Research and implementation of a personalized book recommendation algorithm --Taking the library of Jinan University as an example

Abstract： Taking the basic data and the log data of the various businesses of the automation integrated management system of the library in Jinan University as the research object this paper analyzes the internal relationship between books and between the books and the readers, and designs a personalized book recommendation algorithm, the BookSimValue, on the basis of the user collaborative filteringtechnology. The experimental results show that the recommended book information produced by this algorithm can effectively help the readers to solve the problem of the book information overload, which can bring great convenience to the readers and effectively save the time of the readers＇ selection of the books, thus effectively improving the utilization of the library resources and the service levels.

多主体协同开发社区教育课程的PERSONAL模式探索——基于“我爱我家”的个案研究

通过对“我爱我家”这一社区自发课程的跟踪调查,发现社区自发课程开发实质上是一个组织学习过程,经过个体直觉、知识解释、知识整合等环节实现组织的制度化学习,在推动学习型无边界组织生成的同时,生成社区教育课程。在这一过程中,政策(policies)支持、专家(expert)指导、区域需求和区域特征(regional)、社区系统(system)、组织化(organization)等多要素叠加发挥作用,通过不断拓展新鲜(new)领域的积极行动(action)整合所有资源,并推动跨越边界的学习(learning)贯穿始终。因此,多主体协同的社区自发课程可以不完全地概括为PERSONAL模式。要以PERSONAL模式发展社区自发课程,需要以学习者为中心,注重发展人际互动,营造有利于跨组织交互学习的教育生态系统。

Personal Thermal Management by Radiative Cooling and Heating

Maintaining thermal comfort within the human body is crucial for optimal health and overall well-being.By merely broadening the setpoint of indoor temperatures,we could significantly slash energy usage in building heating,ventilation,and air-conditioning systems.In recent years,there has been a surge in advancements in personal thermal management(PTM),aiming to regulate heat and moisture transfer within our immediate surroundings,clothing,and skin.The advent of PTM is driven by the rapid development in nano/micro-materials and energy science and engineering.An emerging research area in PTM is personal radiative thermal management(PRTM),which demonstrates immense potential with its high radiative heat transfer efficiency and ease of regulation.However,it is less taken into account in traditional textiles,and there currently lies a gap in our knowledge and understanding of PRTM.In this review,we aim to present a thorough analysis of advanced textile materials and technologies for PRTM.Specifically,we will introduce and discuss the underlying radiation heat transfer mechanisms,fabrication methods of textiles,and various indoor/outdoor applications in light of their different regulation functionalities,including radiative cooling,radiative heating,and dual-mode thermoregulation.Furthermore,we will shine a light on the current hurdles,propose potential strategies,and delve into future technology trends for PRTM with an emphasis on functionalities and applications.

Effects of personalized oral hygiene management on oral health status of pregnant women

BACKGROUND The Cariostat caries activity test(CAT)was used to evaluate the effectiveness of personalized oral hygiene management combining oral health education and professional mechanical tooth cleaning on the oral health status of pregnant women.AIM To investigate whether personalized oral hygiene management enhances the oral health status of pregnant women.METHODS A total of 114 pregnant women who were examined at Dalian Women’s and Children’s Medical Center were divided into four groups:High-risk experimental group(n=29;CAT score≥2;received personalized oral hygiene management training),low-risk experimental group(n=29;CAT score≤1;received oral health education),high-risk control group(n=28;CAT score≥2),and low-risk control group(n=28;CAT score≤1).No hygiene intervention was provided to control groups.CAT scores at different times were compared using independent samples t-test and least significant difference t-test.RESULTS No significant difference in baseline CAT scores was observed between the experimental and control groups,either in the high-risk or low-risk groups.CAT scores were reduced significantly after 3(1.74±0.47 vs 2.50±0.38,P<0.0001)and 6 months(0.53±0.50 vs 2.45±0.42,P<0.0001)of personalized oral hygiene management intervention but not after oral health education alone(0.43±0.39 vs 0.46±0.33,P>0.05 and 0.45±0.36 vs 0.57±0.32,P>0.05,respectively).Within groups,the decrease in CAT scores was significant(2.43±0.44 vs 1.74±0.47 vs 0.53±0.50,P<0.0001)for only the high-risk experimental group.CONCLUSION Personalized oral hygiene management is effective in improving the oral health of pregnant women and can improve pregnancy outcomes and the oral health of the general population.

