CHAPTER VII PROPOSED SYSTEM TESTING AND IMPLEMENTATION 7.1 System Testing System testing tests a completely integrated after unit testing to verify that it meets its requirements. i.e, it is the process of verifying and validating that a software program/application/product to meet the requirements that guided its design and development works as expected and can be implemented with the same characteristics. System testing falls within the scope of black box testing, and as such, should require no knowledge of the inner design of the code or logic. As a rule testing takes, as its input, all of the "integrated" software components that have successfully passed integration testing and also the software itself integrated with any applicable hardware (s). The purpose of integration testing is to detect any inconsistencies between the software units that are integrated together (called assemblages) or between any of the assemblages and the hardware. System testing is a more limited type of testing, it seeks to detect defects both within the "inter-assemblages" and also within the as a whole. 7.2 Verification and Validation. Verification is a Quality control process that is used to evaluate whether or not a product, service, or complies with regulations, specifications, or conditions imposed at the start of a development phase. Verification can be in development, scale-up, or production. This is often an internal process. 86
Validation is Quality assurance process of establishing evidence that provides a high degree of assurance that a product, service, or accomplishes its intended requirements i.e., checking the quality of software in both simulated and live environments. Experimental studies of proposed in a simulated environment under various illumination conditions using various cases (both in a rested, alert condition and in a sleep-deprived condition) of different genders, ages, and ethnic backgrounds were conducted to validate the proposed drowsiness monitoring. The validation consisted of two parts; the first involved the validation of the measurement accuracy of their computer vision techniques and the second assessed the validity of the parameters that were computed to characterize drowsiness. On the basis of these experimental results, it was concluded that this monitor is reasonably robust, reliable, and accurate in characterizing and predicting human drowsiness. Besides, the proposed is tested with existing based on technology and criteria evaluation using scientific/engineering guideline and user acceptance elements. This comparison results are shown from table 7.1 to table 7.3. 87
Company Name / Device Name Method DD850 Driver Measuring slow eye closurestructure illumination approach SM face Lab Machine Tracking head, eye, eye lids blink analyze, PERCLOS assessment Smart Eye Smart Eye pro 3.0 Tracking individual facial features and 3D head model no algorithm to monitor drowsiness LC technology Eye gaze analyze % of eyelid closure reliably RP prototype monitor Eye blink frequency, eye closure duration, eye closure speed, PERCLOS Drowsy driver detection Recognize the eye using knowledge based technique Table 7.1: Comparison of driver drowsy monitoring In order to show the results clearly weightage is given like 1 if the supports its particular criteria else 0. Scientific/ Engineering Guidelines Criteria Driver Fatigu Machine facelab Smart Eye Pro 3.0 LC Tech. Eyegaze Analysis System RPI Environmental Device should 0 0 0 0 0 1 operate reliably and accurately in all illumination conditions Environmental Device should 1 1 1 1 0 1 operate over expected range of truck cab temperature, humidity, and vibration conditions Anthropometric Device should accommodate multiple drivers with minimal recalibration 1 1 1 0 1 1 Total 2 2 2 1 1 3 Table 7.2: comparison and criteria Evaluation Scientific / Engineering Guidelines with weight 88
Engineering/Scientific 3.5 3 2.5 2 1.5 1 0.5 0 Driver 2 2 2 Machines facelab 0 Smart Eye LC Tech. Eyegaze Analysis System 1 1 RPI 3 Attributes Fig 7.1: Engineering / Scientific Evaluation User Acceptance Elements Ease of Use Ease of Use Ease of Use Perceived Value Criteria Driver Machines face LAB Smart Eye Pro 3.0 ASL ETS-PC II RPI System Device must accommodate corrective eyeglasses and most types of sunglasses 0 1 1 1 0 1 Device should 1 1 1 0 1 1 present a warning alert to the driver Device should 0 0 0 0 0 1 require minimal training Device should 1 1 1 0 1 1 provide feedback to driver regarding alertness level Total 2 3 3 1 2 4 Table 7.3: comparison and criteria Evaluation User Acceptance with weight 89
User Acceptance 4.5 3.5 4 2.5 3 1.5 2 0.5 1 0 2 T echnology Driver Machines facelab 3 3 0 0 Smart Eye ASL RPI 1 2 4 Attributes Fig 7.2: User Acceptance Evaluation Figure 7.1 shows that the level of scientific and engineering including illumination condition, temperature, humidity, false alarm maintenance of proposed is high when compared with existing. Figure 7.2 shows that the level of acceptance including ease of use, non invasive, alert driver, feed back etc of proposed is high when compared with existing. Figure 7.2 show that User Acceptance level of the proposed is 4 here. User acceptance level of the Smart Eye and Machine is 3 whereas ASL is 1. So, the proposed contributes much more than others. The experimental comparison of the scientific/engineering guidelines and user acceptance elements clearly shows the benefit from our new approach. 90
7.3 Implementation Implementation is transforming a planned design into a working. Once the preparatory work of implementation has taken place i.e., testing, the changeover can begin. The changeover means changing from the old to the new. The changeover may be achieved in number of ways. The most common methods are direct changeover, parallel running, pilot running and staged changeover. Direct changeover is the complete replacement of old by the new, in one move. Here we use direct changeover method to complete the proposed implementation. Three key factors are considered while using direct changeover. They are the Government, manufacturer and driver. Since the human are resources, the Government orders the manufacturer for the provision of monitoring device and insists the driver to switch on the device while driving by making law and may reduce the tax if device is implemented. If not obeyed, some negative weightage may be given to his license. The public should also insist the driver to switch on the monitoring device to protect them while traveling in their own vehicle or rented one. Training and/or incentives are given to driver to make aware of the value of the device. 91