Details Of Components Research Articles

A multi-factor combined traffic flow prediction model with secondary decomposition and improved entropy weight method

Traffic flow (TF) prediction is vital in traffic systems. Aiming at the effect of noise on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), an improved CEEMDAN based on amplitude-aware permutation entropy (AAPE), named ICEEMDAN, is proposed. Aiming at the parameter selection problems on variational mode decomposition (VMD), VMD improved by pelican optimization algorithm (POA) is proposed, called PVMD. Aiming at the parameter selection problems of bidirectional long short-term memory (BiLSTM) and kernel extreme learning machine (KELM), BiLSTM improved by sea-horse optimizer (SHO), named SHOBiLSTM, and KELM improved by nutcracker optimizer algorithm (NOA), named NOAKELM are proposed, respectively. Since the chaotic characteristics of TF, multi-factor combined TF prediction model with ICEEMDAN, PVMD, SHOBiLSTM, NOAKELM, improved entropy weight method is proposed. First, use ICEEMDAN to decompose TF and get intrinsic mode functions (IMFs). Second, refined composite multiscale dispersion entropy (RCMDE) is used to divide IMFs into the fuzzy and detail components, fuzzy components are secondarily decomposed by PVMD, IMFs and factors are multi-factor predicted by SHOBiLSTM and NOAKELM. Finally, improved entropy weight method is proposed to weight SHOBiLSTM and NOAKELM results. TF of the UK highway proves the superiority. Experiments indicate that the proposed model is better than other nine models with RMSE, MAE, MAPE and R2 of 29.5868, 22.0431, 0.0701 and 0.9947 for TF I. The outcomes suggest this proposed model precedes nine models at 99% confidence level, providing data basis and theoretical for travel plans and traffic system.

Ro-YOLOv5: One new detector for Impurity in wheat based on Circular Smooth Label

Wheat impurity content is one of the crucial indicators for evaluating wheat quality grades and prices, serving as an essential inspection parameter for grain storage. Due to the substantial intra-class variations in the aspect ratios of wheat impurities, traditional object detection algorithms fail to consider the diverse shapes and sizes of wheat impurities in real-world scenarios, resulting in low detection accuracy and missed detections. To address those issues, a YOLOv5-based wheat impurity automatic detection method, named Ro-YOLOv5, is proposed for computed tomography (CT) images of wheat samples. This method introduces rotated detection boxes and Circular Smooth Label (CSL) to transform angle regression predictions into angle classification predictions, effectively resolving issues related to angle periodicity and boundary exchange in regression; Additionally, the GIOU loss function in YOLOv5 is replaced with the CIOU loss function, which is more suitable for wheat impurity targets, ensuring the lower loss values and stable boundary regression. When creating the impurity-containing wheat dataset, a hybrid filtering method is introduced for leveraging the damping characteristics of the S-L filter for suppressing high-frequency components in projection images, thereby mitigating oscillation phenomena; Moreover, the Blackman filter is employed for image sharpening to preserve more image detail components. Experiments results have shown that the proposed algorithm achieves a mean average precision of 88.83% on the self-made dataset, representing a 7.56% improvement over the original YOLOv5 baseline network. The average detection time is 11.6ms, meeting the performance requirements for detecting wheat impurities.

Understanding the Nature and Elements of Poem

Poetry is an effective and prosperous instructional approach for the English language. For individuals who are acquiring knowledge of the English language, it serves as an exceptional method to enhance their skills in reading, writing, speaking, and listening. Poetry is an excellent method for instructing English due to its authenticity, capacity to enable children to articulate their thoughts and emotions, its role as a remarkable cultural representative, and its ability to enhance their language proficiency. Poetry is sometimes regarded as the most intricate genre of literature, as it explores a broad spectrum of lyrical, dramatic, and narrative themes. When teaching English through poetry, teachers must consider various elements, including the students' proficiency level, the selected texts, and their teaching approach. Examining the definition of poetry and its core components in great detail is challenging, if not unachievable, due to the lack of prior exploration on the subject. Poets have characterized poetry as the harmonious manifestation that arises from the fusion of intellect and imagination. Authors have included intellectual concepts and notions into poetry, alongside the rhythmic and imaginative aspects of the belletrists.

