Explore the vast range of titles available.

The task of next POI recommendations has been studied extensively in recent years. However, developing a unified recommendation framework to incorporate multiple factors associated with both POIs and users remains challenging, because of the heterogeneity nature of these information. Further, effective mechanisms to smoothly handle cold-start cases are also a difficult topic. Inspired by the recent success of neural networks in many areas, in this paper, we propose a simple yet effective neural network framework, named NEXT, for next POI recommendations. NEXT is a unified framework to learn the hidden intent regarding user's next move, by incorporating different factors in a unified manner. Specifically, in NEXT, we incorporatemeta-data information, e.g., user friendship and textual descriptions of POIs, and two kinds of temporal contexts (i.e., time interval and visit time). To leverage sequential relations and geographical influence, we propose to adopt DeepWalk, a network representation learning technique, to encode such knowledge. We evaluate the effectiveness of NEXT against other state-of-the-art alternatives and neural networks based solutions. Experimental results on three publicly available datasets demonstrate that NEXT significantly outperforms baselines in real-time next POI recommendations. Further experiments show inherent ability of NEXT in handling cold-start.

Point-of-interest (POI) recommendation is a challenging problem due to different contextual information and a wide variety of human mobility patterns. Prior studies focus on recommendation that considers user travel spatiotemporal and sequential patterns behaviours. These studies do not pay attention to user personal interests, which is a significant factor for POI recommendation. Besides user interests, queuing time also plays a significant role in affecting user mobility behaviour, e.g., having to queue a long time to enter a POI might reduce visitor’s enjoyment. Recently, attention-based recurrent neural networks-based approaches show promising performance in the next POI recommendation task. However, they are limited to single head attention, which can have difficulty in finding the appropriate user mobility behaviours considering complex relationships among POI spatial distances, POI check-in time, user interests and POI queuing times. In this research work, we are the first to consider queuing time and user interest awareness factors for next POI recommendation. We demonstrate how it is non-trivial to recommend a next POI and simultaneously predict its queuing time. To solve this problem, we propose a multi-task, multi-head attention transformer model called TLR-M_UI. The model recommends the next POIs to the target users and predicts queuing time to access the POIs simultaneously by considering user mobility behaviours. The proposed model utilises POIs description-based user personal interest that can also solve the new categorical POI cold start problem. Extensive experiments on six real-world datasets show that the proposed models outperform the state-of-the-art baseline approaches in terms of precision, recall, and F1-score evaluation metrics. The model also predicts and minimizes the queuing time. For the reproducibility of the proposed model, we have publicly shared our implementation code at GitHub (https://github.com/sajalhalder/TLR-M_UI).

Point-of-interest (POI) recommendation has gained significant traction recently due to the rising trend of location-based networks. Traditional approaches rely on a centralized collection of user data. Concerning privacy protection, decentralized federated learning employs model training on each user’s device with nearby collaborative training techniques. However, existing decentralized federated recommendations suffer from two major problems: (1) Privacy risks: existing approaches expose geographical location or co-rated items information when constructing user neighborhoods. (2) Performance limitations: existing approaches adopt a simple model without incorporating auxiliary information. To solve these, we propose CA-PDBPR (category-aware privacy preserving POI recommendation using decentralized Bayesian personalized ranking) to address the above challenges. Specifically, we introduce a novel privacy-enhanced neighborhood creation method utilizing POI category preferences to calculate decentralized user similarity through secret sharing technology, ensuring a higher level of privacy. Moreover, we integrate POI category information with a refined Bayesian personalized ranking (BPR) loss function to enhance recommendation performance. Experimental evaluations conducted on real-world datasets validate the effectiveness of the CA-PDBPR model, demonstrating enhanced recommendation quality while minimizing data exposure compared with state-of-the-art alternatives.

Premature ovarian insufficiency (POI), previously known as premature ovarian failure or premature menopause, is defined as loss of ovarian function before the age of 40 years. The risk of POI before the age of 40 is 1%. Clinical symptoms develop as a result of estrogen deficiency and may include amenorrhea, oligomenorrhea, vasomotor instability (hot flushes, night sweats), sleep disturbances, vulvovaginal atrophy, altered urinary frequency, dyspareunia, low libido, and lack of energy. Most causes of POI remain undefined, however, it is estimated that anywhere from 4–30% of cases are autoimmune in origin. As the ovaries are a common target for autoimmune attacks, an autoimmune etiology of POI should always be considered, especially in the presence of anti-oocyte antibodies (AOAs), autoimmune diseases, or lymphocytic oophoritis in biopsy. POI can occur in isolation, but is often associated with other autoimmune conditions. Concordant thyroid disorders such as hypothyroidism, Hashimoto thyroiditis, and Grave’s disease are most commonly seen. Adrenal autoimmune disorders are the second most common disorders associated with POI. Among women with diabetes mellitus, POI develops in roughly 2.5%. Additionally, autoimmune-related POI can also present as part of autoimmune polyglandular syndrome (APS), a condition in which autoimmune activity causes specific endocrine organ damage. In its most common presentation (type-3), APS is associated with Hashomoto’s type thyroid antibodies and has a prevalence of 10–40%. 21OH-Antibodies in Addison’s disease (AD) can develop in association to APS-2.

