Program
Soft Opening
Keynote Speech #1
Cloud computing, "the practice of using a network of remote servers hosted on the Internet to store, manage, and process data, rather than a personal computer," has fundamentally changed the way society performs daily businesses and social activities. Emails, text and video chats, picture and video sharing, blogs and news, are all backed by a large complex collection of Internet services, which we refer as "the Cloud." As dependency on cloud computing increases, society demands high availability, an ideal 24/7 service uptime if possible. Yet, service outages are hard to escape from. Not only do outages hurt customers, they also cause financial and reputation damages. Minutes of service downtimes can create hundreds of thousands of dollar, if not multi-million, of loss in revenue. Company's stock can plummet after an outage. Sometimes, re- funds must be given to customers as a form of apology. As rivals always seek to capitalize an outage, millions of users can switch to another competitor, a company's worst nightmare.
Tutorial Session #1
Higher education institutions are complex and multifaceted organizations comprised of multiple departments that must work together to execute a successful vision. The Microsoft Education Transformation Framework enables a holistic look at the institution but provides you with the ability to develop your digital strategy in discrete phases, answering that all important question, "Where should I start?". The Microsoft Education Transformation Framework provides practical advice to help you develop a strategy for digital transformation with a holistic, long-term view implemented in discrete phases that you can begin today to help drive innovative student engagement, transform operations, and ensure a secure, connected campus to empower you to reimagine education.
Keynote Speech #2
Contact Tracing is the activity of retrieving historical activities and trips for a person where his presence at a specific location might affect other persons within a certain radius. In related to a contagious disease, an infected person might spread the pathogens to the nearby people during close contact that can trigger a chain reaction of community transmission. The biggest problem in obtaining the historical activities in a contact tracing procedure is privacy and security issues. The privacy issue refers to private-related sensitive information that is not meant to be shared with anyone. However, during a contact tracing investigation, the authorities have the right to know every detail from a suspected patient. The security issue refers to the safety of the shared private information to the authority. Due to these issues, many patients are reluctant to share their past activities to the authority. This condition makes it even harder to obtain the right information from the patients. The next consequence is that the spreading of the diseases will be off the radar since contact tracing could not be done correctly. Several methods have been proposed to help contact tracing procedures. In general, there are two types of contact tracing methods, proximity-based and trajectory-based. While the proximity-based method lacks historical trips and suffers from multi-platforms communication issues, trajectory-based suffers from privacy issues. This speech will discuss these methods together with their pros and cons. In conclusion, a method that can preserve privacy and retain the details of the trip will also be explained in this session as an alternative method to support contact tracing.
Keynote Speech #3
Indonesia is severely impacted by COVID-19 with more than two million cases and a current thousand deaths a day. With a 270 million population living in 514 cities within 6,000 islands, it is a logistical nightmare for vaccine distribution. To navigate that challenge Bio Farma as a state-owned enterprise specialized in vaccine production and distribution has been collaborating with several technology companies coordinated by Telkom to develop a Supply Chain 4.0 system of COVID-19 vaccine distribution. A blessing in disguise, the 3-year stalled development of the Supply Chain 4.0 called Track and Trace system, was catalyzed by this pandemic. The system enables us to track and trace every vial of vaccine from the first mile of production pipeline to the last mile delivery at the clinic or hospital. The system applies a 2-D Data Matrix in vaccine vial, secondary package, and tertiary package which allows overall product identification, traceability, and authentication from end-to-end. Utilizing IoT sensors, the system steadily records the location and temperature of vaccines while being stored or transported to ensure vaccine quality until the last mile.The system is integrable with other monitoring such as senior leader's dashboard at the Ministry of Health, the Ministry of State-owned Enterprises, and other senior leader offices. This allows for well-orchestrated operations, fast response to the challenge in operations and data-driven decision making for both operations and strategies.