Impact of O-acetylation on chitin oligosaccharides modulating inflammatory responses in LPS-induced RAW264.7 cells and mice

Chitin oligosaccharides have garnered significant attention due to their biological activities, particularly their immunomodulatory properties. However, O-acetylation in chemically preparing chitin oligosaccharides seems inevitable and leads to some uncertainty on the bioactivity of chitin oligosaccharides. In this study, an O-acetyl-free chitin oligosaccharides and three different O-acetylated chitin oligosaccharides with degree of polymerization ranging from 2 to 6 were prepared using ammonia hydrolysis, and their structures and detailed components were further characterized with FTIR, NMR and MS. Subsequently, the effects of O-acetylation on the immunomodulatory activity of chitin oligosaccharides were investigated in vitro and in vivo. The results suggested that the chitin oligosaccharides with O-acetylation exhibited better inflammatory inhibition than pure chitin oligosaccharides, significantly reducing the expression of inflammatory factors, such as IL-6 and iNOS, in the LPS-induced RAW264.7 macrophage. The chitin oligosaccharides with a degree of O-acetylation of 93 % was found to effectively alleviate LPS-induced endotoxemia in mice, including serum inflammation indices reduction and damage repairment of the intestinal liver, and kidney tissues.

SDRNet: Camouflaged object detection with independent reconstruction of structure and detail

The simultaneous reconstruction of structure and detail is a prevalent strategy in camouflaged object detection. However, the reconstruction features required for structure and detail exhibit disparities, a facet overlooked in existing methods. Therefore, we present a novel methodology, termed SDRNet, which employs a dual-branch approach for the independent reconstruction of structure and detail, aiming to discern camouflaged targets and their edges. Specifically, we propose a decomposition block to segregate encoded features into distinct structure and detail components. Furthermore, structure enhancement block and detail enhancement block are proposed as feature enhancement methods to boost the capacity of structure and detail information. Subsequently, the introduced structure fusion block and detail fusion block progressively amalgamate the enhanced features. Additionally, the shared feature block is designed to serve as a bridge for the interaction between structure and detail information. Experimental results demonstrate that SDRNet outperforms existing state-of-the-art methods significantly on benchmark datasets. Our code is available at https://github.com/whyandbecause/SDRNet/.

An exergy-based analysis of the effects of public incentives on the so-called “energy efficiency” of the residential sector, with emphasis on primary resource use and economics of scale

Improving building efficiency is essential for reducing energy consumption, greenhouse gas emissions, and operational costs. In OECD Countries the average share of the Residential and Commercial Sector for space conditioning accounts for 30–37% of the cumulative final energy use. The current situation is somewhat typical of post-industrialized Countries: while the technology for reducing the external thermal losses and for installing more energy-conscious devices and procedures (including real-time monitoring and better design of the enclosures) is readily available, the cost of such measures is often perceived as excessive for the private user. For this reason, some governments have resolved to launch incentivization campaigns to encourage both private and public actors to invest in building efficiency. This strategy has been successful and its large-scale application -even if enacted on a preliminary basis- led to substantial reductions of the energy load per square meter −50 to 100 kWh/(m2yr)- so that subsidies and incentives are likely to assume a major role in shaping the energy conversion market. Technologies that are deemed “more environmental benign” or “of strategic interest” will receive institutional funding to promote their implementation, the funds being allocated both to design techniques, new materials and less energivorous devices. Since the funding is usually provided in the form of tax rebates, this approach is not devoid of problems: in fact, previous campaigns at regional and national level in the primary Energy Conversion and in the Transportation Sector have resulted in monumental failures. While it is clearly in the interest of a community to enact a reduction of their final energy uses, it is also true that such incentivization plans, if not properly and carefully implemented, may constitute an economic and ecological “doping” of the market (detail price increases, material and components shortages, etc.). This paper is a follow-up of a previous study conducted in 2021–22 that proposed a rational and thermodynamic-based approach to the issue: in that paper we presented an innovative cost/benefit procedure that considers the primary exergy savings of an “energy saving” intervention and the installation/operation costs and combines them with the statistically foreseeable savings in the improvement of the building seismic class. The method is intended to serve as a possible model for future policy decisions, and it makes use of the fundamental principles of Exergy Analysis augmented by a conventional cost/benefit analysis and by basic resilience considerations. The case study analyzed in the previous paper is re-examined here in the light of some recent normative developments the Eco-Sisma-Bonus (“Superbonus”), the incentivization plan launched between 2014 and 2020 by the Italian Government.

