Segmentation Scheme Research Articles

Real-Time Orbit Determination of Micro–Nano Satellite Using Robust Adaptive Filtering

Low-performing GPS receivers, often used in challenging scenarios such as attitude maneuver and attitude rotation, are frequently encountered for micro–nano satellites. To address these challenges, this paper proposes a modified robust adaptive hierarchical filtering algorithm (named IARKF). This algorithm leverages robust adaptive filtering to dynamically adjust the distribution of innovation vectors and employs a fading memory weighted method to estimate measurement noise in real time, thereby enhancing the filter’s adaptability to dynamic environments. A segmented adaptive filtering strategy is introduced, allowing for flexible parameter adjustment in different dynamic scenarios. A micro–nano satellite equipped with a miniaturized dual-frequency GPS receiver is employed to demonstrate precise orbit determination capabilities. On-orbit GPS data from the satellite, collected in two specific scenarios—slow rotation and Earth-pointing stabilization—are analyzed to evaluate the proposed algorithm’s ability to cope with weak GPS signals and satellite attitude instability as well as to assess the achievable orbit determination accuracy. The results show that, compared to traditional Extended Kalman Filters (EKF) and other improved filtering algorithms, the IARKF performs better in reducing post-fit residuals and improving orbit prediction accuracy, demonstrating its superior robustness. The three-axes orbit determination internal consistency precision can reach the millimeter level. This work explores a feasible approach for achieving high-performance orbit determination in micro–nano satellites.

Evaluating Market Segmentation Strategies Using the ARAS Method: A Multi-Criteria Approach

Market segmentation evaluation involves analysing the effectiveness and efficiency of businesses' segmentation strategies. It assesses the chosen criteria, segment identification, and marketing strategies for each segment. By evaluating data and performance indicators, businesses can optimize their marketing efforts and gain a competitive advantage in meeting customer needs. Market segmentation is dividing the market based on demographics, psychographics, behaviour, and geography. Factors such as the size and growth of each segment, attractiveness of the segment structure, company goals and resource allocation are considered. This approach allows companies to align their strategies to use resources effectively and take advantage of market opportunities. The importance of market segmentation research lies in its ability to provide valuable insight and guidance to businesses. Understanding the effectiveness of market segmentation strategies is important for companies that want to target and engage their customers more efficiently. By evaluating market segmentation, businesses can identify the most appropriate criteria for segmenting their target market, accurately identify and select target segments, and optimize their marketing strategies for each segment. This research helps businesses allocate resources effectively, increase customer satisfaction and ultimately gain a competitive edge in the market by tailoring their offerings to specific customer needs and preferences. Market segmentation assessment considers important factors such as target market size, customer base, income level, and product offerings. By analysing these variables, companies can assess market potential and understand the composition of segments. This assessment allows companies to adjust their strategies to effectively meet the needs and preferences of different customer groups, leading to more targeted marketing efforts and better business outcomes. The ARAS methodology, which stands for attractiveness, accessibility, effectiveness, and size, is a structured framework for evaluating market segmentation. It enables businesses to systematically assess and prioritize market segments based on profitability, reachability, reliability, and size. This assessment helps companies make informed decisions about resource allocation, marketing strategies and aligning them with overall business goals. By considering factors such as market growth, competition, accessibility, resource availability, and customer size, the ARAS methodology provides a comprehensive approach to improving market segmentation and increasing business success. Alternate Parameters taken as “Degree of concentration, Laws and government agency regulations, Types of competitors, Contribution margins, Complexity.” Evaluation Parameters taken as “Segment factors, Competition, Technological factors, Socio-political factors, Financial and economic factors”. As the result, the type of competitor is placed first and the Complexity is placed at the end while using ARAS Method. In this paper, the type of competitor is ranked number one in the list and the Complexity has got last.

