CSC8009 Research Assignment 1. Introduction This piece of coursework carries 100% of the overall mark for CSC8009. M.Sc. Computing Science students must complete the exercise described below and submit the completed work through NESS by 14.30 on Thursday 7th May 2020. The purpose of the exercise is to provide students opportunities to: 1. Develop their knowledge of the professional and ethical aspects of life as a computer scientist; and to 2. Become familiar with sources of information available to the practising professional. When marking the coursework, we will be looking for: 1. Evidence of awareness of the codes of practice and conduct affecting computer science professionals. 2. Evidence of awareness of relevant high quality literature (cite serious journals and not just trade press, critically reflect upon the use of Wikipedia as sole source of information). 3. Adequate scientific writing style conforming to common standards (such as objectivity, preciseness, evidence based argumentation, proper citation of references). 4. Evidence of using appropriate methods for conducting research and professional development techniques as introduced during the lectures. Please note that there is a strict word limit combined with layout constraints for the written work: • You must submit your essay as a PDF document. • The work must not exceed 2000 words (excluding references). • Please clearly state your name, title, and the module code at the beginning (header) of your essay. • Your essay should start with an abstract (one paragraph) where you summarise your project (motivation, brief overview of the proposed approach, potential results). • Font sizes allowed are 11pt and 12pt (exception: bibliography, which could be set in 9pt, and footnotes, which should be set in 10pt but only used sparsely) • Single column, single space. • Margin sizes (all four!) between 2 and 2.54 cm (strict!) Your task is to write a project proposal for either one of the pervasive computing systems outlined below (Option 1), or a project of your own choice (Option 2), for instance the project you would like to do for CSC8099). Have fun and good luck! 2. Pervasive Computing for Assisting Individuals In 1991 Mark Weiser presented his vision of the next generation of computing where “… [technologies] weave themselves into the fabric of everyday life until they are indistinguishable from it” (Weiser, 1991). More than 20 years after the introduction of this new computing paradigm1 pervasive computing is virtually omnipresent with the wide availability of miniaturized sensing technology combined with compact and powerful computing platforms and ubiquitous availability of broadband network connections. Probably the most prominent “success story” of ubiquitous computing technology is the stellar rise and public uptake of smartphone platforms such as Apple’s iOS devices or those based on Google’s Android operating system. Additionally, smart environments that integrate a multitude of sensors and actuators in private homes have been subject to both research and commercial development with the goal of providing novel, situated services that support inhabitants of smart environments with context-related and adaptive information. After more than 20 years of ubiquitous computing research many aspects of Weiser’s vision have become reality (Abowd, 2012). After developing core technologies and pioneering explorations, the research community from both academia and industry has now moved on, aiming for exploiting the new techniques in domains that have the potential for substantial impact both economically and societally. A prominent and very important example is healthcare using pervasive computing technology. a) Autism Spectrum Disorder Autism Spectrum Disorder (ASD) corresponds to a complex medical condition that have severe impact on both the individuals affected and on those in their social surroundings. Autism is typically diagnosed through behavioural analysis where trained psychologists observe particular individuals and analyse their social behaviour according to well-defined criteria (cf., e.g., the Autism diagnostic observations schedule – ADOS (Lord et al., 1989)). Based on such behavioural assessments caregivers such as psychologists and occupational therapists adapt their treatment programs and support towards the individual needs. First approaches towards automating these assessments have recently been described in the literature (Goodwin et al., 2011; Plötz et al., 2012). Beyond Autism diagnosis and assessments in clinical environments, pervasive computing technologies have been developed with