shock requires extensive monitoring without neglecting important information from commonly measured signals such as arterial blood pressure. Future studies are needed to understand how individual differences in the response to therapy are associated with different cardiovascular conditions that may become specific therapy targets.

Predictive business intelligence dashboard for food and beverage business

This research was conducted to provide an example of predictive business intelligence (BI) dashboard implementation for the food and beverage business (businesses that sell fast-expired goods). This research was conducted using data from a bakery's transactional database. The data are used to perform demand forecasting using extreme gradient boosting (XGBoost), and recency, frequency, and monetary value (RFM) analysis using mini batch k-means (MBKM). The data are processed and displayed in a BI dashboard created using Microsoft Power BI. The XGBoost model created resulted in a root mean square error (RMSE) value of 0.188 and an R2 score of 0.931. The MBKM model created resulted in a Dunn index value of 0.4264, a silhouette score value of 0.4421, and a Davies-Bouldin index value of 0.8327. After the BI dashboard is evaluated by the end user using a questionnaire, the BI dashboard gets a final score of 4.77 out of 5. From the BI dashboard evaluation, it was concluded that the predictive BI dashboard succeeded in helping the analysis process in the bakery business by: accelerating the decision-making process, implementing a data-driven decision-making system, and helping businesses discover new insights.

B-144 A Comparative Analysis of Unsupervised Machine Learning Algorithms for Polyploidy Analysis Using Flow Cytometry

Abstract Background Recently, there has been a growing interest in using cell differentiation inducers to produce platelets in vitro by inducing megakaryocytic differentiation in cell lines. During this process, cells undergo polyploidization through endomitosis. To measure the degree of polyploidy, cell cycle analysis by flow cytometry is commonly used. However, manual gating can be time-consuming and prone to human error, especially when analyzing large datasets. To address this issue, this study aimed to compare the performance of unsupervised machine learning algorithms for polyploidy analysis of flow cytometry data. Methods The K562 cell line (Korea Cell Line Bank, Korea) was cultured under four conditions, including 1 nM and 2.5 nM of PMA (phorbol 12-myristate 13-acetate; Sigma Aldrich, USA) and 5 μg/mL of phytosphingosine (TCI, Japan), for four days. Propidium iodide (Sigma Aldrich, USA) was used to stain the cells for ploidy analysis, and flow cytometry (Navios, Beckman Coulter Inc, USA) was used to obtain the intensity values. Twelve flow cytometry measurements were obtained for K562 cells cultured under four different conditions, with each condition tested in triplicate. Unsupervised machine learning algorithms, including K-Means, Bisecting K-Means (BKM), Mini Batch K-Means (MBKM), Agglomerative Clustering (AC), Gaussian Mixture Models (GMM), K-Medoids, and Partitioning Around Medoids (PAM), were used to generate boundaries among three clusters (2n, 4n, and ≥8n). The boundary values generated by each algorithm were comparatively analyzed by calculating the standard derivation index (SDI) on each boundary. The concordance of each algorithm with manual gating of flow cytometry data was evaluated by calculating residual errors. Results A total of 168 SDI values were obtained from seven different unsupervised machine learning algorithms for two boundaries among 2n, 4n, and ≥8n clusters of four culture conditions in triplicate. When comparing the average (±95% confidence interval) of SDI for each algorithm for the entire dataset, K-Means showed the most acceptable average SDI value of −0.07 (±0.17) with the narrowest confidence interval followed by −0.13 (±0.54) of AC, −0.26 (±0.18) of MBKM, −0.53 (±0.2) of K-Medoids, −0.58 (±0.2) of PAM, 0.74 (±0.3) of GMM, and 0.84 (±0.35) of BKM. In addition, the average (±95% confidence interval) of the absolute value of the residual errors of each algorithm was calculated, with K-Means showing the lowest value of 6.67 (±2.3), indicating higher concordance with manual gating. AC, MBKM, K-Medoids, PAM, BKM, and GMM had higher average residual errors of 10.04 (±2.5), 10.46 (±4.07), 11.13 (±4.65), 12.04 (±4.83), 12.54 (±3.0), and 12.75 (±3.5), respectively. Conclusion K-means demonstrated the best performance for clustering each ploidy among the seven unsupervised machine learning algorithms tested for the flow cytometry data. In addition, the algorithms achieved acceptable concordance with manual gating in most cases in this study. Therefore, unsupervised machine learning algorithms show promise in automating the gating of flow cytometry data for polyploidy analysis and measuring megakaryocytic differentiation in cell lines.