Superpixel Classification with the Aid of Neighborhood for Water Mapping in SAR Imagery

Water mapping for satellite imagery has been an active research field for many applications, in particular natural disasters such as floods. Synthetic Aperture Radar (SAR) provides high-resolution imagery without constraints on weather conditions. The single-date SAR approach is less accurate than the multi-temporal approach but can produce results more promptly. This paper proposes novel segmentation schemes that are designed to process both a target superpixel and its surrounding ones for the input for machine learning. Mixture-based Superpixel-Shallow Deit-Ti/XGBoost (MISP-SDT/XGB) schemes are devised to generate, annotate, and classify superpixels, and perform the land/water segmentation of SAR imagery. These schemes are applied to Sentinel-1 SAR data to examine segmentation performances. Single/mask/neighborhood models and single/neighborhood models are introduced in the MISP-SDT scheme and the MISP-XGB scheme, respectively. The effects of the contextual information about the target and its neighbor superpixels are assessed on its segmentation performances. Regarding polarization, it is shown that the VH mode produces more encouraging results than the VV, which is consistent with previous studies. Also, under our MISP-SDT/XGP schemes, the neighborhood models show better performances than FCNN models. Overall, the neighborhood model gives better performances than the single model. Results from attention maps and feature importance scores show that neighbor regions are looked at or used by the algorithms in the neighborhood models. Our findings suggest that under our schemes, the contextual information has positive effects on land/water segmentation.

Research on multiple quadrotor UAV formation obstacle avoidance based on finite-time consensus

Abstract Aiming at the problem of fast and consensus obstacle avoidance of multiple unmanned aerial systems in undirected network, a multi-quadrotor unmanned aerial vehicles UAVs (QUAVs) finite-time consensus obstacle avoidance algorithm is proposed. In this paper, multi-QUAVs establish communication through the leader-following method, and the formation is led by the leader to fly to the target position automatically and avoid obstacles autonomously through the improved artificial potential field method. The finite-time consensus protocol controls multi-QUAVs to form a desired formation quickly, considering the existence of communication and input delay, and rigorously proves the convergence of the proposed protocol. A trajectory segmentation strategy is added to the improved artificial potential field method to reduce trajectory loss and improve the task execution efficiency. The simulation results show that multi-QUAVs can be assembled to form the desired formation quickly, and the QUAV formation can avoid obstacles and maintain the formation unchanged while avoiding obstacles.

Early forest flame and smoke detection based on improved feature extraction module with enhanced image processing inspired by YOLOV7

Background The forest environment is intricate and dynamic, with its depiction influenced by various factors such as geographical location, weather conditions, and capture angles. Relying solely on flame or smoke is insufficient for precise fire information. Aims This paper proposes a method for accurate detection on forest flame and smoke based on improved feature extraction module with enhanced image processing. Methods We a fusion-guided filtering image processing method and flame segmentation strategy to augment the quality of dataset. Additionally, an outstanding extraction backbone, incorporating ghost modules and decoupled fully connected (DFC) attention modules, is developed to increase the model’s receptive field. Furthermore, the ELAN-S neck with SimAM attention mechanism is introduced to fuse features from the backbone network, facilitating the extraction of shallow and deep-level semantic information. Key results Compared to YOLOV7, our model demonstrates superior performance with a 5% increase in mean average precision (mAP), a 4.3% increase in average precision for small objects (APS), and a 3–4% enhancement in other metrics. Conclusions The proposed model achieves a good balance between detection speed and detection accuracy. The improved model performs well in real forest fire detection scenarios. Implications In the early forest fire detection, the model considers both flame and smoke information to describe the fire situation, and effectively combines the semantic information of both for fire warning.

Dual-loop Segmented Piston Trajectory Control of Free Piston Linear Generator based on sliding mode control

Free piston linear generator (FPLG) can be applied as range extender for electrical vehicles to reduce greenhouse gas emissions attributed to its fuel flexibility and ultimate freedom of piston motion. However, FPLG still faces several challenges in control such as misfire and collision due to the eliminate of mechanical crankshaft. To fully utilize the potential of the ultimate freedom of piston motion, this paper presents a novel piston trajectory control strategy which employs the piston trajectory on the entire operation process of FPLG as the control objective. Considering disturbances and high coupling of FPLG, a sliding mode controller is employed to track reference piston trajectory. Additionally, a segmented control strategy is implemented to decouple the control of combustion pressure force and electromagnetic force. In order to ascertain the effectiveness of the proposed controller, a prototype of single-piston FPLG and a corresponding numerical model are constructed. The experimental and simulation results demonstrate the proposed controller shows fast response, precise tracking performance, and good robustness at various reference piston trajectories. Furthermore, the experimental results illustrate that the system can achieve cold start through the seamless transition between operation states and long-term stable operation by the controller.