Birds of a Feather #1
Birds of a Feather #2
Birds of a Feather #3
Birds of a Feather #4
Birds of a Feather #5
Greetings and Video Presentation
Welcoming Speech by General Chair of ICoICT 2021
Speech by Universitas Gadjah Mada
Speech by Multimedia University
Speech by IEEE-Indonesia Section
Opening Speech by Rector of Telkom University
Keynote Speech #4
The Covid-19 pandemic is a health crisis that affects all aspects of people's lives, especially the economic aspect. We have now gotten used to the New Normal era, of course, with a high level of vigilance. All countries today are faced with the dilemma of how to restore socio-economic life, in the midst of efforts to stop the spread of Covid-19. Handling COVID-19 in Indonesia involves 3 important roles from stakeholders, namely: Government, Society, and Technology as enablers to facilitate the process of Testing, Tracing, Isolating, to Treatment. The government continues to strive to prepare some strategies for handling Covid-19, one of which is by establishing institutional synergies in the 'Task Force for Research and Technological Innovation for Handling Covid-19 (TFRIC-19) led by the Agency for the Assessment and Application of Technology (BPPT). Digital Transformation is the key to national economic recovery and helps deliver the "new normal" adaptation. This is in line with the President's mandate to expand access, improve infrastructure, accelerate the digital transformation roadmap and its regulations, including the preparation of digital talents. Another aspect that can also encourage increased economic recovery is the aspect of leadership through synergy and collaboration of all related entities. BPPT and TFRIC-19 have established a systematic and constructive ecosystem related to testing technology innovations and medical devices, including: the testing strategy is carried out by designing the RT-PCR test kit which is the golden standard for Covid-19 testing, then the Covid-19 Monitor application is designed which can map the movement of the virus through tracing suspects as carriers. The increase in testing needs is anticipated by building a level-2 biosafety mobile lab equipped with complete test instruments. Strengthening the prevention process is also carried out by preparing appropriate technology facilities and infrastructure in the form of innovative hand washing tools and disinfectant variants. In the realm of Treatment, an AI-based Medical Image Management diagnostic tool has been prepared to process X-Ray and CT-Scan data, which can be a solution for the uneven distribution of health tools and technology that can become an obstacle in the speed of establishing patient diagnoses under supervision. In the curative aspect, especially for Covid patients with severe symptoms who require respiratory aids, 3 variants of emergency ventilators are prepared, as needed. In the future, the plan for mapping the entire virus variant to identify virus profiling will be carried out through pattern recognition. This national genome research will later become a virtual asset for the development of big data and supercomputing to be able to carry out the process of monitoring data collection, mitigation and produce recommendations and strategic actions that will encourage the emergence of product innovations for handling Covid-19 and awaken national independence in the health sector. TRFRIC-19 Next generation will continue to be committed through 5 main actions, including: Action to strengthen economic and technological studies which include supply chain studies, supply demand studies, pre-commercialization studies, manufacturing industry readiness studies, TKDN studies, technology audits and innovation ecosystem map studies, Medical device technology innovation actions, including ICU ventilator innovations, Direct Digital Radiography (DDR), quantitative antibody levels measuring kits and Antigen Rapid Tests, Health supplement technology innovation actions, including fermented garlic-based health supplements, beta glucan-based health supplements and supplements in the form of nutrient dense biscuits. Actions to strengthen scientific data and applications of artificial intelligence, including AI Application Innovations for Covid-19 detection, Bioprospection Database of Medicinal Plants, Microbes and Compounds with Potential Drugs for Covid-19 and other infectious diseases, as Artificial Intelligence Data Sets, Actions to strengthen Cooperation, Commercialization and Media. This activity is expected to provide a positive estuary for product innovation actions developed by the innovation ecosystem. To create an independent Indonesia and help economic recovery during the Covid-19 pandemic.
