Polygraph Research Articles

Association of adenoid hypertrophy and clinical parameters with preoperative polygraphy in pediatric patients undergoing adenoidectomy.

Adenotonsillar hypertrophy is the most frequent cause for obstructive sleep apnea (OSAS) in children. In patients with small tonsils and where adenoid size cannot be assessed, the indication for adenoidectomy often relies on clinical symptoms. However, data on the association of clinical parameters and adenoid hypertrophy with OSAS severity in children undergoing an adenoidectomy is sparse. To investigate the correlation of patient characteristics, adenoid hypertrophy, and clinical symptoms with OSAS severity in pediatric patients indicated for an adenoidectomy. We performed a retrospective chart review of all pediatric patients at our tertiary referral center between 2018 and 2023 who underwent polygraphy (PG) for OSAS diagnostics. Adenoid hypertrophy was assessed as adenoid-choanal ratio (AC-ratio) via nasal endoscopy and clinical symptom score (CS) via physical examination and parental survey. We included all symptomatic children with mild to severe OSAS (apnea-hypopnea index (AHI) ≥ 1). Exclusion criteria were obesity according to BMI and/or the presence of systemic diseases. The patients were divided according to age in a preschool and school cohort. Patient characteristics and PG data were compared between both groups. Linear regression analysis was used to investigate the association of AC-ratio, CS and BMI with the AHI. A total of 121 patients were identified of which 81 were included in our study, resulting in 42 and 39 patients from 3-5 and 6-14years of age, respectively. We observed a significant correlation between CS and BMI (p = 0.026) and the CS and AC-ratio (p < 0.001). Univariable regression analysis showed significant association of the AC-ratio and CS with AHI-score for the total (p < 0.001), the preschool (p < 0.001), and the school cohort (p < 0.001). In multivariable regression analysis, the significant association of AC-ratio and CS remained in the total (p = 0.014; p < 0.001), and the preschool cohort (p = 0.029; p = 0.002). However, only the CS remained as positive predictor in the school cohort. AC-ratio and clinical symptoms seem to be reliable predictors for OSAS severity in patients between 3-14years of age. Moreover, only clinical symptoms were associated with OSAS severity in schoolchildren. Future investigation should contribute to the validation of our results.

A Localized GIS-Based Multi Decision Criteria Approach in Determining Suitable Sites for Community Toilet Facilities in BASECO Compound, Manila City

Abstract. Access to sanitation remains a major concern in the Philippines due to the increasing population and growing demand for basic needs. This study addresses poor sanitary conditions in slum areas, specifically in BaSECo Compound, Manila, where informal settlers rely on shared toilets. Utilizing GIS and MCDA, the study identifies areas suitable for community toilet facility (CTF) development. The Modified Huff Three-Step Floating Catchment Area (MH3SFCA) method quantified spatial accessibility to existing toilets. The SPAI map shows low accessibility in blocks 15 and New Site, with Gawad Kalinga, Habitat, and Old Site (N) having none. The Analytical Hierarchy Process (AHP) prioritized six criteria, with accessibility being the most significant (33.18%), followed by proximity to water supply (31.76%), communal septic tanks (14.53%), land use (8.2%), flood-prone areas (7.44%), and ground slope (4.89%). The final suitability map identified 14.12% of the 0.6 sq. km. area as highly suitable, including Block 15, Gawad Kalinga, Habitat, and Old Site (N). Ground truth verification visited five candidate sites, which were tested for improved SPAI maps. The inclusion of facilities in Block 15, GK 2, OSN, and H improved accessibility in northern BaSECo. Significant service area improvements for each CTF were observed using Voronoi polygons. This study demonstrates the effectiveness of integrating GIS and MCDA methods for CTF site selection.

Insights into the Overlap of Chronic Obstructive Pulmonary Disease and Sleep Apnea: Experience from the Clinic of Pneumology, Târgu Mureș.

