Numerous Items Research Articles

Correlation-aware Cross-modal Attention Network for Fashion Compatibility Modeling in UGC Systems

Empowered by the continuous integration of social multimedia and artificial intelligence, the application scenarios of information retrieval (IR) progressively tend to be diversified and personalized. Currently, User-Generated Content (UGC) systems have great potential to handle the interactions between large-scale users and massive media contents. As an emerging multimedia IR, Fashion Compatibility Modeling (FCM) aims to predict the matching degree of each given outfit and provide complementary item recommendation for user queries. Although existing studies attempt to explore the FCM task from a multimodal perspective with promising progress, they still fail to fully leverage the interactions between multimodal information or ignore the item-item contextual connectivities of intra-outfit. In this paper, a novel fashion compatibility modeling scheme is proposed based on Correlation-aware Cross-modal Attention Network. To better tackle these issues, our work mainly focuses on enhancing comprehensive multimodal representations of fashion items by integrating the cross-modal collaborative contents and uncovering the contextual correlations. Since the multimodal information of fashion items can deliver various semantic clues from multiple aspects, a modality-driven collaborative learning module is presented to explicitly model the interactions of modal consistency and complementarity via a co-attention mechanism. Considering the rich connections among numerous items in each outfit as contextual cues, a correlation-aware information aggregation module is further designed to adaptively capture significant intra-correlations of item-item for characterizing the content-aware outfit representations. Experiments conducted on two real-world fashion datasets demonstrate the superiority of our approach over state-of-the-art methods.

New find of Roman military equipment of the period of the Roman–Bosporan war of 45–49 AD from the Eastern Crimea

The Artezian fortified settlement in the Azov Sea coast of Eastern Crimea perished in a strong fire at the beginning of the Roman–Bosporan war in 46/47 AD. In the homogeneous fire layer, along with numerous items of jewellery, silver, bronze and glass vessels, a heavily burned out round bronze plaque, 7.7–7.8 cm in diameter with a hole in the centre was found. The plaque is decorated along the edge with a figural frieze, depicting two pairs of animals opposing each other: ‘dog–bull’, ‘dog–wild boar’. Besides two animals are running after each other: a lion and a roe deer. The decoration of the plaque from Artezian finds parallels among plaques from the military camps along the limes of Lower and Upper Rhine and Danube. Objects similar in shape depicting animals in circular friezes are also known in Dacia and in the South-Western Crimea. The parallels to the images of the plaque and options of interpreting the function of the piece are discussed. The combination of pairs of opposing animals and animals running after each other finds parallels only on the belt plaques from Asciburgium and Magdalensberg. Thus, there are reasons to consider the disc from Artezian as an element of Roman military equipment of the first half of the 1st century AD.

Gluten-Free Muffin: Effect of Composite Flours (Rice, Pumpkin and Unripe Banana) on The Physicochemical Properties and Sensory Attributes

Muffins are popular breakfast or snack items and are enjoyed in various cultures around the world. It is typically sweet and can come in various flavours such as blueberry, chocolate chip or banana nut. It is one among numerous baked items frequently crafted using wheat flour. However, individuals with gluten-related diseases such as celiac disorder and gluten intolerance are unable to consume wheat flour. In this research, gluten-free muffins made with a composite flour of rice, pumpkin and unripe banana with different ratios F1 (1:1:1), F2 (3:2:1), F3 (2:1:3) and F4 (1:3:2) were applied. The gluten-free muffins prepared with F3 (2 rice: 1 pumpkin: 3 unripe banana) composite flour showed the highest values of springiness and chewiness among all the samples. The gluten-free muffins using F2 (3 rice: 2 pumpkin: 1 unripe banana) composite flours were the highest for lightness and b* yellowness values. In addition, these muffins also obtained the highest percentages for ash and crude fiber contents. The 9-point scale hedonic test showed that consumers' preferences for gluten-free muffins with a ratio of 2 rice: 1 pumpkin: 3 unripe banana flours (F3) were the highest in scores as compared to the other gluten-free muffins. Thus, the study suggested that F3 which contains 2 rice: 1 pumpkin: 3 unripe banana flours was selected as the best formulation to make gluten-free muffins.