Integrated Performance of a Modular Biomass Boiler With a Combined Heat and Power Industrial Rankine Cycle and Supplementary sCO2 Brayton Cycle

Abstract In this paper, the integrated performance of a modular biomass boiler with an existing industrial Rankine steam heat and power cycle and a supplementary supercritical-carbon dioxide (sCO2) Brayton cycle is analyzed. The aim is to leverage the high efficiency supplementary sCO2 cycle to increase net generation and energy efficiency from the existing biomass boiler. Two sCO2 heater configurations situated within the flue gas flow path are investigated, namely a single convective-dominant heater, and a dual heater configuration with a radiative and a convective heater. A quasi-steady-state 1D model was developed to simulate the integrated cycle, including detailed component characteristics for the Rankine and Brayton cycles. The model solves the mass, energy, momentum, and species balance equations. The system is analyzed for three cases: (i) the existing Rankine cycle without the sCO2 integration, (ii) with the single convective-dominant sCO2 heater configuration, and (iii) the dual sCO2 heater configuration. The results show the required rate of overfiring for the sCO2 configurations, with a 15.3% increase in fuel flowrate resulting in an additional 21.2% in net power output. The model quantifies the impact of the sCO2 heaters, with reduced heat uptakes for downstream boiler heat exchangers. Furnace water wall heat uptake increased due to overfiring, offsetting the reduced heat uptakes at downstream evaporative heat exchangers. The dual configuration has more impact on Rankine cycle operation due to the radiative sCO2 heater placement in front of the second superheater, absorbing some of the direct radiation from the furnace.

A NEW METHOD FOR MEDICAL IMAGE FUSION BASED ON GAUSSIAN BLUR FILTER AND ROBINSON COMPASS OPERATOR

Medical image fusion is a process of extracting features from multi-modal medical images and combining them into a composite image. It brings huge support in medical imaging and clinical diagnosis. However, the extraction of both structural and functional information from input MRI and PET images using multi-scale transform fusion methods poses a challenge of providing high-quality decomposition layers since during the decomposition process, images can still lose information such as blur or noise at the edges of the image. To address this limitation, we present a new method to improve the visual information fidelity of medical image fusion. Firstly, the YCbCr color space is utilized to prevent distortion when merging color and grey images. The second algorithm uses the CLAHE model, which allows the input images to have good contrast. Then, a Gaussian blur filter is employed to decompose the images into base and detail layers. The use of Gaussian blur ensures a smoothing filter of the edges. After that, the Robinson compass operator is applied to create the fusion rule of detail components. Finally, the fused base and detail layers are concatenated together to form the final composite image. The experimental results show that the proposed approach outperforms the latest methods in bringing visual information fidelity of the input images to the fused image, which is helpful in supporting doctors and radiologists in visual analysis of the medical images.

Development of a chemically disclosed serum-free medium for mouse pluripotent stem cells.

Mouse embryonic stem cells (mESCs) have been widely used as a model system to study the basic biology of pluripotency and to develop cell-based therapies. Traditionally, mESCs have been cultured in a medium supplemented with fetal bovine serum (FBS). However, serum with its inconsistent chemical composition has been problematic for reproducibility and for studying the role of specific components. While some serum-free media have been reported, these media contain commercial additives whose detailed components have not been disclosed. Recently, we developed a serum-free medium, DA-X medium, which can maintain a wide variety of adherent cancer lines. In this study, we modified the DA-X medium and established a novel serum-free condition for both naïve mESCs in which all components are chemically defined and disclosed (DA-X-modified medium for robust growth of pluripotent stem cells: DARP medium). The DARP medium fully supports the normal transcriptome and differentiation potential in teratoma and the establishment of mESCs from blastocysts that retain the developmental potential in all three germ layers, including germ cells in chimeric embryos. Utility of chemically defined DA-X medium for primed mouse epiblast stem cells (mEpiSCs) revealed that an optimal amount of cholesterol is required for the robust growth of naïve-state mESCs, but is dispensable for the maintenance of primed-state mEpiSCs. Thus, this study provides reliable and reproducible culture methods to investigate the role of specific components regulating self-renewal and pluripotency in a wide range of pluripotent states.