Chronic obstructive pulmonary disease (COPD) has a severe impact on patients' health and can lead to multiple complications. We analyzed the co-occurrence of obstructive sleep apnea (OSA) in COPD patients hospitalized in the Pneumology Clinic of Târgu Mureș, Romania. A total of 150 COPD patients were investigated by clinical examination, STOP-BANG and Epworth questionnaires, ventilatory polygraphy (PG), EKG, cardiac ultrasound, blood lipids, and sugar. Sixty-eight patients (45.3%) had OSA associated with COPD. A total of 61.7% were COPD gr. E, and 30.8% were gr. B. Frequently shown symptoms were snoring and nonrestorative sleep (100%), somnolence (73.5%), nocturnal awakenings (41.17%), morning headache (32.3%), and aggravated dyspnea. Types of OSA included obstructive (97.05%), central (2.5%), and associated obesity-hypoventilation (39.7%). A total of 76.4% were recently diagnosed with OSA. Men predominated at 70.5%, 76.4% were smokers, and 61.7% had experienced alcohol abuse. A total of 25% were overweight, and 71% had obesity. A total of 13.2% belonged to the category of 38-50-year-olds, 55.8% were in the 51-65-year-old category, 17.6% were in the 66-70-year-old category, and roughly 13.2% were in the 71-year-old category. Overlap syndrome (OS) comorbidities and complications were frequently present: 41% experienced respiratory failure, 66.1% experienced blood hypertension, 58.8% experienced ischemic cardiac disease, 32.35% experienced diabetes mellitus, 50% experienced dyslipidemia, and 29.4% experienced cor pulmonale. OS conferred gravity or directly contributed to cardiovascular, respiratory, and metabolic complications. OS was associated with more severe COPD and obesity. The prevalence of smoking in OS patients was higher than the national/European average.

Ambulatory polygraphy as a screening tool for obstructive sleep apnea in combination with semi-continuous rhythm monitoring in patients with atrial fibrillation: a pilot study

Abstract Background Obstructive sleep apnea (OSA) is a common, yet underdiagnosed risk factor in atrial fibrillation (AF) patients. Polysomnography (PSG) is the gold standard for OSA diagnosis but is also costly, time-consuming, and labor-intensive. (Cardio)-respiratory polygraphy (PG) offers an ambulatory screening for OSA detection. Studying the impact of OSA diagnosis and treatment on AF recurrence will require scalable tools for semi-continuous heart rhythm monitoring. Purpose The NOXFib-AF pilot study assessed the feasibility of PG as an OSA screening tool in patients with AF. The study monitored AF recurrences using a Fitbit smartwatch for heart rhythm monitoring with the FibriCheck algorithm. This pilot assessed the feasibility and patient compliance. Methods Overnight OSA testing was performed with the Noxturnal T3 (NOX-T3s) PG device used at home by AF patients, followed by four weeks of heart rhythm monitoring. Both semi-continuous monitoring with the Fitbit Versa 2 smartwatch with FibriCheck algorithm, and spot-check measurements on a smartphone (twice daily and in case of symptoms) were used. Patients with OSA suspicion on PG (Apnea-Hypopnea Index (AHI) cut-off ≥ 11.1 based on previous studies) were referred for PSG confirmation. Patient satisfaction with the PG and Fitbit smartwatch was evaluated through questionnaires. Results Thirty symptomatic AF patients underwent an overnight PG-based OSA screening, achieving an overall success rate of 96.7% (29/30). Interim analysis of 19 patients who underwent PSG evaluation upon referral showed that 12 (63.2%) were correctly diagnosed with at least moderate OSA (i.e., AHI ≥ 15) and were eligible for reimbursed CPAP treatment. PG and PSG agreement for OSA classification was fair (Cohen’s kappa = 0.230), with 68.4% (13/19) correctly classified (normal-mild, moderate-severe). There was high patient adherence to wearing the smartwatch for four weeks, with median compliance (i.e., adherence to the expected number of measurements) of 96.9% (IQR: 94.3% – 97.6%). A median of 150 (IQR: 145 – 151) daily automatic measurements were performed. Spot-check measurements via the smartphone also showed high compliance (110%, IQR: 100.0% – 135.5%) and high patient motivation (i.e., consistency of performing measurements; 90.3%, IQR: 67.7% – 96.8%). Patients were positive for both PG screening (Figure 1A) and Fitbit-based FibriCheck monitoring (Figure 1B). Conclusions PG is a feasible approach as a home screening tool for OSA, positively perceived by patients. Also, the acceptance of semi-continuous Fitbit-based FibriCheck monitoring was high. In a follow-up study, both tools will be used to evaluate the impact of a structured OSA screening and treatment trajectory on AF burden.

