We compared two sorts of explanations for decisions made by an AI system: counterfactual explanations about how an outcome could have been different in the past, and prefactual explanations about how it could be different in the future. We examined the effects of these alternative explanation strategies on the accuracy of users' judgments about the AI app's predictions about an outcome (inferred from information about the causes), compared to the accuracy of their judgments about the app's diagnoses of a cause (inferred from information about the outcome). The tasks were based on a simulated SmartAgriculture decision support system for grass growth outcomes on dairy farms in Experiment 1, and for an analogous alien planet domain in Experiment 2. The two experiments, with 243 participants, also tested users' confidence in their decisions, and their satisfaction with the explanations. Users made more accurate diagnoses of the presence of causes based on information about their outcome, compared to predictions of an outcome given information about the presence of causes. Their predictions and diagnoses were helped equally by counterfactual explanations and prefactual ones.

A parameter extraction method for the LC circuit of a dual-band bandpass filter (DB-BPF) based on the fully connected network is proposed in this article. The network learning process consists of two stages: 1) pretraining and 2) fine-tuning. The network after pretraining has the ability to output the inaccurate values of LC circuit parameters with the desired${S}$-parameters (obtained according to the filter design requirements) as input. The precise LC circuit parameters can be obtained from the network during the subsequent fine-tuning process. This parameter extraction method can be applied to LC circuits of various bandpass filters. In addition to the amplitude of S-parameter, the phase of S-parameter is also used as learning data for the pretraining network. Comparative experiments show that the most accurate LC circuit parameters can be predicted using the network trained with phase information compared with the network trained without phase information. Two 7-order narrowband and two 9-order wideband DB-BPFs with four transmission zeros at different center frequencies are designed to demonstrate the validity of the proposed method, and the experimental results show that the proposed method is valid and effective.