Machine Learning Algorithm as a Firewall Decision and Reinforcement in Market Segmentation and Big Data

In the modern digital landscape, vast amounts of data are generated daily, challenging traditional analytical approaches in both data security and market segmentation. This paper presents a machine learning (ML) algorithm designed to serve a dual purpose: as a decision-support firewall system and as a reinforcement tool for market segmentation within big data environments. By integrating supervised and unsupervised learning models, the proposed algorithm effectively detects anomalies and potential security threats while also identifying distinct customer segments with high precision. The firewall decision-making component utilizes predictive models to detect malicious activity in real-time, enhancing cybersecurity by proactively learning from previous threat patterns. Concurrently, the reinforcement learning component analyses customer behaviour and preferences, dynamically adapting segmentation strategies to maximize marketing effectiveness. The dual implementation of ML in these domains demonstrates significant potential in improving both data security and personalized marketing outcomes. Experimental results indicate enhanced firewall accuracy and a refined segmentation process, suggesting that the proposed ML model provides a comprehensive solution for the challenges posed by big data in cybersecurity and market segmentation. s. Keywords Machine Learning; Firewall Decision; Reinforcement Learning; Market Segmentation; Big Data

Progressive de-preference task-specific processing for generalizable person re-identification

Recently, domain generalization (DG) person re-identification (ReID) has attracted attention. Existing DG person ReID methods train on mixed datasets containing all source domains. However, these mixed datasets have huge inter-domain differences because of varying data distributions across different source domains. Such differences hinder models from learning domain-invariant representations, affecting generalization on unseen domains. To address this issue, we propose a progressive de-preference task-specific processing network (PDTP-Net) for DG person ReID. Initially, we design a progressive de-preference domain segmentation strategy to mitigate inter-domain differences by dividing multiple source domains into different phases, each comprising several training tasks. We then design a global and task-specific processing module that enhances extraction of domain-invariant features by integrating statistical information from other source domains. Finally, we design a multi-granularity attention module and a group-aware batch normalization strategy to ensure the features are more discriminative and better suited for person ReID tasks. The proposed model is validated using three DG person ReID experimental protocols: Protocol-1, Protocol-2, and leave-one-out experiments. On Protocol-1, the model improves mean average precision (mAP) and Rank-1 accuracy on all datasets by an average of 0.7% and 0.3%, respectively. On Protocol-2, the model improves mAP and Rank-1 accuracy on all datasets by an average of 2.525% and 2.725%, respectively. On the leave-one-out experiments, the model improves mAP and Rank-1 accuracy on all tasks by an average of 0.65% and 0.18%, respectively. The results on several popular datasets suggest that the model achieves state-of-the-art performance in DG person ReID.

Preferences of Individuals With Obesity for Online Medical Consultation in Different Demand Scenarios: Discrete Choice Experiments.

