Malaria is the leading cause of morbidity and mortality in Kenya, with close to 70 percent (24 million) of the population at risk of infection. It affects people of all age groups: children under five years of age and...Malaria is the leading cause of morbidity and mortality in Kenya, with close to 70 percent (24 million) of the population at risk of infection. It affects people of all age groups: children under five years of age and pregnant women living in malaria endemic regions who are vulnerable. The main objective was to assess the utilization of the insecticide treated bed nets among the mothers attending MCH/FP in Webuye District Hospital, Bungoma County, Kenya. This research was based at the Webuye District Hospital, Bungoma County, Kenya from February to May, 2013. Sample size included 40 adult mothers attending MCH/FP aged 18 years and above during the study period. The design of the study was cross-sectional where sampling technique employed was non-probabilistic, purposive sampling. Data was collected by interviews using structured questionnaire which was administered by the researchers. SPSS version 16 was employed in Data analysis. The association between the overall knowledge about ITN use and malaria attack and level of education was tested and correlation between knowledge about malaria and ITNs utilization was calculated. Nearly all mothers attending MCH/FP had knowledge about ITNs nets and used it, with majority, 82.5% of the respondents used it for protection and 75% knew the importance of ITNs which were for malaria prevention. A majority of mothers attending MCH/FP were aware of ITNs and used it. Malaria morbidity was influenced by various factors including frequency of ITN use and most respondents interviewed had contracted malaria once before. The difference was found to be highly statistically significant between the overall knowledge about ITN use and malaria attack and level of education (χ2 = 58.7, p = 0.000). There was a significantly moderate positive correlation between total knowledge and ITN utilization (r = 0.449 & p = 0.000). The same was for the frequency of use but it was found to be in a weak magnitude, (r = 0.223 & p = 0.000). There was a strong positive correlation between knowledge about risk which is exposed to the case of non-utilization and the overall knowledge (r = 0.853 & p = 0.000). Based on the above results, it’s recommended that the Ministry of Health increase knowledge of effective malaria prevention and treatment methods in communities where misconceptions and use of unproven prevention and treatment methods are common.展开更多
The VRP is classified as an NP-hard problem. Hence exact optimization methods may be difficult to solve these problems in acceptable CPU times, when the problem involves real-world data sets that are very large. To ge...The VRP is classified as an NP-hard problem. Hence exact optimization methods may be difficult to solve these problems in acceptable CPU times, when the problem involves real-world data sets that are very large. To get solutions in determining routes which are realistic and very close to the actual solution, we use heuristics and metaheuristics which are of the combinatorial optimization type. A literature review of VRPTW, TDVRP, and a metaheuristic such as the genetic algorithm was conducted. In this paper, the implementation of the VRPTW and its extension, the time-dependent VRPTW (TDVRPTW) has been carried out using the model as well as metaheuristics such as the genetic algorithm (GA). The algorithms were implemented, using Matlab and HeuristicLab optimization software. A plugin was developed using Visual C# and DOT NET framework 4.5. Results were tested using Solomon’s 56 benchmark instances classified into groups such as C1, C2, R1, R2, RC1, RC2, with 100 customer nodes, 25 vehicles and each vehicle capacity of 200. The results were comparable to the earlier algorithms developed and in some cases the current algorithm yielded better results in terms of total distance travelled and the average number of vehicles used.展开更多
传统企业合作伙伴推荐方法过度依赖技术特征而忽视多维因素影响。本研究旨在探究企业合作关系的多维影响因素及推荐机制,为企业寻找合适合作伙伴和制定有效创新策略提供技术支持。本研究提出一种基于交叉多头对比学习网络(cross-attenti...传统企业合作伙伴推荐方法过度依赖技术特征而忽视多维因素影响。本研究旨在探究企业合作关系的多维影响因素及推荐机制,为企业寻找合适合作伙伴和制定有效创新策略提供技术支持。本研究提出一种基于交叉多头对比学习网络(cross-attention multi-head contrastive network,CAMC-Net)的企业合作伙伴推荐方法,融合企业、专利和政策数据,通过交叉多头注意力机制建模企业关系的双向互补特性,并引入对比学习策略优化企业表示空间分布。以新能源产业为例,在专利IPC(International Patent Classification)分类号为H02P和H10的企业合作数据集上进行验证,CAMC-Net模型在企业关系识别任务上AUC(area under the curve)分别达到0.9425和0.9251,准确率分别为0.8644和0.8387,F1值分别达到0.8707和0.8471,优于基线模型。通过消融实验证明了政策数据与模型组件的有效性。但现有的研究数据主要基于单一领域,未来需探索跨领域企业合作伙伴推荐方法;同时,模型缺乏对多模态数据的考虑,需要探索更高效的多模态特征融合策略。展开更多
