Matrix Analysis Research Articles

Combined graph convolutional networks with a multi-connection pattern to identify tremor-dominant Parkinson's disease and essential tremor with resting tremor.

Essential tremor with resting tremor (rET) and tremor-dominant Parkinson's disease (tPD) share many similar clinical symptoms, leading to frequent misdiagnoses. Functional connectivity (FC) matrix analysis derived from resting-state functional MRI (Rs-fMRI) offers a promising approach for early diagnosis and for exploring FC network pathogenesis in rET and tPD. However, methods relying solely on a single connection pattern may overlook the complementary roles of different connectivity patterns, resulting in reduced diagnostic differentiation. Therefore, we propose a multi-pattern connection Graph Convolutional Network (MCGCN) method to integrate information from various connection modes, distinguishing between rET and healthy controls (HC), tPD and HC, and rET and tPD. We constructed FC matrices using three different connectivity modes for each subject and used these as inputs to the MCGCN model for disease classification. The classification performance of the model was evaluated for each connectivity mode. Subsequently, gradient-weighted class activation mapping (Grad-CAM) was used to identify the most discriminative brain regions. The important brain regions identified were primarily distributed within cerebellar-motor and non-motor cortical networks. Compared with single-pattern GCN, our proposed MCGCN model demonstrated superior classification accuracy, underscoring the advantages of integrating multiple connectivity modes. Specifically, the model achieved an average accuracy of 88.0% for distinguishing rET from HC, 88.8% for rET from tPD, and 89.6% for tPD from HC. Our findings indicate that combining graph convolutional networks with multi-connection patterns can not only effectively discriminate between tPD, rET, and HC but also enhance our understanding of the functional network mechanisms underlying rET and tPD.

Assessment of human health risks posed by toxic heavy metals in Tilapia fish (Oreochromis mossambicus) from the Cauvery River, India

Heavy metal toxicity is a serious threat to human health due to its bioaccumulation, biomagnification, and persistent nature in the environment including aquatic systems. In the recent past, heavy metal contamination in the environment has occurred due to various anthropogenic sources. The concentration of potentially toxic heavy metals was determined by Atomic Absorption Spectroscopy in Tilapia (Oreochromis mossambicus), a highly farmed and consumed fish species in southern parts of India. The mean levels of Fe were found to be higher in major organs of the fish with the highest levels in liver (Mean 1554.4 ± 1708.7 mg/kg) and lowest in the muscles (Mean 130.757 ± 33.3 mg/kg). Correlation Matrix analysis revealed relationships between the occurrence of various heavy metals in different organs of fish and indicated similar origins and chemical properties. Target hazard quotient for Cd, Co, Pb, and Cr in the Liver, Co and Cr in the Gills, and Co in Muscle were > 1 for adults, which showed a significant health risk from the combined effects of these metals. The potential health risk to humans, according to the cancer risk (CR) assessment is attributed mainly to Cd and Cr levels. Overall, moderate fish consumption is advised to limit the bioaccumulation of heavy metals over prolonged exposure and associated health risks.

Systematic bias due to mismodeling precessing binary black hole ringdown

Accurate waveform modeling is crucial for parameter estimation in gravitational wave astronomy, impacting our understanding of source properties and the testing of general relativity. The precession of orbital and spin angular momenta in binary black hole (BBH) systems with misaligned spins presents a complex challenge for gravitational waveform modeling. Current precessing BBH waveform models employ a coprecessing frame, which precesses along with the binary. In this paper, we investigate a source of bias stemming from the mismodeling of ringdown frequency in the coprecessing frame. We find that this mismodeling of the coprecessing frame ringdown frequency introduces systematic biases in parameter estimation, for high-mass systems in particular, and in the inspiral-merger-ringdown (IMR)-consistency test of general relativity. Employing the waveform model henom, we conduct an IMR-consistency test using a Fisher matrix analysis across parameter space, as well as full injected signal parameter estimation studies. Our results show that this mismodeling particularly affects BBH systems with high-mass ratios, high-spin magnitudes, and highly inclined spins. These findings suggest inconsistencies for all waveform models which do not address this issue. Published by the American Physical Society 2024

