Hierarchical Clustering Algorithm Research Articles

Research on clustering algorithms based on the Iris dataset

In the burgeoning field of machine learning, clustering algorithms play a quintessential role in uncovering hidden patterns and structures within data. This study commences by highlighting the critical importance of machine learning and the expansive application of clustering algorithms across various disciplines. It then provides a brief background, tracing the development history of clustering algorithms and elucidating the unique characteristics and methodologies inherent to different algorithms. Through empirical analysis conducted on the Iris dataset, this research evaluates the performance of the K-means, hierarchical clustering, and DBSCAN algorithms, leveraging experimental charts and datasets for a nuanced assessment. The comparative analysis reveals distinct advantages and disadvantages of each algorithm, facilitating a balanced discussion on their practical implications. The conclusion synthesizes these findings, offering insights into the comparative merits of the algorithms and suggesting avenues for future research. This investigation aims to deepen the comprehension of the application challenges and opportunities presented by clustering algorithms, thus offering a guiding framework for future explorations in the field.

Image Forgery Detection Using Machine Learning

Digital Image Forgery can be done by deceiving the digital image to mask some meaningful or important data of the image. It is usually difficult to spot out the manipulated region of the original image. To sustain the uprightness and legitimacy of the image, the detection of forgery in the image is mandating. Acclimation of the modern way of life and advancement in photography gadgetry has made exploitation of digital image easy with the help of image editing software. Therefore, it is crucial to detect such image forgery operations in the images. The image forgery detection can be done based on object removal, object addition, unusual size modifications in the image. Images are one of the powerful media for communication. In this project we have used algorithms such as Copy move, Canny Edge Defection, Structure Similarity index, Hierarchical Agglomerate Clustering and Neural Network algorithms with improved accuracy rate.

Can convolutional neural networks approximate the phylogenetic tree of human populations with face images?1

Inferring phylogenetic trees in human populations is a challenging task that has traditionally relied on genetic, linguistic, and geographic data. In this study, we explore the application of Deep Learning and facial embeddings for phylogenetic tree inference based solely on facial features. We use pre-trained ConvNets as image encoders to extract facial embeddings and apply hierarchical clustering algorithms to construct phylogenetic trees. Our methodology differs from previous approaches in that it does not rely on preconstructed phylogenetic trees, allowing for an independent assessment of the potential of facial embeddings to capture relationships between populations. We have evaluated our method with a dataset of 30 ethnic classes, obtained by web scraping and manual curation. Our results indicate that facial embeddings can capture phenotypic similarities between closely related populations; however, problems arise in cases of convergent evolution, leading to misclassifications of certain ethnic groups. We compare the performance of different models and algorithms, finding that using the model with ResNet50 backbone and the face recognition module yields the best overall results. Our results show the limitations of using only facial features to accurately infer a phylogenetic tree and highlight the need to integrate additional sources of information to improve the robustness of population classification.

Comparative investigation of neoadjuvant immunotherapy versus adjuvant immunotherapy in perioperative patients with cancer: a global-scale, cross-sectional, large-sample informatics study.

Neoadjuvant and adjuvant immunotherapies for cancer have evolved through a series of remarkable and critical research advances; however, addressing their similarities and differences is imperative in clinical practice. Therefore, this study aimed to examine their similarities and differences from the perspective of informatics analysis. This cross-sectional study retrospectively analyzed extensive relevant studies published between 2014 and 2023 using stringent search criteria, excluding non-peer-reviewed and non-English documents. The main outcome variables are publication volume, citation volume, connection strength, occurrence frequency, relevance percentage, and development percentage. Furthermore, an integrated comparative analysis was conducted using unsupervised hierarchical clustering, spatiotemporal analysis, regression statistics, and Walktrap algorithm analysis. This analysis included 1,373 relevant studies. Advancements in neoadjuvant and adjuvant immunotherapies have been promising over the last decade, with an annual growth rate of 25.18% vs. 6.52% and global collaboration (International Co-authorships) of 19.93% vs. 19.84%. Respectively, five dominant research clusters were identified through unsupervised hierarchical clustering based on machine learning, among which Cluster 4 (Balance of neoadjuvant immunotherapy efficacy and safety) and Cluster 2 (Adjuvant immunotherapy clinical trials) (Average Publication Year [APY]: 2021.70±0.70 vs. 2017.54±4.59) are emerging research populations. Burst and regression curve analyses uncovered domain pivotal research signatures, including microsatellite instability (R2=0.7500, P=0.0025) and biomarkers (R2=0.6505, P=0.0086) in neoadjuvant scenarios, and the tumor microenvironment (R2=0.5571, P=0.0209) in adjuvant scenarios. The Walktrap algorithm further revealed that "neoadjuvant immunotherapy, non-small cell lung cancer (NSCLC), immune checkpoint inhibitors, melanoma" and "adjuvant immunotherapy, melanoma, hepatocellular carcinoma, dendritic cells" (Relevance Percentage: 100% vs. 100%, Development Percentage: 37.5% vs. 17.1%) are extremely relevant to this field but remain underdeveloped, highlighting the need for further investigation. This study identified pivotal research signatures and provided substantial predictions for neoadjuvant and adjuvant cancer immunotherapies. In addition, comprehensive quantitative comparisons revealed a notable shift in focus within this field, with neoadjuvant immunotherapy taking precedence over adjuvant immunotherapy after 2020; such a qualitative finding facilitate proper decision-making for subsequent research and mitigate the wastage of healthcare resources.

