K-Means Clustering of Use-Cases Using MDL

Kumar, Sunil; Bhatia, Rajesh; Kumar, Rajesh

doi:10.1007/978-3-642-29216-3_8

Cited by 4 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hierarchical clustering 5 19,30,33,35,38 Customized clustering algorithm 4 [22][23][24]43 K-means 1 50 Seed algorithm 1 41 Cohesion algorithm 1 41 Graph-based clustering 1 21 Heuristic/Metaheuristic Technique Genetic algorithm (GA) 4 2,27,28,47 Particle swarm optimization (PSO) 1…”

Section: Clustering Algorithmsmentioning

confidence: 99%

Software component identification and selection: A research review

Gholamshahi

Hasheminejad

2018

Softw Pract Exp

View full text Add to dashboard Cite

Summary Nowadays, with the development of software reuse, software developers are paying more attention to component‐related technologies, which have been mostly applied in the development of large‐scale complex applications to enhance the productivity of software development and accelerate time to market. Component‐based software development is well acknowledged as a methodology, which establishes the reusability of software and reduces the development cost effectively. Two crucial problems in component‐based software development are component identification and component selection. The main purpose of this paper is to provide a reference point for future research by categorizing and classifying different component identification and component selection methods and emphasizing their respective strengths and weaknesses. We hope that it can help researchers find the current status of this issue and serve as a basis for future activities.

show abstract

Section: Clustering Algorithmsmentioning

confidence: 99%

Software component identification and selection: A research review

Gholamshahi

Hasheminejad

2018

Softw Pract Exp

View full text Add to dashboard Cite

show abstract

“…Clustering is the process of grouping together items that share some common characteristics. It has been used for several problems such as document classification, crime identity localization, insurance fraud detection and other problems [20]. There exist several types of clustering techniques such as Agglomerative Hierarchical Clustering, Expectation-Maximization (EM) Clustering, Mean-Shift Clustering, K-Means Clustering and more where each excels under some circumstances.…”

Section: Clusteringmentioning

confidence: 99%

“…Now that the problem became of a large scale, we expect to have a wider gap between the two methods. Figures 17,18,19,and 20 show the experimental results. A wider gap is observed as the number of hosts and services increase.…”

Section: Quality Of Solutionsmentioning

confidence: 99%

Machine Learning Models for Scheduling On-Demand Fog Placement and Optimizing Container Deployment. (c2020)

Farhat¹

View full text Add to dashboard Cite

Fog computing is an extended cloud computing technology allowing services embedded into virtual machines or containers to be placed at the edge with closer proximity to the end devices. Nevertheless, one of the main difficulties adding up to the complexity of the on-demand fog placement topic is deciding on the proper time and place of the fog deployment process, and deriving the adequate container and service distribution over the available fogs at a certain location. Several techniques have been suggested in the current literature as potential solutions, in which some consider users preferences or random-based approach for fog deployment, while others reside on threshold-based mechanisms. However, due to the huge increase in the number of requests coming from end devices including IoT users, fog deployment and container placement must be scheduled to serve locations with high service requesting profiles while decreasing the cloud processing load. In this context, we first propose a fog placement model that allows to produce an adequate scheduling decision by using a hybrid technique combining time series forecasting and reinforcement learning. The proposed technique learns the intensity of service invocations and behavior of end devices at different locations over time for predicting the localization plan. Second, we propose a K-Means based clustering model embedded within a multi-objective optimization scheme for fog and container placement. A comparison of our proposed solution with random-based and threshold-based fog placement scheduling approaches show that the number of processed requests performed by the cloud decreases from 100% to 29% compared to 93% and 67% in the other two models. The aforementioned results explore the efficiency of our proposed scheme in scheduling the fogs in their rightful place, which helps in decreasing the cloud’s load, decreasing the network congestion, and increasing the overall quality of service. Moreover, experimental results illustrate that the proposed optimization model and clustering technique further improve the pre-existing heuristic-based solutions for container distribution.

show abstract

Fiber/Fabric‐Based Piezoelectric and Triboelectric Nanogenerators for Flexible/Stretchable and Wearable Electronics and Artificial Intelligence

2019

View full text Add to dashboard Cite

fields is breaking out, such as the Internet of Things (IoTs), big data, humanoid robotics, and artificial intelligence (AI). Nowadays, the rapid advancement of these functional electronic devices is transforming the way people communicate with each other and with their surroundings, which has integrated our world into an intelligent information network. Owing to that no electronics works without electricity, the processes of human informatization and intelligence depend on broad energy supplies and powerful power supports. In other words, electric power can be regarded as the flowing blood that keeps every components of the current society running normally and healthily. However, with the rapid consumption of conventional fossil fuels as well as the growing voice of environmental protection, the current energy structure and its supply status are facing unprecedented challenges. On the one hand, the overwhelming energy crisis and ecological deterioration have become huge bottlenecks restricting socioeconomic development.[1] Some serious situations may even worsen to the root of interstate interest conflicts or the disaster that threatens the survival of mankind. In this case, the transform of energy structure from scarce, pollution-prone, and irreproducible mineral resources to abundant, environmentally friendly, and renewable green energies is desperately required. On the other hand, the traditional centralized, immobile, and ordered energy supply patterns based on power plants are incompatible with the present development of functional electronics associated with individual person, which follows a general trend of miniaturization, portability, and low power. As the information age is coming, billions of things must be connected with sensors for various measurements, perceptions, controls, and data transmissions. [2] These mobile, human-oriented, randomly and massively distributed sensing networks also require the corresponding matched power supply system. Therefore, it turns out that the unreasonable energy structures as well as the mismatched supply pattern lead to the current development dilemma.Portable power supplies and self-powered systems are the most promising solutions for the above straits. For wearable power sources, one of the compromises is to choose small-size Integration of advanced nanogenerator technology with conventional textile processes fosters the emergence of textile-based nanogenerators (NGs), which will inevitably promote the rapid development and widespread applications of next-generation wearable electronics and multifaceted artificial intelligence systems. NGs endow smart textiles with mechanical energy harvesting and multifunctional self-powered sensing capabilities, while textiles provide a versatile flexible design carrier and extensive wearable application platform for their development. However, due to the lack of an effective interactive platform and communication channel between researchers specializing in NGs and those good at textiles, it is rather difficult to achieve fiber...

show abstract

K-Means Clustering of Use-Cases Using MDL

Cited by 4 publications

References 7 publications

Software component identification and selection: A research review

Software component identification and selection: A research review

Machine Learning Models for Scheduling On-Demand Fog Placement and Optimizing Container Deployment. (c2020)

Fiber/Fabric‐Based Piezoelectric and Triboelectric Nanogenerators for Flexible/Stretchable and Wearable Electronics and Artificial Intelligence

Contact Info

Product

Resources

About