Computer Science Laboratory Research Articles

Assessment of Tree Damage with the Forest Health Monitoring (FHM) Method and the Convolutional Neural Network (CNN) Method

So far, the assessment or measurement of tree damage has only been done using the Forest Health Monitoring (FHM) method. This study aims to determine the types of tree damage using Forest Health Monitoring (FHM) and Convolutional Neural Network (CNN) methods. The research was conducted at the TAHURA WAR Utilization Block and the Computer Science Laboratory at FMIPA Lampung University. Measuring the type of tree damage using the FHM method is carried out on trees that are in the FHM cluster. Identification of tree damage types with the CNN algorithm using the MobileNet architecture. The results showed that there were 13 types of tree damage found, with five types of tree damage that were commonly found (> 60 cases): open wounds (218 cases), cancer (94 cases), Broken / Cracks and stems (87 cases), broken or dead branches (73 cases), and loss of dominant shoots (69 cases). As for the identification results with the CNN method, there were nine out of 13 types of damage that obtained precision, recall, and F1 scores of 100%. Thus, five types of dominant tree damage were found, one of which was open wounds (218 cases), and nine types of tree damage obtained high accuracy values.

Politicizing Algorithms by Other Means: Toward Inquiries for Affective Dissensions

AbstractIn this paper, we build upon Bruno Latour’s political writings to address the current impasse regarding algorithms in public life. We assert that the increasing difficulties at governing algorithms—be they qualified as “machine learning,” “big data,” or “artificial intelligence”—can be related to their current ontological thinness: deriving from constricted views on theoretical practices, algorithms’ standard definition as problem-solving computerized methods provides poor grips for affective dissensions. We then emphasize on the role historical and ethnographic studies of algorithms can potentially play in the politicization of algorithms. By both digging into the genealogy of algorithms’ constricted definition and by making their contemporary constitutive relationships more visible, both historical and ethnographic studies can contribute to vascularizing algorithms and making them objects of enlarged disputes. We conclude by giving a flavor of the political potential of the vascularization efforts we call for, using materials from an ethnographic study conducted in a computer science laboratory.

Development of Fuzzy-Based Smart Drip Irrigation System for Chili Cultivation

Chili plants often fail to harvest in the cultivation process due to improper irrigation. Soil temperature and humidity are essential parameters that affect the amount of water needed by plants in the watering process. This research aimed to apply fuzzy logic to the chili plants' irrigation system. The function of this system was to regulate watering due to the needs of the Chili plant automatically in a real-time fashion. The Sugeno fuzzy inference system (FIS) is embedded in a microcontroller to regulate the water based on the plant's needs appropriately. The system was tested on Chili plants located in the iSurf Computer Science Lab IPB University greenhouse. After four days of testing, the soil moisture sensor results were stable at optimal conditions, between 60%-80% after watering. It shows that the irrigation system has automatically regulated watering due to the Chili plant's needs.

Jack Bogle: Champion of the People

1. Andrew W. Lo 1. is the Charles E. and Susan T. Harris professor at MIT Sloan School of Management, director of the MIT Laboratory for Financial Engineering, a principal investigator at the MIT Computer Science and Artificial Intelligence Laboratory, an affiliated faculty member of the MIT

Jack Bogle: Champion of the People

1. Andrew W. Lo 1. is the Charles E. and Susan T. Harris professor at MIT Sloan School of Management, director of the MIT Laboratory for Financial Engineering, a principal investigator at the MIT Computer Science and Artificial Intelligence Laboratory, an affiliated faculty member of the MIT

A Mobile Suitcase for Informatic Teachers Related to the “Digital” Didactic Goals of the 21st Century

This study deals with the optimal equipment of a mobile case for computer science teachers, which offers the possibility to teach the skills of the curricula from primary to high school of the 21st century. First, the Single Board Computers (SBCs) in question are filtered out from previous studies and the accessory parts required are determined through a quantitative market analysis. Then, by combining the results with a qualitative analysis according to Mayring, the degree of curricular coverage of individual accessories is determined and binarized. Afterwards, the optimal equipment of the mobile case is evaluated and established based on the cost overlap by horizontal summation and vertical inclusion of the necessary accessories after recording the prices and the budget. The results were clearly presented in network diagrams and lists. This study thus provides computer science teachers and computer science professors with a budget-dependent basis for making decisions about the contents of a mobile case for computer science lessons or a computer science laboratory for learning the skills of the curricula from primary to high school of the 21st century. The study closes with a summary and an outlook.