Knowledge Transfer
The outbreak of pandemic was quite unexpected. Many digital solutions/innovations were put into place for emergency use only, without considering the long term impact, especially in supporting workforce; however it is becoming increasingly likely that we will be living in this new normal thus we need to rethink, redesign the initial solutions to enhance security, enrich features and improve user experience. In this session I will explore some typical digital solutions for workforce enablement and discuss how these types of technology may impact our work and life and what features that need to be enabled to become more sustainable.
Tutorial Session #2
Inertial Measurement Units (IMUs) is mostly embedded in wearable devices. Nowadays, IMUs motion tracking systems are allowing for long-lasting tracking of user motion in a situated environment. Instead of body motion tracking, on the other hand, wearing IMUs on the chest wall offers a few advantages, such as for cardiac activity parameters estimation and respiration parameter estimation. For example, current research shows that inertial sensors are low-cost and easy-to-use breathing-monitoring systems. Breathing parameters from chest-wall inclination signals are easily measured using IMU. This tutorial presents several techniques for IMUs based motion tracking to reconstruct chest wall motion with respect to angular velocity and linear acceleration. Several techniques for data or signal processing architectures are also discussed. This tutorial also tries to introduce the applications of chest-worn IMUs based motion tracking to estimate heart-rate, blood-pressure, and respiration rate.
1A: Applications for post-pandemic recovery
- The Role of Technology and Innovation Capabilities in Achieving Business Resilience of MSMEs During Covid-19: Empirical Study
- Gaze-Controlled Digital Signage for Public Health Education during Covid-19 Pandemic
- Analysis of the House of Risk (HOR) Model for Risk Mitigation of the Supply Chain Management Process (Case Study: KPBS Pangalengan Bandung, Indonesia)
- Evaluation of the Social Restriction and its Effect to the COVID-19 Spread in Indonesia
- Contributing Clinical Attributes to COVID-19 Mortality in Jakarta: Machine Learning Study
1B: Computer Vision
- Multi-Target Regression Using Convolutional Neural Network-Random Forests (CNN-RF) For Early Earthquake Warning System
- Vision-Based Employee Activity Classification
- Compressive Sensing Image Watermarking Orthogonal Matching Pursuit
- Traffic Sign Recognition with Convolutional Neural Network
- Deep Convolutional Generative Adversarial Network Application in Batik Pattern Generator
1C: Data Science
- Convolutional Neural Networks for Indonesian Aspect-Based Sentiment Analysis Tourism Review
- Sentiment Analysis on Marketplace Review using Hybrid Lexicon and SVM Method
- Forecasting Number of COVID-19 Cases in Indonesia with ARIMA and ARIMAX Models
- Disaster Tweet Classification Based On Geospatial Data Using the BERT-MLP Method
- Cyberbullying Detection on Indonesian Twitter using Doc2Vec and Convolutional Neural Network
1D: E-Learning and HCI
- Digital Nudge Evaluation on COVID-19 tracing Application
- Developing Suicide Risk Idea Identification for Teenager (SERIINA) Mobile Apps Prototype using Extended Rapid Application Development
- Designing An Educational Game Evaluation Framework Based On Game Mechanic
- Cultivating Recycling Awareness in Preschoolers using Animated Interactive Comic
- Analysis Influence of The Organizational Learning Environment Factors To Encourage Employee Motivation Using E-Learning
1E: Healthcare, Bioinformatics, and Biomedical Applications
- Distributed Phylogenetic Tree Processing on Biology Sequences Using Mapreduce
- Linear Regression Model to Predict the Spread of COVID-19 in Tangerang City
- Strategic Information System Planning for Indonesia Non-franchise Pharmacies Based on John Ward and Factor Analysis Method
- Flexible Multi-Layer Condura Fabric Ultra Wide-Band Antenna For Telemedicine Application
- Anonymizing Prescription Data Against Individual Privacy Breach in Healthcare Database
Tutorial Session #3
This tutorial discusses various methods to detect and to identify faces, facial landmarks, and facial attributes in images and videos collected from public spaces. Such methods provide information that might be useful for public space monitoring and access control in particular during the current pandemic situation. Algorithms such as cascaded regression and probabilistic discriminant analysis will be discussed and implemented in the tutorial.