Brain topology improved spiking neural network for efficient reinforcement learning of continuous control.

The brain topology highly reflects the complex cognitive functions of the biological brain after million-years of evolution. Learning from these biological topologies is a smarter and easier way to achieve brain-like intelligence with features of efficiency, robustness, and flexibility. Here we proposed a brain topology-improved spiking neural network (BT-SNN) for efficient reinforcement learning. First, hundreds of biological topologies are generated and selected as subsets of the Allen mouse brain topology with the help of the Tanimoto hierarchical clustering algorithm, which has been widely used in analyzing key features of the brain connectome. Second, a few biological constraints are used to filter out three key topology candidates, including but not limited to the proportion of node functions (e.g., sensation, memory, and motor types) and network sparsity. Third, the network topology is integrated with the hybrid numerical solver-improved leaky-integrated and fire neurons. Fourth, the algorithm is then tuned with an evolutionary algorithm named adaptive random search instead of backpropagation to guide synaptic modifications without affecting raw key features of the topology. Fifth, under the test of four animal-survival-like RL tasks (i.e., dynamic controlling in Mujoco), the BT-SNN can achieve higher scores than not only counterpart SNN using random topology but also some classical ANNs (i.e., long-short-term memory and multi-layer perception). This result indicates that the research effort of incorporating biological topology and evolutionary learning rules has much in store for the future.

Review-based analysis of clustering approaches in a recommendation system

<span>Because of the explosion in data, it is now incredibly difficult for a single person to filter through all of the information and extract what they need. As a result, information filtering algorithms are necessary to uncover meaningful information from the massive amount of data already available online. Users can benefit from recommendation systems (RSs) since they simplify the process of identifying relevant information. User ratings are incredibly significant for creating recommendations. Previously, academics relied on historical user ratings to predict future ratings, but today, consumers are paying more attention to user reviews because they contain so much relevant information about the user's decision. The proposed approach uses written testimonials to overcome the issue of doubt in the ratings' pasts. Using two data sets, we performed experimental evaluations of the proposed framework. For prediction, clustering algorithms are used with natural language processing in this strategy. It also evaluates the findings of various methods, such as the K-mean, spectral, and hierarchical clustering algorithms, and offers conclusions on which strategy is optimal for the supplied use cases. In addition, we demonstrate that the proposed technique outperforms alternatives that do not involve clustering.</span>

Optimized low carbon scheduling strategy of integrated energy sources considering load aggregators

In the context of the global low-carbon energy development strategy, the massive influx of renewable energy leads to the instability of the power system, so it is necessary to carry out effective scheduling strategy and management mechanism for energy. On this basis, the Integrated Energy System including Electricity/Heat/Storage (EHSIES) is discussed in this paper. First, an ordered clustering method using a combination of simulated annealing and improved profile coefficients for load evolution number approximation is proposed. Second, a hybrid load clustering algorithm based on hierarchical clustering algorithm and K-means++ is presented and four types of load scenarios are obtained. Third, an Improved Harris Hawk Optimization (IHHO) algorithm based on the hybrid strategy is proposed and solved to the model of EHSIES. Finally, under the premise of the dynamic carbon trading mechanism considering historical compliance and load aggregator management, the scheduling strategies of flexible electric loads and thermal loads participating in EHSIES are discussed and solved by CPLEX. The results show that the solution time of IHHO is 50% and 33.3% lower than that of particle swarm optimization (PSO) and Harris hawk optimization (HHO), and the number of iterations is 76.6% and 56.25% lower than that of PSO and HHO, respectively. In addition, considering a flexible load aggregator and a compliance-based dynamic carbon trading mechanism in EHSIES scheduling can effectively reduce the actual operating cost by 27.37%, the source-side energy spill rate by 68.75%, and the carbon emission by 51.92% and improve the operating efficiency and economic benefits of EHSIES.