Business Strategy Planning Case Study: PT Sera Food Indonesia

This study aims to look at the position of PT Serafood Indonesia in the rotation of the food business, especially meat processed ingredients. By knowing the position of the company, it will get the right position for stakeholders to develop the company's business. This type of research is a qualitative descriptive. To collect data in this study used field observations and interviews. Resource persons in this study were 7 people consisting of the owner, general manager and managers as decision makers at PT Serafood Indonesia. This study uses a SWOT analysis from Pearce and Robinson. Data analysis used is the IFAS matrix analysis technique (Internal Factor Analysis Summary) and the EFAS matrix (External Factor Analysis Summary) and SWOT matrix analysis (Strengths, Weaknesses, Opportunities, Threats). The EFAS results get a value of 0.054 and IFAS is 0.356. In the SWOT matrix diagram, it shows that the condition of the institution is in quadrant 1. The results of the research analysis can be concluded that PT Serafood Indonesia has opportunities and strengths as well as good abilities in dealing with threats and weaknesses. To win the competition in the processed food industry, the right strategy planning for PT Serafood Indonesia is to support an aggressive growth policy with a choice of strategies are market penetration, market development and product development.

Loan Approval Prediction Improved by XGBoost Model Based on Four-Vector Optimization Algorithm

Abstract. This paper discusses an improved XGBoost model based on four-vector optimization algorithm to improve the accuracy of loan approval prediction. Through the analysis of correlation heat maps, we found that there were significant positive and negative correlations among some variables, which laid the foundation for subsequent machine learning analysis. Based on this, we compare the traditional machine learning algorithm with the improved model to evaluate its performance in loan approval forecasting. In the confusion matrix analysis of the training set, the improved XGBoost model demonstrated excellent performance, with all loan approval predictions being correct with 100% accuracy. However, the performance in the test set was slightly different, with 1,182 projects receiving correct loan approval predictions and 99 projects forecasting errors. Of these, 26 projects that should have been predicted to be "unapproved" were incorrectly labeled as "approved," while 73 projects that should have been predicted to be "approved" were incorrectly labeled as "unapproved." These results suggest that we still need to pay attention to the misjudgment of the model in practical application. By synthesizing all model evaluation indicators, we found that the improved XGBoost model based on the four-vector optimization algorithm has a higher accuracy in loan approval prediction than the traditional XGBoost model, with an increase of 1.5%. In addition, the other evaluation indicators also show a trend of significantly better than the traditional model. This study shows that the four-vector optimization algorithm can effectively improve the application effect of XGBoost model in the field of loan approval, and provide more accurate data support and decision-making basis for the financial industry. In the future, we will continue to explore the potential and application prospects of this algorithm in other fields.

Integrated Chemical and Ecotoxicological Assessment of Metal Contamination in the Andong Watershed: Identifying Key Toxicants and Ecological Risks

This study employed an integrated field monitoring approach, combining chemical analysis and ecotoxicity testing of multiple environmental matrices—water, sediment, and sediment elutriates—to comprehensively assess the environmental health of the Andong watershed, located near a Zn smelter and mining area. The primary objectives were to evaluate the extent of metal contamination, identify key toxicants contributing to ecological degradation, and trace the sources of these pollutants. Our findings revealed severe metal contamination and significant ecotoxicological effects both in proximity to and downstream from industrial sites. Specifically, Cd, Zn, and Pb were strongly linked to the smelter, while Hg, Ni, Cu, and As were predominantly associated with mining activities in the tributaries. To further assess toxicity of field-collected sediment and their elutriates, a logistic regression analysis was employed to estimate benchmark values for distinguishing between toxic and non-toxic samples, using the sum of toxic units for sediment elutriates and the mean probable effect level (PEL) quotient for sediment toxicity. These models demonstrated greater predictive accuracy than conventional benchmarks for determining toxicity thresholds. Our results highlight that integrating chemical and ecotoxicological monitoring with site-specific concentration–response relationships enhances the precision of ecological risk assessments, facilitating more accurate identification of key toxicants driving mixture toxicity in complex, pollution-impacted aquatic ecosystems.

A novel dimension reduction model based on POD and two-grid Crank–Nicolson mixed finite element methods for 3D nonlinear elastodynamic sine–Gordon problem