Clustering and Risk Analysis of The Earthquake in Sulawesi Using Mini Batch K-Means, K-Medoids, and Maximum Likelihood Method

Abstract: The earthquake events have been widely analyzed using a statistical approach. Therefore, the sole purpose of this research is clustering and risk analysis of earthquake events based on the combination of machine learning and statistics. The machine learning, conducted by Mini Batch K-Means and K-Medoids, is validated by the Davies-Bouldin index method to earthquake events cluster. Furthermore, the statistics approach conducted by the maximum likelihood method is to estimate the b-value and a-value of earthquake events. The data used in the earthquake events analysis in Sulawesi have a magnitude 5 SR during the period 1980-2022. The results show that the Mini Batch K-Means method is more efficient and accurate than the K-Medoids, and can cluster the earthquakes, namely cluster 0 below 100 km (shallow earthquake), cluster 1 above 100 km to 350 km (medium earthquake), cluster 2 above 350 km (deep earthquake), while K-Medoids method has two clusters namely cluster 0 below 100 km (shallow earthquake), and cluster 1 above 100 km to 350 km. The regions with b-value and a-value less than 0.9 and 7.5, respectively, and in cluster 0, namely the western part of North Sulawesi, Gorontalo, Middle Sulawesi, and West Sulawesi Province, are as vulnerable to earthquake disasters. Meanwhile, the region in cluster 1 and cluster 2 with b-value and a-value more than 0.9 and 7.5 respectively namely South Sulawesi, the Northern part of North Sulawesi, and Southeast Sulawesi Province, are categorized as minor earthquake disasters. Furthermore, the clustering and risk analysis based on these methods results are good performance, which has recognised cluster and vulnerability of the earthquake events.Abstrak: Kejadian gempa bumi telah banyak dianalisis dengan menggunakan pendekatan statistik. Oleh karena itu, tujuan penelitian untuk menganalisis kejadian gempa dengan menggunakan kombinasi pendekatan machine learning dengan statistik. Pendekatan machine learning dilakukan dengan metode baru yakni metode Mini Batch K-Means dan K-Medoids yang divalidasi dengan metode Davies-Bouldin indeks yang digunakan untuk mengklaster kejadian gempa, sedangkan pendekatan secara statistik dilakukan dengan metode maximum likelihood untuk mengestimasi kerentanan gempa bumi berdasarkan nilai-b dan nilai-a. Data yang digunakan yakni data kejadian gempa di Sulawesi dengan magnitudo ≥ 5 SR dengan periode 1980-2022. Hasil menunjukan bahwa metode Mini Batch K-Means lebih effisien dan akurat dibandingkan dengan metode K-Medoids, dan mengklasifikasi tiga klaster kedalaman gempa, yakni klaster 0 dengan kedalaman kurang dari 100 km (gempa dangkal), klaster 1 dengan kedalaman diantara 100 km dengan 350 km (gempa menengah), klaster 2 dengan kedalaman lebih dari 350 km (gempa dalam). Sementara metode K-Medoids dua klaster kedalama gempa, yakni klaster 0 dengan kedalaman dibawah 100 km (gempa dangkal), dan klaster 1 dengan kedalaman lebih dari 100 km. Beberapa wilayah yang mempunyai nilai-b dan nilai-a secara berurutan kurang dari 0,9 dan 7,5 dan termasuk ke dalam klaster 0, yakni Provinsi Sulawesi Utara bagian barat, Gorontalo, Sulawesi Tengah, dan Sulawesi Barat dikategorikan rawan terhadap bencana gempa; Sedangkan wilayah yang termasuk ke dalam klaster 1 dan klaster 2 dengan nilai-b dan nilai-a secara berurutan lebih dari 0,9 dan 7,5 yakni Provinsi Sulawesi Selatan, Sulawesi Utara bagian Utara, dan Sulawesi Tenggara dikategorikan sebagai rendah terhadap bencana gempa. Dengan demikian, kedua metode dapat digunakan untuk meng-klaster gempa dan identifikasi kerentanan kejadian gempa bumi.