Prediction Intervals for Bus Travel Time Based on Road Segment Sharing, Multiple Routes’ Driving Style Similarity, and Bootstrap Method

Providing accurate information about bus travel times can help passengers plan their itinerary and reduce waiting time. However, due to various uncertainty factors and the sparsity of single-route data, traditional travel time predictions cannot accurately describe the credibility of the prediction results, which is not conducive to passengers waiting based on the predicted results. To address the above issues, this paper proposes a bus travel time prediction intervals model based on shared road segments, multiple routes’ driving style similarity, and the bootstrap method. The model first divides the predicted route into segments, dividing adjacent stations shared by multiple routes into one section. Then, the hierarchical clustering algorithm is used to group all drivers in multiple bus routes in this section according to their driving styles. Finally, the bootstrap method is used to construct a bus travel time prediction interval for different categories of drivers. The travel time data sets of Shenyang 239, 134, and New Area Line 1 were selected for experimental verification. The experimental results indicate that the quality of the prediction interval constructed using a data set fused with multiple routes is better than that constructed using a single-route data set. In the two cases studied, the MPIW of the three time periods decreased by 101.04 s, 151.72 s, 33.87 s, and 126.58 s, 127.47 s, 17.06 s, respectively.

Business Models of Ukrainian Banks: the Impact of the Revolution of Dignity, the COVID–19 Pandemic, and Russia’s Military Aggression

The purpose of the article is to identify key banking activity models in Ukraine and show how they changed under the influence of the Revolution of Dignity, the COVID–19 pandemic, and the imposition of martial law. The proposed method uses cluster analysis of the main indicators for banking activity (concerning assets, liabilities and income) based on Ward’s agglomerative hierarchical clustering algorithm and the Tau index in the NbClust package as the criterion for evaluating the optimal number of clusters. The research covers all Ukrainian banks, spanning the period 2013–2022. In 2014 (after the Revolution of Dignity), the actions of the National Bank of Ukraine (NBU) had a positive impact on the models of Ukrainian banks: there was no opaque model of banks and banking models became more transparent and more resilient to financial shocks. Between 2021 and 2022, five banking models were identified: universal banks, wholesale funding banks, corporate‑investment banks, retail banks, and commission banks. The negative impact of COVID–19 on the Ukrainian economy was reflected in all banking models by the following: (1) a significant increase in the role of securities in assets, which was caused by a decrease in lending due to an increase in their riskiness; (2) the use of central bank funds to liabilities management, which was evidence of a deterioration in financing conditions in the deposit market. The following main changes in Ukraine’s banking system at the end of 2022 (during the war) were identified: (1) a decrease in the number of banks that mainly use funds from the NBU to support their activities; (2) the closure of only four banks by the NBU (including two with majority shareholders from Russia) during the year; (3) an increase in the share of the non‑government debt securities portfolio in banks’ assets; (4) declines in ROE and ROA for all banking models during the war, and three banking models became unprofitable; (5) the significantly higher share of non‑performing loans in the credit portfolio for all banking models, especially for the retail banking model. The value‑added of this research is the analysis of how banking models in Ukraine have changed at the micro level (reflected in the financial statements) inter alia in wartime.