Geometric morphometric anatomy of the lacrimal punctum in normal population: Punctum update (PUP) study – Paper 5

BackgroundTo investigate the geometric morphological differences of the lacrimal punctum by analyzing its shape in relation to age and sex in a normal population. Methods960 high-magnification slit-lamp images were obtained from 320 puncta of normal asymptomatic Indian individuals across eight decades of life. Using advanced geometric morphometric techniques, including Elliptic Fourier Analysis and Principal Component Analysis, the intricate details of the lacrimal punctum's shape in a diverse population sample were categorized by age and sex. High-resolution images of the lacrimal punctum underwent standardization for scale and orientation, followed by precise landmark identification and coordinate data extraction. ResultsThe geometric morphometry of the lacrimal punctum shows significant changes as one ages. However, the gender differences, in isolation, without consideration of age, remain subtle and are not pronounced. Interestingly, detailed Principal Component scores analysis revealed potential sex- and age-related variations specifically for the left and right lower puncta, which warrant further investigation. These changes could reflect unique aging changes in the proximal lacrimal drainage system. ConclusionThe study is a starting point for geometric morphometric analysis of the lacrimal punctum and provides valuable insights into the punctal changes in size, orientation, and overall morphology across different age groups and between sexes. These findings highlight the significance of considering individual age-wise anatomical variations to better understand the lacrimal punctum.

Measuring Communication and Collaboration Skills in Sciences of Secondary School Students in New General Curriculum: A Case of Vietnam

Communication and collaboration are important skills for students in the 21st century. In order to develop these skills, students will interact with others in specific situations, where they will need to face a situation directly. In Vietnam, the new general education curriculum was issued by the Ministry of Education and Training in 2018. This curriculum has been developed using competency-based approach. Communication and collaboration are identified as core competencies in this curriculum, and these competencies have been proposed with detail components and criteria for students at the final stage of each education levels (e.g., primary, lower secondary and upper secondary education). However, one of the practical problems teachers and students facing is that these criteria are too general. Therefore, it is difficult for teachers and teachers to monitor and assess these competencies in specific subjects. The purpose of the present research is to propose a detailed assessment framework and to validate an instrument for assessing communication and collaboration competencies in the Science subject based on general criteria of these competencies in the general education curriculum in Vietnam. The present research used Exploratory Factor Analysis (EFA) to analyse the research data. The results show that there are three components to measure communication and collaboration competencies with 19 out of 20 indicators having good factor loadings. Reliability analysis for each factor using Cronbach’s alpha shows that each factor has internal consistency, with values ranging from .704 to .861.

Nowcasting of advance estimates of personal consumption of Services in the U.S. National Economic Accounts: Individual vs forecasting combination approach

AbstractAs part of continuing effort to research statistical methods for producing timely and accurate early estimates of national accounts statistics, this paper evaluates the ability of individual nowcasting and forecast combination techniques to reduce revisions in the first or advance estimates of U.S. quarterly personal consumption of services at the most detailed component level. At such a level, designated indicators for advance estimates are those directly relevant to the detailed components. Using the same indicators that were used in routine compilations, we show in a real time setting that nowcasting methods are able to reduce revisions in the advance estimates in over 90 percent of the detailed components, and the upper bound of the reductions reached over 60 percent. We evaluate the performances of all methods by comparing their root mean squared revisions for each component. Our study suggests that nowcasting techniques are potentially a powerful tool to reduce revisions in the early estimates in the national account statistics at the most detailed level.

Energy modeling, calibration, and validation of a small-scale greenhouse using TRNSYS

Greenhouse energy modeling is a prevalent tool for optimizing greenhouse energy consumption. However, for a model to serve its intended use, it is imperative to have a high level of confidence in the precision of its predictions. In this paper, a validated greenhouse energy model for a typical small-scale greenhouse in a cold climate is developed. The model is created using TRNSYS, a building performance simulation tool, with detailed energy modeling components and a user-defined crop model. The model is calibrated to fix uncertain parameters. A sensitivity analysis is used first to identify sensible uncertain parameters, followed by a multi-stage automated calibration. The automated calibration method uses a multi-objective genetic algorithm to adjust the uncertain parameters, calibrating the model for the measured indoor air temperature and relative humidity. The model performed well during the free-floating and ventilated stages (56 days) with a combined root mean square error (RMSE) of 1.6 °C for indoor air temperature and 8.3 % for the air relative humidity. The validation process involved assessing the applicability of the calibrated model using two additional datasets. For all the cases, comparing the simulation results with indoor environment measurements resulted in an RMSE of less than 2 °C for air temperature and less than 10 % for air relative humidity; these values compare favorably to the literature. The model achieved a 3.7 % mean relative error (MRE) in estimating monthly energy consumption for a minimally heated greenhouse. Given these results, the model is deemed sufficiently accurate and applicable for future investigations.

