It is reported that since 2016 there are over sixty thousand diagnosed cases of Leukemia in the United States of America alone. It also suggests that Leukemia is the most common type of cancer seen in the age of twenty. Although the study is based on a Western country, it is equally alarming for an Asian country like Bangladesh where healthcare system is not up to the standard. Researches show that the Chronic Lymphocytic Leukemia has about 83% five-year long survival rates. This paper focuses on Acute Lymphocytic Leukemia (ALL) as this is the most common type of Leukemia in Bangladesh. It is common knowledge among oncologists, that cancer is much easier to treat if it is detected in the early stages. Thus the treatment needs to begin as early as possible. We propose a hands-on approach in detecting the irregular blood components (e.g., Neutrophils, Eosinophils, Basophils, Lymphocytes and Monocytes) that are typically found in a cancer patient. In this work, we first identify 14 attributes to prepare the dataset and determine 4 major attributes that play a significant role in determining a Leukemia patient. We have also collected 256 primary data from Leukemia patient. The data is then processed using microscope to obtain images and fetch into Faster-RCNN machine learning algorithm to predict the odds of cancer cells forming. Here we have applied two loss functions to both the RPN (Region Convolutional Neural Network) model and the classifier model to detect the similar blood object. After identifying the object, we have calculated the corresponding object and based on the count of the corresponding object we finally detect Leukemia. The mean average precision observed are 0.10, 0.16 and 0, where the epochs are 40, 60 and 120, respectively.

We carried out an experiment to observe the role of transportation for adolescent female students in rural Bangladesh. A senior high school (in Bangladesh, they call it a college) student spends 180-230 minutes to travel only 22km (11 km, single trip) on an average to commute from home to college. Local transport (Tomtom) stops are not always close to their home. The walk 4km to get to the nearest Tomtom stop. The Tomtom does not have a regular timetable. In worst case, the students wait 30 minutes until the Tomtom driver finds sufficient number of passengers. This 11km distance is Female students find it uncomfortable to share congested space with male passengers. They cannot raise their voice when they face sexual harassment inside the car or when they walk. The parents of the female students find it safer to stop their education and arrange a marriage. We proposed a regular college bus service with an adaptive time schedule that follows the routine of the students. In order to make the service sustainable, we designed a model of multi service vehicle named SSW, so that it can earn extra income during its idle time. We concluded that the operational cost can be covered through the SSW model. We identified new requirements for multiservice vehicle to satisfy the needs of a rural community.

Fundamental requirements in mobility are time, cost and comfort. Individual car ownership satisfies comfort component and to some extent, the time component as well. However, owning and maintaining a car is prohibitive for many due to cost and convenience implications. In selecting other public modes of transportation, a taxi or rental car would provide a more comfortable ride with little to none waiting time and conforms to the passengers mobility requirements. However, the cost is too high and cannot be sustained as a regular mode of transport. On the other hand, shared public transport such as bus or train is more affordable but requires the passenger to conform their schedule to a set timetable that operates no matter the changes in demand. In developing countries, however, the shared public transport alternatives do not have timetables and waiting time could be up to an hour. Recent research in shared mobility systems, specifically Demand Responsive Transport (DRT), addresses this situation. Solutions to DRT trip scheduling are constrained to the variation of DRT specifications but does not vehicle schedule and quorum specifications considerations. We aim to reduce passenger waiting time for shared mobility and propose a design of a DRT-based Demand Responsive MaaS (Mobility as a Service) model that provides centralized management and ICT support. Our design adds time constraints of vehicle schedule to the DRT problem. We propose a trip scheduling and cost sharing algorithm for our designed model and base our approach on a DRT heuristic algorithm and a quorum to enforce a minimum demand. A simulation experiment showed average waiting time reduced by 44.4% compared to other DRT time optimization solutions. We conducted a pilot study in Dhaka, Bangladesh for 4 months. Actual average waiting time reduced to 25% compared to current public transport in Dhaka.

Non-communicable diseases (NCDs) are no longer just a problem for high-income countries, but they are also a problem that affects developing countries. Preventive medicine is definitely the key to combat NCDs; however, the cost of preventive programs is a critical issue affecting the popularization of these medicine programs in developing countries. In this study, we investigate predictive modeling for providing a low-cost preventive medicine program. In our two-year-long field study in Bangladesh, we collected the health checkup results of 15,075 subjects, the data of 6,607 prescriptions, and the follow-up examination results of 2,109 subjects. We address three prediction problems, namely subject risk prediction, drug recommendation, and future risk prediction, by using machine learning techniques; our multiple-classifier approach successfully reduced the costs of health checkups, a multi-task learning method provided accurate recommendation for specific types of drugs, and an active learning method achieved an efficient assignment of healthcare workers for the follow-up care of subjects.

We present a remote healthcare consultancy system that enables healthcare workers to identify noncommunicable diseases in unreached communities. The healthcare system combines medical sensors with mobile health and is called a Portable Health Clinic. The Portable Health Clinic fits into a briefcase and is operated by the healthcare worker. The goal of this research is to empower the healthcare worker further by allowing her to recognize spurious measurements and to make lifestyle recommendations. In this paper, we show how to process the data: combine, link and compare - captured in patient electronic health records stored in database. We applied association rule technique to find common set of rules in order to build a clinical decision support system. We also showed examples of the meaningful information from the analyzed data to build a better clinical decision support.