An automated weed identification framework for sugarcane crop: A deep learning approach

Automatic weed identification using deep learning (DL) models will mark a revolution in developing site– specific artificial intelligence (AI) based herbicide sprayers which intend to maximize herbicide efficiency with reduced herbicide application in agriculture production systems and hence contribute to higher yields. Conventional weed control strategies pose challenges for integrating smart herbicide delivery and machinery systems. This deep learning approach significantly impacts developing a system for weed identification required in establishing successful real time precision weed management systems like smart spraying systems and AI based smart machinery. Minimal research has been done on automatic weed identification in sugarcane (Saccharum officinarum L.) cropping systems. This study analyzed the feasibility of a computer vision based DL approach for weed identification to achieve autonomous weed control. The image dataset containing 5660 augmented images was deployed to train and evaluate DL models with a spilt of 90% for training and the rest for validation. We trained the six DL models for identifying weeds in sugarcane crop using field imagery (5094 images), validated (566 images) and further evaluated their accuracy and F1 score performance. Model training was undertaken by varying the hyperparameters, such as mini batch size (16 and 32) and epoch (10, 20 and 30) at a learning rate of 0.001. DarkNet53 accomplished a high F1 score value (>99%) and outperformed other models (AlexNet, GoogLeNet, InceptionV3, ResNet50, and Xception) for the identification of weeds in actively growing sugarcane crop. Weeds can be identified with a higher level of confidence (>98%) with a minimum error rate (<1%) at the mini batch size of 16 and epochs 20. Post-training and validation, DarkNet53 was tested (stage I) with an independent 200-image dataset followed by stage II testing (30 images) and obtained 96.6% net accuracy compared with naked eye weed identification. Based on the high – level performance of DarkNet53, we conclude that DL based weed identification laid a potential future avenue with an effective decision system in the machine vision aspects of a precision herbicide applicator for weed control in sugarcane fields through a low cost camera integrated with a single board computer.

Advanced Spam Filtering in Electronic Mail Using Hybrid the Mini Batch K-Means Normalized Mutual Information Feature Elimination with Elephant Herding Optimization Technique

Advanced Spam Filtering in Electronic Mail Using Hybrid the Mini Batch K-Means Normalized Mutual Information Feature Elimination with Elephant Herding Optimization Technique

RETRACTED ARTICLE: A novel multi-layer multi-spiking neural network for EEG signal classification using Mini Batch SGD

RETRACTED ARTICLE: A novel multi-layer multi-spiking neural network for EEG signal classification using Mini Batch SGD

Implementation of Takagi Sugeno Kang Fuzzy with Rough Set Theory and Mini-Batch Gradient Descent Uniform Regularization

The Takagi Sugeno Kang (TSK) fuzzy approach is popular since its output is either a constant or a function. Parameter identification and structure identification are the two key requirements for building the TSK fuzzy system. The input utilized in fuzzy TSK can have an impact on the number of rules produced in such a way that employing more data dimensions typically results in more rules, which causes rule complexity. This issue can be solved by employing a dimension reduction technique that reduces the number of dimensions in the data. After that, the resulting rules are improved with MBGD (Mini-Batch Gradient Descent), which is then altered with uniform regularization (UR). UR can enhance the classifier's fuzzy TSK generalization performance. This study looks at how the rough sets method can be used to reduce data dimensions and use Mini Batch Gradient Descent Uniform Regularization (MBGD-UR) to optimize the rules that come from TSK. 252 respondents' body fat data were utilized as the input, and the mean absolute percentage error (MAPE) was used to analyze the results. Jupyter Notebook software and the Python programming language are used for data processing. The analysis revealed that the MAPE value was 37%, falling into the moderate area. Doi: 10.28991/ESJ-2023-07-03-09 Full Text: PDF

Path Planning in the Case of Swarm Unmanned Surface Vehicles for Visiting Multiple Targets