Explainable outlier detection: What, for Whom and Why?

Outlier algorithms are becoming increasingly complex. Thereby, they become much less interpretable to the data scientists applying the algorithms in real-life settings and to end-users using their predictions. We argue that outliers are context-dependent and, therefore, can only be detected via domain knowledge, algorithm insight, and interaction with end-users. As outlier detection is equivalent to unsupervised semantic binary classification, at the core of interpreting an outlier algorithm we find the semantics of the classes, i.e., the algorithm’s conceptual outlier definition. We investigate current interpretable and explainable outlier algorithms: what they are, for whom they are, and what their value proposition is. We then discuss how interpretation and explanation and user involvement have the potential to provide the missing link to bring modern complex outlier algorithms from computer science labs into real-life applications and the challenges they induce.

Contributors’ Notes

Contributors’ Notes

Friends in Comment—A Conversation With Regina Barzilay

This is the first of a series of interviews, named Friends in Comment, where I share conversationswith friends and colleagues in areas related to ours. This first interview is with Regina Barzilay. Regina is currently a School of Engineering Distinguished Professor for AI and Health with the Department of Electrical Engineering and Computer Science and a member of the Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. She is an AI faculty lead for Jameel Clinic, an MIT center for Machine Learning in Health. She was a postdoc with Cornell University, Itahaca, NY, USA, for a year. Her research interests include natural language processing.

Developing open-source software for bioimage analysis: opportunities and challenges

Fast-paced innovations in imaging have resulted in single systems producing exponential amounts of data to be analyzed. Computational methods developed in computer science labs have proven to be crucial for analyzing these data in an unbiased and efficient manner, reaching a prominent role in most microscopy studies. Still, their use usually requires expertise in bioimage analysis, and their accessibility for life scientists has therefore become a bottleneck. Open-source software for bioimage analysis has developed to disseminate these computational methods to a wider audience, and to life scientists in particular. In recent years, the influence of many open-source tools has grown tremendously, helping tens of thousands of life scientists in the process. As creators of successful open-source bioimage analysis software, we here discuss the motivations that can initiate development of a new tool, the common challenges faced, and the characteristics required for achieving success.

Developing open-source software for bioimage analysis: opportunities and challenges.

Fast-paced innovations in imaging have resulted in single systems producing exponential amounts of data to be analyzed. Computational methods developed in computer science labs have proven to be crucial for analyzing these data in an unbiased and efficient manner, reaching a prominent role in most microscopy studies. Still, their use usually requires expertise in bioimage analysis, and their accessibility for life scientists has therefore become a bottleneck. Open-source software for bioimage analysis has developed to disseminate these computational methods to a wider audience, and to life scientists in particular. In recent years, the influence of many open-source tools has grown tremendously, helping tens of thousands of life scientists in the process. As creators of successful open-source bioimage analysis software, we here discuss the motivations that can initiate development of a new tool, the common challenges faced, and the characteristics required for achieving success.

Computer science labs with social distancing

Computer science (CS) labs support student in grasping the main concepts by writing the program codes and seeing them in execution. CS labs are important mainly for introductory CS courses where the students learn the basics of computer concepts and programming. To make the CS lab effective, students are supported by instructors and other lab assistants in pair programming approach where instructors or lab assistant help students write code working side by side at a single computer working on the same problem.Due to COVID-19 restriction, this process could not be continued since two persons must maintain social distancing. To provide the students with the highest quality of instruction in practical lab, CS labs were instead organized using zoom. Students were placed in different breakout zoom rooms, where instructor or lab assistant would drop in to help the student. The instructor and students would be in the lab while lab assistants would connect remotely and would be placed in a breakout room by instructor. While this technology allowed to view student’s code privately and support them, there were issues such as loss of time in arranging this setup in every labs, difficulty in connecting to zoom, difficult to understand student/instructor, difficulty for students to ask their question as student’s computer did not have microphone. We adapted to the situation and were able to support our students. In this work, we will share how we used this system and discuss the advantages, disadvantages and future improvements on this teaching process.

Research and Implementation of Scheduling Strategy in Kubernetes for Computer Science Laboratory in Universities

How to design efficient scheduling strategy for different environments is a hot topic in cloud computing. In the private cloud of computer science labs in universities, there are several kinds of tasks with different resource requirements, constraints, and lifecycles such as IT infrastructure tasks, course design tasks submitted by undergraduate students, deep learning tasks and and so forth. Taking the actual needs of our laboratory as an instance, these tasks are analyzed, and scheduled respectively by different scheduling strategies. The Batch Scheduler is designed to process tasks in rush time to improve system throughput. Dynamic scheduling algorithm is proposed to tackle long-term lifecycle tasks such as deep learning tasks which are hungry for GPU resources and have dynamically changing priorities. Experiments show that the scheduling strategies proposed in this paper improve resource utilization and efficiency.