Updated component analysis method for naturally occurring sophorolipids from Starmerella bombicola

Sophorolipids (SLs) are promising glycolipid biosurfactants as they are easily produced and functional. SLs from microorganisms are comprised of mixtures of multiple derivatives that have different structures and properties, including well-known acidic and lactonic SL (ASLs and LSLs, respectively). In this study, we established a method for analyzing all SL derivatives in the products of Starmerella bombicola, a typical SL-producing yeast. Detailed component analyses of S. bombicola products were carried out using reversed-phase high-performance liquid chromatography and mass spectrometry. Methanol was used as the eluent as it is a good solvent for all SL derivatives. With this approach, it was possible to not only quantify the ratio of the main components of ASL, LSL, and SL glycerides but also confirm trace components such as SL mono-glyceride and bola-form SL (sophorose at both ends); notably, this is the first time these components have been isolated and identified successfully in naturally occurring SLs. In addition, our results revealed a novel SL derivative in which a fatty acid is bonded in series to the ASL, which had not been reported previously. Using the present analysis method, it was possible to easily track compositional changes in the SL components during culture. Our results showed that LSL and ASL are produced initially and that SL glycerides accumulate from the middle stage during the fermentation process.Key points• An easy and detailed component analysis method for sophorolipids (SLs) is introduced.• Multiple SL derivatives were identified different from known SLs.• A novel hydrophobic acidic SL was isolated and characterized.Graphical

A new two-stage decomposition and integrated hybrid model for short-term wind speed prediction

Accurate wind speed prediction is of essential importance for the stability and safe operation of power systems. Given the complexity of wind speed sequence, this paper proposed a new two-stage decomposition and integrated hybrid model to improve the accuracy of wind speed prediction. A two-stage decomposition method combining robust local mean decomposition (RLMD), sample entropy (SE) and variational modal decomposition (VMD) was used to decompose the wind speed signal in the data preprocessing stage. Firstly, the wind speed signal was decomposed into various components by RLMD, and the complexity of each component was calculated using the SE to classify them into random, detail component and trend component. Then, a secondary decomposition of the random component with the highest SE was performed using the VMD. In the prediction stage, two different prediction models were used for prediction depending on the smoothness of each component. Stochastic configuration networks (SCN) was used to predict the detail and trend components with relatively smoothness. Echo state network (ESN) was used to predict the components of the secondary decomposition. Finally, the actual wind speed data were compared by different prediction models, which illustrated that the prediction method proposed in this paper had good prediction accuracy and generalizability.

Efficient water recovery and power generation system based on air-cooled fuel cell with semi-closed cathode circulation mode

Air-cooled proton exchange membrane hydrogen fuel cell with on-line hydrogen production by hydrolysis has potential for portable applications due to its high volumetric power density and self-humidification. However, plenty of reserve water significantly reduces the power density of fuel cell system. Moreover, water recovery from fuel cell tail gas is difficult, because the tail gas humidity is very low due to excess cathode air as coolant. In this work, the dead-ended anode and semi-closed cathode proton exchange membrane fuel cell is proposed to achieve efficient water recovery and energy conversion via semi-closed cathode circulation mode. In this mode, cathode O2-poor tail gas is recycled as coolant instead of fresh air, which helps to enlarge the tail gas humidity by reducing the stoichiometric ratio of cathode to anode gas. The system lumped model with detailed component description is developed for optimization. >96% water production can be recycled under atmosphere temperature. The demand of fresh air is greatly reduced from 56 to 2 times of the consumption. Besides, the multi-objective optimization between water recovery and electrochemical performance shows high-efficiency water recovery of 94.70% and high energy conversion efficiency of 54.82%.

RANCANG BANGUN PURWARUPA TOILET PORTABLE BERDINDING PDLC DENGAN SISTEM SOLAR TRACKING BERBASIS ESP32

Indonesia, as an archipelagic country in the Pacific region, is vulnerable to various natural disasters such as earthquakes, tsunamis, and volcanic eruptions. In such situations, infrastructure is often damaged or inaccessible. Therefore, a research team has designed an innovative sanitation solution in the form of a portable toilet with solar tracking and PDLC walls for disaster-prone evacuation areas. This Capstone Project aims to design a portable toilet that can generate independent electrical energy to operate the entire system within the toilet. The data collection methods involve observations and testing of hardware and software components, such as PIR sensors, ultrasonic sensors, DC voltage of 25 volts, ACS712 current sensors, I2C LCD display, and testing the accuracy of command timing from the NTP server sent by ESP32 to Arduino. Referring to research [5] where the solar panel angle can be adjusted by 20° every hour using LDR sensors, the research team developed the study using an NTP program that moves every hour from 09:00 to 17:00 to maximize solar energy absorption. A 20 Wp solar panel reaches its maximum power of 16.46 watts at 11:00 AM local time, and a 12V 9Ah battery can be used for 3 hours and 10 minutes with a 3 Ah load. This portable toilet can operate automatically and be monitored via a mobile phone. Further research is recommended to include detailed electronic component analysis and the implementation of a 2-axis tracking system.