Earthquake, petroleum and gas extraction, and underground nuclear test all could cause nonlinear tectonic deformation. It is of great significance to effectively predict and evaluate the disasters and impacts of these geological structure deformation. In this end, a three-dimension (3D) nonlinear elastodynamic sine–Gordon model that can be used to describe nonlinear tectonic deformation including 3D displacement vector, 3 × 3 symmetric stress tensor matrix, nonlinear sin term, and singular initial value functions is first proposed. Then, a new time semi-discrete mixed Crank–Nicolson (TSDMCN) scheme for the 3D nonlinear elastodynamic sine–Gordon model is developed, and the existence, stability, and error estimates of the TSDMCN solutions are proved. Next, a new two-grid mixed finite element Crank–Nicolson (TGMFECN) method with unconditional stability for the 3D nonlinear elastodynamic sine–Gordon model is developed, and the existence, stability, and error estimates of the TGMFECN solutions are proved. Thenceforth, it is the most important thing is that a novel reduced-dimensional iterative TGMFECN (RDITGMFECN) method in matrix form is established by resorting to proper orthogonal decomposition only to lower the unknown TGMFECN solution coefficient vectors and keep TGMFECN basis functions unchanged, which can ensure that the RDITGMFECN method has the same accuracy as the usual TGMFECN method, but can greatly lower the dimension of the unknown TGMFECN solution coefficient vectors so as to mitigate calculated workload, save CPU operating-time, improve computing efficiency, and improve real-time calculating accuracy. In theory, the existence, stability, and error estimates of RDITGMFECN solutions are demonstrated by matrix analysis such that the theoretical analysis becomes very intuitive and easy to be understood by the public, which is a new attempt of theoretical analysis. In application, two numerical examples are used to simulate the 3D nonlinear tectonic deformation caused by earthquake and to verify the correctness of our theoretical results and the effectiveness of the RDITGMFECN method.

Detection of Ovarian Tumors Using TVUS Imaging and Segmentation Techniques

Ovarian most cancers remains a giant health subject due to its regularly asymptomatic development until superior stages, where treatment options are confined. Early detection is critical for enhancing affected person outcomes and survival costs. This observe proposes a comprehensive technique leveraging superior photograph processing techniques for the early detection and category of ovarian tumors the usage of trans vaginal ultrasound (TVUS) snap shots. The method starts with preprocessing steps which include median filtering to do away with noise artifacts inclusive of salt and pepper noise from ultrasound photos. Ultimately, picture enhancement techniques are applied to enhance contrast and intensity, observed through binary sample evaluation to signify texture features vital for tumor identification. Photo segmentation is performed the use of okay- manner clustering and gray degree Co-prevalence Matrix (GLCM) analysis to isolate and analyze areas of interest within the ovarian photos. A Convolutional Neural community (CNN) is then hired for correct classification of ovarian tumors as regular, benign, or malignant primarily based on the extracted functions. This approach not handiest enhances the diagnostic accuracy but also minimizes affected person publicity to ionizing radiation, making it appropriate for ordinary medical applications. The proposed methodology represents a considerable advancement within the discipline of ovarian cancer detection, presenting a non-invasive and green way to evaluate ovarian health and facilitate timely intervention. Destiny research directions include refining the set of rules’s performance with large datasets and exploring additional imaging modalities for complete ovarian fitness evaluation.

Flavonoids Mitigate Nanoplastic Stress in Ginkgo biloba.

Microplastics/nanoplastics are a top global environmental concern and have stimulated surging research into plant-nanoplastic interactions. Previous studies have examined the responses of plants to nanoplastic stress at various levels. Plant-specialized (secondary) metabolites play crucial roles in plant responses to environmental stress, whereas their roles in response to nanoplastic stress remain unknown. Here, we systematically examined the physiological and biochemical responses of Ginkgo biloba, a species with robust metabolite-driven defenses, to polystyrene nanoplastics (PSNPs). PSNPs negatively affected seedling growth and induced phytotoxicity, oxidative stress, and nuclear damage. Notably, PSNPs caused significant flavonoid accumulation, which enhances plant tolerance and detoxification against PSNP stress. To determine whether this finding is universal in plants, we subjected Arabidopsis, poplar, and tomato to PSNP stress and verified the common response of enhanced flavonoids across these species. To further confirm the role of flavonoids, we employed genetic transformation and staining techniques, validating the importance of flavonoids in mitigating excessive oxidative stress induced by NPs. Matrix analysis of transgenic plants with enhanced flavonoids further demonstrated altered downstream pathways, allocating more energy towards resilience against nanoplastic stress. Collectively, our results reveal the flavonoid multifaceted roles in enhancing plant resilience to nanoplastic stress, providing new knowledge about plant responses to nanoplastic contamination.

