Introduction: Lie Detection System

Lie detection, also referred to as deception detection, uses questioning techniques along with technology that record physiological functions to ascertain truth and falsehood in response

• A lie detection system is made using various simulated medical sensors, attached to the subject.

• The system will ask subject a series of questions, including non trivial and tricky questions, and capture reading from different sensors.

– Simulated GSR(Galvanic Skin Response) Sensor will measure the perspiration rate of the subject.

– Simulated ECG will sensor the heart beat per minute.

– Simulated Sphygmomanometer will measure the blood pressure in Hg-mm.

– Simulated Respiratory rate sensor measures rate in breaths per minute.

– Simulated eye sensors observes persons cognitive reactions.

– A trained expert observes eye movements, overall profile of the subject, reactions to different questions and provide his remarks for final evaluation.

• Thea which is capable of simultaneously recording changes in several physiological variables while the subject is asked a series of questions pertaining to a specific issue under investigation.

• The charts generated during the polygraph examination are interpreted by a polygraph examiner.

• The system aims to record, store, and analyze physiological changes during a polygraph examination. It combines conventional polygraph procedure with a sophisticated state-of-the-art computer.

Step 1: General Overview

General questions and testing techniques

There are typically three types of questions used in testing :

• Irrelevant questions establish a baseline to compare other answers by asking simple questions with clear true and false answers.

• Comparison questions have an indirect relationship to the event or circumstance, and they are designed to encourage the subject to lie.

• Relevant questions are compared against comparison questions (which should represent false answers) and irrelevant questions (which should represent true answers). They are about whatever is particularly in question.

The control question test and the guilty knowledge test

• The Control Question Test (CQT) uses control questions, with known answers, to serve as a physiological baseline in order to compare them with questions relevant to a particular incident. The control question should have a greater physiological response if truth was told and a lesser physiological response for lying.

• The Guilty Knowledge Test (GKT) is a multiple-choice format in which answer choices or one correct answer and additional incorrect answers are read and the physiological response is recorded. The controls are the incorrect alternative answers. The greater physiological response should be to the correct answer. Its point is to determine if the subject has knowledge about a particular event.

• Both are considered to be biased against those that are innocent, because the guilty who fear the consequences of being found out can be more motivated to cheat on the test. Various techniques (which can be found online) can teach individuals how to change the results of the tests, including curling the toes, and biting the tongue. Mental arithmetic was found to be ineffective by at least one study, especially in students counting backward by seven. A study has found that in The Guilty Knowledge Test subjects can focusing on the alternative answers and make themselves look innocent

Layered Architecture

• The system consists of four layers :

– Graphical User Interface

– Processing Logic

– Database controller

– Database

Step 2: Use Case Diagram & Vital Parameters


of standard range of vital parameters

• Heart Rate : 60-100 beats per minute

• Blood Pressure : 120/80 mm-Hg

• GSR : 5-25KΩ

• Respiratory Rate : 12-20 breaths per minute

• Eye Movement : Eye brows raised/ pupil dilated

• Overall Profile : Voice response/ tonal rise/ facial expression normal/ delayed verbal response

Step 3: Start Test

It was a windows based application that simulated a lie detection system.

1. Top most layer was the user interface, where suspect would read the questions, respond by giving answers, and sensor reading were fed into the system and finally the result would be displayed. UI was made using java swings. Questions were read to suspect by the system. For this text to speech API can be used, i.e. freetts API.

Step 4: Sensor Reading Logic Layer

2. Second layer was the sensor reading logic layer. These readings were taken from the database they were fed into, and result was found using decision tree logic. For this we used J48 decision tree.

3. Database control layer was an intermediate layer to establish connections to database. JDBC was used to make this connection to the database.

Step 5: Displaying Result

4. Questions being asked from the suspect, his responses, sensor readings were captured in oracle sql database.

5. During test a simultaneous graph was being built of sensor readings captured. Graphs can be built using jfreechart API.

6. After the test is over, the result is displayed on the screen.