De La Salle University – Dasmariñas

College of Science and Computer Studies

Computer Studies Department

Computer Science Benchmark

The Computer Studies Department has designed a new research strategy in order to
be a leader in technology and computer science research. These are focused on the National
Higher Education Research Agenda and CHED are aimed at assisting in the strengthening of
the country's economy and development by delivering research projects that can be used by
the general public.

These efforts aim to collaborate partnership with local and international research institutes.

Embedded Systems Programming Models for Parallel Signal Processing

Advanced Architectures for Multimedia Signal Processing
Rapid Prototyping Techniques Architecture,
compiler optimization
Mobile and Game AR/VR Games, RGP, 2D, 3D games
Development Intelligence Mobile Application, Mobile GIS and mapping
application
Mobile Application in different domain, Application
Automation
Graphics Application Processing and Modelling
Dynamic Simulation and Immersive Computing
Bioinformatics Structure Prediction like Homology Modelling
Building Predictive Models for Disease Diagnoses
Natural Language Processing Human-like Language Generation
Multimodal and Embodied Semantics
Robotics Artificial Intelligence
Tele-operations
Intelligent Sensing
Motion Control and Agile Locomotion
Image Processing/Signal Biomedical Imaging
Processing Image Segmentation and Classification
Intelligent Systems Remote Sensing, Data Simulation
Human Identification using various biometric modalities (face,
fingerprint, iris, hand)
Visual Surveillance/Inspection
Forecasting and Optimization Detection
COMPUTER SCIENCE BENCHMARK CSD DEPARTMENT
 Computer Vision Edge Detection
Image Recognition, Classification and Localization
Machine Learning Deep Learning (Artificial Neural Network, Convolutional Neural
Network, Recurrent Neural Network, Self-organizing maps,
Boltzmann Machines, Auto Encoders)
Internet of Things Applied ML to IoT for the smart devices, wearable, smart
home, smart city, smart healthcare, smart agriculture, traffics
etc.
GIS Application GIS Datamining, Data Analysis, Web Mapping
Big Data Analytics Realtime Processing and Decision Making
Computer Forensics Information Forensic and Security

MACHINE LEARNING
Machine learning (particularly deep learning) can assist in the solution of problems that are difficult
or impossible to solve using traditional computation methods. The following are some of the
problems:

• Recognizing patterns in data series and predicting future values (e.g.

deducing personalized product recommendations from previous purchases).
• Clustering datasets and assigning categories (e.g. image or facial recognition).
• Detecting deviations from normal behavior (e.g. fault detection in operation).

Requirements:

• Trained Model (Supervise and unsupervised)

• Data Exploration
• Explore Models
• Feature Engineering
• Training Scale
• Model Development
• Model Deployment
• Model Monitoring
• Model Optimization

COMPUTER SCIENCE BENCHMARK CSD DEPARTMENT

 Machine Learning Criteria:

----------------------------------------------------------------------------------------
Accuracy

The accuracy of the category mapping or prediction is the most critical quality characteristic
of a machine learning algorithm. The level of precision that can be achieved is determined
by the problem, the model, and the type and quantity of input data.

Robustness

Another important quality trait is the robustness with respect to varying inputs. You must try
to avoid two opposing problems: bias and overfitting.

Learning efficiency and adaptation

To achieve accurate results, how many learning cycles (input data) does the system require?
This is yet another machine learning consistency criterion. The device changes the weightage
assigned to each parameter in its internal model with each new input, i.e. with each learning
cycle. A system can achieve optimum accuracy with fewer or more learning cycles, depending
on the model and algorithm.

Performance

Remember to think about the system's success, which includes the memory and computing
resources needed to complete pre-processing and training. Last but not least, the amount of
time it takes to determine the actual result for each new input must follow those criteria.

Embedded System

Research in this area explores the design, development, and use of computer architectures and
compilers to improve computational efficiency, throughput and security. Efficiency, throughput and
security of code execution at the machine level is influenced by the machine architectures, the
static and dynamic compilation of high-level languages, and use of parallelism and multi-processors.

Requirements:

----------------------------------------------------------------------------------------
• Enhancement of computer micro-architectures

COMPUTER SCIENCE BENCHMARK CSD DEPARTMENT

 • Enhancement of compilers to support system security
• Grasp machine learning techniques for improvement
• Use dynamic binary translation and optimization techniques to support system virtualization
• Program execution monitoring for optimization, testing, debugging and security

Bioinformatics
Research in this area explores the use of computational methods to better categorize,
visualize, and model biological data and systems. These problems often involve massive, high-
dimensional datasets and their solutions draw from many disciplines of computer science including
database management, data mining, machine learning, and algorithmic optimization.

Requirements:

----------------------------------------------------------------------------------------
• Algorithms for sequence and structure analysis, protein structure prediction, virtual screening
and lead discovery, data modeling of scientific applications, DBMS (database management
system) extensions in support of brain image and proteomics analyses and building predictive
models for effective disease diagnoses.