a view on supporting caregivers of largely younger children with special needs thereby focusing on everyday life situations (Kientz et al., 2007). Decision Support System for Individuals with ASD For this application area we want to focus on pervasive computing technology for supporting older individuals with Autism in their everyday life activities. We will target our developments to a cohort of clients that have an age range of young adults (20+ years old) to retirement age (65 years). These individuals live either in their own homes or in an assisted living facility. Common to all is that they are not able to live independently, i.e., they require care and supervision from either their parents or from professional caregivers (such as occupational therapists or nurses).1 Since Autism is a spectrum disorder the challenges these individuals face in their everyday life are very diverse. However, common to most individuals on the Autism spectrum are difficulties in social interactions and coping with “unusual” events. For example, it could be stressful for autistic individuals to deal with shopping situations where particular products are out of stock and alternative decisions have to be made. b) Adults aged over 65 Older adults (those aged 65 and over) can face a range of physical and mental challenges. Common problems including reduced dexterity, decreased general mobility, as well as social isolation (Dickinson et al., 2002; Gregor et al., 2002). These factors can negatively impact on a person’s mental health as well as their perceived capability in learning new skills which may improve their well-being and may help manage or counteract any decreases in mobility. Studies have shown that older adults generally under-estimate their capability to learn new skills, and studies have shown that an older person’s capability of learning new skills is actually only slightly lower than a young adult (Eastin and LaRose, 2000; Grembowski et al., 1993; Marquie et al., 2002). One suggestion for the phenomena is a theory that older adults have low self-efficacy (the perception about one’s capability to learn something new) (Bandura, 1997) and that methods that specifically target improving one’s self efficacy would be helpful. The phenomena of low selfefficacy in older adults may further be caused by negative stereotypes of ageing, low commercial interest in providing suable technologies for older people as well as long term disengagement from learning (Dickinson et al., 2002). In the computing industry, there is little to no interest in providing tools or support for older people. This has lead to the “grey digital divide” (Millward, 2003) where older people miss out on the social and economic benefits of having a computing device and internet access. In more recent times, people who are retiring today are likely to have had some experience with computers in the workplace, are not continuing their usage of newer technologies post-retirement. This has been termed “digital disengagement” (Olphert and Damodaran, 2013). When technologies are provided for older people, they are often in the form of simplified, toy like devices with are viewed negatively by the target audience as been too childlike, less useful and the devices/services design not line line with their tastes or preferences (Eisma et al., 2004; Nesbitt,
2013). Decision Support System for Adults aged over 65 If you choose this scenario, you should focus on providing a ubiquitous device or service that will cater for adults aged 65 who may be unfamiliar with current computing technologies such as smart phones. People in this age group could be living independently, or with family members, sheltered accommodation or in a care facility. Furthermore, people in this age group may have none, mild to severe physical and cognitive problems (e.g. Arthritis, Dementia). 1 Note that a number of synonyms for pervasive computing are widely used including Ubiquitous Computing, Ambient Intelligence, Smart Environments and so forth. Therefore, the type of solution should focus on assisting the user to adapt or overcome a specific issue (i.e. a person with mild arthritis, but is largely independent however they need reminders when to take painkillers). c) Depression in Adults It is estimated that 1 in 4 people in the UK suffer from a mental health issue (“How common are mental health problems? | Mind, the mental health charity – help for mental health problems,” n.d.). With depression being one of the common types of mental health issues. In general, a person is diagnosed as having depression if they have had at least 5 of following