Omni-Detection of Adversarial Examples with Diverse Magnitudes

Deep neural networks(DNNs)are poten-tially susceptible to adversarial examples that are ma-liciously manipulated by adding imperceptible pertur-bations to legitimate inputs,leading to abnormal be-havior of models.Plenty of methods have been pro-posed to defend against adversarial examples.How-ever,the majority of them are suffering the follow-ing weaknesses:1)lack of generalization and prac-ticality.2)fail to deal with unknown attacks.To ad-dress the above issues,we design the adversarial na-ture eraser(ANE)and feature map detector(FMD)to detect fragile and high-intensity adversarial examples,respectively.Then,we apply the ensemble learning method to compose our detector,dealing with adver-sarial examples with diverse magnitudes in a divide-and-conquer manner.Experimental results show that our approach achieves 99.30%and 99.62%Area un-der Curve(AUC)scores on average when tested with various Lp norm-based attacks on CIFAR-10 and Im-ageNet,respectively.Furthermore,our approach also shows its potential in detecting unknown attacks.

An Empirical Study on the Effectiveness of Adversarial Examples in Malware Detection

Antivirus vendors and the research community employ Machine Learning(ML)or Deep Learning(DL)-based static analysis techniques for efficient identification of new threats,given the continual emergence of novel malware variants.On the other hand,numerous researchers have reported that Adversarial Examples(AEs),generated by manipulating previously detected malware,can successfully evade ML/DL-based classifiers.Commercial antivirus systems,in particular,have been identified as vulnerable to such AEs.This paper firstly focuses on conducting black-box attacks to circumvent ML/DL-based malware classifiers.Our attack method utilizes seven different perturbations,including Overlay Append,Section Append,and Break Checksum,capitalizing on the ambiguities present in the PE format,as previously employed in evasion attack research.By directly applying the perturbation techniques to PE binaries,our attack method eliminates the need to grapple with the problem-feature space dilemma,a persistent challenge in many evasion attack studies.Being a black-box attack,our method can generate AEs that successfully evade both DL-based and ML-based classifiers.Also,AEs generated by the attack method retain their executability and malicious behavior,eliminating the need for functionality verification.Through thorogh evaluations,we confirmed that the attack method achieves an evasion rate of 65.6%against well-known ML-based malware detectors and can reach a remarkable 99%evasion rate against well-known DL-based malware detectors.Furthermore,our AEs demonstrated the capability to bypass detection by 17%of vendors out of the 64 on VirusTotal(VT).In addition,we propose a defensive approach that utilizes Trend Locality Sensitive Hashing(TLSH)to construct a similarity-based defense model.Through several experiments on the approach,we verified that our defense model can effectively counter AEs generated by the perturbation techniques.In conclusion,our defense model alleviates the limitation of the most promising defense method,adversarial training,which is only effective against the AEs that are included in the training classifiers.

Framework for Personalized Chronic Pain Management:Harnessing AI and Personality Insights for Effective Care

This paper introduces a cutting-edge framework for personalized chronic pain management,leveraging the power of artificial intelligence(AI)and personality insights.It explores the intricate relationship between personality traits and pain perception,expression,and management,identifying key correlations that influence an individual’s experience of pain.By integrating personality psychology with AI-driven personality assessment,this framework offers a novel approach to tailoring chronic pain management strategies for each patient’s unique personality profile.It highlights the relevance of well-established personality theories such as the Big Five and the Myers-Briggs Type Indicator(MBTI)in shaping personalized pain management plans.Additionally,the paper introduces multimodal AI-driven personality assessment,emphasizing the ethical considerations and data collection processes necessary for its implementation.Through illustrative case studies,the paper exemplifies how this framework can lead to more effective and patient-centered pain relief,ultimately enhancing overall well-being.In conclusion,the paper positions the need of an“AI-Powered Holistic Pain Management Initiative”which has the potential to transform chronic pain management by providing personalized,data-driven solutions and create a multifaceted research impact influencing clinical practice,patient outcomes,healthcare policy,and the broader scientific community’s understanding of personalized medicine and AI-driven interventions.