Aptamer-functionalized magnetic blade spray coupled with nucleic acid dye-based mass tag strategy for miniature mass spectrometry analysis of endoglin

Ambient ionization mass spectrometry (AIMS) allows rapid analysis of targets, while its overall selectivity is somewhat limited due to the lack of chromatographic separation. Recently, magnetic blade spray (MBS) has enhanced AIMS by incorporating immunomagnetic beads instead of the traditional coated blade spray (CBS) coating, thereby improving selectivity and sensitivity by targeted analyte detection and reducing background interference. In this study, an aptamer-functionalized and nucleic acid dye (GelRed)-loaded MS probe (AGMP) was developed and employed with MBS-based miniature mass spectrometer. Specifically, AGMP was assembled using aptamer-functionalized magnetic nanoparticles loaded with GelRed as mass tags for highly sensitive analysis of endoglin (CD105). For preparation of AGMP, the CD105 binding aptamer of End-A2 was first selected through three rounds of capillary electrophoresis (CE)-SELEX with an optimal affinity of 62.3 pM. After optimizing the critical parameters that affected adsorption, desorption, and ionization efficiency, this method displayed satisfactory sensitivity with detection and quantitation limits of 0.2 and 1 ng/mL, respectively, as well as reliable recoveries of 90.1–106.8% with relative standard deviations of 1.6–5.4%. Besides, the method effectively mitigated the matrix effects with a slope deviation of 10.03%, and exhibited good selectivity and environmental friendliness. Furthermore, this AGMP-based MBS strategy was successfully applied for CD105 detection in serum samples, demonstrating its potential for sensitive and on-site biomolecule analysis in complex matrices.

Individual tree mortality: Risks of climate change in the eastern Brazilian Amazon region

The mortality of trees in humid tropical forests plays a fundamental role in understanding forest development, particularly after disturbances such as those caused by logging and extreme weather events. The aim of this study was to evaluate estimates of individual tree mortality following Reduced Impact Logging (RIL) in the Eastern Brazilian Amazon at biennial intervals from 2005 to 2012. RIL is based on operations planning, personnel training, and investments in forest management, and harvesting through RIL must: (a) minimize environmental damage, (b) diminish operation cost by increasing work efficiency, and (c) reduce operational waste. A mortality model was constructed based on the estimation of three distance-independent competition-indices (DII) and five models for predicting the probability of individual tree mortality. The Kolmogorov-Smirnov statistical test was used to determine the most representative model, from which a Neural Network Autoregressive (NNAR) model was constructed to forecast mortality after RIL. Mortality data was correlated with the El Niño–Southern Oscillation (ENSO) and climate (Rainfall, Maximum, Minimum, and Average air temperature). The tested models showed similar and accurate estimates with R2 exceeding 0.90, although underestimation and overestimation trends were observed. The NNAR satisfactorily represented species mortality over the simulated years. The period from 2012 to 2014 was characterized by a Neutral and Weak El Niño event, and exhibited the highest mortality value for a 25 cm DBH (diameter at breast height), the smallest DBH class measured in this study. In the correlation matrix analysis, maximum air temperature showed the highest positive correlation with trees mortality. Despite the challenges in estimating individual tree mortality in tropical forests after selective logging, accurate estimates were achieved using traditional regression techniques and NNAR. These results can support technical and silvicultural decisions regarding forest management in the Eastern Amazon region of Brazil.

A new fourth-order compact finite difference method for solving Lane-Emden-Fowler type singular boundary value problems

We develop a novel fourth-order compact finite difference scheme to solve nonlinear singular ordinary differential equations. Such problems occur in many fields of science and engineering, such as studying the equilibrium of an isothermal gas sphere, reaction–diffusion in a spherical permeable catalyst, etc. These problems are challenging to solve because of their singularity or nonlinearity. By our proposed method, we can easily solve these complex problems without removing or modifying the singularity. To construct the new fourth-order compact difference method, Initially, we created a uniform mesh within the solution domain and developed a compact finite difference scheme. This scheme approximates the derivatives at the boundary nodal points to handle the problem’s singularity effectively. Employing a matrix analysis approach, we discussed the convergence analysis of the methods. To demonstrate its efficacy, we apply our approach to solve various real-life problems from the literature. The new method offers high-order accuracy with minimal grid points and provides better numerical results than the nonstandard finite difference method and exponential compact finite difference method.