symptoms for more than two weeks: • Low mood with or without irritability • Reduced interest in activities a person previously found enjoyable. • Significant changes to weight and appetite. • Changes in sleep patterns • Changes in physical activity • Fatigue and loss of energy • Feelings of guilt and/or worthlessness • Diminished consternation • Suicide ideation (American Psychiatric Association, 2013) The first line treatments for depression are antidepressant medications (such as Selective Serotonin Reuptake Inhibitors [SSRIs]) (Hyttel, 1994) and talking treatments such as Cognitive Behavioural Therapy (CBT) (Beck, 2011). CBT is undertaken with a trained councillor, either in the Doctor’s surgery, or in a private meeting venue. The effectiveness of antidepressants and CBT are well established (American Psychiatric Association, 2013; Driessen and Hollon, 2010; National Collaborating Centre for Mental Health (UK), 2010), and are commonly offered together as a combined treatment (Driessen and Hollon, 2010). However, a barrier to successful remission is poor patient compliance with their prescribed treatment (Sawada et al., 2009). One suggested approach to improve treatment compliance is the application of Shared Decision Making (SDM) between the clinician and patient when deciding treatment options (D. Flynn et al., 2015). SDM involves the clinician informing the patient of the available treatment options, while allowing the patient to choose their preferred option based on their own preferences. Compared to the traditional paternalistic decision making model, where the clinician makes the salient choices, SDM has lead to improved treatment compliance and patient satisfaction (Charles et al., 1997; Elwyn et al., 2001; Flynn et al., 2012). Decision Support System for Adults with Depression Decision support tools can be used to assist with SDM, for example, by visualising the risks and benefits of a treatment when a patient decides their treatment options (D. D. Flynn et al., 2015). For adults with depression, a pervasive device could be used to allow the user to keep track of their progress and note down any issues they face. Note taking is a common activity as part of CBT as the councillor will keep track of the patients progress, and discuss specific issues they have encounter between appointments. An alternative application for a pervasive computing device may be used to motor the vital statistics of the patient (i.e. heart rate). Monitoring patent stats could be useful for identifying stressful situations, or could be used as an indicator of interoperate side effects of an antidepressant medication, which may lead to a clinician changing the patient’s medication. 3. Option 1 You work as a system developer who is going to build a system that provides situated support for the aforementioned target group of individuals detailed in your chosen application area (a, b or c above). Such a system must provide decision support whenever the user (the individuals described in the application area) needs it. In its final version the system will automatically detect whether the user needs support and react accordingly. For doing so the system shall employ non-obtrusive sensing technology, sophisticated data analysis techniques, and intuitive means of interaction. Task Describe the process of system development where you focus on 1. Background and Requirement Analysis Given the enormous range of behavioural phenotypes in people you need to analyse to what extent a somewhat standardized product can actually be used for a rather heterogeneous cohort of users. Identify one particular aspect you want to focus your support on (e.g., decision support for leisure activities where your system would give suggestions on how to proceed during grocery shopping if a particular item is out of stock). Provide a brief overview of existing pervasive computing system that focus on support for individuals described in your chosen application area. a) Describe the process of knowledge gathering, i.e., how you obtain information about your target group and their requirements. b) Focus on the ethical implications of this requirement analysis especially in the light of the target user group. Which roles do the caregivers of your users play? 2. Problem Specification After the requirement analysis you need to define the problem you are working on as specifically as possible. Note that you should focus on one problem. The references provided (and your own literature research) will help you finding a specific problem you want to address. 