Personalized Perioperative Care for a Patient with a 10-Year-Old Postpartum Old Thrombus after Neoadjuvant Therapy for Breast Cancer

Breast cancer is one of the most common malignant tumors in women, and has become the main cause threatening women’s health. A case of breast cancer with neoadjuvant chemotherapy was discharged after active treatment and nursing.

Correlation of personality with individual reproductive success in shrub-nesting birds depends on their life history style

Two questions in the research of animal personality—whether there is a correlation between a personality trait and individual reproductive success,and what is the genetic basis underlying a personality trait—remain unresolved.We addressed these two questions in three shrub-nesting birds,the Azure-winged Magpie(Cyanopica cyanus,AM),White-collared Blackbird(Turdus albocinctus,WB),and Brown-cheeked Laughingthrush(Trochalopteron henrici,BL).The personality type of an individual was first identified according to its response to a territorial intruder.Then,we compared the fleeing distance,breeding parameters,and differential expressed genes(DEGs) in the brain transcriptome between bold and shy breeders.In the three species,bold breeders exhibited more aggressiveness towards an intruder of their territory than did shy breeders.The reproductive success of bold breeders was significantly higher than that of shy breeders in AM but not in WB and BL.The three species shared one DEG,crabp1,which was up-regulated in bold relative to in shy individuals.By regulating the expression of corticotropin-releasing hormone,higher crabp1 gene expression can decrease cellular response to retinoic acid.Therefore,bold individuals are insensitive to external stresses and able to exhibit more aggressiveness to intruders than their shier counterparts.Aggressiveness is beneficial to bold individuals in AM but not in WB and BL because the former could evoke neighbors to make the same response of defending against intruders but the latter could not.Although a personality trait may have the same genetic basis across species,its correlation with reproductive success depends largely on the life history style of a species.

Mutations in Ras homolog family member A in patients with peripheral T-cell lymphoma and implications for personalized medicine

Genome sequencing has revealed frequent mutations in Ras homolog family member A(RHOA)among various cancers with unique aberrant profiles and pathogenic effects,especially in peripheral T-cell lymphoma(PTCL).The discrete positional distribution and types of RHOA amino acid substitutions vary according to the tumor type,thereby leading to different functional and biological properties,which provide new insight into the molecular pathogenesis and potential targeted therapies for various tumors.However,the similarities and discrepancies in characteristics of RHOA mutations among various histologic subtypes of PTCL have not been fully elucidated.Herein we highlight the inconsistencies and complexities of the type and location of RHOA mutations and demonstrate the contribution of RHOA variants to the pathogenesis of PTCL by combining epigenetic abnormalities and activating multiple downstream pathways.The promising potential of targeting RHOA as a therapeutic modality is also outlined.This review provides new insight in the field of personalized medicine to improve the clinical outcomes for patients.

Autoimmune hepatitis:Towards a personalized treatment

Autoimmune hepatitis is an uncommon condition that affects both adults and children and is characterized by chronic and recurrent inflammatory activity in the liver.This inflammation is accompanied by elevated IgG and autoantibody levels.Historically,treatment consists of steroids with the addition of azathioprine,which results in remission in approximately 80%of patients.Despite significant advancements in our understanding of the immune system over the past two decades,few modifications have been made to treatment algorithms,which have remained largely unchanged since they were first proposed more than 40 years ago.This review summarized the various treatment options currently available as well as our experiences using them.Although steroids are the standard treatment for induction therapy,other medications may be considered.Cyclosporin A,a calcineurin inhibitor that decreases T cell activation,has proven effective for induction of remission,but its long-term side effects limit its appeal for maintenance.Tacrolimus,a drug belonging to the same family,has been used in patients with refractory diseases with fewer side effects.Sirolimus and everolimus have interesting effects on regulatory T cell populations and may become viable options in the future.Mycophenolate mofetil is not effective for induction but is a valid alternative for patients who are intolerant to azathioprine.B celldepleting drugs,such as rituximab and belimumab,have been successfully used in refractory cases and are useful in both the short and long term.Other promising treatments include anti-tumor necrosis factors,Janus kinases inhibitors,and chimeric antigen receptor T cell therapy.This growing armamentarium allows us to imagine a more tailored approach to the treatment of autoimmune hepatitis in the near future.

