An Innovative Security Screening Architecture for Detecting Illicit Goods and Threats

Every year, millions of letters/parcels containing illicit goods are detected by customs authorities, which use traditional security screening equipment. However this equipment cannot detect all kinds of illicit goods and the detection procedure heavily depends on the attention of the customs officer. In order to achieve sufficiently fast intelligent screening of the large volumes of letters/parcels and detect all common kinds of threats, this paper proposes a highly innovative architecture well-beyond the state-of–art. In particular the proposed architecture monitors every letter/parcel by incorporating: (a) terahertz/X-ray sensors, (b) chemical, biological, radiological and nuclear (CBNR) sensors, (c) artificial robot-noses for narcotics, explosives etc., (d) magnetometers for weapons, firearms, banknotes etc., (e) acoustic sensors for liquids/gases/solids, (f) weight/pressure sensors to measure weight distribution, size and shape. Sensory information can be: (a) used to create a “Spectral Signatures Dictionary of Illicit Goods and Threats”, (b) fused to segment/isolate illicit goods and (c) visualized in the form of annotated high-resolution tensor-structured (3D/4D) multisensory image data. The proposed solution also gathers available information for the sender/recipient from various resources, while it also analyzes data from the dark web. All information is forwarded to an AI-based knowledge infrastructure.

Electrocardiogram lead selection for intelligent screening of patients with systolic heart failure

Electrocardiogram (ECG)-based intelligent screening for systolic heart failure (HF) is an emerging method that could become a low-cost and rapid screening tool for early diagnosis of the disease before the comprehensive echocardiographic procedure. We collected 12-lead ECG signals from 900 systolic HF patients (ejection fraction, EF < 50%) and 900 individuals with normal EF in the absence of HF symptoms. The 12-lead ECG signals were converted by continuous wavelet transform (CWT) to 2D spectra and classified using a 2D convolutional neural network (CNN). The 2D CWT spectra of 12-lead ECG signals were trained separately in 12 identical 2D-CNN models. The 12-lead classification results of the 2D-CNN model revealed that Lead V6 had the highest accuracy (0.93), sensitivity (0.97), specificity (0.89), and f1 scores (0.94) in the testing dataset. We designed four comprehensive scoring methods to integrate the 12-lead classification results into a key diagnostic index. The highest quality result among these four methods was obtained when Leads V5 and V6 of the 12-lead ECG signals were combined. Our new 12-lead ECG signal–based intelligent screening method using straightforward combination of ECG leads provides a fast and accurate approach for pre-screening for systolic HF.