3. Sensing Solution Briefly (!) describe what you would need to take into consideration if you were to implement your sensing system in order to detect if and when support is needed. There are a number of options for doing so including interactive and automatic systems. You don’t have to actually implement the solution you describe. Thus, the focus is not on an exact description of all technical details (although the described solution should be realistic). You should focus on how a particular sensing solution would meet the constraints and requirements of the target users. For example, you could ask yourselves whether camera-based solutions would be appropriate for everyday life (and potentially public) situations. 4. Project Planning Describe how you would implement the system you envision. Be realistic (you are working alone!) in terms of schedules and milestones. a Which project management approach did you chose? Why? b How will you keep track of your progress? c What is your strategy for dealing with unexpected difficulties? Remember the special circumstances and the challenges you will have to expect when working with/for a population with special needs. 5. Evaluation Describe how you would evaluate the effectiveness of your developed solution: a) How can you measure the success of your endeavour? b) Which role do the users play in this evaluation? c) Which approach would be best for such an evaluation (to provide actual evidence for the effectiveness)? 4. Option 2 If you have already chosen what project you would like to do for your dissertation project in CSC8099, then you can produce a project proposal on that topic. The format for the proposal should follow the same structure as described above for Option 1. 1. Background You should briefly describe the general area of study and introduce the topic. This should include coverage of relevant literature in the area so that your descriptions of problem and solution will make sense to a general reader. You should state how you will gather requirements for your system. 2. Problem Specification After the background you need to define the problem you are working on as spe
cifically as possible. Note that you should focus on one problem. You need to give a motivation for why you want to study this problem and why it is important. 3. Problem Solution Briefly (!) describe what you would need to take into consideration if you were to implement your system. You don’t have to actually implement the solution you describe, although if you intend to study this problem in CSC8099 then you would do so then, so it clearly needs to be viable to be implemented by one MSc student in the time available. The focus is not on an exact description of all technical details (although the described solution should be realistic). You should focus on how your solution would solve the problem specified and what you intend to achieve. 4. Project Planning Describe how you would implement the system you envision. Be realistic (you are working alone!) in terms of schedules and milestones. a) Which project management approach did you chose? Why? b) How will you keep track of your progress? c) What is your strategy for dealing with unexpected difficulties? If there are particular ethical or organisational considerations associated with your problem then you should state how you will manage these. 5. Evaluation Describe how you would evaluate the effectiveness of your developed solution: a) How can you measure the success of your endeavour? b) Which approach would be best for such an evaluation (to provide actual evidence for the effectiveness)? c) If you are conducting a user study or using questionnaires, who will be your target group and how will you recruit them for your study? References Abowd, G.D., 2012. What next, ubicomp?: celebrating an intellectual disappearing act, in: Proceedings of the 2012 ACM Conference on Ubiquitous Computing. ACM, pp. 31–40. American Psychiatric Association, 2013. Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition. ed. American Psychiatric Association. https://doi.org/10.1176/appi.books.9780890425596 Bandura, A., 1997. Self-efficacy: The exercise of control. Worth Publishers. Beck, J.S., 2011. Cognitive behavior therapy: Basics and beyond. Guilford press. Charles, C., Gafni, A., Whelan, T., 1997. Shared decision-making in the medical encounter: what does it mean?(or it takes at least two to tango). Soc. Sci. Med. 44, 681–692. Dickinson, A., Eisma, R., Syme, A., Gregor, P., 2002. UTOPIA: Usable technology for older people: Inclusive and appropriate. New Res. Agenda Older Adults Proc BCS HCI Lond. 38– 39. Driessen, E., Hollon, S.D., 2010. Cognitive Behavioral Therapy for Mood Disorders: Efficacy, Moderators and Mediators. Psychiatr. Clin. North Am. 33, 537–555. https://doi.org/10.1016/ j.psc.2010.04.005 Eastin, M.S., LaRose, R., 2000. Internet Self-Efficacy and the Psychology of the Digital Divide. J. Comput. Commun. 