文摘Malaria is the leading cause of morbidity and mortality in Kenya, with close to 70 percent (24 million) of the population at risk of infection. It affects people of all age groups: children under five years of age and pregnant women living in malaria endemic regions who are vulnerable. The main objective was to assess the utilization of the insecticide treated bed nets among the mothers attending MCH/FP in Webuye District Hospital, Bungoma County, Kenya. This research was based at the Webuye District Hospital, Bungoma County, Kenya from February to May, 2013. Sample size included 40 adult mothers attending MCH/FP aged 18 years and above during the study period. The design of the study was cross-sectional where sampling technique employed was non-probabilistic, purposive sampling. Data was collected by interviews using structured questionnaire which was administered by the researchers. SPSS version 16 was employed in Data analysis. The association between the overall knowledge about ITN use and malaria attack and level of education was tested and correlation between knowledge about malaria and ITNs utilization was calculated. Nearly all mothers attending MCH/FP had knowledge about ITNs nets and used it, with majority, 82.5% of the respondents used it for protection and 75% knew the importance of ITNs which were for malaria prevention. A majority of mothers attending MCH/FP were aware of ITNs and used it. Malaria morbidity was influenced by various factors including frequency of ITN use and most respondents interviewed had contracted malaria once before. The difference was found to be highly statistically significant between the overall knowledge about ITN use and malaria attack and level of education (χ2 = 58.7, p = 0.000). There was a significantly moderate positive correlation between total knowledge and ITN utilization (r = 0.449 & p = 0.000). The same was for the frequency of use but it was found to be in a weak magnitude, (r = 0.223 & p = 0.000). There was a strong positive correlation between knowledge about risk which is exposed to the case of non-utilization and the overall knowledge (r = 0.853 & p = 0.000). Based on the above results, it’s recommended that the Ministry of Health increase knowledge of effective malaria prevention and treatment methods in communities where misconceptions and use of unproven prevention and treatment methods are common.
文摘The VRP is classified as an NP-hard problem. Hence exact optimization methods may be difficult to solve these problems in acceptable CPU times, when the problem involves real-world data sets that are very large. To get solutions in determining routes which are realistic and very close to the actual solution, we use heuristics and metaheuristics which are of the combinatorial optimization type. A literature review of VRPTW, TDVRP, and a metaheuristic such as the genetic algorithm was conducted. In this paper, the implementation of the VRPTW and its extension, the time-dependent VRPTW (TDVRPTW) has been carried out using the model as well as metaheuristics such as the genetic algorithm (GA). The algorithms were implemented, using Matlab and HeuristicLab optimization software. A plugin was developed using Visual C# and DOT NET framework 4.5. Results were tested using Solomon’s 56 benchmark instances classified into groups such as C1, C2, R1, R2, RC1, RC2, with 100 customer nodes, 25 vehicles and each vehicle capacity of 200. The results were comparable to the earlier algorithms developed and in some cases the current algorithm yielded better results in terms of total distance travelled and the average number of vehicles used.
文摘传统企业合作伙伴推荐方法过度依赖技术特征而忽视多维因素影响。本研究旨在探究企业合作关系的多维影响因素及推荐机制,为企业寻找合适合作伙伴和制定有效创新策略提供技术支持。本研究提出一种基于交叉多头对比学习网络(cross-attention multi-head contrastive network,CAMC-Net)的企业合作伙伴推荐方法,融合企业、专利和政策数据,通过交叉多头注意力机制建模企业关系的双向互补特性,并引入对比学习策略优化企业表示空间分布。以新能源产业为例,在专利IPC(International Patent Classification)分类号为H02P和H10的企业合作数据集上进行验证,CAMC-Net模型在企业关系识别任务上AUC(area under the curve)分别达到0.9425和0.9251,准确率分别为0.8644和0.8387,F1值分别达到0.8707和0.8471,优于基线模型。通过消融实验证明了政策数据与模型组件的有效性。但现有的研究数据主要基于单一领域,未来需探索跨领域企业合作伙伴推荐方法;同时,模型缺乏对多模态数据的考虑,需要探索更高效的多模态特征融合策略。
