为了提高兴趣点(point of interest,POI)推荐的准确性和个性化,提升用户对推荐结果的满意度,针对不同活跃度用户的特点,提出一种融合用户活跃度的上下文感知兴趣点推荐算法(A POI recommendation algorithm that integrates geographica...为了提高兴趣点(point of interest,POI)推荐的准确性和个性化,提升用户对推荐结果的满意度,针对不同活跃度用户的特点,提出一种融合用户活跃度的上下文感知兴趣点推荐算法(A POI recommendation algorithm that integrates geographical,categorical,and temporal factors,while simultaneously considering user activity),简称AU-GCTRS。首先,为缓解数据稀疏性和冷启动问题,引入多维上下文信息;其次,通过挖掘用户签到频率、签到兴趣点数量和签到时间,将用户划分为不同活跃度的群体;最后,综合用户活跃度与上下文分数,将得分高的前K个兴趣点推荐给用户。在真实数据集上进行实验表明,AU-GCTRS算法比其他流行算法更有效地缓解了数据稀疏性和冷启动问题,提高了推荐准确率和召回率。展开更多
The number of students demanding computer science(CS)education is rapidly rising,and while faculty sizes are also growing,the traditional pipeline consisting of a CS major,a CS master’s,and then a move to industry or...The number of students demanding computer science(CS)education is rapidly rising,and while faculty sizes are also growing,the traditional pipeline consisting of a CS major,a CS master’s,and then a move to industry or a Ph.D.program is simply not scalable.To address this problem,the Department of Computing at the University of Illinois has introduced a multidisciplinary approach to computing,which is a scalable and collaborative approach to capitalize on the tremendous demand for computer science education.The key component of the approach is the blended major,also referred to as“CS+X”,where CS denotes computer science and X denotes a non-computing field.These CS+X blended degrees enable win-win partnerships among multiple subject areas,distributing the educational responsibilities while growing the entire university.To meet the demand from non-CS majors,another pathway that is offered is a graduate certificate program in addition to the traditional minor program.To accommodate the large number of students,scalable teaching tools,such as automatic graders,have also been developed.展开更多
BACKGROUND Cerebral infarction patients need to be bedridden for long periods of time often resulting in pressure injuries,which may represent a serious threat to patients'life and health.An effective nursing prog...BACKGROUND Cerebral infarction patients need to be bedridden for long periods of time often resulting in pressure injuries,which may represent a serious threat to patients'life and health.An effective nursing program should be adopted for timely intervention in patients with pressure wounds.AIM To explore the value of nursing services based on a multidisciplinary collaborative treatment team in patients with pressure injury wounds following cerebral infarction.METHODS Patients with cerebral infarction pressure injury wounds in our hospital from December 2016 to January 2021 were selected and divided into one study group and one control group based on the simple random number table method.The control group was treated with conventional nursing care(CNC),and the study group was treated with care services based on multidisciplinary collaborative care(MDCC).The Pressure Ulcer Scale for Healing(PUSH),healing effect,Self-Perceived Burden Score(SPBS),and satisfaction with the intervention were calculated before and after 2 and 4 wk of intervention in both groups.RESULTS Sixty-two patients were enrolled,and 31 patients were assigned to each group.The results of the interventions were as follows:(1)There was no significant difference between the PUSH scores of the MDCC group(11.19±2.46)and CNC group(12.01±2.79)before the intervention(P>0.05),and the PUSH scores were lower after 2 and 4 wk of intervention in the MDCC group(6.63±1.97 and 3.11±1.04)than in the CNC group(8.78±2.13 and 4.96±1.35 points)(P<0.05);(2)The rate of wound healing in the MDCC group(96.77%)was higher than that in the CNC group(80.65%)(P<0.05);(3)There was no significant difference between the SPBS scores of emotional factors(21.15±3.11),economic factors(9.88±2.15),and physical factors(8.19±2.23)in the two groups before the intervention.The scores of emotional factors(13.51±1.88),economic factors(6.38±1.44),and physical factors(5.37±1.08)were lower in the MDCC group than in the CNC group(16.89±2.05,7.99±1.68 and 7.06±1.19)after 4 wk of intervention(P<0.05);and(4)Satisfaction with the intervention was higher in the MDCC group(93.55%)than in the CNC group(74.19%)(P<0.05).CONCLUSION Interventions for patients with cerebral infarction pressure wounds based on an MDCC treatment team can effectively reduce patients'self-perceived burden,improve pressure wound conditions,facilitate wound healing,and increase patient satisfaction with the intervention.展开更多