2A: Networking, IoT, and Security
- Simulation Of Jellyfish Topology Link Failure Handling Using Floyd-Warshall and Johnson Algorithm in Software Defined Network Architecture
- Game Theoretical Power Control in Heterogeneous Network
- IoT Drone Camera for a Paddy Crop Health Detector with RGB Comparison
- A Review on IoT with Big Data Analytics
- Vehicle Blind Spot Area Detection Using Bluetooth Low Energy and Multilateration
2B: Computer Vision
- Facial Emotion Recognition using Transfer Learning of Alexnet
- Visually Similar Handwritten Chinese Character Recognition with Convolutional Neural Network
- Pneumonia Classification using Gabor-Convolutional Neural Networks and Image Enhancement
- Fingerprint Enhancement using Iterative Contextual Filtering for Fingerprint Matching
- Histogram of Oriented Gradient Random Template Protection for Face Verification
2C: Data Science
- Aspect-Based Sentiment Analysis in Beauty Product Reviews Using TF-IDF and SVM Algorithm
- Aspect Term Extraction Using Deep Learning-Based Approach on Indonesian Restaurant Reviews
- Spam Detection on Indonesian Beauty Product Review
- Emotion Classification on Indonesian Twitter Using Convolutional Neural Network (CNN)
- Mapping Complex Tourist Destination Preferences: Network Perspectives
2D: E-Learning and HCI
- Exploring the existence and variation of Game Player Traits among Undergraduate students in Malaysia
- Implementation of Continuous Integration and Continuous Delivery (CI/CD) on Automatic Performance Testing
- Understanding Government Reorganization Impact from Knowledge Management Perspective: A Study Case
- RPA-based Bots for Managing Online Learning Materials
- Enterprise Resource Planning Teaching in Post Pandemic using Gamification
2E: Healthcare, Bioinformatics, and Biomedical Applications
- Holick's Rule Implementation: Calculation of Produced Vitamin D from Sunlight Based on UV Index, Skin Type, and Area of Sunlight Exposure on the Body
- T-COFFEE Multiple Sequence Aligner on Hadoop Spark Cluster
- Relaxation Oscillator Using Closed-loop Dual Comparator for Biomedical Applications
- Wireless Programmable body sensor networks and Situated Healthcare
Keynote Speech #5
Kazem Rahimi is a Professor of Cardiovascular Medicine and Population Health, at the University of Oxford and a consultant cardiologist at the Oxford University Hospitals NHS Trust. His research interests include hypertension, heart failure, multimorbidity and cardiovascular risk management, using a variety of methodologies such as individual-patient meta-analysis, large-scale decentralised clinical trials, and digital health technologies. Kazem leads the Deep Medicine programme at the Nuffield Department of Women's and Reproductive Health with a major interest in the application of machine learning approaches to electronic health records. He also leads the Blood Pressure Lowering Treatment Trialists' Collaboration (BPLTTC), which is an international collaboration of all the major trials of blood pressure lowering drugs. He is the Director of the Martin School Programme on Informal Cities and a Co-Investigator of the PEAK-Urban programme.
Keynote Speech #6
Sentiment analysis is the computational study of people's opinions, attitudes, and emotions expressed in a text or written language. Due to many challenging research problems and a wide range of practical applications, it has become one of the most active research areas in natural language processing in recent years. In this talk, I will discuss mainstream sentiment analysis research before moving on to describe some more recent work on modelling opinion and comments of COVID-19 Pandemic on Social Media. This research naturally connects computer science and social science, especially communication and political sciences, in social media analysis.