Personalized Lower Limb Gait Reconstruction Modeling Based on RFA-ProMP

Personalized gait curves are generated to enhance patient adaptability to gait trajectories used for passive training in the early stage of rehabilitation for hemiplegic patients.The article utilizes the random forest algorithm to construct a gait parameter model,which maps the relationship between parameters such as height,weight,age,gender,and gait speed,achieving prediction of key points on the gait curve.To enhance prediction accuracy,an attention mechanism is introduced into the algorithm to focus more on the main features.Meanwhile,to ensure high similarity between the reconstructed gait curve and the normal one,probabilistic motion primitives(ProMP)are used to learn the probability distribution of normal gait data and construct a gait trajectorymodel.Finally,using the specified step speed as input,select a reference gait trajectory from the learned trajectory,and reconstruct the curve of the reference trajectoryusing the gait keypoints predictedby the parametermodel toobtain the final curve.Simulation results demonstrate that the method proposed in this paper achieves 98%and 96%curve correlations when generating personalized lower limb gait curves for different patients,respectively,indicating its suitability for such tasks.

Personality Trait Detection via Transfer Learning

Personality recognition plays a pivotal role when developing user-centric solutions such as recommender systems or decision support systems across various domains,including education,e-commerce,or human resources.Tra-ditional machine learning techniques have been broadly employed for personality trait identification;nevertheless,the development of new technologies based on deep learning has led to new opportunities to improve their performance.This study focuses on the capabilities of pre-trained language models such as BERT,RoBERTa,ALBERT,ELECTRA,ERNIE,or XLNet,to deal with the task of personality recognition.These models are able to capture structural features from textual content and comprehend a multitude of language facets and complex features such as hierarchical relationships or long-term dependencies.This makes them suitable to classify multi-label personality traits from reviews while mitigating computational costs.The focus of this approach centers on developing an architecture based on different layers able to capture the semantic context and structural features from texts.Moreover,it is able to fine-tune the previous models using the MyPersonality dataset,which comprises 9,917 status updates contributed by 250 Facebook users.These status updates are categorized according to the well-known Big Five personality model,setting the stage for a comprehensive exploration of personality traits.To test the proposal,a set of experiments have been performed using different metrics such as the exact match ratio,hamming loss,zero-one-loss,precision,recall,F1-score,and weighted averages.The results reveal ERNIE is the top-performing model,achieving an exact match ratio of 72.32%,an accuracy rate of 87.17%,and 84.41%of F1-score.The findings demonstrate that the tested models substantially outperform other state-of-the-art studies,enhancing the accuracy by at least 3%and confirming them as powerful tools for personality recognition.These findings represent substantial advancements in personality recognition,making them appropriate for the development of user-centric applications.

Personalized treatment of perihilar cholangiocarcinoma based on tumor genetic and molecular characteristics

This editorial discusses the article written by Tchilikidi et al that was published in the latest edition of the World Journal of Gastrointestinal Surgery.Genetic and molecular profiling of perihilar cholangiocarcinoma(pCCA)has identified a number of key abnormalities that drive tumor growth and spread,including pyruvate kinase M2,proline rich 11,and transcription factor 7,etc.pCCA has specific genetic and molecular features that can be used to develop personalized treatment plans.Personalized treatment approaches offer new opportunities for effectively targeting the underlying drivers of tumor growth and progression.The findings based on tumor genetic and molecular characteristics highlight the importance of developing personalized treatment strategies.

