Hybrid evolutionary optimization for takeaway order selection and delivery path planning utilizing habit data

The last years have seen a rapid growth of the takeaway delivery market, which has provided a lot of jobs for deliverymen. However, increasing numbers of takeaway orders and the corresponding pickup and service points have made order selection and path planning a key challenging problem to deliverymen. In this paper, we present a problem integrating order selection and delivery path planning for deliverymen, the objective of which is to maximize the revenue per unit time subject to maximum delivery path length, overdue penalty, reward/penalty for large/small number of orders, and high customer scoring reward. Particularly, we consider uncertain order ready time and customer satisfaction level, which are estimated based on historical habit data of stores and customers using a machine-learning approach. To efficiently solve this problem, we propose a hybrid evolutionary algorithm, which adapts the water wave optimization (WWO) metaheuristic to evolve solutions to the main order selection problem and employs tabu search to route the delivery path for each order selection solution. Experimental results on test instances constructed based on real food delivery application data demonstrate the performance advantages of the proposed algorithm compared to a set of popular metaheuristic optimization algorithms.

Efficient algorithms to minimize Makespan of the unrelated parallel Batch-processing machines scheduling problem with unequal job ready times

This paper considers the minimization of makespan in the unrelated parallel batch processing machines scheduling problem with considering non-identical job size and dynamic job ready time. The considered unrelated machines have different capacity and different processing speed. Each machine processes a number of the jobs as a batch at the same time so that the machine’s capacity is not exceeded. The batch processing time and the batch ready time are equal to the largest processing time and the largest ready time of jobs in the same batch, respectively. In this paper, a Mixed Integer Linear Programming (MILP) model, two categories of the heuristic procedures (six heuristics) and a meta-heuristic algorithm are proposed to solve the problem. A lower bound is also presented by relaxing of the original problem to evaluate the quality of the proposed algorithms. The computational experiments show the performance of the proposed algorithms under the considered measures.

EXPLORING CONFIDENTIAL DEDUPLICATION OF DATA USING BIG DATA IN CLOUD COMPUTING STORAGE

To decrease the selecting time and reaction time between Token deals and reaction, File move or download mentioning and results. It diminishes the extent of extra room in flowed limit. To ensure about the assurance of information differential confirmed copy check is utilized. It presents this supported copy check in half and half cloud structure. The mutt cloud arrangement proposes about both the open cloud and the private cloud. So as to give progressively conspicuous security, the private cloud is equipped with staggered check. Kinds of progress in scattered figuring are inciting a promising future for Collaborative Cloud Computing (CCC). To decrease the getting ready time and reaction time between Token deals and reaction, File move or download mentioning and results. Where comprehensive dispersed dissipated cloud assets having a spot with various affiliations or people (i.e., segments) are aggregately utilized in a strong strategy to give organizations. The records are dealt with in the cloud. That is each customer selects an information key to encode the information that he plans to store in the cloud. It depicts a computationally unassuming procedure for making all log portions made. Going before the logging machine's trade off unfathomable for the assailant to examine and besides hard to elusively adjust or wreck. Each Client computes an information key to encode the information that he would like to store in the cloud

PENGOPTIMALAN RUTE PENDISTRIBUSIAN TABUNG GAS LPG 3 KG DENGAN ALGORITMA SEQUENTIAL INSERTION (Studi Kasus: Koperasi Pegawai Kantor Gubernur Kalimantan Barat)

LPG (Liquid Petrolium Gas) adalah salah satu komoditas sektor migas yang diproduksi oleh PT. Pertamina (Persero). Salah satu permasalahan yang dihadapi Koperasi Pegawai Negeri Kantor Gubernur Kalimantan Barat yaitu mendistribusikan tabung gas LPG dari Stasiun Pengisian Bahan Bakar Elpiji (SPBE) ke setiap pangkalan. Permasalahan rute pendistribusian termasuk dalam Vehicle Routing Problem (VRP) yaitu permasalahan penentuan rute kendaraan untuk melayani beberapa pelanggan. Salah satu variasi VRP yaitu Capacitated Vehicle Routing Problem (CVRP) dimana permasalahan setiap kendaraan yang mempunyai kapasitas terbatas. Variasi ini dapat diselesaikan menggunakan algoritma Sequential Insertion dimana terdapat empat kriteria dalam pemilihan pelanggan pertama yaitu earliest deadline, earliest ready time, shortest time window dan longest travel time. Penyelesaian permasalahan pendistribusian Gas LPG 3 kg di Koperasi Pegawai Negeri Kantor Gubernur Kalimantan Barat dengan algoritma Sequential Insertion memiliki hasil perhitungan dengan total jarak dan waktu tempuh yang berbeda untuk setiap kriteria yaitu untuk kriteria earliest deadline didapat total jarak dan waktu tempuh adalah 280.3 km dan 15.071 jam, Kriteria earliest ready time didapat total jarak dan waktu tempuh 293.66 km dan 15.4055 jam, Kriteria Shortest time window didapat total jarak dan waktu tempuh 276.54 km dan 14.6355 jam dan kriteria longest travel time didapat total jarak dan waktu tempuh 256.16 km dan 14.468 jam. Pada permasalahan ini dalam penentuan pelanggan awal dengan Kriteria longest travel time menghasilkan jarak dan waktu yang lebih optimal sehingga sistem pendistribusian lebih efisien dan juga menghemat biaya dalam penggunaan bahan bakar bensin dan waktu dalam mendistribusikan LPG.Kata Kunci: Vehicle Routing Problem, Capacitated Vehicle Routing Problem, Sequential nsertion