An analysis of fog and low stratus life‐cycle regimes over central Europe

AbstractA better understanding of fog and low stratus (FLS) life cycles, in particular the typical onset and dissipation times, can help traffic safety and solar power planning. Besides its high dependence on the prevalent meteorological conditions, the FLS life cycle is further determined by the FLS type as well as the underlying geography and climate. While satellite‐based FLS data sets with high temporal and spatial resolution are available, an objective, large‐scale, satellite‐based classification of FLS life‐cycle regions, which would allow for more targeted analyses of the FLS life cycle, is lacking. In this study, a hierarchical clustering algorithm is applied to identify regions of similar relationships of the FLS life cycle to environmental conditions over central Europe. The clustering reveals major FLS life‐cycle regimes with distinct differences in FLS occurrence, temporal FLS life‐cycle patterns, and climatic characteristics. Based on regime‐specific sensitivity analyses, the relationships of the FLS life cycle with near‐ground temperature and specific humidity are identified as the most relevant input relationships for the clustering algorithm, especially in the Mediterranean region. FLS life‐cycle regimes are further presented at a regional scale, outlining the applicability of the derived FLS life‐cycle regimes to future regional process‐oriented FLS life‐cycle studies.

Application of machine learning for identification of heterotic groups in sunflower through combined approach of phenotyping, genotyping and protein profiling

Application of machine learning in plant breeding is a recent concept, that has to be optimized for precise utilization in the breeding program of high yielding crop plants. Identification and efficient utilization of heterotic grouping pattern aided with machine learning approaches is of utmost importance in hybrid cultivar breeding as it can save time and resources required to breed a new plant hybrid/variety. In the present study, 109 genotypes of sunflower were investigated at morphological, biochemical (SDS-PAGE) and molecular levels (through micro-satellites (SSR) markers) for heterotic grouping. All the three datasets were combined, scaled, and subjected to unsupervised machine learning algorithms, i.e., Hierarchical clustering, K-means clustering and hybrid clustering algorithm (hierarchical + K-means) for assessment of efficiency and resolution power of these algorithms in practical plant breeding for heterotic grouping identification. Following the application of machine learning unsupervised clustering approach, two major groups were identified in the studied sunflower germplasm, and further classification revealed six smaller classes in each major group through hierarchical and hybrid clustering approach. Due to high resolution, obtained in hierarchical clustering, classification achieved through this algorithm was further used for selection of potential parents. One genotype from each smaller group was selected based on the maximum seed yield potential and hybridized in a line  ×  tester mating design producing 36 F1 cross combinations. These F1s along with their parents were studied in open field conditions for validating the efficacy of identified heterotic groups in sunflowers genetic material under study. Data for 11 agronomic and qualitative traits were recorded. These 36 F1 combinations were tested for their combining ability (General/Specific), heterosis, genotypic and phenotypic correlation and path analysis. Results suggested that F1 hybrids performed better for all the traits under investigation than their respective parents. Findings of the study validated the use of machine learning approaches in practical plant breeding; however, more accurate and robust clustering algorithms need to be developed to handle the data noisiness of open field experiments.

Performance Analysis and Evaluation of Clustering Algorithms using WEKA

Clustering, an unsupervised learning technique, to find inherent groupings in un-labelled data. It seems to be referring to a study or research paper that examines and uses a number of clustering algorithms, including the canopy method, k-Means clustering, hierarchical clustering, density-based clustering, and EM algorithm. WEKA, a clustering program, is used for the examination of these techniques. and the effectiveness of these algorithms is evaluated through experiments using social network Ads datasets. The goal of this research paper or study seems to be to assess how well these clustering algorithms perform in grouping data within social network Ads datasets. Such analyses can help identify the most suitable algorithm for a specific type of data or problem domain and may lead to insights into the underlying structure of the data.

A metaheuristic algorithm for model predictive control of the oil-cooled motor in hybrid electric vehicles

The current energy management methods for hybrid vehicles are primarily focused on matching the power flow between the engine and the motor. In order to further reduce overall energy consumption and extend the vehicle's lifespan, this paper utilizes model predictive control (MPC) in the energy management of hybrid vehicles to control the energy consumption and temperature of the oil-cooled motor, with a focus on studying the algorithm for solving the optimization problem in MPC. The main work includes: Establishing a simplified model for the oil-cooled motor and training the working condition prediction model based on the worldwide harmonized light vehicles test cycle (WLTC) conditions utilizing long short-term memory (LSTM) recurrent neural network technology. Furthermore, proposing a novel metaheuristic algorithm based on the temporal nature of the problem, multiple hierarchical clustering algorithm (MHCA). In comparison with typical metaheuristic algorithms, the MPC optimized using MHCA exhibits significantly reduced computation time, with an average time of 0.1967s, indicating that using MHCA can theoretically achieve real-time control and eliminate lag in actual control processes. Furthermore, compared to other optimization algorithms, the MHCA algorithm demonstrates the lowest correlation between computation time and operational conditions, highlighting its high robustness in ensuring the safety of practical control.