The Impact of Big Five Personality Traits on Older Europeans’ Physical Health

Investigating the role of Big Five personality traits in relation to various health outcomes has been extensively studied. The impact of “Big Five” on physical health is here explored for older Europeans with a focus on examining age groups differences. The study sample included 378,500 respondents derived from the seventh data wave of Survey of Health, Aging and Retirement in Europe (SHARE). The physical health status of older Europeans was estimated by constructing an index considering the combined effect of well-established health indicators such as the number of chronic diseases, mobility limitations, limitations with basic and instrumental activities of daily living, and self-perceived health. This index was used for an overall physical health assessment, for which the higher the score for an individual, the worst health level. Then, through a dichotomization process applied to the retrieved Principal Component Analysis scores, a two-group discrimination (good or bad health status) of SHARE participants was obtained as regards their physical health condition, allowing for further con-structing logistic regression models to assess the predictive significance of “Big Five” and their protective role for physical health. Results showed that neuroti-cism was the most significant predictor of physical health for all age groups un-der consideration, while extraversion, agreeableness and openness were not found to significantly affect the self-reported physical health levels of midlife adults aged 50 up to 64. Older adults aged 65 up to 79 were more prone to open-ness, whereas the oldest old individuals aged 80 up to 105 were mainly affected by openness and conscientiousness. .

Justification of and Response to the Specificity of Workers’Personality Rights

The pervasive existence of subordination in the work-place endows workers’personality rights with a distinct specificity that differs from other civil subjects.The specificity of workers’per-sonality rights is primarily manifested in three aspects:the exercise of rights is restricted by the employer;personality rights infringements often accompany violations of workers’economic property rights;and the scope of rights is not limited to the duration of employment.To respond to the specificity arising in the labor domain,certain disputes concerning workers’personality rights should be handled through la-bor dispute resolution procedures.In individual cases,judicial author-ities should differentiate among protection levels based on the specific type of personality rights involved,with a focus on examining the rea-sons,methods,and extent of the employer’s restrictive actions,thereby establishing a practical and reasonable review system.。

Personalized medicine and opioid use disorder

Opioid use disorder(OUD)is a major public health problem affecting millions of people worldwide.Although OUD is a chronic and relapsing disorder,a variety of pharmacological and non-pharmacological interventions are available.Medication-assisted treatment of OUD generally relies on competition for opioid receptors against the addictive substance.The mechanisms of this competition are to block or inactivate the opioid receptor or activate the receptor with a substance that is intermittent or long acting.Methadone and buprenorphine are two United States Food and Drug Administration-approved medications that have long-term positive effects on the health of opioid-dependent individuals.Although clinical studies of drugs generally demonstrate efficacy in thousands of people and toxicity is excluded,it cannot be predicted whether the given drug will cause side effects in one of the patients at the treatment dose.Individual differences can be explained by many biological and environmental factors.Variations in genes encoding drug metabolism or cellular drug targets significantly explain the variability in drug response between individuals.Therefore,for the effects of candidate genes to be accepted and included in individual treatment protocols,it is important to repeat studies on individuals of different ethnic backgrounds and prove a similar effect.

Transforming Healthcare:AI-NLP Fusion Framework for Precision Decision-Making and Personalized Care Optimization in the Era of IoMT