An Efficient Load Balancing Method by Using Machine Learning-Based VM Distribution and Dynamic Resource Mapping

In cloud computing, balancing the load among VMs and resources is a major research area, which still needs attention. The primary aim of this research is to expand an effective cloud load balancing approach, enhance the reaction time, lessen the ready time, premiere utilization of sources as well lessen the activity rejection time. The proposed MLBL method is primarily based on the SVM and Ksuggest clustering method. In the proposed MLBL technique SVM classification method used to create activity businesses based totally at the size. Later Kmethod clustering technique is used to create the institution of Virtual machines based totally on their usage of CPU and number one memory (RAM). We are providing an MLBL method based totally on system learning-based VM distribution and dynamic aid mapping. In cloud computing, VMs are scheduled to hosts as in keeping with their utilization (a host which has better availability of memory) without thinking about common utilizations. The proposed technique divides the assets into various organizations as well as VMs and then follow dynamic aid mapping. The proposed MLBL technique creates VMs clusters to execute comparable task agencies that enhance the QoS and ideal utilization of sources in addition to lessen the process rejection time.

Improving the Performance of the Prediction by Machine Learning Algorithms

in the course of latest a long term, system gaining knowledge of (ML) has superior from the task of barely any laptop devotees abusing the plausibility of desktops figuring out a way to play around, and a chunk of mathematics (facts) that superb occasionally belief to be computational methodologies, to a free research area that has now not just given the essential base to measurable computational requirements of studying systems, yet moreover has created wonderful calculations which can be generally carried out for content material material translation, layout acknowledgment, and a numerous excellent commercial enterprise features or has precipitated a simply one among a type studies eagerness for data removal to differentiate wearing a veil regularities or abnormality within group facts that developing via way of next. This thesis centers round clarifying the concept and development of device learning, a portion of the mainstream device gaining knowledge of calculations and attempt to reflect onconsideration on 3 most ordinary calculations relying on a few essential thoughts. Sentiment140 dataset turn out to be utilized and execution of each estimate concerning getting ready time, expectation time and precision of forecast had been archived and analyzed.

Disease Prediction by Machine Learning from Healthcare Communities

To promote sustainable improvement, the smart town implies a global imaginative and prescient that merges artificial intelligence, choice making, statistics and conversation era (ICT), and the net-of-things (IoT). in this mission, the subject of disease prediction and prognosis in clever healthcare is reviewed. due to records progress in biomedical and healthcare groups, correct have a look at of clinical data advantages early disorder recognition, patient care and network services. whilst the exceptional of medical information is incomplete the exactness of study is reduced. moreover, exclusive areas exhibit specific appearances of certain regional illnesses, which can also bring about weakening the prediction of sickness outbreaks. within the proposed system, it offers gadget gaining knowledge of algorithms for effective prediction of various disorder occurrences in ailment-frequent societies and predicts the waiting time for each treatment project for every patient as well as a hospital Queuing advice (HQR) system is advanced for recommending treatment mission sequence with appreciate to anticipated ready time. It experiments on a nearby chronic illness of cerebral infarction. using structured and unstructured facts from health centre it makes use of system studying selection Tree algorithm and KNN algorithm. To the first-rate of our knowledge inside the place of medical huge records analytics none of the existing paintings focused on each information types. in comparison to several normal estimate algorithms, the calculation exactness of our proposed set of rules reaches 94.8% with a convergence speed which is faster than that of the CNN-based totally uni-modal ailment threat prediction (CNN-UDRP) algorithm. similarly, challenges within the deployment of sickness diagnosis in healthcare had been mentioned.