How Do Household Coping Strategies Evolve With Increased Food Insecurity? An Examination of Nigeria's Food Price Shock of 2015–2018

ABSTRACTFaced with a significant devaluation of its currency and a surge in food prices, the Nigerian government prohibited the use of foreign currency for food imports. This essentially blocked the importation of numerous food items under the guise of stimulating the domestic output of these staples. Consequently, food prices in Nigeria increased despite a global decline in food prices, and the incidence and severity of food insecurity escalated. This study examines the changes in the types and severity of coping mechanisms for food insecurity resulting from the food price shock caused by the oil price crash, currency devaluation, and restrictions on foreign exchange. Nigeria's General Household Survey Panel data from 2012 and 2015, during periods of high oil prices, is compared with data from 2018 when oil prices had remained low, the currency had been devalued, and the treasury had been depleted. Alongside detailed descriptive statistics, logistic and hurdle regressions are employed for statistical analysis. Findings indicate a rise in the percentage of Nigerian households grappling with food insecurity from 2015 to 2018. During this period, 68.7% of households resorted to at least one coping mechanism, 31.8% adopted six or more coping strategies, and 43.2% resorted to severe coping strategies. The issue stems not primarily from natural disasters or conflicts but from a failure in macroeconomic and agricultural economic policies. Our findings confirm that these policies come at great cost, particularly to female‐headed households, single‐parent households, households headed by elderly people, and other vulnerable populations, pushing them deeper into food insecurity.

Assessment of multi-professional primary healthcare center quality by patients with multimorbidity

BackgroundThe main aim of this study was to build an item bank for assessing the care quality of multi-professional healthcare centers (MPHCC) from the perspective of patients with multimorbidity. This study was part of the QUALSOPRIM (QUALité des SOins PRIMaires; primary healthcare quality) research project to create a psychometrically robust self-administered questionnaire to assess healthcare quality.MethodsFirst, twelve experts built an item bank using data from a previous qualitative work and a systematic literature review. Second, the validity of each item was assessed in a sample of patients. Adult patients with multimorbidity were recruited from six French MPHCC. Items were assessed based on ceiling effects, the level of missing or neutral responses and patient feedback. Patient feedback was recorded after the item bank completion. Based on results, items were validated, improved, or removed during expert meetings. In case of disagreement the Delphi method was used to reach consensus.ResultsThe study sample included 209 outpatients. The most frequent medical conditions were cardiovascular risk factors, cardiovascular diseases and rheumatological conditions. In total, a bank of 109 items classified in nine domains was built. The validity assessment led to the removal of 34 items. Retained items explored a variety of topics related to care quality: availability, accessibility, premises’ layout and building, technical care, expertise, organization, relationships with caregivers and communication, involvement and personal relationships.ConclusionsThis study allowed cross-validation of a bank of 75 items, leading to a complete picture of the patient perception of care quality items. Overall, patients were generally satisfied with their care at the MPHCC. Nonetheless, there were still numerous items on subjects for which patients’ satisfaction could be improved.

Identifying the drivers of overall rating of cancer care: Insights from the second wave of the Swiss Cancer Patient Experiences study.