In this study, we present a hybrid approach of Ant Colony Optimization algorithm (ACO) with fuzzy logic and clustering methods to solve multiobjective path planning problems in the case of swarm Unmanned Surface Vehicles (USVs). This study aims to further explore the performance of the ACO algorithm by integrating fuzzy logic in order to cope with the multiple contradicting objectives and generate quality solutions by in-parallel identifying the mission areas of each USV to reach the desired targets. The design of the operational areas for each USV in the swarm is performed by a comparative evaluation of three popular clustering algorithms: Mini Batch K-Means, Ward Clustering and Birch. Following the identification of the operational areas, the design of each USV path to perform the operation is performed based on the minimization of traveled distance and energy consumption, as well as the maximization of path smoothness. To solve this multiobjective path planning problem, a comparative evaluation is conducted among ACO and fuzzy inference systems, Mamdani (ACO-Mamdani) and Takagi–Sugeno–Kang (ACO-TSK). The results show that depending on the needs of the application, each methodology can contribute, respectively. ACO-Mamdani generates better paths, but ACO-TSK presents higher computation efficiency.

Clustering heterogeneous categorical data using enhanced mini batch K-means with entropy distance measure

&lt;span lang="EN-US"&gt;Clustering methods in data mining aim to group a set of patterns based on their similarity. In a data survey, heterogeneous information is established with various types of data scales like nominal, ordinal, binary, and Likert scales. A lack of treatment of heterogeneous data and information leads to loss of information and scanty decision-making. Although many similarity measures have been established, solutions for heterogeneous data in clustering are still lacking. The recent entropy distance measure seems to provide good results for the heterogeneous categorical data. However, it requires many experiments and evaluations. This article presents a proposed framework for heterogeneous categorical data solution using a mini batch k-means with entropy measure (MBKEM) which is to investigate the effectiveness of similarity measure in clustering method using heterogeneous categorical data. Secondary data from a public survey was used. The findings demonstrate the proposed framework has improved the clustering’s quality. MBKEM outperformed other clustering algorithms with the accuracy at 0.88, v-measure (VM) at 0.82, adjusted rand index (ARI) at 0.87, and Fowlkes-Mallow’s index (FMI) at 0.94. It is observed that the average minimum elapsed time-varying for cluster generation, &lt;/span&gt;&lt;em&gt;&lt;span lang="EN-US"&gt;k&lt;/span&gt;&lt;/em&gt;&lt;span lang="EN-US"&gt; at 0.26 s. In the future, the proposed solution would be beneficial for improving the quality of clustering for heterogeneous categorical data problems in many domains.&lt;/span&gt;

Drainage network flow anomaly classification based on XGBoost

&lt;p&gt;Identifying and classifying anomalies in on-line monitoring systems of drainage systems is important to reduce urban water pollution. In the context of big data, the mini-batch K-means combined with the XGBoost drainage network abnormal flow identification and classification model is proposed to precisely identify and classify abnormalities that occur in real-time updates of online drainage network data while resolving problems with subjectivity and the lack of uniform standards for classification. First, using Mini Batch K-means, the unclassified drainage network data were sorted into four categories: normal drainage, sneaky drainage, rainwater and sewage mixing, and inflow and infiltration. Next, XGBoost performs data modeling to create a model for classification and identification of drainage flow anomalies. To increase the accuracy of the model, the features were ultimately chosen based on the ranking of the importance of the features, and the model parameters were established using grid search and cross-validation. The results showed that the XGBoost Drainage Network Anomaly Classification and Identification Model can accurately identify four drainage network situations with high classification accuracy and good performance. It was also validated through the application of data from the online system monitoring points in Changsha, China, in 2020.&lt;/p&gt;&#x0D;

Learning rate selection in stochastic gradient methods based on line search strategies

Finite-sum problems appear as the sample average approximation of a stochastic optimization problem and often arise in machine learning applications with large scale data sets. A very popular approach to face finite-sum problems is the stochastic gradient method. It is well known that a proper strategy to select the hyperparameters of this method (i.e. the set of a-priori selected parameters) and, in particular, the learning rate, is needed to guarantee convergence properties and good practical performance. In this paper, we analyse standard and line search based updating rules to fix the learning rate sequence, also in relation to the size of the mini batch chosen to compute the current stochastic gradient. An extensive numerical experimentation is carried out in order to evaluate the effectiveness of the discussed strategies for convex and non-convex finite-sum test problems, highlighting that the line search based methods avoid expensive initial setting of the hyperparameters. The line search based approaches have also been applied to train a Convolutional Neural Network, providing very promising results.