Obesity is a unique chronic disease, with China having the largest number of people living with overweight and obesity in the world. There has been little research from the demand perspective for online medical consultation (OMC) by individuals living with obesity. With the growing demand for obesity OMC, especially due to the emergence of new pharmacotherapies, such as glucagon-like peptide-1 receptor agonists, individuals living with obesity are seeking both advice on obesity management and the prescription of obesity drugs. Therefore, our demand scenarios defined 2 OMC motivations to manage obesity: "For-Drugs" use and "For-Advice" use. This study aims to assess and compare the preferences for For-Drugs and For-Advice OMC among individuals living with obesity in China. Following the International Society for Pharmacoeconomics and Outcomes Research's checklist and comprising 400 participants assigned to the For-Drugs scenario and 400 to the For-Advice scenario, the For-Drugs and For-Advice preferences were estimated through discrete choice experiments. The groups in the 2 scenarios followed a similar distribution, and the 2 different demand scenarios shared the same discrete choice experiment design, comprising 16 choice sets with 6 representative attributes. Mixed logit modeling was used to estimate the willingness to pay and relative importance scores. Doctors with well-known and general expert titles, versus ordinary doctors; doctors from high-level, provincial, tertiary, and municipal hospitals, versus lower-level county hospitals; less waiting time; and lower OMC fees were preferred in both the For-Drugs and For-Advice scenarios. The differences between the 2 scenarios lay in the consultation format, consultation duration, and the relative importance of consultation duration versus waiting time. The For-Advice group preferred telephone consultations, while the For-Drugs group did not; the For-Drugs group preferred longer consultation duration (β=.029), while the For-Advice group preferred shorter consultation duration (β=-.030); and the For-Drugs group rated consultation duration higher than waiting time, while the For-Advice group rated the waiting time as more important than consultation duration. Combined with our qualitative research, the differences can be explained by the different consultation needs in the 2 scenarios, where longer patient consultations were preferred by the For-Drugs patients who sought detailed advice on drug side effects, while quick and direct responses were preferred by the For-Advice participants. By revealing user preferences on costs, doctors' titles and hospital level, wait time, and consultation duration and format, our research informs OMC platforms, OMC regulators, and doctors on market segmentation and service differentiation strategies.

Root segmentation of horticultural plants in X-Ray CT images by integrating 2D instance segmentation with 3D point cloud clustering

X-ray computed tomography (CT) is a powerful tool for in situ plant root system architecture (RSA) characterization. Accurate root segmentation from CT images is integral to studying RSA. Research studies on segmenting roots from CT images have been mainly limited to image processing-based approaches which may require parameter tuning and often lack common segmentation metrics, e.g., Dice and IoU. A recent deep learning approach utilizes a volumetric encoder-decoder network to achieve a high Dice score and IoU. However, training a volumetric model is dependent on the availability of fully annotated scans of the growing medium column, obtaining which can be time-consuming, tedious, and resource intensive. In this study, an efficient method using deep learning-based instance segmentation in conjunction with density-based spatial clustering of applications with noise (DBSCAN)-based filtering was developed and evaluated for two horticultural plant species. A pretrained Mask R-CNN model was fine-tuned on images selected along different axes of the three-dimensional scans to identify the best view selection strategy for volumetric root segmentation. DBSCAN was used to filter noise from the volumetric segmentation with an automated parameter tuning technique. The proposed method was evaluated on scans of poinsettias and onions and achieved best average scores of 0.831, 0.839, 0.834, and 0.718 for Precision, Recall, Dice, and IoU, respectively. Further experiments showed reducing the training data to 1 % did not significantly impact the segmentation accuracy. Therefore, the proposed method has promising potential to facilitate RSA analysis with its high utility.

PromptCNER: A Segmentation-based Method for Few-shot Chinese NER with Prompt-tuning

Recognizing Chinese entities in low-resource settings is a challenging but promising task, which extracts structured pre-defined entities and corresponding types from unstructured text. Compared with the prosperous Named Entity Recognition (NER) methods for Indo-European languages, such as English, the research on Chinese NER is still in its infancy. The main obstacles to the development of Chinese NER methods include the ambiguity of Chinese entity boundary recognition and limited data resources. To address these issues, in this paper, a word-segmentation-based model is present for few-shot Chinese NER. First, we enumerate all possible candidate entity spans on the character level for accurate entity boundary identification with the proposed word segmentation and combination strategy. Then, one kind of question-answer-based prompt template loaded with the candidate entity spans is proposed to cast entity extraction into the masked token prediction task, for dealing with the low-data problem by taking full advantage of the generality and transferability of the pre-trained language model. The extensive experimental results show that our method outperforms the state-of-the-art baselines in low-data settings and also achieves comparable performance in full-data settings.