Research on CNN-BiLSTM-SAM and Multimodal Feature Fusion for Speech Lie Detection

Lying state detection is a typical psychological calculation problem with significant spatiotemporal dynamic changes. However, most existing detection methods have not fully considered the dynamic changes in psychological states, and the distribution information of time series in multimodal spaces has not effectively utilized. The current detection systems lack adaptive fusion methods for multimodal features and it is difficult to extract their spatiotemporal dependencies. Therefore, a novel speech lie detection model was proposed that combines a Convolutional Neural Network (CNN) with a Bidirectional Long Short-Term Memory (BiLSTM) neural network and multimodal feature fusion of Spatiotemporal Attention Mechanism (SAM). CNN has the ability to extract local spatial features, while BiLSTM can handle long sequences and long-term dependencies in bidirectional information flows, and the contextual information in sequences can be captured. The proposed model combined the short-term stationary characteristics in time and the diversity of semantic environments in space, and introduced SAM to fuse multimodal features of temporal and spatial dependencies as feature vectors for the detection model of lying psychological states. The simulation experiment results on the Open-source Real Life Trial lie database show that the average lie detection rate reaches 88.09%. In general, the proposed speech lie detection model has a significant detection accuracy improvement compared to the existing lie detection models.

Honesty repeats itself: comparing manual and automated coding on the veracity cues total details and redundancy

AbstractLie detection research comparing manual and automated coding of linguistic cues is limited. In Experiment 1, we attempted to extend this line of research by directly comparing the veracity differences in manual coding and two coding software programs (Text Inspector and Linguistic Inquiry and Word Count [LIWC]) on the linguistic cue “total details” across eight published datasets. Mixed model analyses revealed that LIWC showed larger veracity differences in total details than Text Inspector and manual coding. Follow-up classification analyses showed that both automated coding and manual coding could accurately classify honest and false accounts. In Experiment 2, we examined if LIWC’s sensitivity to veracity differences was the result of honest accounts including more redundant (repeated) words than false accounts as LIWC—but not Text Inspector or manual coding—accounts for redundancy. Our prediction was supported, and the most redundant words were function words. The results implicated that automated coding can detect veracity differences in total details and redundancy, but it is not necessarily better than manual coding at accurately classifying honest and false accounts.

A Semi-Supervised Lie Detection Algorithm Based on Integrating Multiple Speech Emotional Features

When people tell lies, they often exhibit tension and emotional fluctuations, reflecting a complex psychological state. However, the scarcity of labeled data in datasets and the complexity of deception information pose significant challenges in extracting effective lie features, which severely restrict the accuracy of lie detection systems. To address this, this paper proposes a semi-supervised lie detection algorithm based on integrating multiple speech emotional features. Firstly, Long Short-Term Memory (LSTM) and Auto Encoder (AE) network process log Mel spectrogram features and acoustic statistical features, respectively, to capture the contextual links between similar features. Secondly, the joint attention model is used to learn the complementary relationship among different features to obtain feature representations with richer details. Lastly, the model combines the unsupervised loss Local Maximum Mean Discrepancy (LMMD) and supervised loss Jefferys multi-loss optimization to enhance the classification performance. Experimental results show that the algorithm proposed in this paper achieves better performance.

Lie Detection Based on Acoustic Analysis

Acoustic lie detection, prized for its covert nature and capability for remote processing, has spurred growing interest in acoustic features that can reliably aid in lie detection. In this study, the aim was to construct an acoustic polygraph based on a variety of phonetic and acoustic features rather than on electrodermal, cardiovascular, and respiratory values. Sixty-two participants from the University of Science and Technology of China, aged 18-30 years old, were involved in the mock crime experiment and were randomly assigned to the innocent and guilty groups. We collected 31 deceptive and truthful audios to analyze the performance of voice onset time (VOT) in lie detection. Our findings revealed that VOT performed well in lie detection. Both the average sensitivity and specificity of the area under the curve are 0.888, and its lower and upper confidence limit are up to 0.803 and 0.973 respectively at the 95% confidence level. Although the other acoustic features had a lower reference value, they also provided a general trend in the judgment of lie detection. Our results suggested that some acoustic features can be effectively used as aids to lie detection. Through a similar approach, we will explore more acoustic and phonetic features that contribute to detecting lies in the future.