Centrifugal compressor design and cycle analysis of large-scale high temperature heat pumps using hydrocarbons

Using natural refrigerants in heat pumps, including hydrocarbons, is becoming attractive because of the tightening regulations concerning synthetic refrigerants. In the literature there is lack of studies investigating detailed component design, including compressor design when using hydrocarbons. This study investigates numerically centrifugal compressor design with hydrocarbons for large-scale high-temperature heat pumps. The compressor analysis was combined with a thermodynamic analysis of a two-stage heat pump. The effect of temperature lift and flash intercooler temperature on compressor sizing, rotational speed, efficiency, axial force, and Mach number were investigated. Generally, the use of hydrocarbons with five carbon atoms resulted in higher coefficient of performance and required lower compressor rotational speeds and larger compressor dimensions when compared to the hydrocarbons with four carbon atoms. The simulated rotational speeds were ranging from 8 krpm to 30 krpm, impeller diameters from 0.15 m to over 0.7 m and compressor efficiencies from 77% to over 85%. The use of cyclic molecules, namely cyclopentane and cyclobutene resulted in the highest heat pump coefficient of performance. Also, the flash intercooler temperature had a notable effect on the compressor design and axial force which has to be taken into account in heat pump cycle design.

Experimental Study on Pulse Electrochemical Machining of Inconel 718 By IJISRT

The properties of the Inconel 718 super alloy are used in the manufacturing of aircraft components, due to high hardness and toughness machining of such alloy by conventional machining process is difficult. To overcome this, nonconventional techniques are used, from which electrochemical machining (ECM) is good alternative. Electrochemical Machining (ECM) is a nonconventional manufacturing process widely employed in various industries due to its precision in shaping complex, detailed components. This study focuses on exploring and optimizing the key machining parameters in ECM to enhance machining efficiency and surface finish quality of Inconel 718. The research methodology involves a systematic experimental investigation, employing a series of controlled tests on an ECM machine. The controllable process parameters selected which are current, voltage and duty cycle. The aim is to comprehend the nuanced influence of these variables on material removal rate (MRR) and overcut and to investigate optimum level of process parameter. The analysis shows that the duty cycle and current are most influencing factor for controlling depth of overcut and for improving MRR, but excessive high duty cycle can be counterproductive which results in increased heat generation because continuous current flow generates heat in the electrolyte and work piece.

HRU-TNet: Hybrid Residual U-Transformer Network for diabetic retinopathy multi-lesion segmentation

The automatic segmentation of diabetic retinopathy (DR) holds significant importance for assisting physicians in diagnosis and treatment. Given the complexity, high inter-class similarity, and uncertainty of DR, it is crucial to integrate multiscale information between lesions and establish global correlations among them. To address these issues, a novel HRU-TNet (Hybrid Residual U-Transformer Network) algorithm for retinal lesion segmentation is proposed. In this framework, the network is augmented with lightweight self-attention residual U-modules (LSA-RSU) to capture high-frequency details of the lesions and global contextual information. The skip connections are then enhanced through interactive residual transformer fusion modules (IRTF) and channel-cross attention (CCA), promoting dependencies among features at different scales and filtering out interfering information to guide feature fusion and eliminate ambiguity. Additionally, a novel retinal image enhancement technique is devised, employing local wavelet transformations to capture detailed components of the retinal images, thereby enhancing the representational capacity of the segmentation network. Data augmentation is also performed to ensure network adaptability to small datasets. Comprehensive experiments conducted on the publicly available IDRID and e_ophtha datasets yielded average AUC_PR values of 0.709 and 0.451, respectively. The proposed approach demonstrated superior generalization on the DDR dataset compared to other methods mentioned in the literature. These results demonstrate that our proposed method is better suited for small retinal datasets, exhibiting improved segmentation accuracy and generalization compared to existing approaches.