Nighttime light (NTL) images have been broadly applied to extract urban built-up areas in recent years. However, the typical NTL images provided by Defense Meteorological Satellite Program/Operational Linescan System (DMSP/OLS) and National Polar-Orbiting Partnership’s Visible Infrared Imaging Radiometer Suite (NPP/VIIRS) have the drawbacks of low resolution and blooming effect, which bring difficulty for the application of them in urban built-up area extraction. Therefore, this paper proposes the POI (point of interest) and LST (land surface temperature) adjusted NTL urban index (PLANUI) to extract the urban built-up areas with high accuracy. PLANUI is the first urban index to integrate POI and NTL for urban built-up area extraction. In this paper, NPP/VIIRS and Luojia 1-01 images were introduced as the original NTL data and the vegetation adjusted NTL urban index (VANUI) was selected as the comparison item. The threshold method was utilized to extract urban built-up areas from these data. The results show that: (1) Based on the comparison with the reference data, the PLANUI can make up the shortcoming of low resolution and the blooming effect of NTL effectively. (2) Compared with the VANUI, the PLANUI can significantly improve the accuracy of the urban built-up areas extracted and characterize urban features. (3) According to the results based on NPP/VIIRS and Luojia 1-01 images, the PLANUI has extensive applicability, both for regions with different degrees of economic development and NTL data with different resolutions. PLANUI can enhance the features of urban built-up areas with social sensing data and natural remote sensing data, which helps to weaken the NTL blooming effect and improve the extraction accuracy. PLANUI can provide an effective approach for urban built-up area extraction, which plays a certain guiding role for the study of urban structure, urban expansion, and urban planning and governance.

PurposePrimary ovarian insufficiency (POI) represents ovarian dysfunction related to very early aging of the ovaries. While the cause of POI in a majority of clinical cases remains undefined, autoimmunity is responsible for approximately 4–30% of POI cases. In the present paper, we aim to provide a critical appraisal and update review on the role of autoimmunity in POI patients.MethodsA literature review was conducted for all relevant articles reporting on POI and autoimmunity. PubMed/MEDLINE and the Cochrane library were searched for the best available evidence on this topic.ResultsPatients with POI and coexisting autoimmunity are indistinguishable from those with negative autoimmune screen with regard to age of onset, prevalence of primary amenorrhea, or their endocrine profiles. A specific noninvasive reliable diagnostic test for the diagnosis of an autoimmune etiology is lacking; therefore, patients should be screened for the most common autoantibodies, i.e., steroid cell antibodies, anti-ovarian antibodies, and anti-thyroid antibodies. Moreover, treatment strategies to POI infertility are lacking and controversial.ConclusionsNowadays, guidelines for the treatment of autoimmune POI are not available. Moreover, since diagnostic and treatment strategies to POI infertility are still lacking and controversial, further large clinical studies are needed to investigate the true impact of autoimmunity on POI and to identify the selected groups of patients who are most likely to benefit from immunossuprresive treatment.