THE PARTICULARITIES OF THE APPLICATION OF SPECIAL KNOWLEDGE IN PSYCHO-CRIMINALISTICS

In this article we propose to make an analysis and evaluation of some aspects related to the application of the polygraph to the investigation of crimes. Attention will be paid to the professional skills and competences of the polygraph examiner, as well as the need to know the special procedures that can be applied during the testing. We will establish criteria for classifying the profile of the criminal under psycho-criminological and criminological aspects.The circumstances to be elucidated by applying the polygraph to the investigation of acts of terrorism. We will analyze the psycho-criminological profile of the victim, witnesses and other categories of people to be tested by applying the polygraph. We will focus on the manner and methodology of conducting the polygraph examination and make recommendations for further research in the field of polygraph application.

The Effectiveness of The Polygraph Instrument (Lie Detector) As Evidance In Court

Polygraph is a computer technology that is capable of interpreting fraud up to 98% through physiological data such as changes in skin moisture due to anxiety, blood pressure, respiratory frequency and pulse frequency. The National Police Chief's Regulation (Perkap) Number 10 of 2009 Article 9 Paragraph (2) Letter A stipulated that the use of a polygraph as evidence in court will provide assistance to the judge in making a decision although the polygraph cannot be used as evidence because it does not meet the required standards. The purpose of this research is how to study the law on the use of polygraph equipment as valid evidence in court as written in the ITE Law Number 19 of 2016 concerning amendments to the UU ITE Number 11 of 2008. The research uses normative law as a research method and uses primary, secondary and data. tertiary. Research has found that a polygraph cannot be used as evidence, but if supported by expert opinion it can be used as valid supporting evidence in court.

Lie detection algorithms disrupt the social dynamics of accusation behavior

Humans, aware of the social costs associated with false accusations, are generally hesitant to accuse others of lying. Our study shows how lie detection algorithms disrupt this social dynamic. We develop a supervised machine-learning classifier that surpasses human accuracy and conduct a large-scale incentivized experiment manipulating the availability of this lie-detection algorithm. In the absence of algorithmic support, people are reluctant to accuse others of lying, but when the algorithm becomes available, a minority actively seeks its prediction and consistently relies on it for accusations. Although those who request machine predictions are not inherently more prone to accuse, they more willingly follow predictions that suggest accusation than those who receive such predictions without actively seeking them.

Use of special technical means (polygraph) on personnel recruitment in corporate structures

The article studies some aspects of specialized polygraph device application in the process of personnel recruitment in corporate structures. The authors cite the sociological surveys results that reflect the attitude of employers and employees towards polygraph checks at the stage of their employment. The methods and spheres of polygraph application for professional-psychological selection have been analyzed. The special psychophysiological research procedure with the use of the polygraph has been described, including recommendations on the questions formulation to obtain reliable results. The legislation of the Russian Federation regulating the conduct of such research has also been considered. The authors concluded that the use of the polygraph device is a relevant and promising tool, which is increasingly used in the personnel recruitment in corporate structures, as evidenced by the sociological surveys results. However, the research peculiarity on the polygraph tests prospects in personnel recruitment is currently complicated by the lack of open data from the companies themselves, since such data constitute commercial secrets and are not subject to public disclosure in accordance with the Federal Law “On Trade Secrets”.

An Automatic Lie Detection Model Using EEG Signals Based on the Combination of Type 2 Fuzzy Sets and Deep Graph Convolutional Networks.

In recent decades, many different governmental and nongovernmental organizations have used lie detection for various purposes, including ensuring the honesty of criminal confessions. As a result, this diagnosis is evaluated with a polygraph machine. However, the polygraph instrument has limitations and needs to be more reliable. This study introduces a new model for detecting lies using electroencephalogram (EEG) signals. An EEG database of 20 study participants was created to accomplish this goal. This study also used a six-layer graph convolutional network and type 2 fuzzy (TF-2) sets for feature selection/extraction and automatic classification. The classification results show that the proposed deep model effectively distinguishes between truths and lies. As a result, even in a noisy environment (SNR = 0 dB), the classification accuracy remains above 90%. The proposed strategy outperforms current research and algorithms. Its superior performance makes it suitable for a wide range of practical applications.

Novel Technologies and the Choices We Make: Historical Precedents for Managing Artificial Intelligence

Artificial intelligence needs ongoing and meaningful democratic oversight. Understanding the history of how the early nuclear weapons complex, novel biotechnology, and polygraph testing were managed can inform AI governance today.