Patient experience surveys gather information on various aspects of care via numerous survey items. Identifying the most critical areas of patient experience to prioritize for quality care improvement can be challenging. The objective of this study was to determine which care experience items are the drivers influencing patients' overall rating of cancer care. Data from 2750 adult patients with cancer from the second wave of the Swiss Cancer Patient Experiences study were analyzed. This cross-sectional survey was conducted in eight Swiss hospitals from September 2021 to February 2022. Stepwise logistic regression examined the relationship between overall care rating and 29 patient experience items covering different patient-centered care dimensions while adjusting for sociodemographic and health variables. Overall, patients rated their cancer care experience at 8.9 out of 10. Stepwise regression identified seven drivers contributing to overall care rating. The strongest drivers were "professionals worked well together" (odds ratio [OR],4.81) and "tests were not repeated" (OR,2.09) from the coordination and integration dimension, "offered support for symptoms during treatment" (OR,2.11) from the physical comfort dimension, followed by "hospital staff ensured available home support" (OR,1.99), "offered to see health professional for concerns" (OR,1.91), "treatment options were explained" (OR,1.75), and "involved in treatment decisions as desired" (OR,1.68). This study evaluated the care experiences of patients with cancer with a comprehensive tool that identified seven key factors independently associated with overall care rating. By concentrating on these areas, hospitals can not only improve the patient care experience but also efficiently allocate resources to quality improvement initiatives.

Optimized Deep LSTM-Based Multi-Object Tracking with Occlusion Handling Mechanism

The multi-object tracking is a basic computer vision process having a huge class of real-life tools that range from monitoring of medical video to surveillance. The goal of tracking numerous items is to place numerous objects in a scene, handle their identities throughout time, and construct trajectories for analysis. However, this is a complex task, because of certain issues like occlusions, complicated object dynamics, and variations in the appearance of objects. In this research, a new technique named TPRO-based Deep LSTM is developed for tracking multi-object with occlusion handling. Here, the videos are considered as input wherein the extraction of frames is done from each video. Each frame undergoes pre-processing with filtering to eliminate noise from frames. By using a sparse Fuzzy c-Means (FCM) and Local Optimal-Oriented Pattern (LOOP) features, the localization of objects is done. Moreover, the visual and spatial trackings are considered for hybrid tracking. The second derivative model and neighborhood search model are used to perform visual tracking. Then the occlusion handling is performed. Concurrently, with the use of Deep Long Short-Term Memory (Deep LSTM) the spatial tracking is performed and the Taylor Poor Rich Optimization (TPRO) algorithm assigns the weight and bias of the Deep LSTM. The TPRO is obtained by the unification of the Taylor series along with the Poor and Rich Optimization algorithm. By combining visual and spatial tracking, the final tracked output is generated. The devised method achieves a performance with the highest value of 88.9% for Multiple Object Tracking Precision (MOTP), smallest tracking distance (TD) of 4.185, average MOTP of 0.889, average TD of 4.201, and highest tracking number (TN) of 14.

The Evolution of Domestic Abuse as a Process (DAP) Model: An Initial Statement

A new model of intimate partner violence, the Domestic Abuse Process (DAP) model, is presented to address how domestic abuse emerges, evolves, and escalates in a romantic relationship over time. A review of the relevant literature on intimate partner violence, including studies examining the role of resources, relationship goals and means for achieving these goals, and relationship stressors is conducted. Important theories such as symbolic interactionism, strain, intergenerational transmission of violence, and the process model of family violence are also reviewed and discussed within the context of domestic abuse. A short discussion of how the proposed model could be empirically tested using a survey instrument containing numerous items that are administered to respondent couples is provided. Follow-up interviews with respondent couples would be used to clarify survey responses and to obtain more detailed insights into how abuse entered and intensified in respondent relationships. Both quantitative and qualitative analyses would be performed on the subsequent data to glean important factors and patterns empirically involved in the process. The model provides additional insights into intimate partner violence and abuse that could inform treatment practices and policy.