该文在奇异值矩阵分解方法的基础上,提出了一种融合景点季节演变信息的旅游推荐算法。该算法根据景点属性与季节演变之间的关联,将旅游景点的属性划分为静态方面和动态方面,并通过设计包含时间因素的动态偏置函数来刻画用户偏好与景点...该文在奇异值矩阵分解方法的基础上,提出了一种融合景点季节演变信息的旅游推荐算法。该算法根据景点属性与季节演变之间的关联,将旅游景点的属性划分为静态方面和动态方面,并通过设计包含时间因素的动态偏置函数来刻画用户偏好与景点之间的动态关联。这些静态和动态方面的信息被作为新的偏置项融入有偏奇异分解(Bias singular value decomposition,Bias SVD)模型,以改善用户对旅游景点的评分预测。标准数据集Yelp上的实验结果表明,相比于对用户签到数据无差别对待的推荐方法,该文方法在推荐精度和用户体验方面均有明显的提升。展开更多
文摘为了提高兴趣点(point of interest,POI)推荐的准确性和个性化,提升用户对推荐结果的满意度,针对不同活跃度用户的特点,提出一种融合用户活跃度的上下文感知兴趣点推荐算法(A POI recommendation algorithm that integrates geographical,categorical,and temporal factors,while simultaneously considering user activity),简称AU-GCTRS。首先,为缓解数据稀疏性和冷启动问题,引入多维上下文信息;其次,通过挖掘用户签到频率、签到兴趣点数量和签到时间,将用户划分为不同活跃度的群体;最后,综合用户活跃度与上下文分数,将得分高的前K个兴趣点推荐给用户。在真实数据集上进行实验表明,AU-GCTRS算法比其他流行算法更有效地缓解了数据稀疏性和冷启动问题,提高了推荐准确率和召回率。
文摘The number of students demanding computer science(CS)education is rapidly rising,and while faculty sizes are also growing,the traditional pipeline consisting of a CS major,a CS master’s,and then a move to industry or a Ph.D.program is simply not scalable.To address this problem,the Department of Computing at the University of Illinois has introduced a multidisciplinary approach to computing,which is a scalable and collaborative approach to capitalize on the tremendous demand for computer science education.The key component of the approach is the blended major,also referred to as“CS+X”,where CS denotes computer science and X denotes a non-computing field.These CS+X blended degrees enable win-win partnerships among multiple subject areas,distributing the educational responsibilities while growing the entire university.To meet the demand from non-CS majors,another pathway that is offered is a graduate certificate program in addition to the traditional minor program.To accommodate the large number of students,scalable teaching tools,such as automatic graders,have also been developed.
文摘BACKGROUND Cerebral infarction patients need to be bedridden for long periods of time often resulting in pressure injuries,which may represent a serious threat to patients'life and health.An effective nursing program should be adopted for timely intervention in patients with pressure wounds.AIM To explore the value of nursing services based on a multidisciplinary collaborative treatment team in patients with pressure injury wounds following cerebral infarction.METHODS Patients with cerebral infarction pressure injury wounds in our hospital from December 2016 to January 2021 were selected and divided into one study group and one control group based on the simple random number table method.The control group was treated with conventional nursing care(CNC),and the study group was treated with care services based on multidisciplinary collaborative care(MDCC).The Pressure Ulcer Scale for Healing(PUSH),healing effect,Self-Perceived Burden Score(SPBS),and satisfaction with the intervention were calculated before and after 2 and 4 wk of intervention in both groups.RESULTS Sixty-two patients were enrolled,and 31 patients were assigned to each group.The results of the interventions were as follows:(1)There was no significant difference between the PUSH scores of the MDCC group(11.19±2.46)and CNC group(12.01±2.79)before the intervention(P>0.05),and the PUSH scores were lower after 2 and 4 wk of intervention in the MDCC group(6.63±1.97 and 3.11±1.04)than in the CNC group(8.78±2.13 and 4.96±1.35 points)(P<0.05);(2)The rate of wound healing in the MDCC group(96.77%)was higher than that in the CNC group(80.65%)(P<0.05);(3)There was no significant difference between the SPBS scores of emotional factors(21.15±3.11),economic factors(9.88±2.15),and physical factors(8.19±2.23)in the two groups before the intervention.The scores of emotional factors(13.51±1.88),economic factors(6.38±1.44),and physical factors(5.37±1.08)were lower in the MDCC group than in the CNC group(16.89±2.05,7.99±1.68 and 7.06±1.19)after 4 wk of intervention(P<0.05);and(4)Satisfaction with the intervention was higher in the MDCC group(93.55%)than in the CNC group(74.19%)(P<0.05).CONCLUSION Interventions for patients with cerebral infarction pressure wounds based on an MDCC treatment team can effectively reduce patients'self-perceived burden,improve pressure wound conditions,facilitate wound healing,and increase patient satisfaction with the intervention.
文摘该文在奇异值矩阵分解方法的基础上,提出了一种融合景点季节演变信息的旅游推荐算法。该算法根据景点属性与季节演变之间的关联,将旅游景点的属性划分为静态方面和动态方面,并通过设计包含时间因素的动态偏置函数来刻画用户偏好与景点之间的动态关联。这些静态和动态方面的信息被作为新的偏置项融入有偏奇异分解(Bias singular value decomposition,Bias SVD)模型,以改善用户对旅游景点的评分预测。标准数据集Yelp上的实验结果表明,相比于对用户签到数据无差别对待的推荐方法,该文方法在推荐精度和用户体验方面均有明显的提升。