Electrodermal Activity in Polygraph Testing

Electrodermal Activity in Polygraph Testing

The use of a polygraph in the investigation of criminal offences: problems of tactics and legal regulation

The use of a polygraph in the investigation of criminal offences: problems of tactics and legal regulation

Exploring facial cues: automated deception detection using artificial intelligence

Deception detection is an interdisciplinary field attracting researchers from psychology, criminology, computer science, and economics. Automated deception detection presents unique challenges compared to traditional polygraph tests, but also offers novel economic applications. In this spirit, we propose an approach combining deep learning with discriminative models for deception detection. Therefore, we train CNNs for the facial modalities of gaze, head pose, and facial expressions, allowing us to compute facial cues. Due to the very limited availability of training data for deception, we utilize early fusion on the CNN outputs to perform deception classification. We evaluate our approach on five datasets, including four well-known publicly available datasets and a new economically motivated rolling dice experiment. Results reveal performance differences among modalities, with facial expressions outperforming gaze and head pose overall. Combining multiple modalities and feature selection consistently enhances detection performance. The observed variations in expressed features across datasets with different contexts affirm the importance of scenario-specific training data for effective deception detection, further indicating the influence of context on deceptive behavior. Cross-dataset experiments reinforce these findings. Notably, low-stake datasets, including the rolling dice Experiment, present more challenges for deception detection compared to the high-stake Real-Life trials dataset. Nevertheless, various evaluation measures show deception detection performance surpassing chance levels. Our proposed approach and comprehensive evaluation highlight the challenges and potential of automating deception detection from facial cues, offering promise for future research.

Использование приема «смена установки» при проведении специального психофизиологического исследования с применением полиграфа

Introduction. The article considers the tacticsissues of conducting special psychophysiological examination with application of polygraph during professional psychological selection of citizens entering the service in the internal affairs bodies of the Russian Federation.When using polygraph inpersonnel work, there are often situations when it is difficult for a polygraph examiner to make a decision about the significance of the reactions detected, as they may be associated not with the presence of a certain risk factor (deviant behavior) preventingthe subject’s entering the police service, but with the manifestation of situational anxiety, which is difficult for the candidate to control in the situation assessed as stressful. To solve this problem and increase the reliability of polygraph examinationsresults, the specialists use “attitude change”techniquethat makes it possible to draw objective conclusion about the significance of a particular “risk factor” for the subject, taking into account his or her individual psychological characteristics. Research Method. Psychophysiological method of lie detection (polygraph) allows to solve important issues of candidates selection for service in law enforcement agencies who do not have a tendency to deviant behavior, which further ensures the quality and efficiency of professional activities of police officers. Results. Within the framework of the conducted research the possibility of creating special attitude in the subject, providing the emergence of reaction to a stimulus previously not significant for him/her, related to some test subject, was shown. The effectiveness of the “attitude change” technique use, which helps to neutralize the “accusatory bias” of the polygraph test when working with subjects of the anxious and suspiciouscircle, was revealed. It is proved that “attitude change” technique use in the process of screening checks leads to the reduction of errors of the first kind (“false alarm”) and provides reliability of the results of psychophysiological examination with application of polygraph.

EEG Lie Detection Evidence and Potential Australian Jurors

EEG Lie Detection Evidence and Potential Australian Jurors

Взаимодействие следователя и специалиста по результатам исследования с применением полиграфа

One of the problematic issues of research using a polygraph is the importance of “polygraph results” for the investigation. The Supreme Court's denial of the evidentiary value of psychophysiological research forces investigators to seek ways to effectively apply the results obtained by a specialist in a study using a polygraph. In order to determine the preferences of investigators in the options for interaction between an investigator and a specialist based on the results of a polygraph study, a survey of forensic investigators undergoing advanced training at the Moscow Academy of the Investigative Committee of the Russian Federation was conducted. The results of the survey allow us to draw conclusions that investigators use “polygraph results” in preparation for interrogation, use them to exert legitimate psychological influence on the interrogated, in order to expose false testimony; They highly appreciate the expediency of promptly notifying the investigator about the preliminary results of the polygraph test, as well as the expediency of interrogating a specialist “polygraphologist” in order to explain to the investigator the “results of the polygraph” and give them a procedural status.