6, 0–0. https://doi.org/10.1111/j.1083-6101.2000.tb00110.x Eisma, R., Dickinson, A., Goodman, J., Syme, A., Tiwari, L., Newell, A.F., 2004. Early user involvement in the development of information technology-related products for older people. Univers. Access Inf. Soc. 3, 131–140. https://doi.org/10.1007/s10209-004-0092-z Elwyn, G., Edwards, A., Mowle, S., Wensing, M., Wilkinson, C., Kinnersley, P., Grol, R., 2001. Measuring the involvement of patients in shared decision-making: a systematic review of instruments. Patient Educ. Couns. 43, 5–22. https://doi.org/10.1016/S0738-3991(00)00149- X Flynn, D., Knoedler, M.A., Hess, E.P., Murad, M.H., Erwin, P.J., Montori, V.M., Thomson, R.G., 2012. Engaging patients in health care decisions in the emergency department through shared decision-making: a systematic review. Acad. Emerg. Med. Off. J. Soc. Acad. Emerg. Med. 19, 959–967. https://doi.org/10.1111/j.1553-2712.2012.01414.x Flynn, D., Nesbitt, Daniel, De Brún, Aoife, Craggs, Craig, Afolabi, Busola, Keilty, Isabelle, Lee, Chris, Bradwell, Stephen, Pointon, Sian, Gerrard, S, Williamson, Rosie, 2015. A theory- based educational film about shared decision making in primary care for depression. Newcastle University, Digital Media Services, Newcastle upon Tyne. Flynn, D., Nesbitt, D, McMeekin, P., Rodgers, H., Price, C., Ford, G., Thomson, R., 2015. A Computerised Decision Aid for Treatment of Acute Stroke with Thrombolysis (COMPASS). http://eprints.ncl.ac.uk. Goodwin, M.S., Intille, S.S., Albinali, F., Velicer, W.F., 2011. Automated detection of stereotypical motor movements. J. Autism Dev. Disord. 41, 770–782. Gregor, P., Newell, A.F., Zajicek, M., 2002. Designing for dynamic diversity: interfaces for older people, in: Proceedings of the Fifth International ACM Conference on Assistive Technologies. pp. 151–156. Grembowski, D., Patrick, D., Diehr, P., Durham, M., Beresford, S., Kay, E., Hecht, J., 1993. SelfEfficacy and Health Behavior Among Older Adults. J. Health Soc. Behav. 34, 89–104. https://doi.org/10.2307/2137237 How common are mental health problems? | Mind, the mental health charity – help for mental health problems [WWW Document], n.d. URL https://www.mind.org.uk/information- support/types-of-mental-health-problems/statisticsand-facts-about-mental-health/how- common-are-mental-health-problems/ (accessed 3.9.18). Hyttel, J., 1994. Pharmacological characterization of selective serotonin reuptake inhibitors (SSRIs). Int. Clin. Psychopharmacol. 9 Suppl 1, 19–26. Kientz, J.A., Hayes, G.R., Westeyn, T.L., Starner, T., Abowd, G.D., 2007. Pervasive computing and autism: Assisting caregivers of children with special needs. IEEE Pervasive Comput. 6. Lord, C., Rutter, M., Goode, S., Heemsbergen, J., Jordan, H., Mawhood, L., Schopler, E., 1989. Austism diagnostic observation schedule: A standardized observation of communicative and social behavior. J. Autism Dev. Disord. 19, 185–212. Marquie, J.C., Jourdan-Boddaert, L., Huet, N., 2002. Do older adults underestimate their actual computer knowledge? Behav. Inf. Technol. 21, 273–280. Millward, P., 2003. The’grey digital divide’: Perception, exclusion and barriers of access to the Internet for older people. First Monday 8. National Collaborating Centre for Mental Health (UK), 2010. Depression: The Treatment and Management of Depression in Adults (Updated Edition), National Institute for Health and Clinical Excellence: Guidance. British Psychological Society, Leicester (UK). Nesbitt, D.J., 2013. Evaluation of the Use of Digital Photography to Aid Self-efficacy for Ageing IT Novices (MPhil Thesis). University of Newcastle upon Tyne. Olphert, W., Damodaran, L., 2013. Older People and Digital Disengagement: A Fourth Digital Divide? Gerontol. Basel 59, 564–70. http://dx.doi.org/10.1159/000353630 Plötz, T., Hammerla, N.Y., Rozga, A., Reavis, A., Call, N., Abowd, G.D., 2012. Automatic assessment of problem behavior in individuals with developmental disabilities, in: Proceedings of the 2012 ACM Conference on Ubiquitous Computing. ACM, pp. 391–400. Sawada, N., Uchida, H., Suzuki, T., Watanabe, K., Kikuchi, T., Handa, T., Kashima, H., 2009. Persistence and compliance to antidepressant treatment in patients with depression: A chart review. BMC Psychiatry 9, 38. https://doi.org/10.1186/1471-244X-9-38 Weiser, M., 1991. The Computer for the 21 st Century. Sci. Am. 265, 94–105.