Clustering analysis for the evolutionary relationships of SARS-CoV-2 strains.

To explore the differences and relationships between the available SARS-CoV-2 strains and predict the potential evolutionary direction of these strains, we employ the hierarchical clustering analysis to investigate the evolutionary relationships between the SARS-CoV-2 strains utilizing the genomic sequences collected in China till January 7, 2023. We encode the sequences of the existing SARS-CoV-2 strains into numerical data through k-mer algorithm, then propose four methods to select the representative sample from each type of strains to comprise the dataset for clustering analysis. Three hierarchical clustering algorithms named Ward-Euclidean, Ward-Jaccard, and Average-Euclidean are introduced through combing the Euclidean and Jaccard distance with the Ward and Average linkage clustering algorithms embedded in the OriginPro software. Experimental results reveal that BF.28, BE.1.1.1, BA.5.3, and BA.5.6.4 strains exhibit distinct characteristics which are not observed in other types of SARS-CoV-2 strains, suggesting their being the majority potential sources which the future SARS-CoV-2 strains' evolution from. Moreover, BA.2.75, CH.1.1, BA.2, BA.5.1.3, BF.7, and B.1.1.214 strains demonstrate enhanced abilities in terms of immune evasion, transmissibility, and pathogenicity. Hence, closely monitoring the evolutionary trends of these strains is crucial to mitigate their impact on public health and society as far as possible.

Weighted double Q-learning based eco-driving control for intelligent connected plug-in hybrid electric vehicle platoon with incorporation of driving style recognition

Driving style poses significant impacts on eco-driving performance of vehicles, especially for those with hybrid powertrains. By incorporating driving style recognition, an efficient velocity planning and energy management strategy is developed for a platoon of intelligent connected plug-in hybrid electric vehicles (PHEVs). Firstly, a high-fidelity driving style classification and recognition model is established based on the agglomerative hierarchical clustering algorithm, and then the support vector machine algorithm is employed to recognize the driving style. Next, a multi-objective velocity planning problem is formulated with the consideration of the fuel economy, driving adaptability and comfort, following performance, and driving safety optimization as the optimization objective, and is then solved based on orthogonal collocation direct transcription and the interior-point methods. Finally, an energy management strategy incorporating model predictive control and weighted double Q-learning algorithm is built. The simulation results demonstrated that the velocity planning algorithm incorporating driving styles achieved preferable adaptability and comfort. The proposed strategy can achieve up to most 98.88 % energy economy of the stochastic dynamic programming for the following PHEVs, and reduce the overall fuel consumption by 27.39 % for the platoon, comparing to that without driving style incorporation.

Robotic Multi-Boll Cotton Harvester System Integration and Performance Evaluation

Several studies on robotic cotton harvesters have designed their end-effectors and harvesting algorithms based on the approach of harvesting a single cotton boll at a time. These robotic cotton harvesting systems often have slow harvesting times per boll due to limited computational speed and the extended time taken by actuators to approach and retract for picking individual cotton bolls. This study modified the design of the previous version of the end-effector with the aim of improving the picking ratio and picking time per boll. This study designed and fabricated a pullback reel to pull the cotton plants backward while the rover harvested and moved down the row. Additionally, a YOLOv4 cotton detection model and hierarchical agglomerative clustering algorithm were implemented to detect cotton bolls and cluster them. A harvesting algorithm was then developed to harvest the cotton bolls in clusters. The modified end-effector, pullback reel, vacuum conveying system, cotton detection model, clustering algorithm, and straight-line path planning algorithm were integrated into a small red rover, and both lab and field tests were conducted. In lab tests, the robot achieved a picking ratio of 57.1% with an average picking time of 2.5 s per boll. In field tests, picking ratio was 56.0%, and it took an average of 3.0 s per boll. Although there was no improvement in the lab setting over the previous design, the robot’s field performance was significantly better, with a 16% higher picking ratio and a 46% reduction in picking time per boll compared to the previous end-effector version tested in 2022.