Closing day 2
Opening day 3
Tutorial Session #4
Bioinformatics and cloud technologies have been beneficial in many countries' decision-making during this pandemic. Sequence analysis algorithms, such as fast algorithms on sequence alignment, de-novo assembly, gene annotation, gene expression analysis, gene prediction, and antibiotic resistance finding, have been crucial in solving an outbreak. Nowadays, DNA sequencing has become a routine task, and people can even do it in their kitchen. Improvements in DNA sequencing techniques have encouraged the popularity of shotgun metagenomics. The whole metagenome shotgun enables finding the microbial diversity - or in medical bioinformatics, the list of pathogens - in one sample. Additionally, it is also the primary key to discover the cure for genetic diseases and cancer. Together with microbiome research, bioinformatics has encouraged fecal microbiota transplant (FMT) research to cure many diseases such as CDI, bipolar disorder, autism, and cancer.
3A: Networking, IoT, and Security
- AADC 3: Active-Active Distributed Controller with 3-in-1 Asynchronous Heartbeat Synchronization Method in Software-Defined Networks
- 4G LTE Cellular Network Coverage Planning and Simulation on Mandalay Area with Propagation Model Cost-Hatta
- USB Flash Drives Forensic Analysis to Detect Crown Jewel Data Breach in PT. XYZ (Coffee Shop Retail - Case Study)
- Detection of Sinusoids with Frequency Drift in White Gaussian Noise
- Tone Detection System Design for Targets with Frequency Drift
3B: Computer Vision
- Enhanced AlexNet with Super-Resolution for Low-Resolution Face Recognition
- An End-to-End Optical Character Recognition Pipeline for Indonesian Identity Card
- A Study of Batik Style Transfer using Neural Network
- Tomato Plant Disease Identification through Leaf Image using Convolutional Neural Network
3C: Data Science
- Non-Stationary Order of Vector Autoregression in Significant Ocean Wave Forecasting
- FN-Net: A Deep Convolutional Neural Network for Fake News Detection
- Sentiment Analysis of Ojek Online User Satisfaction Based on the Naïve Bayes and Net Brand Reputation Method
- Raw Paper Material Stock Forecasting with Long Short-Term Memory
- Mobile Customer Behaviour Predictive Analysis for Targeting Netflix Potential Customer
3D: E-Learning and HCI
- Implementation and Analysis of Reusability Framework Design for Event User Interface Component in Phaser 3
- Master Data Management Maturity Model (MD3M) Assessment: A Case Study in Secretariat of Presidential Advisory Council
- Capturing Institution and Learners Readiness of e-Learning Implementation: A Case Study of a University in Bandung, Indonesia
- Satisfaction Factors of Indonesian National Civil Servant Recruitment System
- The Preliminary Study on the Perception of Engineering Students on Blended Learning
3E: Healthcare, Bioinformatics, and Biomedical Applications
- Implant Segmentation in Radiographic Imagery Using Wavelet Decomposition and Multiresolution MTANN
- Improving Multi-Class Motor Imagery EEG Signals Classification Using Ensemble Learning Method
- Implementation and Experimental Characterization of Dual-Band Wearable Reflector Composed of AMC Structure for Wireless Communication
Tutorial Session #5
Every day, approximately 2.5 quintillion bytes of data are created. These data come from digital pictures, videos, posts to social media sites, intelligent sensors, purchase transaction records, cell phone GPS signals, to name a few. This is known as Big Data. There is no doubt that Big Data and especially what we do with it has the potential to become a driving force for innovation and value creation. Innovations in technology and greater affordability of digital devices have presided over today's Age of Big Data, an umbrella term for the explosion in the quantity and diversity of high frequency digital data. These data hold the potential as yet largely untapped to allow decision makers to track development progress, improve social protection, and understand where existing policies and programmes require adjustment. Turning Big Data-call logs, mobile-banking transactions, online user-generated content such as blog posts and Tweets, online searches, satellite images, etc. into actionable information requires using computational techniques to unveil trends and patterns within