Non-autoregressive personalized bundle generation

The personalized bundle generation problem, which aims to create a preferred bundle for user from numerous candidate items, receives increasing attention in recommendation. However, existing works ignore the order-invariant nature of the bundle and adopt sequential modeling methods as the solution, which might introduce inductive bias and cause a large latency in prediction. To address this problem, we propose to perform the bundle generation via non-autoregressive mechanism and design a novel encoder–decoder framework named BundleNAT, which can effectively output the targeted bundle in one-shot without relying on any inherent order. In detail, instead of learning sequential dependency, we propose to adopt pre-training techniques and graph neural network to fully embed user-based preference and item-based compatibility information, and use a self-attention based encoder to further extract global dependency pattern. We then design a permutation-equivariant decoding architecture that is able to directly output the desired bundle in a one-shot manner. Experiments on three real-world datasets from Youshu and Netease show the proposed BundleNAT significantly outperforms the current state-of-the-art methods in average by up to 35.92%, 10.97% and 23.67% absolute improvements in Precision, Precision+, and Recall, respectively.

Kurgans of Gazanbulag

This article presents the results of rescue archaeological excavations carried out in November 2015 — January 2016 (following the program of archaeological research in new building sites, within the framework of the South Caucasus Pipeline Expansion project) near the Gazanbulag River, in the Borsunli kurgan cemetery, and the samples of material culture of the ancient Azerbaijan population identified within the site. The surveyed area is located about one kilometer north from the village of Veyisli, on the right side of the highway leading to the district center — the city of Goranboy (Goranboy district, the Republic of Azerbaijan), at an altitude of 219 m.a.s.l. During the archaeological exploration work carried out in 2013, about 30 burial mounds were discovered on the territory of the Borsunlu “Camp” and near the Gazanbulag River. In 2015–2016, nine burial mounds were excavated at the “Camp” site. All these mounds had a covering consisting of medium and large stones. The space between the stone rows of mounds was filled with earth. Burial chambers were found in all of them except for kurgans 3 and 8. Despite the fact that mounds 7 and 9 had chambers and equipment, they did not contain human remains. In some mounds (Nos. 6, 7, 9) the burial chambers were located in the center of the mound covering, while in others (Nos. 1, 2, 4, and 5) on its slopes. In the burials, representative archaeological materials were revealed, which shed light on the study of religious beliefs, social status and life of ancient inhabitants of the analysed area of Azerbaijan. Samples of ceramic vessels found in the mounds are characteristic to the Khojaly-Gadabay archaeological culture in their shape and content. Apart from pottery, numerous bronze items of jewellery were found in the graves: bracelets, rings, earrings, diadems, flat buttons, headbands, beads. The discovered iron products are represented by knife blades and iron rod. It can be assumed that persons with a special high social status were interred in the Gazanbulag kurgan cemetery. Based on the type, structure, grave goods recovered, as well as the results of the radiocarbon analysis, the analysed burial mounds are mainly dated to the end of the Bronze Age and the begin-ning of the Early Iron Age, precisely to the 10th–9th c. BC.

Causality-aware social recommender system with network homophily informed multi-treatment confounders

Typical recommender systems utilize observed ratings of users as inputs to learn their preferences and aim to output recommendations of new items that users will like by predicting their potential ratings. The real world is driven by causality given that whether or not a user is made exposed to the item may significantly affect the rating. While some recent methods have taken a causal view to mitigate the confounding bias in observed rating data, few have recognized recommendation as a multiple causal inference problem that concerns numerous items simultaneously in practice. By framing the recommendation as a multiple causal inference problem, this paper develops a causality-aware social recommender that incorporates underlying social network structures with matrix factorization methods for deconfounding in networked observational data to enhance social recommendations. Leveraging social network information, which inherently confounds with the preferences of users, is particularly crucial but not trivial for inferring unobserved confounders in social recommender systems. Considering that connected users in a social network share similar attributes, we propose to incorporate the network homophily into the matrix factorization models through regularization to better learn the latent variables. The extracted latent variables then capture the network informed multi-treatment confounders to mitigate the confounding bias and improve the rating prediction accuracy. The models are estimated through a proximal gradient-based optimization framework, which not only eases the incorporation of the network structure constraints but also improves the computational efficiency of the proposed method. Simulation and case studies are conducted to validate the proposed method.