Teaching Computer Science with CLIL Methodology

In this paper, methodological and organizational aspects of applying CLIL methodology in teaching computer science for students of universities are analyzed. It is shown that European countries, as well as the United Kingdom, the United States of America, and Canada, where part of the curriculum has been taught in a foreign language for several decades, are most actively introducing content and language integration and promoting an interdisciplinary approach to education. CLIL methodology features and benefits are identified, namely, a comprehensive focus, stimulating learning environment, authenticity, active learning, gradual learning and collaboration. The peculiarity of CLIL methodology is that its use requires a stable elementary skill in the grammar of a foreign language, as well as knowledge of subject-specific language. In accordance with various conditions, CLIL model can be presented in various forms: it can be a full course of a foreign language discipline, a module from a specific topic area, a part of any course, a project, a laboratory workshop, and a research, too. The paper presents a plan for computer science lectures and labs in a foreign language, which contains seven stages, each of which is performed in English. Integration of computer science and teaching in English at the Kremenchuk Mykhailo Ostrohradskyi National University is implemented using developed bilingual course program “Computer for beginners”. The course content includes a study of the material necessary for obtaining skills in using modern ICT and a personal computer using English glossary. Conclusions are drawn regarding conditions and principles of teaching computer science in a foreign language. The scientific novelty of the work is that for the first time a comprehensive analysis of the expediency of using CLIL methodology was carried out at the Kremenchuk Mykhailo Ostrohradskyi National University. The practical significance of the work is that its results can be used for further implementation of content and language integration in Ukraine universities. The development of new content and language integrated courses with CLIL methodology for teaching courses in a foreign language is considered promising.

COSMOS educational toolkit

This paper focuses on the K-12 educational activities of COSMOS-<u>C</u>loud enhanced <u>O</u>pen <u>S</u>oftware defined <u>MO</u>bile wireless testbed for city-<u>S</u>cale deployment. The COSMOS wireless reasearch testbed is being deployed in West Harlem (New York City) as part of the NSF Platforms for Advanced Wireless Research (PAWR) program. COSMOS' approach for K-12 education is twofold: (i) create an innovative and concrete set of methods/tools that allow teaching STEM subjects using live experiments related to wireless networks/IoT/cloud, and (ii) enhance the professional development (PD) of K-12 teachers and collaborate with them to create hands-on educational material for the students. The COSMOS team has already conducted successful pilot summer programs for middle and high school STEM teachers, where the team worked with the teachers and jointly developed innovative real-world experiments that were organized as automated and repeatable math, science, and computer science labs to be used in the classroom. The labs run on the COSMOS Educational Toolkit, a hardware and software system that offers a large variety of pre-orchestrated K-12 educational labs. The software executes and manages the experiments in the same operational philosophy as the COSMOS testbed. Specifically, since it is designed for use by non-technical middle and high school teachers/students, it adds easy-to-use enhancements to the experiments' execution and the results visualization. The labs are also supported by Next Generation Science Standards (NGSS)-compliant teacher/student material. This paper describes the teachers' PD program, the NGSS lessons created and the hardware and software system developed to support the initiative. Additionally, it provides an evaluation of the PD approach as well as the expected impact to K-12 STEM education. Current limitations and future work are also included as part of the discussion section.

Flipping Laboratory Sessions in a Computer Science Course: An Experience Report

Contribution: This article presents an experience report on the application of flipped classroom (FC) to the laboratory sessions (henceforth lab sessions) of an undergraduate computer science course. Background: Hands-on work in computer science lab sessions is typically preceded by technical instructions on how to install, configure, and use the software and hardware tools needed during the lab. In the course under study, this initial explanation took between 14% and 50% of the lab time, reducing drastically the time available for actual practice. It was also observed that students missing any of the labs had trouble catching up. Intended Outcomes: The application of FC is expected to increase the time for hands-on activities, and improve students' performance and motivation. This improvement is expected to be more noticeable in those students who are unable to attend all lab sessions. Application Design: The study compares the application of FC and a traditional methodology. It encompasses two academic courses and involves 434 students and six lecturers. Findings: The FC is suitable for lab sessions in computer science. Among other results, flipping the labs resulted in 24 more minutes of practical and collaborative work on average at each lab session. It was observed a significant improvement in the motivation of students, with 9 out of every 10 students preferring it over traditional methodologies. Also, the FC made it much easier for students to catch up after missing a lab, making the final grades less dependent on lab attendance.

