A Survey of Image Gradient Inversion Against Federated Learning

In order to preserve data privacy while fully utilizing data from different owners, federated learning is believed to be a promising approach in recent years. However, aiming at federated learning in the image domain, gradient inversion techniques can reconstruct the input images on pixel-level only by leaked gradients, without accessing the raw data, which makes federated learning vulnerable to the attacks. In this paper, we review the latest advances of image gradient inversion techniques and evaluate the impact of them to federated learning from the attack perspective. We use eight models and four datasets to evaluate the current gradient inversion techniques, comparing the attack performance as well as the time consumption. Furthermore, we shed light on some important and interesting directions of gradient inversion against federated learning.<br>

A Survey of Image Gradient Inversion Against Federated Learning

In order to preserve data privacy while fully utilizing data from different owners, federated learning is believed to be a promising approach in recent years. However, aiming at federated learning in the image domain, gradient inversion techniques can reconstruct the input images on pixel-level only by leaked gradients, without accessing the raw data, which makes federated learning vulnerable to the attacks. In this paper, we review the latest advances of image gradient inversion techniques and evaluate the impact of them to federated learning from the attack perspective. We use eight models and four datasets to evaluate the current gradient inversion techniques, comparing the attack performance as well as the time consumption. Furthermore, we shed light on some important and interesting directions of gradient inversion against federated learning.<br>

Forest Optimization based Test Case Generation for Multiple Paths with Metamorphic Relations

In general multiple paths are covered by multiple runs which is a time consuming task. Now a days, metaheuristic techniques are widely used for path coverage. In order to reduce the time, an efficient method is proposed based on Forest Optimization Algorithm (FOA) with Metamorphic Relations (MRs) that cover multiple paths at a time in one run unlike the traditional search based testing. In the proposed approach, initial test case is generated using FOA, the successive test cases are generated using MRs without undergoing several runs. The motive of using FOA is that the searching mechanism of this algorithm having resemblance with the branch / path coverage techniques of testing. To the best of our knowledge, FOA has not been implemented in software testing. The experimental results are compared with three existing work. The efficiency of simply FOA is also shown how it able to cover multiple paths. The results show that FOA with MRs is more efficient in terms of time consumption and number of paths covered.

IMPACT OF INNOVATIONS ON THE SAVING OF THE PRODUCTION COMPANY'S WORKING TIME FUND

The article deals with innovation management in the conditions of a manufacturing company whose aim is to reduce the working time fund that directly determines productivity or efficiency of the company in competitive market conditions. Based on explicit quantification of time frames based on an analytical – chronometric method applicable to production operations in the process. The results of observation, time measurement, research and evaluation of time consumption during the implementation of a repeated production operation, or its complex part within defined production site are presented. Based on explicitly performed quantitative analysis, introducing of innovative technology, innovative solutions in the field of production technology management that support sustainable development with an emphasis on the development of environmental quality are presented including an explicit quantification of working time fund savings through the implementation of innovative machinery and equipment in critical production operations of the analysed production process.

Extended Jaccard Indexive Buffalo Optimized Clustering on Geo-social Networks with Big Data

Clustering is a general task of data mining where partitioning a large dataset into dissimilar groups is done. The enormous growth of Geo-Social Networks (GeoSNs) includes users, who create millions of heterogeneous data with a variety of information. Analyzing such volume of data is a challenging task. The clustering of large volume of data is used to identify the frequently visited location information of the users in Geo-Social Networks. In order to improve the clustering of a large volume of data, a novel technique called Extended Jaccard Indexive Buffalo Optimized Data Clustering (EJIBODC) is introduced for grouping the data with high accuracy and less time consumption. The main aim of EJIBODC technique is to partition the big dataset into different groups. In this technique, many clusters with centroids are initialized to group the data. After that, Extended Jaccard Indexive Buffalo Optimization technique is applied to find the fittest cluster for grouping the data. The Extended Jaccard Index is applied in the Buffalo Optimization to measure the fitness between the data and the centroid. Based on the similarity value, using a gradient ascent function, the data finds the fittest cluster centroid for grouping. After that, the fitness value of cluster is updated and all the data gets grouped into a suitable cluster with high accuracy and minimum error rate. An experimental procedure is involved with big geo-social dataset and testing of different clustering algorithms. The series discussion is carried out on factors such as clustering accuracy, error rate, clustering time and space complexity with respect to a number of data. Experimental outcomes demonstrate that the proposed EJIBODC technique achieves improved performance in terms of higher clustering accuracy, less error rate, time consumption and space complexity when compared to previous related clustering techniques.