Natural Language Processing

Natural language processing (NLP) or computational linguistics is an area in machine learning
and artificial intelligence that deals with understanding the meaning of human-style language
and its interactions with machines. It also has strong connections with computer vision and
machine learning research for natural language generation based on image content and text-to-
image reference resolution.

Requirements:

----------------------------------------------------------------------------------------
• Algorithm techniques
• Data Extraction, detection and identification
• Classification
• Analysis and evaluation accuracy
• Modeling

COMPUTER SCIENCE BENCHMARK CSD DEPARTMENT

 • Detection
• Validation and Verification
• Search , Retrieval and Tracing

Image Processing/Signal Processing

Image processing is manipulation of an image that has been digitized and uploaded into a
computer. Software programs modify the image to make it more useful, and can for example be
used to enable image recognition.

Classes:

• Image enhancement
• Image Restoration
• Image Analysis
• Image Compression

Requirements:

----------------------------------------------------------------------------------------
• Digital scientific images should be treated as data
• Manipulations of digital images should always be done on a copy of the raw image
data
• Adjustments to the entire image
• Digital images that will be compared to one another should be acquired under
identical conditions
• Intensity measurements of digital images should perform on raw data and calibrated
to a known standard

Intelligent Systems/Robotics
Intelligent systems are technologically advanced machines that perceive and respond to the
world around them. The field of intelligent systems also focuses on how these systems interact
with human users in changing and dynamic physical and social environments.

COMPUTER SCIENCE BENCHMARK CSD DEPARTMENT

Requirements:

---------------------------------------------------------------------------------------

• Integration of knowledge in Programming, Data Structures and Algorithms, Pattern

Recognition, Machine Learning, Artificial Intelligence, Physics, Numerical Methods
and Psychology

Computer Vision
Computer vision is the field of computer science that focuses on replicating parts of the
complexity of the human vision system and enabling computers to identify and process objects
in images and videos in the same way that humans do.

Requirements:

---------------------------------------------------------------------------------------
• Algorithm
• Trained Model
• Image/Object Exploration (Classification, Identification, Verification, Detection,
Landmark Detection, Segmentation and Recognition)
• Recognition Tracking (Video Motion Analysis, Image Segmentation and Restoration)
• Acquisition of an Image
• Analysis

Internet of Things
Internet of Things (IoT) as defined by the ICT (Information and Communication
Technology) as a dynamic global network infrastructure with self-configuring capabilities based
on standard and inter operable communication protocols where physical and virtual things have
identities, physical attributes and virtual personalities use intelligent interface and seamlessly
integrated into the information network. IoT is the inter-networking of physical devices,
vehicles, buildings and other items embedded with electronics, software, sensors, actuators,
and network connectivity that enable these objects to collect and exchange data.

COMPUTER SCIENCE BENCHMARK CSD DEPARTMENT

Requirements:

---------------------------------------------------------------------------------------
• Algorithms
• Hardware and Software systems
• Analytics
• Security and Privacy
• Openness
• Robustness
• Architecture and Dependencies

GIS Application
Research in this area explores efficient storage, retrieval, analysis, and visualization of data
for analysis and pattern discovery.

Requirements:

---------------------------------------------------------------------------------------
• Algorithm
• Input Data
• Data Storage
• Data Manipulation and Processing
• Output Data
• Hardware and software
• Users and User’s Needs
• Information
• Information Sources

COMPUTER SCIENCE BENCHMARK CSD DEPARTMENT

Mobile and Game Development
• Originality of the game
• Unique game idea
• Good Graphics
• Original Sounds, effects, music
• Level design (application of the over-all game design to specific segments of the game)
• Game play
• Performance
• Levelling/ Stages
• Machine Learning Application and Algorithms

Computer Graphics
Research in this area explores data visualization, non-photorealistic renderings, and
perception in virtual environments. It draws from and contributes to work in algorithms, human
perception, art, animation, computer vision, and image processing.

Requirements:

---------------------------------------------------------------------------------------
• Models
• Viewing of Images
• Creation of techniques for representing and rendering the models
• Creation of techniques for specifying and controlling the motion of the models
• Analysis

COMPUTER SCIENCE BENCHMARK CSD DEPARTMENT

COMPUTER AND DIGITAL FORENSIC
Forensic science assists the investigation expert in analyzing, inspecting, identifying, and
preserving digital evidence stored on a variety of electronic devices. Software forensics
principles and demonstrations of proper digital evidence collection. The method of preserving,
identifying, extracting, and documenting electronic data that can be used in a court of law is
known as digital forensics. It is the science of extracting information from digital media such as
a device, smartphone, server, or network. It equips the forensic team with the most up-to-date
methods and tools for resolving complex digital cases.

Requirements:

---------------------------------------------------------------------------------------

• Imaging Software
• Image acquisition
• Storage Acquisition
• Memory Acquisition
• Mounting and Exploring an image file
• Evidence Analysis
• Web browser forensic
• Mobile Forensics

COMPUTER SCIENCE BENCHMARK CSD DEPARTMENT