TARGET RECOGINITION AND DETECTION USING DEEP LEARING TECHNIQUE

Object detection is a fundamental computer vision function for identifying and locating things in images or videos. Unlike image classification, object detection not only classifies the items in an image but also locates them inside the picture by constructing a bounding box around each one. Defence objects include a wide range of key assets needed for military and security activities. Tanks, armoured personnel carriers (APCs), military trucks, planes, helicopters, naval boats, and unmanned ground vehicles (UGVs) are among the types of vehicles included. Detection of these vehicles is critical for tracking troop movements, analysing battlefield dynamics, and maintaining operational preparedness. The modern defence scenario demands improved surveillance and security measures to successfully counter growing threats. This work suggests using the You Only Look Once (YOLO) method for real-time identification of numerous defence items. The project's goal is to improve security by properly detecting a variety of items, including cars, individuals, equipment, and structures, with a single deep learning model. Methodologically, a broad dataset containing photos and videos of defence items in various locations is collected and preprocessed. The YOLO algorithm is then trained on this dataset, with parameters optimised for high accuracy and recall rates. Performance evaluation include thorough testing on various datasets to determine accuracy, speed, and resilience. KEYWORDS: Target recognition, Detection, YOLO algorithm, Military applications, Flying objects, Vehicles, Sensor integration, Real-time processing, Threat detection, Situational awareness.

Ranking on user–item heterogeneous graph for Ecommerce next basket recommendations

Recommender systems have become an indispensable engine for online applications, which can help users locate the items they need among numerous other candidate items. Despite the success of general models, sequential recommender systems based on sequential patterns have garnered attention, especially in e-commerce, because customers do not necessarily purchase the same items over time. Markov chains and neural networks are the most adopted models in previous studies, but few integrated user sequential order information and user numeric rating feedback. To simultaneously capture the time-aware demands and time-invariant interests of e-commerce customers, this study proposes a unique heterogeneous graph structure to model sequential buying order and rating feedback and develops a query-based recommendation approach to predict future purchase behavior. Experiments on four different datasets show that the approach demonstrates improved performance for different metrics.

A pilot study on gamified and conventional e-quizzes reinforcing human histology among first-year medical and physiotherapy students.

The present retrospective, descriptive, and quasi-experimental study aimed to explore students' perceptions of traditional teaching combined with gamified and nongamified e-tests for postlecture reinforcement. Midterm knowledge retention and academic performance were also analyzed. The study was conducted from February 2021 to May 2022, involving a single group of first-year medical and physiotherapy students enrolled in equivalent core subjects on human histology at the University of Las Palmas de Gran Canaria (ULPGC). Lectures were supplemented with gamified Quizizz (QQ) or nongamified Moodle questionnaires (MQ) after lecture (t0) and 30 days later (t30). From 171 attendees, 162 volunteers were surveyed on their perceptions on the experience. Furthermore, 97 volunteers participated in the DOCENTIA-ULPGC survey on the students' satisfaction, and 123 participants individually answered 20 QQ and 20 MQ. Data were analyzed using the program Jamovi 2.3.24. The survey on volunteers' perception comprised 11 Likert items and 3 numerical scale items. The former showed acceptable internal consistency (ω-McDonald, 0.70) and validity (KMO, 0.58). Both types of e-questionnaires facilitated learning and motivated pre-reading contents but QQs were preferred. Reinforced lectures were rated higher than those unreinforced. Volunteers expressed higher overall satisfaction though DOCENTIA-ULPGC survey than the prepandemic control group. Average scores peaked at t0 with higher MQ rates. At t30, MQ and QQ scores were acceptable and similar. Participants' outcomes in the final exam tended to improve compared to the prepandemic control group, but without statistical significance. In summary, gamified and nongamified e-quizzes enhanced the student satisfaction and motivation and facilitated midterm knowledge retention.