and between these extremely large socioeconomic datasets. New insights gleaned from such data mining should complement official statistics, survey data, and information generated by Early Warning Systems, adding depth and nuances on human behaviours and experiences and doing so in real time, thereby narrowing both information and time gaps. The promise of data-driven decision-making is now being recognized broadly, and there is growing enthusiasm for the notion of ``Big Data.'' There is currently a wide gap between its potential and its realization. Heterogeneity, scale, timeliness, complexity, and privacy problems with Big Data impede progress at all phases of the pipeline that can create value from data. A large amount of data today is not natively in structured format; for example, tweets and blogs are weakly structured pieces of text, while images and video are structured for storage and display, but not for semantic content and search. Transforming such content into a structured format for later analysis is a major challenge. The value of data explodes when it can be linked with other data, thus data integration is a major creator of value. Since most data is directly generated in digital format today, we have the opportunity and the challenge both to influence the creation to facilitate later linkage and to automatically link previously created data. Data analysis, organization, retrieval, and modeling are other foundational challenges. Data analysis is a clear bottleneck in many applications, both due to lack of scalability of the underlying algorithms and due to the complexity of the data that needs to be analyzed. Finally, presentation of the results and its interpretation by non-technical domain experts is crucial to extracting actionable knowledge.The many novel challenges and opportunities associated with Big Data necessitate rethinking many aspects of these data management platforms, while retaining other desirable aspects. It should be point out that the appropriate investment in Big Data will lead to a new wave of fundamental technological advances that will be embodied in the next generations of Big Data management and analysis platforms, products, and systems. Thus, we should believe that these research problems are not only timely, but also have the potential to create huge economic value in the world economy for years to come. However, they are also hard, requiring us to rethink data analysis systems in fundamental ways. A major investment in Big Data, properly directed, can result not only in major scientific advances, but also lay the foundation for the next generation of advances in science, medicine, and business.
4A: Networking, IoT, and Security
- Modified Pixel Value Ordering-based Predictor for Reversible Data Hiding on Video
- Simulation Analysis of Partial Transmit Sequence on Palm Date Leaf Clipping for PAPR Value Reduction
- Design Automation of Single Photon Counting Method for Quantum Random Number Generation
- On the Modifications of a Digital Signature Algorithm with Secret Sharing
- Connected Vehicle Communication Concept for Flood Level Warning Using Low Cost Microcontroller
- Randomness, Uniqueness, and Steadiness Evaluation of Physical Unclonable Functions
4B: Computer Vision
- A Low-Cost High-Accuracy Thermal Camera Using Off-the-shelf Hardware Devices
- Sentinel 1 Classification for Garlic Land Identification using Support Vector Machine
- Recognition of Academic Emotions in Online Classes
- Image Steganography Compressive Sensing Orthogonal Matching Pursuit
4C: Data Science
- Hoax Identification on Tweets in Indonesia Using Doc2Vec
- Electronic Nose Dataset for Classifying Rice Quality using Neural Network
- SVM Parallel Concept Test with SMO Decomposition on Cancer Microarray Dataset
- Detecting Online Recruitment Fraud Using Machine Learning
- Data Mining for Revealing Relationship Between Google Community Mobility and Macro-Economic Indicators
4D: E-Learning and HCI
- Suitable Knowledge Management Process Implementation: a case study of PT XYZ
- Critical Success Factors for Project Tracking Software Implementation: A Case Study at a Banking Company in Indonesia
- Assurance Case Pattern using SACM Notation
- Sustainability And Aptness Of Game Elements In A Gamified Learning Environment
