EMERGING SECURITY RISKS OF E-HAIL TRANSPORT SERVICES: FOCUS ON UBER TAXI IN NAIROBI, KENYA
Cosmas Ekwom Kamais , Egerton University, Kenya
This study attempted to examine the emerging security risks brought about by the e-hail taxi mode of transportation. It argues that despite the fact that the security risks associated with traditional taxi transportation still apply to e-hail taxi services, there are emergent risks that are unique to the app-based taxi hailing services. It further contends that as evidenced by the reactionary way of addressing security issues arising form usage of the service, it is clear that security was not a factor during conceptualisations, development and operation of the app-based taxi service. The study conducted a survey of uber customers and drivers in Nairobi County Kenya, and data was collected from 400 respondents with 85% response rate. Majority of the respondents indicated that they somewhat often (32.23%), agreed that Uber is more convenient (58.76%), indicated that Uber offers more business and job opportunities (86.46%). Despite the positive opinions by the respondents, 65.31% opined that Uber portend security risks. Majority indicated that the following risks are likely; abductions (40.82%), carjacking (40.82%), sexual harassment (38.14%), murders (35.71%), robbery (41.84%) and burglaries (34.69%). However, a majority of 28.57% thought that hackings into sensitive customer and company data was less likely. Furthermore, 57.14% of the respondents felt that the regulatory framework for appbased taxi hailing system were not sufficient to guarantee safety and security while 75.51% were optimistic that the e-hail transport industry will take meaningful security mitigation measures from the lessons they have learned. Finally, 92.93% of the respondents felt that government authorities should do more in regulating app-based services such Uber while 85.86% opined that founders and managers of ehail taxi services should be held responsible for security lapses. The study recommends that a review of existing traffic laws and criminal laws be done to take care of the emerging security risks associated by app-based service providers.
e-hail Taxi, app-based, Uber, Transport, Security Risks, Convenience, Information Technology, collaborative economy
For More Details :
DE-IDENTIFICATION OF PROTECTED HEALTH INFORMATION PHI FROM FREE TEXT IN MEDICAL RECORDS
Geetha Mahadevaiah1 , Dinesh M.S1 , Rithesh Sreenivasan1, Sana Moin1 and Andre Dekker2
Medical health records often contain clinical investigations results and critical information regarding patient health conditions. In these medical records, along with patient health information, patient Protected Health Information (PHI) such as names, locations and date information can co-exist. As per Health Insurance Portability and Accountability Act (HIPAA), before sharing the medical records with researchers and others, all types of PHI information needs to be de-identified. Manual de-identification through human annotators is laborious and error prone, hence, a reliable automated de-identification system is need of the hour.
In this work, various state of the art techniques for de-identification of patient notes in electronic health records were analyzed for their performance, based on the performance quoted in the literature, NeuroNER was selected to de-identify Indian Radiology reports. NeuroNER is a named-entity recognition text de-identification tool developed by Massachusetts Institute of Technology (MIT). This tool is based on the Artificial Neural Networks written in Python and uses Tensorflow machine-learning framework and it comes with five pre-trained models.
To test the NeuroNER models on Indian context data such as name of the person and place, 3300 medical records were simulated. Medical records were simulated by extracting clinical findings, remarks from MIMIC-III data set. For collection of all the relevant Indian data, various websites were scraped to include Indian names, Indian locations (all towns and cities), and Indian Hospital and unit names. During the testing of NeuroNER system, we observed that some of the Indian data such as name, location, etc. were not de-identified satisfactorily. To improve the performance of NeuroNER on Indian context data, along with the existing NeuroNER pre-trained model, a new pre-trained model was added to handle Indian medical reports. Medical dictionary lookup was used to reduce number of misclassifications. Results from all four pre-trained models and the model trained on Indian simulated data were concatenated and final PHI token list was generated to anonymize the medical records to obtain de-identified records. Using this approach, we improved the applicability of the NeuroNER system to Indian data and improved its efficiency and reliability. 2000 simulated reports were used for transfer learning as training set, 1000 reports were used for test set and 300 reports were used for validation (unseen) set.
De-identification, Free text, Protected Health Information, Medical records, Radiology reports, Indian context data
For More Details :