Radial Basis Kernel Regressive Feature Extraction and Robert Ensembled Brown Boost Classifier for Attack Detection in Cloud Environment

Cloud computing shares the resource in information technology field. The existing technique is failed to provide better results for identifying unknown attacks with higher accuracy and lesser time consumption. In order to address these problems, Radial Basis Kernel Regressive Feature Extracted Brown Boost Classification (RBKRFEBBC) method is introduced for performing the attack detection in cloud computing. The main objective of RBKRFEBBC method is to improve the attack detection performance with higher accuracy and minimal time consumption. Dichotomous radial basis kernelized regressive function is used in RBKRFEBBC method to extract the relevant features through determining the correlation between the output and one or more input variables (i.e., features of patient transaction data). After extracting relevant features, GRNBBC algorithm is used in RBKRFEBBC method to improve the secured data communication performance through classifying the patient data transaction as attack presence or attack absence. By this way, attack detection is carried out in accurate manner. Experimental evaluation is carried out by NSL-KDD dataset using different metrics like attack detection accuracy, attack detection time and error rate. The evaluation result shows RBKRFEBBC method improves the accuracy and minimizes the time consumption as well as error rate than existing works.

An Efficient Satellite Resource Cooperative Scheduling Method on Spatial Information Networks

To overcome the low timeliness of resource scheduling problems in spatial information networks, we propose a method based on a dynamic reconstruction of resource request queues and the autonomous coordinated scheduling of resources. First, we construct a small satellite network and combine the graph maximum flow theory to solve the link resource planning problem during inter-satellite data transmission. In addition, we design a multi-satellite resource scheduling algorithm with minimal time consumption based on graph theory. The algorithm is based on graph theory to reallocate the resource request queue to satellites with idle processing resources. Finally, we simulate the efficient resource scheduling capability in the spatial information network and empirically compare our approaches against two representative swarm intelligence baseline approaches and show that our approach has significant advantages in terms of performance and time consumption during resource scheduling.

Effectiveness of Progressive Muscle Relaxation Technique among the Antenatal Mothers above 32 Weeks of Gestation on the Reactivity and Time Consumption of Non Stress Test: A Randomized Controlled Trial

Background: Non Stress Test is a simple, inexpensive and non-invasive method to assess the wellbeing of the fetus by observing the FHR with its acceleration in response to the movement of the fetus. Objective: To assess the effectiveness of progressive muscle relaxation technique among the antenatal mothers above 32 weeks of gestation on reactivity and time consumption of Non Stress Test Design: Randomized controlled trial Setting: Obstetrics and Gynaecology OPD, PGIMER, Chandigarh Participant: 120 Antenatal mothers ³32 weeks of gestation Methods: 120 pregnant mothers i.e sixty each in Experimental and Control group willing to participate and available at the time of data collection were enrolled through a random sampling technique. Progressive muscle relaxation technique was demonstrated and was performed simultaneously by the antenatal mothers 15 to 20 minutes prior to NST who were enrolled under the Experimental group. Routine care was given to Control group. Data were collected by using an interview schedule in the month of October to December 2020. Non stress test was done as per schedule of antenatal visit and interpretation of NST graph in relation to the reactivity, time consumption and baseline fetal heart rate were compared in both the group. Results: It revealed that all the antenatal mothers in the Exp. group and 90% of mothers in the Control group showed reactivity of Non stress test. In relation to time consumption of Non stress test, all mothers in the Experimental group took normal time i.e 20 minutes. Out of the 90% of antenatal mothers who were reactive in the Control group, 5% took more than 20 minutes. A statistical significant difference was found in relation to reactivity by applying Chi Square (p<0.05). The finding also showed a significant difference in between the Experimental and Control group in relation to the reactivity of Non stress test as shown by Mann Whitney U test, baseline fetal heart rate during NST, all the antenatal mothers had normal BHR between 110 to 160 bpm in both groups. Conclusion: It can be concluded that Progressive muscle relaxation technique performed prior to Non stress test can be used for improving the Non stress test results, time-saving, evokes positive feeling and satisfaction among the antenatal mothers. Keywords: Non Stress Test, Progressive Muscle Relaxation Technique, Reactivity.

Practicality of Wound Detection Using Smartphone Measure App

The record of the pressure sore with photo needs to be measurable. We compare the time consumption of wound assessment ruler and measure application of smartphone and the satisfaction of the users. The time needed is 20 and 35 seconds for the ruler and the application on average. But the satisfaction is better for application for its convenience, less infection, and the accuracy of measurements.

Cloud Computing Storage Data Access Control Method Based on Dynamic Re-Encryption

In order to improve data security, ensure user privacy, and solve the problems of low data access control accuracy, long time consumption, and high energy consumption in traditional methods, a cloud computing storage data access control method based on dynamic re-encryption is proposed. The principal component analysis method is used to reduce the dimension of the cloud computing storage data, and the random forest algorithm is further used to classify and process the cloud computing storage data according to the processing results. On the basis of data preprocessing, an access control tree is established to obtain the correlation of data nodes. Finally, the dynamic re-encryption method is used for data security state transformation, and the data access control of cloud computing storage is realized through key generation, encryption, re-encryption key generation, and decryption. The experimental results show that the data access control accuracy of the method in this paper is high, time consumption is small, and energy consumption is small, and it is more suitable for cloud computing systems with huge data and information.