Mobile final year project ideas
Mobile final year project ideas from the free Sefism library, each scoped for a single semester with a suggested stack and deliverables.
- 300 project ideas
Ideas and guidance, not finished projects
These are project ideas and scoping guidance, published free for students to use as a starting point. I do not build, write, or sell final-year projects, and I do not complete coursework for anyone. Take an idea, make it yours, and build it.
49 ideas · page 1 of 3
Antenatal Follow-Up Prioritiser: Which Pregnant Women a Health Worker Should Call This Week
A health worker with 150 pregnant women on her list cannot call all of them every week. Build a mobile app and ranking model that suggests who to contact first, based on missed visits, risk factors and engagement history, and measures whether the ranking finds women who would otherwise drop out of antenatal care. The project is about fair, explainable prioritisation under a fixed call budget, not about diagnosing anyone.
Closed-Loop Patient Referral Tracking Between Village Health Workers and District Hospitals
When a village health worker refers a patient to a hospital, nobody usually finds out whether the patient arrived, what happened, or whether follow-up is needed. Build an offline-first referral app and a simple hospital desk screen that close the loop: referral slip with a short code, arrival check-in, outcome note and a follow-up task back to the worker. Measure how many referrals get an outcome recorded.
USSD and SMS Revision Quizzes for Students on Feature Phones
Many secondary school students in Kenya, Nigeria, Pakistan and Bangladesh have access only to a family feature phone, with no data plan. Build a revision quiz service over USSD menus and SMS that delivers short, syllabus-linked multiple-choice quizzes, adapts to each student's weak topics and gives teachers a web dashboard. Engineer it for USSD's tight limits: short sessions, 160-character screens and dropped connections.
Crop Disease Photo Triage That Knows When to Ask an Agronomist, on Budget Android Phones
Most crop disease apps give a confident answer for every photo, even blurry ones, the wrong crop or a disease they never saw in training. Build an on-device classifier for a few crops that abstains when unsure and sends those photos to an agronomist review queue; the agronomist's answers become new training labels. The project measures how much accuracy improves when the app is allowed to say "I don't know".
Human-Approved AI Agent for Filing and Tracking Citizen Service Requests
Filing a complaint or service request with a city or government office means finding the right portal, filling long forms, attaching documents and then chasing it for weeks. Build an agent that turns a citizen's plain description (in Urdu, Roman Urdu or English) into a correctly filled request, pauses for the citizen to approve every submission, then tracks status and reminds them to follow up. Built and tested against a realistic mock portal you create.
Protocol-Locked Danger Sign Triage Assistant for Community Health Workers in Urdu, Bangla and Arabic
Build a phone assistant that walks a community health worker through a sick child visit in Urdu, Bangla or Arabic, where the triage decision comes from an encoded clinical protocol, never from a language model. The model only does what it is good at: understanding a spoken or typed answer in a local language and turning it into a protocol field. The project tests whether that split keeps the decisions safe while making the tool easier to use than a long paper form.
Buy Now Pay Later Stacking Tracker and Affordability Check Across Providers
Young shoppers in the Gulf, India and the UK often have several buy now pay later plans with different providers at once, and no single place shows the total due each month. Build a privacy-first mobile app that collects instalments from order emails, SMS or manual entry, shows a combined calendar of what is due, and runs an affordability check against the user's income and fixed costs before they take on another plan.
Pairwise Preference Labelling App for Urdu LLM Answers with Rater Calibration
Language models learn what 'good' means from human preference data, and very little of it is in Urdu. Build a mobile-friendly app where raters compare two model answers to an Urdu or Roman Urdu prompt, choose the better one against a clear rubric, and explain why. The system checks rater consistency, corrects for position bias, and produces a clean, documented preference dataset and a small leaderboard.
Medicine Box and Strip Identification for Pharmacy Dispensing Double-Checks
Build a camera check for small pharmacies: the assistant scans the medicine picked from the shelf, and the app matches the box or blister strip to a catalogue, reads the strength and warns when it does not match the prescription line. Look-alike packaging and similar names cause dispensing mistakes, and small pharmacies rarely have barcode systems. The project uses image retrieval with a pretrained model, so new medicines can be added from a few photos without retraining.
Urdu Handwriting Practice App for Children with Stroke Order and Letter Form Feedback
Build a tablet and phone app where young children trace and write Urdu letters with a finger or stylus, and the app checks stroke order, direction, dot placement and the joined forms letters take at the start, middle and end of words, then shows exactly what to fix. Teachers in crowded classrooms cannot watch every child form every letter, and bad habits set early. The technical core is recognising and comparing handwriting as a sequence of strokes, not as a finished image.
Cattle Weight Estimation from Phone Photos for Small Dairy Farmers and Livestock Buyers
Build a phone app that estimates the live weight of a cow or bull from a side photo and a printed reference marker, records weight over time and shows a likely range rather than a single number. Small farmers rarely own a scale, so they guess weight for feeding, medicine doses and sale, and buyers at livestock markets do the same. The project trains a lightweight keypoint and regression model and validates it against a weighbridge with a veterinary or livestock farm partner.
Electricity Slab Tracker App That Warns Before You Lose the Protected Tariff
Build a mobile app where households enter their meter reading every few days and see how many units they will use by the end of the billing cycle, the estimated bill and how close they are to the next tariff slab. In Pakistan, crossing the 200-unit protected threshold in one month can raise bills for months afterwards. The app turns occasional meter readings into a forecast and timely warnings, with the tariff rules kept as editable data.