This study presents an ICT based transport system called Social Services on Wheels (SSW) that reduces villager's long distance trip-frequency in unreached communities. Trip-frequency is decreased using a community car to eliminate villager's need to travel to urban areas by bringing welfare services - access to healthcare, education, learning and purchasing - to the rural village. The community car brings measuring devices, PC notebooks and team members (Village entrepreneur, healthcare worker, IT assistant) to temporary service points within villages. The measuring devices and notebook applications are supported a back-end data operations office using mobile network coverage and Internet. The villager walks to the nearest service point and interfaces with the SSW operations and information systems. Social Service on Wheels has been tested in two rural villages in Bangladesh during October 2013 to February 2014. The results showed that 4,496 long distance trips were reduced because the villager were satisfactorily served without leaving their village. The villagers tended to associate the delivery of six social services with the Toyota community car rather than the SSW teams who performed the tests or helped with IT issues. SSW empowered the community by hiring locally and training the SSW teams. The sustainability of SSW project is a challenging area and is still being investigated.

Blood Pressure readings are widely accepted as a measure to determine the risk of non-communicable diseases such as hypertension and stroke. Affordable healthcare devices and sensors allow individuals to monitor blood pressure at home or at a local service point on a daily basis. ICT based healthcare systems interpret the readings and give feedback to individuals or may trigger a telemedicine call to a remote doctor. This paper introduces case studies for ICT healthcare studies undertaken in Japan and Bangladesh. Blood Pressure data collected by the Omron WellnessLink (500,000 readings) and the Kyushu University/Grameen Portable Heath Clinic (21,252 readings) are examined for similarities and differences. The results show similarities in gender and temporal influences. Males have higher blood pressure and readings appear to be rhythmic according to day and month. The differences indicate that the mean Systolic Blood Pressure (SBP) for Japanese males is higher than Bangladesh males and SBP for Bangladesh females is higher than Japanese females. The impact of climate is stronger on Japanese SBP than Bangladesh SBP. The Bangladesh data shows progressive increase in SBP in each ten year age category until 80 years; this is also reflected by BMI categories. The study reveals that affordable devices connected to basic ICT based healthcare systems reveal underlying factors in the Blood Pressure variability.

Presently, 75% of the world's population do not have access to the Internet. Most of them are people at the BOP (Base of the Pyramid, the poorest but largest economic group in the world). Many of the efforts to popularize ICT focus on increasing villagers' access to facilities and on training in ICT use to demonstrate the power of ICT to bring financial or social benefits. Users are viewed as information consumers only. We have developed an information platform where BOP can be both information producers and owners. In order to generate and upload web contents, the challenges observed are the villagers' text literacy limitations, the limited capability of the devices they use, and the available network capability. In order to overcome these limitations, we propose a BoP adaptation layer in the current social information infrastructure. This paper introduces the BOP adaptation layer concept, its architecture, and an example of how a low-literate village farmer can generate and upload his/her product information on the web.

In traditional conferencing systems, participants have little or no privacy, as their voices are by default shared with all others in a session. Such systems cannot offer participants the options of muting and deafening other members. The concept of narrowcasting can be applied to make these kinds of filters available in multimedia conferencing systems. Our system treats media sinks (in the simplest case, listeners) as full citizens, peers of the media sources (con- versants' voices), and we defined therefore duals of mute & select : deafen & attend, which respectively block a sink or focus on it to the exclusion of others. In this article, we describe our prototyped system, which uses existing standard Session Initiation Protocol (SIP) methods to control fine-grained narrowcasting sessions. The design considers the policy configured by the participants and provides a policy evaluation algorithm for media mixing and delivery. We have integrated a "virtual reality"-style interface with this SIP backend to display and control articulated narrowcasting with figurative avatars.

Media and the vectors of its transmission is private information and should be made available only to authorized participants in a conference. In a traditional conference system, users' voices might by default be shared with all others, but a participant might want to select a subset of the conference members to send his/her media to or receive streams from. We review the concept of narrowcasting, a technique for limiting such information streams in a multimedia conference, and pro- pose manipulation of media policies in centralized conferencing systems in a SIP framework. This system allows each participant to flexibly select another participant or group of participants for media transmission using existing standard protocol (SIP )f or configuring fine-grained narrowcasting sessions.

In traditional conferencing systems, participants' voices might by default be shared with all others. However a VOIP user might want to select a subset of session members to selectively exchange media streams. In this article, we describe an implementation of narrowcasting, a model for limiting such information streams in a multimedia conferences, as a class of policies, prototyping a system using existing standard Session Initiation Protocol (SIP) methods for controlling fine-grained narrowcasting sessions.

In existing meeting scheduling systems, finding a common free time slot of all (prospective) participants is the goal. When such a free-time slot is not found, the host has to ask the busy participants to change their schedules. Changing a schedule is a complex process requiring a lot of negotiations and, there is no guarantee that the goal will be achieved. In the worst case the host has to ignore the time slot (which was probably the first choice) and try to schedule the meeting in another time slot (probably a lesser choice). The process will continue till the scheduling succeeds. We argue that it is not always necessary for all the participants to attend a meeting. There are some participants whose presence is mandatory for the meeting. The presence of other participants are non-mandatory. The meeting can proceed in the absence of some of the non-mandatory participants. This allows greater flexibility and more efficient scheduling. This paper introduces the concept of a Quorum in the meeting scheduling process and proposes a two-round negotiating protocol to find the time-slot which meets the quorum requirements. To establish the robustness of our scheduler, we simulated scheduling in our lab, and showed its flexibility in scheduling a meeting.