Recently, the challenges of security systems in protecting citizens from crime and disasters have become very difficult. While some organizations have developed fire detection security systems, incidents of intrusions...
Recently, the challenges of security systems in protecting citizens from crime and disasters have become very difficult. While some organizations have developed fire detection security systems, incidents of intrusions, thefts, and hostage-taking in government and private agencies indicate the inadequacy of current security systems. In this paper, the security system combines the detection of people, weapons, and fires through the analysis of surveillance cameras and videos is presented. The system is built by using deep learning techniques. The system deals with the video frames and processes them using a set of digital filters. The system analyzes the tires and goes through the processes of detecting faces, detecting weapons, and detecting fires respectively. After that, the classification stage begins to identify people’s faces if they are outlaws and to identify the type of weapon. The deep learning models were applied in the classification process: Convolutional Neural Network (CNN), VGG-19 network, and GoogleNet with Inception module. The Inception network archives the highest accuracy for face recognition. The VGG network archived 95.5%, and 99.7% for weapon and fire detection respectively.
Images can communicate a service, brand or product. Moreover, images provide depth and context to a description or story and give a much more intense experience than writing alone. Image retrieval is the highest searc...
详细信息
Recently, on account of the Covid-19 pandemic online learning has become a main strategy of learning in any educational environment. The main problem is the lack of focus or attention during a student watching an onli...
详细信息
In recent years,the research field of data collection under local differential privacy(LDP)has expanded its focus fromelementary data types to includemore complex structural data,such as set-value and graph ***,our co...
详细信息
In recent years,the research field of data collection under local differential privacy(LDP)has expanded its focus fromelementary data types to includemore complex structural data,such as set-value and graph ***,our comprehensive review of existing literature reveals that there needs to be more studies that engage with key-value data *** studies would simultaneously collect the frequencies of keys and the mean of values associated with each ***,the allocation of the privacy budget between the frequencies of keys and the means of values for each key does not yield an optimal utility *** the importance of obtaining accurate key frequencies and mean estimations for key-value data collection,this paper presents a novel framework:the Key-Strategy Framework forKey-ValueDataCollection under ***,theKey-StrategyUnary Encoding(KS-UE)strategy is proposed within non-interactive frameworks for the purpose of privacy budget allocation to achieve precise key frequencies;subsequently,the Key-Strategy Generalized Randomized Response(KS-GRR)strategy is introduced for interactive frameworks to enhance the efficiency of collecting frequent keys through group-anditeration *** strategies are adapted for scenarios in which users possess either a single or multiple key-value ***,we demonstrate that the variance of KS-UE is lower than that of existing *** claims are substantiated through extensive experimental evaluation on real-world datasets,confirming the effectiveness and efficiency of the KS-UE and KS-GRR strategies.
In this paper,we study the prize-collecting k-Steiner tree(PCkST) *** are given a graph G=(V,E) and an integer *** graph is connected and undirected.A vertex r ∈ V called root and a subset R?V called terminals are al...
详细信息
In this paper,we study the prize-collecting k-Steiner tree(PCkST) *** are given a graph G=(V,E) and an integer *** graph is connected and undirected.A vertex r ∈ V called root and a subset R?V called terminals are also given.A feasible solution for the PCkST is a tree F rooted at r and connecting at least k vertices in *** a vertex from the tree incurs a penalty cost,and including an edge in the tree incurs an edge *** wish to find a feasible solution with minimum total *** total cost of a tree F is the sum of the edge costs of the edges in F and the penalty costs of the vertices not in *** present a simple approximation algorithm with the ratio of 5.9672 for the *** algorithm uses the approximation algorithms for the prize-collecting Steiner tree(PCST) problem and the k-Steiner tree(kST) problem as *** we propose a primal-dual based approximation algorithm and improve the approximation ratio to 5.
We reprove the countable splitting lemma by adapting Nawrotzki’s algorithm which produces a sequence that converges to a solution. Our algorithm combines Nawrotzki’s approach with taking finite cuts. It is construct...
详细信息
Mobile Money (MM) technologies are popular in developing countries where people are unbanked, and they are exploited as means of financial transactions in the economy. Sophisticated cyber-phishing techniques successfu...
详细信息
In this paper, we study a modification of the mathematical model describing inflammation and demyelination patterns in the brain caused by Multiple Sclerosis proposed in [Lombardo et al. (2017), Journal of Mathematica...
详细信息
In the problem of maximizing regularized two-stage submodular functions in streams, we assemble a family ■ of m functions each of which is submodular and is visited in a streaming style that an element is visited for...
详细信息
In the problem of maximizing regularized two-stage submodular functions in streams, we assemble a family ■ of m functions each of which is submodular and is visited in a streaming style that an element is visited for only once. The aim is to choose a subset S of size at most ■ from the element stream ■, so as to maximize the average maximum value of these functions restricted on S with a regularized modular term. The problem can be formally cast as ■, where c:■ is a non-negative modular function and ■ is a non-negative monotone non-decreasing submodular function. The well-studied regularized problem of ■ is exactly a special case of the above regularized two-stage submodular maximization by setting m=1 and ■=k. Although f(·)-c(·) is submodular, it is potentially negative and non-monotone and admits no constant multiplicative factor approximation. Therefore, we adopt a slightly weaker notion of approximation which constructs S such that f(S)-c(S)≥ρ·f(O)-c(O) holds against optimum solution O for some ρ∈(0, 1). Eventually, we devise a streaming algorithm by employing the distorted threshold technique, achieving a weaker approximation ratio with ρ=0.2996 for the discussed regularized two-stage model.
暂无评论