Background: Primary ovarian insufficiency (POI) is a heterogeneous disorder with multifactorial etiologies. Accurate diagnosis requires an integrated clinical, hormonal, and genetic evaluation, yet data from Pakistan are limited, and the burden of idiopathic and genetically predisposed cases remains largely unknown. Methods: A total of 345 women under 40 years presenting with amenorrhea or menstrual irregularities were screened. After excluding pregnancy, cases not meeting the European Society of Human Reproduction and Embryology (ESHRE) diagnostic criteria, and incomplete records, 290 women were included. Comprehensive clinical, hormonal, and genetic investigations were performed according to ESHRE guidelines to determine underlying etiologies. Results: The mean age at presentation was 33 ± 4.5 years, with a median symptom duration of 6 months. The mean age at menarche was 13 ± 1 years, and the mean body mass index (BMI) was 24.5 ± 3.4 kg/m2. Most women presented with amenorrhea (80%) or oligomenorrhea (20%). Secondary infertility was reported in 72.8% and primary infertility in 2.4%. A history of miscarriage was documented in 5.9% of participants. Common clinical features included hot flushes (75.9%), depression (72.4%), high stress (65.5%), mood changes (62.1%), vaginal dryness or dyspareunia (55.2%), and night sweats (54.5%). Coexisting comorbidities were observed in 12.4%, most frequently migraines (4.1%). Hormonal evaluation confirmed elevated follicle-stimulating hormone (FSH) levels (>25 IU/L) and low estradiol (<50 pg/mL) in all participants. Etiological classification identified iatrogenic causes in 7.2%, genetic causes in 3.8% (confirmed in women with suggestive genetic features or isolated POI), autoimmune causes in 6.6%, and idiopathic POI in 82.4%. Statistically significant differences in confirmed diagnoses were observed among most etiological groups (p < 0.0001), except for women with features suggestive of a genetic cause (p ≈ 0.8500). Conclusions: POI presents with diverse clinical features. Evaluation based on ESHRE guidelines enables identification of iatrogenic, autoimmune, and genetic contributors, and highlights the high prevalence of idiopathic cases, which may have an underlying genetic predisposition.

The effective Point-of-Interest (POI) recommendation can significantly assist users to find their preferred POIs and help POI owners to attract more customers. As a result, a variety of methods have been proposed to tackle the issue of POI recommendation recently. However, it is still very difficult to precisely model the strong correlations between the POIs visited by the user and the POIs to be visited next, which leads to the poor performance of POI recommendation. In this paper, we propose a context- and preference- aware model (CPAM) to incorporate both contextual influence and user preferences into POI recommendation. Firstly, we design a Skip-Gram based POI Embedding Model (SG-PEM) to capture the contextual influence of POIs and learn the vector representation (embedding) of POIs from visiting sequences. The users’ preferences for the target POIs are obtained from the learned embeddings via similarity metric. Secondly, for the implicit feedback information contained in the check-in data, we use the Logistic Matrix Factorization (LMF) algorithm to model the users’ personalized preferences for POI. Finally, we unify SG-PEM and LMF as the CPAM model to perform personalized recommendation by leveraging contextual influence and user preferences. The experimental results on two real-world datasets of Foursquare and Gowalla show that the proposed model outperforms the state-of-the-art baselines.

Route schema is difficult to plan for tourists, because they demand to pick points of interest (POI) in unknown areas that align with their preferences and limitations. This research proposes a novel personalized method for POI route recommendation that employs contextual data. The proposed approach enhances the existing methods by considering user preferences and multifaceted tourism contexts. Due to the sparsity of the data, the proposed method employs two-level clustering (DBSCAN based on the Manhattan distance) that reduces the time to discover POI. In specific, this approach utilizes the following: first, a topic pattern model is employed to discover the users’ attraction diffusion while improving the user–user similarity model using a novel asymmetric schema. Second, it has used explicit demographic information to alleviate the cold start issue, and third, it proposes a new strategy for assessing user preferences and also combined the context parameters in the form of a vector model with the Term Frequency Inverse Document Frequency technique to find contexts’ similarity. Furthermore, our framework discovers a list of optimal candidate trips by involving personalized POIs in sequential patterns’ mining (SPM); also, it used an adjusted forgotten function to involve the date context of each trip. Based on two datasets (Flickr and Gowalla), our methodology beats other prior approaches in F-score, RMSE, MAP, and NDCG factors in the experimental evaluation.

Nowadays, many people like to share the places they visited in the Location-based Social Networks (LBSNs). A Point of Interest (POI) recommendation, as one of the location-based services, helps users find new locations they prefer to visit. Recently, researchers have proposed many methods to leverage user-generated content, such as check-ins, for POI recommendation. However, due to the sparsity of user check-in information, it is still very difficult to recommend appropriate and accurate locations to users. To address the problem, in this paper, we propose a novel POI recommendation method named NGPR. Firstly, we construct a heterogeneous LBSN graph of users, POIs, categories and time periods. based on check-in records. Subsequently, the Node2Vec technique is employed to establish the latent vectors of POIs and users. Finally, we integrate comprehensive factors including the category preference, geographical distance and POI popularity for POI recommendation. The NGPR method is applied to two real LBSN datasets for experimental analysis. The experimental results show that the precision@5 of our method achieves 18.82% and 19.19% higher than that of the second best method on two real LBSN datasets respectively.