Digital Detection of Suspicious Behavior With Gesture Recognition and Patterns Using Assisted Learning Algorithms

This chapter presents a study to identify with classification techniques and digital recognition through the construction of a prototype phase that predicts criminal behavior detected in video cameras obtained from a free platform called MOTChallenge. The qualitative and descriptive approach, which starts from individual attitudes, expresses a person in his expression, anxiety, fear, anger, sadness, and neutrality through data collection and feeding of some algorithms for assisted learning. This prototype begins with a degree higher than 40% on a scale of 1-100 of a person suspected, subjected to a two- and three-iterations training parameterized into four categories—hood, helmet, hat, anxiety, and neutrality—where through orange and green boxes it is signaled at the time of the detection and classification of a possible suspect, with a stability of the 87.33% and reliability of the 96.25% in storing information for traceability and future use.

A Study on Efficient Clustering Techniques Involved in Dealing With Diverse Attribute Data

The compatibility issues among the characteristics of data involving numerical as well as categorical attributes (mixed) laid many challenges in pattern recognition field. Clustering is often used to group identical elements and to find structures out of data. However, clustering categorical data poses some notable challenges. Particularly clustering diversified (mixed) data constitute bigger challenges because of its range of attributes. Computations on such data are merely too complex to match the scales of numerical and categorical values due to its ranges and conversions. This chapter is intended to cover literature clustering algorithms in the context of mixed attribute unlabelled data. Further, this chapter will cover the types and state of the art methodologies that help in separating data by satisfying inter and intracluster similarity. This chapter further identifies challenges and Future research directions of state-of-the-art clustering algorithms with notable research gaps.

Strain Field Pattern Recognition for Structural Health Monitoring Applications

Strain field pattern recognition, also known as strain mapping, is a structural health monitoring approach based on strain measurements gathered through a network of sensors (i.e., strain gauges and fiber optic sensors such as FGBs or distributed sensing), data-driven modeling for feature extraction (i.e., PCA, nonlinear PCA, ANNs, etc.), and damage indices and thresholds for decision making (i.e., Q index, T2 scores, and so on). The aim is to study the correlations among strain readouts by means of machine learning techniques rooted in the artificial intelligence field in order to infer some change in the global behavior associated with a damage occurrence. Several case studies of real-world engineering structures both made of metallic and composite materials are presented including a wind turbine blade, a lattice spacecraft structure, a UAV wing section, a UAV aircraft under real flight operation, a concrete structure, and a soil profile prototype.

Signal Processing and Pattern Recognition in Electronic Tongues

This chapter reviews the development of solutions related to the practical implementation of electronic tongue sensor arrays. Some of these solutions are associated with the use of data from different instrumentation and acquisition systems, which may vary depending on the type of data collected, the use and development of data pre-processing strategies, and their subsequent analysis through the development of pattern recognition methodologies. Most of the time, these methodologies for signal processing are composed of stages for feature selection, feature extraction, and finally, classification or regression through a machine learning algorithm.

Detection and Classification of Wear Fault in Axial Piston Pumps

Variable displacement axial piston hydraulic pumps (VDAP) are the heart of any hydraulic system and are commonly used in the industrial sector for its high load capacity, efficiency, and good performance in the handling of high pressures and speeds. Due to this configuration, the most common faults are related to the wear and tear of internal components, which decrease the operational performance of the hydraulic system and increase maintenance costs. So, through data acquisition such as signals of pressure and the digital processing of them, it is possible to detect, classify, and identify faults or symptoms in hydraulic machinery. These activities form the basis of a condition-based maintenance (CBM) program. This chapter shows the developed methodology to detect and classify a wear fault of valve plate taking into account six conditions and the facilities providing by wavelet analysis and ANNs.