The Strategy of Agroindustry Development of Teng-Teng Apel (A Case Study on Hilwa Nusantara Shop in Batu City)

This study is conducted by purpose of identifying company environment and analyzing the strategy for agroindustry development of Teng-Teng Apel (cake made from apple fruit) in Hilwa Nusantara Shop in Batu City. The methods of data analysis used in this study are internal and external company analysis, Internal Factor Evaluation (IFE) Matrix, External Factor Evaluation (EFE), SWOT analysis, and Quantitative Strategic Planning Matrix (QSPM) analysis. The results of the study have showed that SWOT analysis indicates IFAS score 2.84 and EFAS value 2.94. Moreover, agroindustry position of Teng-Teng Apel of Hilwa Nusantara Shop is at Quadrant One (I). Based on company position, there are three alternative strategies, 1. To increase production capacity and quality using technology, 2. To extend market in developing sales volume, and 3. To maintain relationship and trust with raw material suppliers. First becomes first priority for Hilwa Nusantara with TAS value 5.49.

The Research of the Correlation Between USD Index and S&P500

This paper investigates existence of equilibrium relationships among the USD index and S&P500 in the long term in the United States. By applying correlation matrix analysis to daily data for the 2016:07:302023:08:01 period, this paper finds that there was a slight negative correlation between the USD index and the S&P 500. Basing on the Augmented Dickey-Fuller test (ADF test), this paper shows that that the correlation between the USD index and the S&P 500 is stable while vector autoregressive model (VAR model) proving that changes in the USD index can cause changes in the S&P 500 index. Firstly, using ADF test and VAR model to investigate the relationships between the USD index and A&P500, this paper reveals not only judge the negative relationship between this two, but also studying the stability of this relationship, proving the validity to explain the changes of S&P500 by the changes of the USD index. This conclusion can act as a good judging basic for US leaders to make economic decisions such as raising or lowering interest rates.

Evaluation of focused antenatal care services quality at University of Gondar Comprehensive Specialized Hospital, Central Gondar zone, Northwest Ethiopia.

Antenatal care is the care that women receive during their pregnancy to ensure the health of the mother and her baby. The provision of information on birth preparedness in Ethiopia is still low, which implies identification of pre-existing health conditions that may affect the outcome of pregnancies was not provided. Even if the Focused Antenatal Care service was provided in our setup, maternal death was still high. In addition, as far as our search, the quality of antenatal care service in this facility has not yet been evaluated. As a result, the purpose of this study was to assess the quality of focused antenatal care services at the University of Gondar Comprehensive Specialized Hospital, Northwest Ethiopia. A mixed method case study evaluation design was employed at the University of Gondar Comprehensive Specialized Hospital from February 29 to March 29, 2020. Quantitative data was collected through exit interviews of 411 mothers who attended antenatal care follow-up and review of 422 clients' cards 2 months prior to the study period. Similarly, 35 items of resources inventory, 10 direct observations, and 12 key informant interviews were conducted. The data were entered into Epi-Data version 4.6 and exported to SPSS version 25 and it was analysed with the Evaluation judgment matrix analysis method. Qualitative data were transcribed, translated and analysed by using thematic analysis. The evaluation focused on availability, compliance, and satisfaction dimensions with 25 indicators to judge the quality of antenatal care services. The overall quality of focused antenatal care services was judged as good, based on pre-set judgment criteria (76.7%), to which availability of resources, healthcare provider's compliance with the national guideline, and maternal satisfaction contributed, 73.3, 77.75, and 78.8%, respectively. Auditory and visual privacy were practiced which enhances patient confidentiality and personal dignity. The waiting area was perceived to be satisfactory by the majority (89%) of ANC clients, but there is no separate waiting area for ANC clients. Ten (10) client/provider interactions were observed, demonstrating that all clients were counseled about pregnancy danger signs. The overall focused antenatal care services quality was relatively good, although the availability of resources was fair. Some essential drugs and medical equipment were out of stock. Therefore, the hospital had better fulfill crucial medicines and equipment for better service quality.

Mitigating Membrane Fouling in Abattoir Wastewater Treatment: Integration of Pretreatment Step with Zwitterion Modified Graphene Oxide–Polyethersulfone Composite Membranes

