Kemas Muslim Lhaksmana

Bio: Kemas Muslim Lhaksmana is an academic researcher from Telkom University. The author has contributed to research in topics: Computer science & Cascading failure. The author has an hindex of 6, co-authored 38 publications receiving 117 citations. Previous affiliations of Kemas Muslim Lhaksmana include Kyoto University.

Analisis Sentimen Jasa Transportasi Online Pada Twitter Menggunakan Metode Naïve Bayes Classifier

Abstract: Abstrak Dengan berkembangnya dunia teknologi informasi, alat transportasi juga berkembang dengan adanya jasa transportasi online. Saat ini penggunaan jasa transportasi online sudah seperti kebutuhan, maka perlu melakukan analisis sentimen terhadap jasa transportasi online untuk mengetahui bagaimana tanggapan masyarakat terhadap jasa tranportasi online tersebut. Data yang digunakan harus merupakan data yang valid. Media yang penulis gunakan untuk mengambil data merupakan dari salah satu platform media sosial yaitu Twitter. Tugas Akhir ini dibuat untuk menganalisa tanggapan masyarakan dengan analisis data yang berupa tweet kemudian diklasifikasikan menjadi kelas positif dan negatif menggunakan metode NaA¯ve Bayes Classifier. Berdasarkan sistem yang dibangun, didapatkan hasil sentimen positif sebesar 88.60% dan sentimen negatif sebesar 11.40% dengan akurasi sebesar 86.80%. Hasil menunjukkan tingkat sentimen positif dari tweet masyarakat lebih besar dibandingkan dengan tingkat sentimen negatif. Kata kunci : transportasi online, analsis sentimen, Twitter, NaA¯ve Bayes Classifier. Abstract With the development of the world of information technology, transportation equipment is also developing with the existence of online transportation services. Currently the use of online transportation services is like a need, it is necessary to conduct a sentiment analysis of online transportation to find out how people respond to these online transportation services. The data used must be valid data. The media that I use to retrieve data is from one of the social media platforms, namely Twitter. This Final Project was made to analyze community responses with data analysis in the form of tweets then classified into positive and negative classes using the NaA¯ve Bayes Classifier method. Based on the system built, there were 88.60% positive sentiments and 11.40% negative sentiments with an accuracy of 86.80%. The results show the level of positive sentiment from public tweets is greater than the level of negative sentiment. Keywords: online transportation, sentiment analysis, Twitter, NaA¯ve Bayes Classifier

Role-Based Modeling for Designing Agent Behavior in Self-Organizing Multi-Agent Systems

Abstract: Self-organization has been proposed to be implemented in complex systems which require the automation capabilities to govern itself and to adapt upon changes Self-organizing systems can be modeled as multi-agent systems (MAS) since they share common characteristics in that they consist of multiple autonomous systems However, most existing MAS engineering methodologies do not fully support self-organizing systems design since they require predefined goals and agent behaviors, which is not the case in self-organizing systems Another feature that is currently not supported for designing self-organizing MAS is the separation between the design of agent behaviors and behavior adaptation, ie how agents adapt their behaviors to respond upon changes To tackle these issues, this paper proposes a role modeling method, in which agent behaviors are represented as roles, to design how agents perform behavior adaptation at runtime by switching between roles The applicability of the proposed role modeling method

Generating Travel Itinerary Using Ant Collony Optimization

Abstract: Travelling is one of the activities needed by everyone to overcome weariness. The number of information about the tourism destination on the internet sometimes does not provide easiness for oncoming tourists. This paper proposes a system capable of making travel itinerary, for tourists who want to visit an area within a few days. For generating itinerary, the system considers several criterias (Multi-criteria-based), which include the popularity level of tourist attractions to visit, tourist visits that minimize budgets or tourist visits with as many destinations as possible. To handle multi criteria-based itinerary, we use the concept of multi attribute utility theory (MAUT). The running time of multi criteria-based itinerary is not significantly different from time-based itinerary. In addition, the number of tourist attractions in the itinerary is more than time-based itinerary, because the combination of solutions from each ant becomes more diverse.

Analysis of Large-Scale Service Network Tolerance to Cascading Failure

Abstract: The future Internet will be populated with a massive number of cooperating services due to the rapid growth of publicly available services and the adoption of service-oriented computing (SOC) into the Internet of Things. The adoption of SOC enables combining the functionalities of smart devices as combining services by means of service composition. These cooperating services form a large-scale service network where the nodes and the links represent services and the dependency between services, respectively. The dependency between services potentially causes cascading failure, where the failure of a service propagates to its dependent services. Due to the lack of research in this type of cascading failure, we analyzed cascading failure in service networks for different topology and different degree of service interdependency. We found that the number of cascading failure is somewhat linear to the average number of required services, and decays exponentially over the average number of alternate services. The latter suggests that cascading failure tolerance can be significantly improved by adding few alternate services to each required service if the average number of alternate services is currently low. In addition, we also found that scale-free topology provides better tolerance, subsequently followed by exponential and random topology.