Evaluation of risk factors affecting the safety of coal mine construction projects using an integrated DEMATEL-ISM approach

Purpose The purpose is to identify and evaluate the safety risk factors in the coal mine construction process.Design/methodology/approach The text mining technique was applied in the stage of safety risk factor identification. The association rules method was used to obtain associations with safety risk factors. Decision-Making Trial and Evaluation Laboratory (DEMATEL) and Interpretative Structural Modeling (ISM) were utilized to evaluate safety risk factors.Findings The results show that 18 safety risk factors are divided into 6 levels. There are 12 risk transmission paths in total. Meanwhile, unsafe behavior and equipment malfunction failure are the direct causes of accidents, and inadequate management system is the basic factor that determines the safety risk status.Research limitations/implications Due to the limitation of the computational matrix workload, this article only categorizes numerous lexical items into 18 factors. Then, the workshop relied on a limited number of experts; thus, the findings may be potentially biased. Next, the accident report lacks a universal standard for compilation, and the use of text mining technique may be further optimized. Finally, since the data are all from China, subsequent cross-country studies should be considered.Social implications The results can help China coal mine project managers to have a clear understanding of safety risks, efficiently carry out risk hazard identification work and take timely measures to cut off the path of transmission with risks identified in this study. This helps reduce the economic losses of coal mining enterprises, thus improving the safety standards of the entire coal mining industry and the national standards for coal mine safety policy formulation.Originality/value Coal mine construction projects are characterized by complexity and difficulties in construction. Current research on the identification and assessment of safety risk factors in coal mine construction is insufficient. This study combines objective and systematic research approaches. The findings contribute to the safety risk management of China coal mine construction projects by providing a basis for the development of safety measures.

Developing a measure of participant experience of trials: qualitative study and cognitive testing

Background To encourage participation in trials, people need to have a positive experience. However, researchers do not routinely measure participant experience. Our aim is to facilitate routine measurement by developing a measure that captures the participant perspective, in a way that is meaningful, acceptable and useful to trial teams and participants. Methods We conducted a focus group and 25 interviews with trial professionals and trial participants to explore how participant experiences of trials should be measured, and to identify domains and items to include in the measure. Interviewees were also asked to comment on a list of candidate domains and items informed by a previous review of the literature on participant experience measures. Interviews were analysed thematically. Candidate domains and items were incorporated into a draft measure. Cognitive testing was undertaken in two rounds to ensure the items were comprehensible and grounded in participant experience. Results Interviewees and patient and public contributors reported that standardising the measurement of participant experience of trials had the potential to improve trial experience but described issues around the timing of measurement. Cognitive testing highlighted issues with comprehension, recall and response and numerous items were removed or refined. We developed a standard and a short version of the measure for feasibility testing. Conclusions We developed a measure covering important domains of participant experience of trials, which could assist trial teams and participants to improve trial design and enhance delivery of a meaningful participant experience.

Feasibility Study of the Boston Naming Test for the Arab Population.

Introduction The Boston Naming Test (BNT) is a widely used USneuropsychological evaluation of confrontation naming for the examination of adults and children with learning disabilities and diagnosis of communication disorders, aphasia, dementia, and acquired brain injury or dysfunction. The purpose of the present study is to evaluate the practicality of the original English version of the 60-item BNT (BNT-60) on an Arab population and the need for a new adaptive Arabic version sensitive to cultural biases and to offer normative data that can serve as a reference for researchers and clinicians in the Gulf region, especially the Kingdom of Saudi Arabia (KSA). Data relating to the familiarity degree of the BNT-60 were also collected. Methods This research involved 105 randomly selected and cognitively healthy college students who were native Arabic speakers recruited in Jeddah. The Montreal Cognitive Assessment (MOCA) was administered with a cutoff score of 26. The participants were examined for naming accuracy, naming agreement, and familiarity in using theBNT-60. The data were then analyzed and compared with the findings from studies conducted in the United States. Results The BNT-60 was administered to 105 university students from the KSA, and the results were compared with the BNT-60 booklet norms (second edition). Their average performance was noticeably below the norms established by the original test standards. Compared with the participants in the USstudies, the participants made approximately 65% more errors on the items including pretzel, wreath, beaver, harmonica, acorn, stilts, harp, hammock, knocker, pelican, muzzle, unicorn, funnel, accordion, asparagus, tripod, yoke, and trellis and 25% more errors on the items including seahorse, dart, igloo, sphinx, palette, and abacus. The item "boomerang" was not compared with the USsample because of differences in the version of the BNT, but the errors in naming this item were as frequent as those in naming the other misrecognized items. The internal consistency among the items' degrees of familiarity was also very high (α = 0.966), and a significant connection (r = 0.837, P < 0.001) was observed between object familiarity and naming accuracy. The Arabic-speaking population in the KSA and English-speaking population in the United States showed very different levels of familiarity with numerous items. Conclusion The participants' familiarity with the BNT objects varied depending on their culture and impacted their naming accuracy and overall scores on the test. Accordingly, the possibility of cultural biases should be considered when administering the BNT to the population of the KSA and the possibility of making changes so that the test better reflects the Arab culture as suggested.