Sony Computer Science Laboratories: Sustaining a Culture and Organization for Fundamental Research

In late 2019, Dr. Hiroaki Kitano, the president and director of research at Sony Computer Science Laboratories (Sony CSL), had decided he would be stepping down from his position soon. Sony CSL, a small blue-sky fundamental research facility funded by Sony, had always operated on the strength of the trust between Sony's CEO and the lab's director. Sony had been hands-off in its management, leaving Kitano to hire, fire, fund, and evaluate the lab's researchers and project portfolio at his own discretion. Now that he was stepping down, however, he worried that Sony CSL could not withstand his departure. Kitano wanted to make a transparent plan for the organization's future before he handed off Sony CSL to his successor. That plan involved three key decisions. First, what should be the optimal structure and governance of Sony CSL? Should it maintain its independence and autonomy, or should it align more closely with Sony's business priorities? Second, how could Sony CSL scale its impact on Sony and society at large, given its small size? Finally, should Sony CSL establish some standard methods of measuring project success and strength of the portfolio? In making these decisions, Kitano wanted to ensure that he preserved the unique culture that had allowed Sony CSL to pursue path-breaking research and innovation.

Online computer science workshops for educators in higher education during Covid-19: challenges and opportunities of a forced distance learning

Abstract This study focuses on a course belonging to the University of Bologna’s bachelor’s degrees ‘Expert in Social and Cultural Education’ and ‘Educator in Childhood Social Services’ called ‘Computer Science Lab–based course’, which aims to develop digital competences necessary for the educational profession. Before COVID-19, this face-to-face compulsory workshop-based course consisted of nine parallel teachings with different programmes and teachers. Due to the impossibility of providing regular lessons, teachers have been forced to revise their working methods by using different distance learning strategies. This paper aims to offer an understanding of the situation by analysing teachers’ and students’ perceptions collected through questionnaires in relation to the following aspects: most used and effective teaching strategies; technical, communicative and relational difficulties encountered by teachers and students; aspects related to distance learning methods and perception of the usefulness of the course for the educational profession.

Pegando o jeito de domar o bicho

Neste artigo pretendemos refletir sobre o processo de aprendizagem das tecnologias digitais por idosos, a partir de pesquisa etnográfica realizada no ano de 2016 em plataformas como o Facebook e no curso de informática para a Melhor Idade ofertado pelo Laboratório de Informática da PRAE/CPD da UFSM. Nossa intenção é mostrar como o relacionamento com computadores constitui um processo complexo para esses sujeitos que estão tendo contato com a tecnologia digital pela primeira vez, requerendo o aprendizado de uma série de ações e dos gestos técnicos. Através de distintas situações etnográficas discorreremos sobre a constituição de um conjunto de saberes e gestos que são corporificados e ilustram a relação entre a materialidade da tecnologia, corpo e motricidade no processo de “pegar o jeito” do computador e “domá-lo”.

A Robust 2D-SLAM Technology With Environmental Variation Adaptability

Simultaneous localization and mapping (SLAM) in complicated indoor/outdoor unknown environments is challenging. With a demand on high mobility and high integrity intelligent robotics, it is desired that the SLAM system should be portable and possibly standalone. To carry out the pose estimation as well as the mapping without relying on the information from other sensors, such as image, inertial measurement unit, rotary encoder of ground vehicle and so on, a single 2D light detection and ranging (LiDAR) is considered in this paper. In order to fulfill a robust 2D SLAM technology in unknown environments, the principal component analysis (PCA) is utilized to evaluate LiDAR scan contours and to carry out a corridor detector. The corridor detector is further extended to achieve adaptive unstable points removal, mapping probability adjustment as well as loop closure. Based on an adaptive grid map segmentation scheme, the cumulative mapping errors can obviously be reduced and a precise 2D map can be eventually carried out. Many experiments are conducted to verify the proposed method. Finally, for comparison, this paper utilizes the scan data and ground truth provided by the Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology (MIT), to verify the localization precision of the proposed algorithm. Experiment shows that from the scan data in the route up to about 350 m, the maximum error can be as low as about 20 cm.