Sparrow Search Optimization with Transfer Learning-Based Crowd Density Classification

Due to the rapid increase in urbanization and population, crowd gatherings are frequently observed in the form of concerts, political, and religious meetings. HAJJ is one of the well-known crowding events that takes place every year in Makkah, Saudi Arabia. Crowd density estimation and crowd monitoring are significant research areas in Artificial Intelligence (AI) applications. The current research study develops a new Sparrow Search Optimization with Deep Transfer Learning based Crowd Density Detection and Classification (SSODTL-CD2C) model. The presented SSODTL-CD2C technique majorly focuses on the identification and classification of crowd densities. To attain this, SSODTL-CD2C technique exploits Oppositional Salp Swarm Optimization Algorithm (OSSA) with EfficientNet model to derive the feature vectors. At the same time, Stacked Sparse Auto Encoder (SSAE) model is utilized for the classification of crowd densities. Finally, SSO algorithm is employed for optimal fine-tuning of the parameters involved in SSAE mechanism. The performance of the proposed SSODTL-CD2C technique was validated using a dataset with four different kinds of crowd densities. The obtained results demonstrated that the proposed SSODTL-CD2C methodology accomplished an excellent crowd classification performance with a maximum accuracy of 93.25%. So, the proposed method will be highly helpful in managing HAJJ and other crowded events.     

K-submodular function-based service-limit incentive mechanisms for crowd heterogeneous sensing

Recently, crowd sensing, as a new paradigm, uses mobile devices from users to efficiently fulfill allocated tasks, enabling many novel applications such as location sensing and air pollution monitoring. To achieve high-quality service, extensive user participation is crucial. Most of existing works only apply for the homogeneous task scene where the requester has a budget limit and types of sensors used are homogeneous. On the contrary, we investigate a different scenario where the platform has a service limit and types of sensors are heterogeneous. Specially, we design the two service-limit incentive mechanisms, called SCH and SWH, respectively, by minimizing the total cost for a more general case where the value function is monotone $K$-submodular for participatory users so that given services can be fulfilled. The two mechanisms make it possible to extend current small-scale crowd sensing to large-scale crowd sensing, which have the following properties: individual rationality, task feasibility, computational efficiency, truthfulness, and constant frugality. Finally, we use extensive simulations to validate theoretical properties of our mechanisms.     

稠密向量实体检索模型的二值化提速压缩

在实体检索任务中，为了从大规模实体库中高效筛选与查询相关的候选实体，可使用稠密向量检索模型.然而在现有的稠密向量检索模型中，由于实体向量维度较高，导致实时计算效率较低、存储空间较大.文中通过实验发现这些实体向量存在大量的冗余信息：一方面，绝大多数实体向量分布在互不相同的象限里；另一方面，语义相近的实体所在的象限也更近.因此，文中提出二值化的实体检索方法，用于压缩实体向量，加速相似度计算.具体而言，方法利用符号函数(sign),二值化压缩高维稠密的浮点向量，并通过汉明距离加快检索.从理论上分析文中方法保证检索性能的原因.通过定性、定量的分析实验验证理论的正确性，并给出基于随机升维旋转的二值检索性能改善方法.