QSAR Study of Fusidic Acid Derivative as Anti-Malaria Agents by using Artificial Neural Network-Genetic Algorithm

Abstract: Malaria is a disease that caused many adverse effects on humans Various attempts have been done to find new anti-malarial agents due to the resistance problem of the existing drug Fusidic acid is known as one of a compound that is promising to be used as an anti-malaria agent However, this compound should be derived to obtain a new fusidic acid derivative that has better activity The exploration of the compound in conventional style has a shortcoming in the term of time and cost Therefore, an alternative method is required to accelerate the design In this study, we applied a quantitative structure-activity relationship (QSAR) to produce a predictive model The produced model can be used to predict the activity of the compound as an anti-malaria agent The development of the model was performed by using genetic algorithm (GA) for feature selection and artificial neural network (ANN) for model development We developed five models by utilizing a different number of the descriptor in each model The validation process was performed by evaluating several validation parameters, such as accuracy According to the results, we found that the model 3, which is comprised of seven descriptors, produce a better result with the accuracies of internal and external data set are 096 and 092, respectively

RODE: Learning Roles to Decompose Multi-Agent Tasks

Abstract: Role-based learning holds the promise of achieving scalable multi-agent learning by decomposing complex tasks using roles. However, it is largely unclear how to efficiently discover such a set of roles. To solve this problem, we propose to first decompose joint action spaces into restricted role action spaces by clustering actions according to their effects on the environment and other agents. Learning a role selector based on action effects makes role discovery much easier because it forms a bi-level learning hierarchy -- the role selector searches in a smaller role space and at a lower temporal resolution, while role policies learn in significantly reduced primitive action-observation spaces. We further integrate information about action effects into the role policies to boost learning efficiency and policy generalization. By virtue of these advances, our method (1) outperforms the current state-of-the-art MARL algorithms on 10 of the 14 scenarios that comprise the challenging StarCraft II micromanagement benchmark and (2) achieves rapid transfer to new environments with three times the number of agents. Demonstrative videos are available at this https URL .

Cascading Failures in Internet of Things: Review and Perspectives on Reliability and Resilience

Abstract: In the Internet of Things (IoT), various devices operate collaboratively in collecting data, relaying information to one another, and processing information intelligently. Due to interactions and dependencies between the IoT devices, the malfunction of one device may trigger a cascade of unexpected and often undesired state changes of other devices, introducing or accelerating catastrophic cascading failures. Understanding the causes of cascading failures and modeling their behavior and effects is crucial for guaranteeing the reliability of IoT systems and delivering the desired quality of service. This article systematically reviews cascading failures modeling and reliability analysis methodologies, as well as mitigation strategies for building the resilience of IoT systems against cascading failures. The review covers diverse IoT applications, from smart grids to smart homes, from sensor networks to IoT cloud computing, and from transportation networks to interdependent infrastructure networks. Opportunities and open research issues are also discussed in relation to restrictions of the current cascading failure models and methods, and potential new technologies and complexity of the constantly evolving IoT systems.

ROMA: Multi-Agent Reinforcement Learning with Emergent Roles

Abstract: The role concept provides a useful tool to design and understand complex multi-agent systems, which allows agents with a similar role to share similar behaviors. However, existing role-based methods use prior domain knowledge and predefine role structures and behaviors. In contrast, multi-agent reinforcement learning (MARL) provides flexibility and adaptability, but less efficiency in complex tasks. In this paper, we synergize these two paradigms and propose a role-oriented MARL framework (ROMA). In this framework, roles are emergent, and agents with similar roles tend to share their learning and to be specialized on certain sub-tasks. To this end, we construct a stochastic role embedding space by introducing two novel regularizers and conditioning individual policies on roles. Experiments show that our method can learn specialized, dynamic, and identifiable roles, which help our method push forward the state of the art on the StarCraft II micromanagement benchmark. Demonstrative videos are available at this https URL.

Dual DCT-DWT-SVD digital watermarking algorithm based on particle swarm optimization

Abstract: Robust invisible watermarking plays an important role in copyright protection. Such watermarking has high requirements for robustness and security, and transparency and capacity cannot be ignored. Although there are many algorithms using singular value decomposition, most algorithms do not take security and reliability into account. Moreover, a meaningful watermark cannot be extracted under some attacks, resulting in the failure of copyright protection. In this paper, combined with particle swarm optimization (PSO), a secure and robust dual-embedded watermarking algorithm is proposed. First, the watermark image is encrypted by the generalized Arnold transform, then the original host image and the encrypted watermark image are processed by discrete cosine transform and multi-level discrete wavelet transform, and the singular values of the watermark image are embedded into the low-frequency and high-frequency regions of the host image, respectively. In addition, the embedding factor matrices are optimized by PSO. The simulation results based on the normal and medical host and watermark images show that the algorithm can meet the four basic characteristics of the watermarking algorithm. Moreover, the proposed watermarking algorithm has high capacity and good robustness, and can extract watermark with good visual effect under most attacks, so it can be used in copyright protection.

ROMA: Multi-Agent Reinforcement Learning with Emergent Roles

Abstract: The role concept provides a useful tool to design and understand complex multi-agent systems, which allows agents with a similar role to share similar behaviors. However, existing role-based methods use prior domain knowledge and predefine role structures and behaviors. In contrast, multi-agent reinforcement learning (MARL) provides flexibility and adaptability, but less efficiency in complex tasks. In this paper, we synergize these two paradigms and propose a role-oriented MARL framework (ROMA). In this framework, roles are emergent, and agents with similar roles tend to share their learning and to be specialized on certain sub-tasks. To this end, we construct a stochastic role embedding space by introducing two novel regularizers and conditioning individual policies on roles. Experiments show that our method can learn specialized, dynamic, and identifiable roles, which help our method push forward the state of the art on the StarCraft II micromanagement benchmark. Demonstrative videos are available at this https URL.