Marine vibrator using electromagnetic acceleration

Abstract Optimizing the low-frequency performance of the vibrator is an important direction for the development of marine vibrators. In order to solve the problems of high resonance frequency, small low-frequency displacement and difficulty in generating low-frequency signals of marine vibrators, this study proposed a strategy of high-frequency and low-frequency distributed vibration. In the low-frequency part, electromagnetic acceleration is innovatively combined with the vibrator, and the Ansys Maxwell finite element simulation software is used for analysis. In the high-frequency part, the traditional moving coil vibrator structure is used, and experimental verification is carried out in the anechoic tank. The simulation results show that the low-frequency part of the marine vibrator using electromagnetic acceleration can achieve low-frequency vibration, and the vibration is still relatively stable. The experimental results of the anechoic tank show that within the test frequency band, the sound source level generated meets the requirements of seismic exploration for high-frequency vibrators. This study uses the frequency segmentation strategy to improve the overall working efficiency of the vibrator and provides new ideas for the design of marine vibrators.

The impact of multi-class information decoupling in latent space on skin lesion segmentation

Noise, out-of-distribution (OOD) challenges, and boundary ambiguity are not only challenges in skin disease segmentation, but also difficulties in the field of medical image segmentation. Although various medical image segmentation networks have emerged, there are certain limitations in addressing these issues because previous research has neglected the expression of medical image features in latent space. In this article, we study the relationship between latent space information and medical image segmentation. We demonstrate that the decoupling of multi-class information in latent space is closely related to the accuracy of medical image segmentation. Therefore, this study proposes a new segmentation scheme - Contextual directional decoupling network (CodeNet), which aims to enhance feature representation by decoupling multi-class information in latent space, enabling the model to successfully address noise, artifacts, OOD challenges, and boundary ambiguity. Comprehensive experiments on four public datasets and one private dataset show that our proposed CodeNet is superior to other state-of-the-art models and achieves good performance on multiple commonly used metrics. This demonstrates the effectiveness of our method in skin lesion segmentation.

Engineering Premium Customer Acquisition: A Technical Framework for Value-Based Bidding Implementation

This technical article presents a comprehensive analysis of Value-Based Bidding (VBB) implementation frameworks and their impact on digital advertising performance. Through examination of data from 1,000 e-commerce campaigns encompassing 5 million customer transactions and $250 million in ad spend during 2023-2024, we demonstrate the effectiveness of VBB in premium customer acquisition. The article establishes a novel technical framework for VBB implementation, incorporating real-time data processing of over 1 million customer interaction points per second. Key findings reveal significant improvements across critical metrics: 92% attribution accuracy (a 14% increase), 85% cross-device matching success rate, and 73% improvement in offline conversion capture. The implementation of sophisticated customer segmentation strategies resulted in ROI improvements of 185% for high-value segments and 125% for medium-value segments. Furthermore, the article introduces advanced optimization algorithms that achieved a 23% reduction in customer acquisition costs while improving bid efficiency scores to 0.92. These findings provide a technical blueprint for organizations seeking to enhance their digital advertising effectiveness through value-based methodologies Value-Based Bidding (VBB) represents an advanced approach to digital marketing that focuses on maximizing return on investment. The system analyzes customer behavior and value to make smart decisions about advertising spend. Key performance indicators like Return on Ad Spend (ROAS – how much revenue you generate for each advertising dollar spent) and Customer Acquisition Cost (CAC – the cost to acquire a new customer) help measure success. The data shows impressive improvements, with ROAS increasing by 156% and CAC reducing by 23%, meaning more efficient spending and better results.

