Deep supervised hashing techniques have exhibited remarkable efficiency in cross-modal retrieval tasks, because they enable the transformation of data from different modalities into compact binary codes that preserve semantic similarity structures. Nonetheless, existing methods often rely on pairwise or triplet relationships within known (or in-distribution) semantics during training, failing to capture comprehensive ranking information inherent web encompasses diverse concepts. In addition,...

To explore the feasibility of applying artificial intelligence in nurse-patient interaction to assist nurses grasping patient status and reducing their working hours.Artificial has been reshaping health care industry immense potential nursing care, but there is still a lack suitable methods improve efficiency that takes much time nurses.An intelligence-based intelligent surveillance system was developed reduce nurses' hours interaction, two-wave follow-up design adopted this study. The data...

Robot path planning is a complicated problem which needs to balance many factors. In pathfinding, the robot has find shortest destination and avoid obstacles. Ant colony optimization heuristic algorithm excellent features in pathfinding. This paper proposed heterogeneous feature ant (HFACO) solve problem. method, two kinds of ants with different are designed influence convergence rate by controlling number them. We also applied some other novel strategies that enhance solving quality...

The maximum available capacity is an important indicator for determining the State-of-Health (SOH) of a lithium-ion battery. Upon analyzing experimental results cycle life and open circuit voltage tests, novel health factor which can be used to characterize was proposed predict battery’s SOH. contains features extracted from terminal drop during battery rest. In real applications, obtaining such has following advantages. only needs have rest after it charged or discharged, easy implement....

The performance behavior of the lithium-ion battery can be simulated by model and thus applied to a variety practical situations. Although particle swarm optimization (PSO) algorithm has been used for development, it is usually unable find an optimal solution during iteration process. To resolve this problem, adaptive random disturbance PSO proposed. updated continuously obtaining new location around particle’s historical location. There are two conditions considered perform Initially, test...

Correspondence estimation is one of the fundamental challenges in computer vision lying core many problems, from stereo and motion analysis to object recognition. The direct matching method would fitness for every pixel resolution space it sensitive illumination change other change. For image attained by distance transformation can weaken bad influence under geometric distortion edge change, have ability resistant inversion. PSO algorithm supports parallel search multiple points that are...

Two-lane, one-way freeways compose a large percent of the freeway system nationwide. Preserving, expending, and enhancing these result in many work zones which have caused safety concern for traveling public. Aimed at reducing crashes attributed to existence zones, an evaluation speed reduction measures was carried out freeway. The speeds before after three strategies were measured. mean 85 percentile speed, standard deviation analyzed statistically. It can be concluded that effect...

Based on psychological theories, the paper analyzed relationship between acuity and brightness ratio of letter background in guide signs. Because luminance values for five grades retro-reflective sheeting were constant gap was wide GB5768-1999 Traffic Signs Markings roads, adjusted dynamically by adding declining onto it. By field experiments, impact grade visibility studied, distance established. The results show that there exists a certain which can optimize visibility, we get best...