Recent Patents on Computer Science (Discontinued)

The special issue contains research papers elaborating advancements in Swarm Intelligence and Machine learning for optimizing problems in image processing and data analytics. Swarm Intelligence, is an artificial intelligence technique, involving the study of collective behavior in decentralized systems [1-3]. Swarm Intelligence refers to the problem-solving behavior that emerges from the interaction between individuals of such systems, and computational SI refers to algorithmic models of such behaviours. These algorithmic models have shown to be able to adapt well in changing environments, and are immensely flexible and robust. The last decade has shown an exaggerated amount of research interests in Swarm Intelligence, by a significant increase in the number of research publications on various techniques of SI, especially on Ant Colony Optimization (ACO), Bee Colony Optimization (BCO), Firefly Swarm, Cat Swarm and many more. Lots of research is undergoing in many realworld applications in the range from scientific research to engineering tasks. In this special issue, we aim to bring interaction of two important areas- Swarm Intelligence and Machine Learning as fusion towards solving complex problems in the area of Image Processing and Data Analytics. The special issue contains 8 papers, selected after a vigorous reviewing process conducted by a team of renowned Swarm Intelligence experts. These papers deal with applying SI techniques in the area of Image Processing, Healthcare and Pattern Recognition.

Artificial intelligence is getting significance in our daily life. Everyday, new ideas are proposed by scientists, researchers, academicians and event students to develop new apps, tools or machines to make our livelihood earlier. Therefore, artificial intelligence and machine learning remain one of the sprightliest extents of discussion and attentiveness in current technology developments. Machine learning and artificial intelligence contribute to an operative elucidation in engineering applications. They cover pattern recognition, computer vision, artificial neural network, image processing, biometric systems, fuzzy systems, reasoning, evolutionary algorithms, and quantum computing, amid others. Such practices are supplementary to social intellect for managing uncertainty and individual vagueness in the course of making decisions. Another innovative research era in the development of machine learning and artificial intelligence models is data analytics and optimization which play a significant role in many research directions. Accordingly, the fast growth of computer science research has elevated the importance of in-depth junction of machine learning and artificial intelligence computing models. Additionally, applying machine learning and artificial intelligence coordination for engineering applications is viable and rigorous. Another latest research direction now is deep learning which is more steps ahead to create a human computer interface for reaching new goals in artificial intelligence. This is providing enormous opportunities for researchers. Therefore, this thematic issue has a primary goal to circulate the innovations and applications of machine learning and artificial intelligence methodologies. The different engineering systems include various sub-branches as pattern recognition, computer vision, artificial neural network, image processing, biometric systems, swarm intelligence, computational intelligence, fuzzy systems, reasoning, evolutionary algorithms, and quantum computing. There are many manuscripts submitted by researchers for this thematic issue. After double blind review of submitted articles, it is not possible to accept all the papers for publication due many reasons like, out of scope of Thematic Issue, novelty of research work etc. This is “Part I” of Thematic Issue - “Artificial Intelligence and Machine Learning: Recent Advances and Applications”, which has 5 accepted articles. This thematic issue starts with an article from Sekhar et al. [1] in which, they developed a method to predict essential proteins by using the topological feature, and biological features. In this proposed solution, two methodologies, Mean Weighted Average and Recursive Feature Elimination are used to predict essential proteins and compared to select the best one. In Mean Weighted Average, consecutive slot data is to be taken into aggregated count, to get the nearest value which is considered as a prescription for the best proteins for the slot, whereas in Recursive Feature Elimination method, whole data is spilt into different slots and the essential protein for each slot is determined. Once the prediction is done, the prescribed proteins have to correlate. The result shows that the accuracy using Recursive Feature Elimination is at-least nine percentage superior when compared to Mean Weighted Average and Between-ness Centrality. The authors Prasanna et al. [2] proposed an IoT tool to increase the performance of the postures of the Yogis, through yoga assistant kit with prediction intelligence which will assist in performing suitable yoga postures. This will help the Yogis to achieve more positive results in the practice of Yoga, with the highest quality of meditation. The developed IoT kit consists of a hardware module (embedded in wrist band) and a mobile application. The yogi should wear the wrist band while practising yoga. The wrist band consists of various sensors like temperature sensor, pressure sensor, humidity sensor etc. which sense body parameters and store them in a central database. Using neural networks and embedded intelligence, our system aims to predict the number of sun salutations a person (yogi) should perform based on the parameters collected from the kit. The results showed that our system works as a virtual trainer which suggests the yogi with the appropriate asana to be performed based on present body conditions. Chowdhary [3] highlighted novel techniques on 3D object recognition system with local shape descriptors and depth data analysis. The proposed work is applied to RGBD and COIL100 datasets and this is of four-fold including pre-processing, feature generation, dimensionality reduction, and classification. The first stage of pre-processing is smoothing by 2D median filtering on the depth (Z-value) and registration by orientation correction on 3D object data. The next stage is of feature generation, having two phases of shape map generation with shape index map and SIFT/SURF descriptors. The dimensionality reduction is the third stage of this proposed work where linear discriminant analysis and principal component analysis are used. The final stage is fused on classification. Here, calculation of the discriminative subspace for the training set, testing of object data and classification are done by comparing target and query data with different aspects for finding proper matching tasks. Parimala [4] discussed recent advances in the field of information and social network which led to the problem of community detection that has received much attention among the researchers. This paper focuses on community discovery, a fundamental task in network analysis by balancing both attribute and structural similarity. The attribute similarity is evaluated using the Jaccard coefficient and structural similarity is achieved through modularity. The proposed algorithm, Structural Attribute Graph Clustering, is based on multiphase approach and has proved to be more scalable and efficient when compared with other stateof- the-art algorithms. The extensive analysis is performed on real world datasets like Facebook, DBLP, Twitter and Flickr with different sizes that demonstrate the effectiveness and efficiency of the SAGC algorithm over other algorithms. Additionally, the clusters are detected based on structural and attribute similarity by achieving high intracluster similarity and low inter cluster similarity. The study by Vincent et al. [5] aims to develop a predictive model for diagnosing the Major Depressive Disorder among the IT professionals by reducing the feature dimension using feature selection techniques and evaluate them by implementing three machine learning classifiers such as Naïve Bayes, Support Vector Machines and Decision Tree. Major Depressive Disorder (MDD) is in simple terms a psychiatric disorder may be indicated by having mood disturbances which are consistent for more than a few weeks. It is considered a serious threat to psychophysiology which when left undiagnosed, may even lead to the death of the victim so it is more important to have an effective predictive model. Major Depressive disorder is often termed as comorbid (medical condition that co-occurs with another) medical condition, it is hardly possible for the physicians to predict that the victim is under depression, timely diagnosis of MDD may help in avoiding other comorbidities. Machine learning is a branch of artificial intelligence which makes the system capable of learning from the past and with that experience it improves the future results even without programming explicitly. As in recent days because of high dimensionality of features, the accuracy of the predictions is comparatively low. In order to get rid of redundant and unrelated features from the data and improve the accuracy, relevant features must be selected using effective feature selection methods.