TOLGAN: An End-To-End Framework for Producing Traditional Orient Landscape

We present TOLGAN that generates traditional oriental landscape (TOL) image from a map that specifies the locations and shapes of the elements composing TOL. Users can create a TOL map by using a user interface or a segmentation scheme from a photograph. We design the generator of TOLGAN as a series of decoding layers where the map is applied between the layers. The generated TOL image is further enhanced through an AdaIN architecture. The discriminator of TOLGAN processes a generated image and its groundtruth TOL artwork image. TOLGAN is trained through a dataset composed of paired TOL artwork images and their TOL maps. We present a tool through which users can produce a TOL map by specifying and organizing the elements of TOL artworks. TOLGAN successfully generates a series of TOL images from the TOL map. We evaluate our approach using a quantitative way by estimating FID and ArtFID scores and a qualitative way by executing two user studies. Through these studies, we prove the excellence of our approach by comparing our results with those from several important existing works.

Development of age-specific population-based paediatric computational phantoms for image-based data mining and other radiotherapy applications

Objective.Computational anatomical models have many applications in paediatric radiotherapy. Age-specific computational anatomical models were historically developed to represent average and/or healthy individuals, where cancer patients may present with anatomical variations caused by the disease and/or treatment effects. We developed RT-PAL, a library of computational age-specific voxelized anatomical models tailored to represent the paediatric radiotherapy population.Approach.Data from patients undergoing craniospinal irradiation (CSI) were used (n = 74, median age 7.3y, range: 1-17y). The RT-PAL phantoms were generated using groupwise deformable image registration to spatially normalize and average a sub-set of twenty clinical CTs and contours (n = 74, median age 7.7y, range: 3-14 y). To assess their anatomical and age-dependency plausibility, the RT-PAL models were compared against clinical cancer patient data and two healthy population based libraries of phantoms: the International Commission on Radiological Protection (ICRP) pediatric reference computational phantoms (n = 8, median age 7.5y, range: 1-15y) and a range of 4D paediatric extended cardiac torso (XCAT) phantoms (n = 75, median age 9.1y, range: 1-18y). For each dataset, nineteen organs were segmented on all age models to determine their volume. Each set was evaluated through a linear fit of organ volume with age, where comparisons were made relative to the linear fit of the clinical data.Main Results.Overall good anatomical plausibility was found for the RT-PAL phantoms. The age-dependency reported was comparable to both the clinical data and other phantoms, demonstrating their efficacy as a library of age-specific phantoms. Larger discrepancies with the clinical, ICRP and XCAT organ data were attributable to differences in organ filling, segmentation strategy and age distribution of the datasets, limitations of RT-PAL generation methodology, and/or possible anatomical differences between healthy and cancer populations.Significance.The RT-PAL models showed potential in representing the paediatric radiotherapy cohort, who are most likely to benefit from dedicated, age-specific anatomical phantoms.

A three-classification model for identifying migraine with right-to-left shunt using lateralization of functional connectivity and brain network topology: a resting-state fMRI study.

Right-to-left shunting has been significantly associated with migraine, although the neural mechanisms remain complex and not fully elucidated. The aim of this study was to investigate the variability of brain asymmetry in individuals with migraine with right-to-left shunting, migraine without right-to-left shunting and normal controls using resting-state fMRI technology and to construct a three-classification model. Firstly, asymmetries in functional connectivity and brain network topology were quantified to laterality indices. Secondly, the laterality indices were employed to construct a three-classification model using decision tree and random forest algorithms. Ultimately, through a feature score analysis, the key brain regions that contributed significantly to the classification were extracted, and the associations between these brain regions and clinical features were investigated. Our experimental results showed that the initial classification accuracy reached 0.8961. Subsequently, validation using an independent sample set resulted in a classification accuracy of 0.8874. Further, after expanding the samples by the segmentation strategy, the classification accuracies were improved to 0.9103 and 0.9099. Additionally, the third sample set yielded a classification accuracy of 0.8745. Finally, 9 pivotal brain regions were identified and distributed in the default network, the control network, the visual network, the limbic network, the somatomotor network and the salience/ventral attention network. The results revealed distinct lateralization features in the brains of the three groups, which were closely linked to migraine and right-to-left shunting symptoms and could serve as potential imaging biomarkers for clinical diagnosis. Our findings enhanced our understanding of migraine and right-to-left shunting mechanisms and offered insights into assisting clinical diagnosis.