In the rapidly evolving landscape of healthcare,the integration of Artificial Intelligence(AI)and Natural Language Processing(NLP)holds immense promise for revolutionizing data analytics and decision-making processes.Current techniques for personalized medicine,disease diagnosis,treatment recommendations,and resource optimization in the Internet of Medical Things(IoMT)vary widely,including methods such as rule-based systems,machine learning algorithms,and data-driven approaches.However,many of these techniques face limitations in accuracy,scalability,and adaptability to complex clinical scenarios.This study investigates the synergistic potential of AI-driven optimization techniques and NLP applications in the context of the IoMT.Through the integration of advanced data analytics methodologies with NLP capabilities,we propose a comprehensive framework designed to enhance personalized medicine,streamline disease diagnosis,provide treatment recommendations,and optimize resource allocation.Using a systematic methodology data was collected from open data repositories,then preprocessed using data cleaning,missing value imputation,feature engineering,and data normalization and scaling.Optimization algorithms,such as Gradient Descent,Adam Optimization,and Stochastic Gradient Descent,were employed in the framework to enhance model performance.These were integrated with NLP processes,including Text Preprocessing,Tokenization,and Sentiment Analysis to facilitate comprehensive analysis of the data to provide actionable insights from the vast streams of data generated by IoMT devices.Lastly,through a synthesis of existing research and real-world case studies,we demonstrated the impact of AI-NLP fusion on healthcare outcomes and operational efficiency.The simulation produced compelling results,achieving an average diagnostic accuracy of 93.5%for the given scenarios,and excelled even further in instances involving rare diseases,achieving an accuracy rate of 98%.With regard to patient-specific treatment plans it generated them with an average precision of 96.7%.Improvements in early risk stratification and enhanced documentation were also noted.Furthermore,the study addresses ethical considerations and challenges associated with deploying AI and NLP in healthcare decision-making processes,offering insights into risk-mitigating strategies.This research contributes to advancing the understanding of AI-driven optimization algorithms in healthcare data analytics,with implications for healthcare practitioners,researchers,and policymakers.By leveraging AI and NLP technologies in IoMT environments,this study paves the way for innovative strategies to enhance patient care and operational effectiveness.Ultimately,this work underscores the transformative potential of AI-NLP fusion in shaping the future of healthcare.

Enhancing personalized exercise recommendation with student and exercise portraits

The exercise recommendation system is emerging as a promising application in online learning scenarios,providing personalized recommendations to assist students with explicit learning directions.Existing solutions generally follow a collaborative filtering paradigm,while the implicit connections between students(exercises)have been largely ignored.In this study,we aim to propose an exercise recommendation paradigm that can reveal the latent connections between student-student(exercise-exercise).Specifically,a new framework was proposed,namely personalized exercise recommendation with student and exercise portraits(PERP).It consists of three sequential and interdependent modules:Collaborative student exercise graph(CSEG)construction,joint random walk,and recommendation list optimization.Technically,CSEG is created as a unified heterogeneous graph with students’response behaviors and student(exercise)relationships.Then,a joint random walk to take full advantage of the spectral properties of nearly uncoupled Markov chains is performed on CSEG,which allows for full exploration of both similar exercises that students have finished and connections between students(exercises)with similar portraits.Finally,we propose to optimize the recommendation list to obtain different exercise suggestions.After analyses of two public datasets,the results demonstrated that PERP can satisfy novelty,accuracy,and diversity.

Personalized medicine:Clinical oncology on molecular view of treatment

Cancer,the second leading global cause of death,impacts both physically and emotionally.Conventional treatments such as surgeries,chemotherapy,and radiotherapy have adverse effects,driving the need for more precise approaches.Precision medicine enables more targeted treatments.Genetic mapping,alongside other molecular biology approaches,identifies specific genes,contributing to accurate prognoses.The review addresses,in clinical use,a molecular perspective on treatment.Biomarkers like alpha-fetoprotein,beta-human chorionic gonadotropin,5-hydroxyindoleacetic acid,programmed death-1,and cytotoxic T lymphocyte-associated protein 4 are explored,providing valuable information.Bioinformatics,with an emphasis on artificial intelligence,revolutionizes the analysis of biological data,offering more accurate diagnoses.Techniques like liquid biopsy are emphasized for early detection.Precision medicine guides therapeutic strategies based on the molecular characteristics of the tumor,as evidenced in the molecular subtypes of breast cancer.Classifications allow personalized treatments,highlighting the role of trastuzumab and endocrine therapies.Despite the benefits,challenges persist,including high costs,tumor heterogeneity,and ethical issues.Overcoming obstacles requires collaboration,ensuring that advances in molecular biology translate into accessible benefits for all.