Composite polyethersulfone (PES) membranes containing N-aminoethyl piperazine propane sulfonate (AEPPS)-modified graphene oxide (GO) were integrated with either of the two pretreatment processes (activated carbon (AC) adsorption or polyelectrolyte coagulation) to assess their effectiveness in mitigating membrane fouling during the treatment of abattoir wastewater. The AEPPS@GO-modified membranes, as compared to the pristine PES membranes, showed improved hydrophilicity, with water uptake increasing from 72 to 118%, surface porosity increasing from 2.34 to 27%, and pure water flux (PWF) increasing from 235 to 673 L.m−2h−1. The modified membranes presented improved antifouling properties, with the flux recovery ratio (FRR) increasing from 59.5 to 93.3%. This study compared the effectiveness of the two pretreatment processes, AC, coagulation, and the integrated system (coagulation/AC-UF membrane), in the removal of natural organic matter (NOM) and improvement of abattoir wastewater’s pH, electrical conductivity, TDS, and turbidity. The integrated systems produced improved water quality in terms of pH, EC, TDS, turbidity, and organic content. The fluorescence excitation–emission matrix (FEEM) analysis exhibited almost no fluorescence peak post-treatment following organic loading removal. The quality of the water met the South African non-potable water reuse standards. The sole membrane treatment systems exhibited good fouling resistance without the pretreatment systems; however, integrating these systems can offer extended longer filtration periods, thereby assisting in cost aspects of the abattoir wastewater treatment system.

The Analysis and Compensation Experiment of Linear Feed Axis Positioning Error Based on Matrix Operation

The positioning accuracy of the linear feed axis is a key factor affecting the machining accuracy of CNC machine tools. The generation process of the positioning error of the linear feed axis is expounded. The Z axis of the vertical linear feed axis of the machining center is the research object, the positioning error analytical matrix is established, and the positioning error calculation of the Z axis of the vertical linear feed axis is completed based on the principle of solving the inhomogeneous linear equation. The positioning error detection of the vertical linear feed axis Z axis of the CNC machining center is carried out. Based on the characteristics of the error detection data, an error compensation model is constructed. , the variance of the positioning error detection point after compensation is reduced to 1.562, which meets the needs of precision machining.

New Approach to Identifying Barriers and Potentials in Peripheral and Less-Known Areas Using a Multi-Criteria Analytical Matrix

The purpose of the article is to present the author’s methodology for identifying and assessing potentials and barriers occurring in various locations related to cultural tourism. The research aimed to develop a methodology to identify barriers and potentials for tourism development in peripheral and less-known locations. The potentials and barriers identified in a given location are important determinants of the development of cultural tourism and therefore economic development in the mentioned area. The identification of development potentials and barriers refers to the existing features of a given area or place and factors that activate or limit the possibilities of its using cultural resources. The study was based on the analysis of eight case studies of destinations with interesting cultural values. The entire series of analyses addressed various aspects of these destinations. Areas of different sizes and scales were considered, including areas in transboundary regions, rural areas, historic city centres, and archaeological or industrial sites. The work presents the author’s methodology for integrating the various elements that define the features and factors of cultural tourism and establishes a framework for a strategy for its sustainable development. To achieve this, a tool in the form of a comprehensive matrix was developed to assess the situation of each pilot site. Based on this tool, the pilot sites identified key features or factors as a barrier or potential and furthermore defined their territorial scope and their impact on their chosen dominant types of tourism. Barriers and potentials were identified based on a set of 47 previously developed features and factors. During the research, 38 most important potentials and 15 barriers were identified. The tool presented in the paper is comprehensive and universal, so it can be applied to any destination.

Research and Development on an Internet Q and A Platform for Corporate Innovation and Management

This paper analyses and develops an online platform for innovation and management cooperation that benefits small and medium-sized enterprises (SMEs) through enhanced cooperation and support. Helping SMEs to adapt to market changes and promote internal improvements. With limited access to information and cutting-edge technologies, SMEs often struggle to solve identified problems. We use a web-based platform to help SMEs find problems and solutions. Through market analyses and BCG Matrix analyses we delved into the feasibility of the platform as well as developed innovative features.

Machine Learning in Agriculture: KNN-Based Classification of Fruits and Vegetables

In modern agriculture and the food industry, it is essential to classify fruits and vegetables accurately and efficiently to meet growing consumer demand and reduce post-harvest losses. Traditional manual methods are often labor-intensive and error prone, highlighting the need for automated solutions. This paper discusses the application of the k Nearest Neighbor (KNN) algorithm to fruit and vegetable recognition using image processing technology. In this study, image data sets are used for feature extraction using Directional Gradient Histogram (HOG) and dimensionality reduction using Principal Component Analysis (PCA). The accuracy of KNN model on verification set and test set reaches 97%, which proves its validity. Confusion matrix analysis and F1 score evaluation further revealed the strengths and areas of improvement of the model, particularly in distinguishing visually similar categories. The results show that the integration of artificial intelligence (especially KNN) offers great potential for the automation of agricultural classification tasks. Future studies could combine more advanced models, such as CNNS, with larger datasets to improve accuracy and robustness.