School Hearing Screening App with Ambient Noise Monitoring and Referral Tracking
Build an Android app that lets a school nurse or trained teacher run a pure-tone hearing screen with calibrated headphones, refuses to test when the room is too noisy, catches children who tap at random and tracks referrals to an audiologist. Many children with hearing loss in Pakistan are never screened and are seen as inattentive in class. The project follows a published smartphone screening method and checks its results against an audiologist's tests.
Video-Observed TB Treatment App with Offline Upload for Patients and Treatment Supporters
Build an Android app that lets a tuberculosis patient record a short video of taking each day's medicine, stores it encrypted, uploads it when there is signal and lets a treatment supporter review doses and follow up on missed ones. Daily in-person observation is hard for patients who work, live far from a clinic or have to travel. The project follows the model of a published randomised trial and focuses on making it work on cheap phones and poor connections.
On-Device LLM Benchmark App for Budget Android Phones with Urdu Quality Tests
Build an Android app that runs small language models on the phone itself and measures what developers need to know before shipping on-device AI: speed, memory, battery drain, heating over a sustained run, crashes, and answer quality on Urdu and Roman Urdu tasks. Results from volunteers' phones feed a public table of how common budget models actually perform. Most published numbers come from flagship phones and English prompts, which tells a developer in Pakistan very little.
Phone Spyware Check Kit for Domestic Abuse Support Workers, in English and Urdu
Build a laptop-based kit that a trained support worker uses to check a survivor's Android phone for stalkerware, risky dual-use apps, unknown device admins and account access the survivor did not set up. It runs over a USB cable without installing anything on the phone, and explains results in plain English and Urdu. It follows the clinical computer security approach developed by researchers at Cornell Tech.
Offline Child Growth Monitoring App for Lady Health Workers with WHO Z-Scores
Build an offline Android app that community health workers use at household visits to record a child's weight, length and arm circumference, compute WHO growth z-scores on the phone, flag faltering growth across visits and generate referrals. Paper growth charts are often incomplete and hard to read, and the WHO desktop software does not go to the doorstep. The core is correct z-score computation, validated against the WHO reference implementation, and a sync design that survives weeks offline.
Pheromone Trap Moth Counting from Phone Photos for Cotton Pest Scouts
Build an app and model that count bollworm moths on a pheromone trap's sticky card from a phone photo, log the count with the trap's location and date, and show agriculture extension staff where catches are rising. Scouts count moths by eye today and write numbers on paper, so the data arrives late and is hard to compare. The project uses an existing phone and trap, not new hardware.
Offline Bird Call Survey App for Wetland and Wildlife Field Teams
Build an Android app that records bird calls during a structured field survey, identifies likely species on the phone with an open bird sound model, filters suggestions to species expected in that region and season, and sends uncertain recordings to an expert for review. Wildlife departments, university ecology groups and birdwatchers survey Pakistan's wetlands, often with paper forms and no signal. The project turns each survey into consistent, checkable data.
Loan and Wallet App Privacy Label Checker That Compares Claims With Real Traffic
Build a test bench that installs Android finance apps, records what they request, store and send, and compares that with the Data Safety section each app declares on Google Play. Predatory loan apps in Pakistan have harvested contact lists to harass borrowers, and the declared labels are often incomplete. The output is a per-app evidence report useful to researchers, journalists, regulators and careful users.
Fingernail Photo Anaemia Screening App for Community Health Workers
Build an offline phone app that guides a community health worker to take a fingernail photo with a colour reference card, estimates whether the person is likely to be anaemic and tracks referral for a blood test. Anaemia is common among women and children in South Asia and often goes unnoticed because a blood test means travelling to a lab. The project reproduces a published smartphone method, checks it against a haemoglobin meter with clinical partners and is clear that it screens, not diagnoses.
Verifiable Committee (ROSCA) Ledger with Provably Fair Payout Draws
Build a ledger app for informal committees (ROSCAs, also called BCs) where every payment entry is signed and hash-chained, so the organiser cannot quietly edit history, and the monthly payout order is decided by a commit-reveal draw that any member can verify. The app never holds money; it records it. The project combines applied cryptography, offline-first sync and a real social problem.
Low-Cost Beehive Weight and Temperature Monitor for Migratory Beekeepers
Build a solar-powered hive scale and sensor node that records hive weight, inside temperature and humidity every few minutes, sends data over LoRa to a gateway at the apiary and alerts the beekeeper to swarming, a nectar flow ending, a hive tipped over or a colony losing weight. Beekeepers who move hives between flowering areas cannot inspect every box every day. The core is accurate weighing outdoors and turning weight curves into events.
Offline Reading Level Assessment App for Teaching at the Right Level Programmes
Build an offline Android app that volunteers and teachers use to assess each child's reading level in Urdu with a short oral test, group children by level for remedial classes and track progress every few weeks. Programmes that teach children at their actual level depend on quick, reliable assessments, which are usually done on paper. The project adds consistency checks between assessors and audio-backed moderation, without relying on speech AI.
Browse project ideas by domain and difficulty
Each of these is its own page, so you can send someone straight to the AI ideas or the beginner ones.
Stuck on something specific?
Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Sessions are free for approved Sefism members, and a few slots open each week.
- 1:1 Mentorship
- Fresh Graduate Mentorship
- Career Guidance
Brand deals, promos and partnerships: tauseeffayyaz@gmail.com
Follow along
New writing, resources and project ideas land here first.