RESEARCH ON COTTAGE INDUSTRY: A REVIEW

Small-scale industries, also known as cottage industries, are usually defined as home-based businesses with fewer workers, who may or may not be family members. In certain cases, such as when producing goods, these workers are traditional artisans and craftsmen who have inherited their craft from their ancestors. Dress fabrics like khadi, wool, muslin, leather, silk, cotton, etc., as well as numerous valuable items like jewellery, ornaments, statues, idols, gems, and stones, as well as edible items like spices, oils, honey, etc., are among the many goods they produce. These items are in high demand both in India and abroad.

An Empirical Study on Personalized Product Recommendation Based on Cross-Border E-Commerce Customer Data Analysis

Thanks to the rapid growth of cross-border e-commerce platforms, numerous cross-border items are now available to customers. Several serious issues with cross-border e-commerce platforms related to item promotion and consumer product screening have arisen. Particular importance should be placed on studying and implementing personalized recommendation systems based on international e-commerce. In light of the quick expansion of commodities, when making individualized suggestions, traditional recommendation algorithms have had to deal with issues such as scant data, a chilly start to the market, and trouble identifying user preferences. To automatically mine the implicit and latent relationships between users and objects in recommendation systems, this study employs deep learning with nonlinear learning capabilities, which resolves the challenges of user interest mining. The weaknesses of the existing global recommendation research are emphasized, the study of conventional recommendation algorithms mixed with deep learning technology is deep factorization machine (DeepFM) and neural matrix factorization (NeuMF) models. Both models excel in recommending implicit feedback data. The DeepFM model yields the lowest loss function values, while the NeuMF model outperforms the competing models in terms of HR@20 (a commonly used indicator to measure the recall rate) and loss functions. In summary, this research addresses critical issues in cross-border e-commerce by developing personalized recommendation systems and integrating deep learning with traditional recommendation algorithms to enhance global recommendations.

The influences of upscaling furniture towards tomorrows sustainable: A case study at Universiti Malaysia Kelantan

This research delves into the sustainability practices, at Universiti Malaysia Kelantan by investigating the impact of implementing student-led furniture upcycling projects within university premises to address sustainability concerns effectively. The study meticulously explores the benefits and challenges associated with student driven initiatives for upcycling and enhancing furniture in education institutions. A significant amount of furniture labeled as beyond repair, in universities is frequently discarded unnecessarily. Upon examination though it becomes evident that numerous items exhibit slight imperfections which present a golden opportunity, for refurbishment or transformation into state of the art products. The research conducted in this study employed methodologies such as observations and interviews in addition to a survey targeting university faculty members and students along with members of the local recycling community. The primary objective is to discover approaches that leverage the creativity and ingenuity, in student projects. The study aims to enhance the university communitys dedication to responsibility and ignite a future by refurbishing furniture that seems neglected.