Data augmentation strategies for semi-supervised medical image segmentation

Exploiting unlabeled and labeled data augmentations has become considerably important for semi-supervised medical image segmentation tasks. However, existing data augmentation methods, such as Cut-mix and generative models, typically dependent on consistency regularization or ignore data correlation between slices. To address cognitive biases problems, we propose two novel data augmentation strategies and a Dual Attention-guided Consistency network (DACNet) to improve semi-supervised medical image segmentation performance significantly. For labeled data augmentation, we randomly crop and stitch annotated data rather than unlabeled data to create mixed annotated data, which breaks the anatomical structures and introduces voxel-level uncertainty in limited annotated data. For unlabeled data augmentation, we combine the diffusion model with the Laplacian pyramid fusion strategy to generate unlabeled data with higher slice correlation. To enhance the decoders to learn different semantic but discriminative features, we propose the DACNet to achieve structural differentiation by introducing spatial and channel attention into the decoders. Extensive experiments are conducted to show the effectiveness and generalization of our approach. Specifically, our proposed labeled and unlabeled data augmentation strategies improved accuracy by 0.3% to 16.49% and 0.22% to 1.72%, respectively, when compared with various state-of-the-art semi-supervised methods. Furthermore, our DACNet outperforms existing methods on three medical datasets (91.72% dice score with 20% labeled data on the LA dataset). Source code will be publicly available at https://github.com/Oubit1/DACNet.

Identification of asymmetrical abnormalities in functional connectivity and brain network topology for migraine sufferers: A preliminary study based on resting-state fMRI data

Research on the neural mechanisms underlying brain asymmetry in patients with migraine patients using fMRI is insufficient. This study proposed using lateralized algorithms for functional connectivity and brain network topology and investigated changes in their lateralization in patients with migraine. In study 1, laterality indices of functional connectivity (LFunctionCorr) and brain network topological properties (LBetweennessCentrality, LDegree, and LStrength) were defined. Differences between migraineurs and normal subjects were compared at whole-brain, half-brain, and region levels. In study 2, laterality indices were used to classify migraine and were validated using independent samples and the segment method for repeatability. In study 3, abnormal brain regions related to migraine were extracted based on the classification results and differences analysis. Study 1 found no significant differences related to in for migraine at the whole-brain level; however, significant differences were identified at the half-brain level for the hemispheric lateralization of the LFunctionCorr, while 11 significantly different brain regions were also identified at the brain region level. Furthermore, the classification accuracy in study 2 was 0.9366. With repeated validation, the accuracy reached 0.8561. Furthermore, after extending the samples according to the segmentation strategy, the classification accuracies were improved to 0.9408 and 0.8585. Study 3 identified 10 crucial brain regions with asymmetrical specificity based on laterality indices distributed across the visual network, the frontoparietal control network, the default mode network, the salience/ventral attention network and the limbic system. The results revealed novel insights and avenues for research into the mechanisms of migraine asymmetry and showed that the laterality indices could be used as a potential diagnostic imaging marker for migraine.

Analysis of Marketing Strategies in Increasing Sales of Pesticide Products

Agriculture is a very important sector in Indonesia, because it has natural resources (SDA) and Human Resources (HR). Based on researchers' observations that have been carried out at UD. Makmur Tani uncovered problems involving many similar, tight competing companies with limited pesticide products and inappropriate marketing strategies. This research aims to analyze the marketing strategy implemented by UD. Makmur Tani in an effort to increase sales of pesticide products. The main focus of the research is on the three main indicators of marketing strategy, namely segmentation, targeting and positioning. Based on this explanation, the type of research used in this research is qualitative research, which is because it is not in the form of numbers or numbers so it only takes the form of statements or sentences. The research results show that UD. Makmur Tani has implemented a market segmentation strategy based on geography and farmer demographics. In terms of targeting, the company focuses on farmers in certain regions. The positioning strategy implemented is by positioning certain products. Further analysis revealed that implementation of this strategy has contributed to increased sales of pesticide products. However, there are still several obstacles in its implementation, especially related to market competition and changes in consumer preferences.