- User Interface Model for Visualization of Learning Materials in Comic Strip Form Using Goal-Directed Design Method
4E: Networking, IoT, and Security
- Accessibility and Response Time Analysis on the COVID19 Website in Indonesia
- Modified Bit Parity Technique for Error Detection of 8 Bit Data
- IoT Application on Agricultural Area Surveillance and Remote-controlled Irrigation Systems
- Hunting Cyber Threats in the Enterprise Using Network Defense Log
- Present-80 Encryption Algorithm Implementation on GPRS Arduino Mega-2560 Cyber Physical Tracking System
5A: Networking, IoT, and Security
- Learning Method of Performance-oriented Congestion Control (PCC) for Video Streaming Analysis
- Building an ID Card Repository with Progressive Web Application to Mitigate Fraud based on the Twelve-Factor App methodology
- XB-Pot: Revealing Honeypot-based Attacker's Behaviors
- Design of a Snort-based IDS on the Raspberry Pi 3 Model B+ Applying TaZmen Sniffer Protocol and Log Alert Integrity Assurance with SHA-3
- Experimental Investigation of Wave Absorber Made of Ring Resonator-Based AMC Structure
5B: Data Science
- Information Cascade Mechanism and Measurement of Indonesian Fake News
- Fraud Accounts Identification Modelling on Multi-Platform E-Commerce
- Classification on Participants Renewal Process in Insurance Company: Case Study PT XYZ
- Hybrid Space-Time Model and Machine Learning for Forecasting Multivariate Spatio-Temporal Data
- Comparative Study of Covid-19 Tweets Sentiment Classification Methods
5C: Data Science
- Forecasting of COVID-19 Cases in Jakarta using Poisson Autoregression
- Optimization of Crops Allocation Planning in Cianjur Involving Water Cost Constraints Using Genetic Algorithm
- Fake News Detection with Hybrid CNN-LSTM
- Aspect Based Sentiment Analysis With Combination Feature Extraction LDA and Word2vec
- Sentiment Analysis on Beauty Product Reviews using LSTM Method
5D: Data Science
- Indonesian ID Card Extractor Using Optical Character Recognition and Natural Language Post-Processing
- Analysis of Records Management Maturity Level for Data Collection of Network Assets in Indonesian Telecommunication Industry
- Data Acquisition Guide for Forest Fire Risk Modelling in Malaysia
- Implementation of Hidden Markov Model (HMM) to Predict Financial Market Regime
- Prediction of Graduation with Naïve Bayes Algorithm and Principal Component Analysis (PCA) on Time Series Data
5E: Data Science
- Comparative Analysis of Support Vector Machine (SVM) and Random Forest (RF) Classification for Cancer Detection using Microarray
- Evaluating the BPPT Medical Speech Corpus for An ASR Medical Record Transcription System
- Implementation of Simulated Annealing-Support Vector Machine on QSAR Study of Indenopyrazole Derivative as Anti-Cancer Agent
- Ransomware Detection on Bitcoin Transactions Using Artificial Neural Network Methods
- Emotional Context Detection on Conversation Text with Deep Learning Method Using Long Short-Term Memory and Attention Networks
Keynote Speech #7
The emergence of SARS-CoV-2 in December 2019 in China and its worldwide dissemination has become a major public health priority, including in Indonesia. In this talk, I will share some background stories of my involvement in the SIMCOVID consortium that model the disease and help local governments in the country in fighting the pandemic. I will discuss some mathematical models and methods that we developed, that have been used to extract information for developing and evaluating policy responses. I will also discuss my ‘apologies' on the limitations of the work.
Keynote Speech #8
Scientists in the field of machine learning (ML) - including deep learning (DL) -- aspire to build better models (usually judged by beating SOTA in well-defined tasks and datasets); successful applications of such models, on the other hand, are about product-market fit (PMF) in environments with ever-growing complexities. As many expect ML to play a bigger role in our society, ML scientists' ability to influence this journey will depend on putting ML research in a PMF context and vice versa (i.e., optimizing for market.fit()+⍺*model.fit(), instead of optimizing for model.fit() alone). Therefore, in this talk, I aim to cover the general principals of building AI products in the "real world", covering topics such as AI product-market fit and impact evaluation in medicine