HAAR Characteristics-Based Traffic Volume Method Measurement for Street Intersections

Traffic volume is an important measurement to design mobility strategies in cities such as traffic light configuration, civil engineering works, and others. This variable can be determined through different manual and automatic strategies. However, some street intersections, such as traffic circles, are difficult to determine their traffic volume and origin-destination matrices. In the case of manual strategies, it is difficult to count every single car in a mid to large-size traffic circle. On the other hand, automatic strategies can be difficult to develop because it is necessary to detect, track, and count vehicles that change position inside an intersection. This chapter presents a vehicle counting method to determine traffic volume and origin-destination matrix for traffic circle intersections using two main algorithms, Viola-Jones for detection and on-line boosting for tracking. The method is validated with an implementation applied to a top view video of a large-size traffic circle. The video is processed manually, and a comparison is presented.

Recent (Dis)similarity Measures Between Histograms for Recognizing Many Classes of Plant Leaves

The accurate identification of plant species is crucial in botanical taxonomy as well as in related fields such as ecology and biodiversity monitoring. In spite of the recent developments in DNA-based analyses for phylogeny and systematics, visual leaf recognition is still commonly applied for species identification in botany. Histograms, along with the well-known nearest neighbor rule, are often a simple but effective option for the representation and classification of leaf images. Such an option relies on the choice of a proper dissimilarity measure to compare histograms. Two state-of-the-art measures—called weighted distribution matching (WDM) and Poisson-binomial radius (PBR)—are compared here in terms of classification performance, computational cost, and non-metric/non-Euclidean behavior. They are also compared against other classical dissimilarity measures between histograms. Even though PBR gives the best performance at the highest cost, it is not significantly better than other classical measures. Non-Euclidean/non-metric nature seems to play an important role.

Cost-Effective Tabu Search Algorithm for Solving the Controller Placement Problem in SDN

Software-defined networks (SDN) is an emerging paradigm that has been widely explored by the research community. At the same time, it has attracted a lot of attention from the industry. SDN breaks the integration between control and data plane and creates the concept of a network operating system (controller). The controller should be logically centralized, but it must comply with availability, reliability, and security requirements, which implies that it should be physically distributed in the network. In this context, two questions arise: How many controllers should be included? and Where should they be located? These questions comprise the controller placement problem (CPP). The scope of this study is to solve the CPP using the meta-heuristic Tabu search algorithm to optimize the cost of network operation, considering flow setup latency and inter-controller latency constraints. The network model presented considers both controllers and links as IT resources as a service, which allows focusing on operational cost.

Analytical Observations Between Subjects' Medications Movement and Medication Scores Correlation Based on Their Gender and Age Using GSR Biofeedback

Increasing stress levels in people is creating higher tension levels that ultimately result in chronic headaches. To get the best result, the subjects are divided into two groups. One group will be introduced under EMG, and the other will be handled under GSR. The change in the behaviour of subject (i.e., the change in the stress level) is measured at the intervals of one month, three months, six months, and twelve months. The main aim of the research is to study the effects of tension type headache using biofeedback therapies on various modes such as audio modes, visual modes, and audio-visual modes. The groups were randomly allocated for galvanic skin resistance (GSR) therapies, and the other one was control group (the group that was not under any type of allopathic or other medications). Except for the control group, the groups were treated in a session for 20 minutes in isolated chambers. The results were recorded over a specific period of time.

Weed Estimation on Lettuce Crops Using Histograms of Oriented Gradients and Multispectral Images

Each crop has their own weed problems. Therefore, to understand each problem, agronomists and weed scientists must be able to determine the weed abundance with the most precise method. There are several techniques to scouting, including visual counting for density or estimations for coverage of weeds. However, this technique depends by the evaluator subjectivity, performance, and training, causing errors and bias when estimating weeds abundance. This chapter introduces a methodology to process multispectral images, based on histograms of oriented gradients and support vector machines to detect weeds in lettuce crops. The method was validated by experts on weed science, and the statistical differences were calculated. There were no significant differences between expert analysis and the proposed method. Therefore, this method offers a way to analyze large areas of crops in less time and with greater precision.