Regionalization of hydroclimate variables in the contiguous United States

AbstractWe apply a hierarchical clustering algorithm to the Parameter-elevation Relationships on Independent Slopes Model (PRISM) database. The method employs linkage clustering while forcing spatial contiguity. We apply it to the lower-48 United States, deriving regions that are based on temperature and precipitation averages and anomalies, as well as statistical parameters underlying several drought and intense precipitation measures. Resulting regions make intuitive sense from the perspective of driving influences on temperature and precipitation averages and anomalies, and are compatible with results from another empirically derived clustering scheme. Regions selected for individual variables show high similarity across different time frames. There is slightly less similarity when comparing regions created for different monthly or daily hydroclimate variables, and relatively low similarity between monthly vs. daily measures. It is unlikely that any one regionalization solution could summarize hydroclimate extremes given the wide range of variables used to describe them, but geographically sensitive datasets like PRISM and flexible algorithms provide useful methods for regionalization that can aid in drought monitoring and forecasting, and with impacts and planning associated with heavy precipitation.

Damage evolution analysis of concrete based on multi-feature acoustic emission and Gaussian mixture model clustering

In this work, a novel method for damage evolution analysis of concrete under uniaxial compression is proposed based on the multi-feature acoustic emission (AE) and the Gaussian mixture model (GMM) clustering. The hierarchical clustering algorithm is adopted to select optimal AE parameters, while multiple features of these parameters are generated through the principal component analysis (PCA). Then the concrete damage signals are separated by using the GMM clustering with multiple features. Meanwhile, the waveform signals associated with concrete damage in each cluster are validated using the Fast Fourier transform (FFT) and the continuous wavelet transform (CWT). Finally, the damage evolution process of concrete under uniaxial compression is divided based on the variation of AE characteristics. The results show that the frequency ranges of signals for micro-cracks, mixed cracks and friction of concrete under uniaxial compression are 20–30 kHz, 20–65 kHz, and 100–120 kHz, respectively. The damage process of concrete under uniaxial compression is divided into three stages according to the inflection points of the cumulative energy curve, namely the initial compaction stage, the crack formation stage and the failure stage.

Environmental performance driven optimization of urban modular housing layout in Singapore

ABSTRACT With the growing size of cities and the need to renew residential areas, architects are calling for more efficient use of already settled areas. This paper presents a performance-driven architectural design (PDAD) workflow for shape generation and genetic optimization based on environmental data, using public housing in the Singapore region as a case study. It integrates three-dimensional cellular automata, parametric performance simulation, genetic optimization algorithms, and hierarchical clustering algorithms. The results show that the average value of Useful Daylight Illuminance (UDI) is 85.19%, the average value of Energy Use Intensity (EUI) is 159.41 kWh/m2, and the average value of Predicted Mean Vote (PMV) is 0.64 for the optimal set of solutions produced after genetic optimization. The optimal solution set was further classified into 4 categories by a hierarchical clustering algorithm and was visualized for further evaluation and selection by the architect. The study helps architects to integrate data analysis results with human decision-making as a design research method in the early stages of design and leads to further discussion on bottom-up design approaches in the urban renewal process.

Identifying definite patterns of unmet needs in patients with multiple sclerosis using unsupervised machine learning.

People with multiple sclerosis (PwMS) exhibit a spectrum of needs that extend beyond solely disease-related determinants. Investigating unmet needs from the patient perspective may address daily difficulties and optimize care. Our aim was to identify patterns of unmet needs among PwMS and their determinants. We conducted a cross-sectional multicentre study. Data were collected through an anonymous, self-administered online form. To cluster PwMS according to their main unmet needs, we performed agglomerative hierarchical clustering algorithm. Principal component analysis (PCA) was applied to visualize cluster distribution. Pairwise comparisons were used to evaluate demographics and clinical distribution among clusters. Out of 1764 mailed questionnaires, we received 690 responses. Access to primary care was the main contributor to the overall unmet need burden. Four patterns were identified: cluster C1, 'information-seekers with few unmet needs'; cluster C2, 'high unmet needs'; cluster C3, 'socially and assistance-dependent'; cluster C4, 'self-sufficient with few unmet needs'. PCA identified two main components in determining the patterns: the 'public sphere' (access to information and care) and the 'private sphere' (need for assistance and social life). Older age, lower education, longer disease duration and higher disability characterized clusters with more unmet needs in the private sphere. However, demographic and clinical factors failed in explaining the four identified patterns. Our study identified four unmet need patterns among PwMS, emphasizing the importance of personalized care. While clinical and demographic factors provide some insight, additional variables warrant further investigation to fully understand unmet needs in PwMS.