In recent days the need for energy resources is dramatically increasing world-wide. Overall 80% of the energy resource is supplied in the form of fuel based energy source and nuclear based energy source. Where fuel based energy resources are very essential in day-to-day life. Fossil fuel is also one among the energy resource and due to the high demand we face shortage in these resources. Providing electricity in rural areas is still a difficult process because of the shortage of energy resources. This issue can be rectified by choosing an alternate to electricity. To achieve this we have integrated many renewable energy sources to form a hybrid-renewable energy source system and this is capable of providing power supply to these areas. We have adopted artificial neural networks (ANN) technique based on machine learning to accomplish this process. For short-term prediction other techniques such as MLP, CNN, RNN and LSTM are used. These values are used as reference value in final execution.

/pdf/fault-diagnosis-in-hybrid-renewable-energy-sources-with-57t5mhc7dd.pdf

Fault Diagnosis in Hybrid Renewable Energy Sources with Machine Learning Approach

The speech signal contains a vast spectrum of information about the speaker such as speakers’ gender, age, accent, or health state. In this paper, we explored different approaches to automatic speaker’s gender classification and age estimation system using speech signals. We applied various Deep Neural Network-based embedder architectures such as x-vector and d-vector to age estimation and gender classification tasks. Furthermore, we have applied a transfer learning-based training scheme with pre-training the embedder network for a speaker recognition task using the Vox-Celeb1 dataset and then fine-tuning it for the joint age estimation and gender classification task. The best performing system achieves new state-of-the-art results on the age estimation task using popular TIMIT dataset with a mean absolute error (MAE) of 5.12 years for male and 5.29 years for female speakers and a root-mean square error (RMSE) of 7.24 and 8.12 years for male and female speakers, respectively, and an overall gender recognition accuracy of 99.60%.

Gender and Age Estimation Methods Based on Speech Using Deep Neural Networks.

Smart city infrastructure has a significant impact on improving the quality of humans life. However, a substantial increase in the urban population from the last few years poses challenges related to resource management, safety, and security. To ensure the safety and security in the smart city environment, this paper presents a novel approach by empowering the authorities to better visualize the threats, by identifying and predicting the highly-reported crime zones in the smart city. To this end, it first investigates the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) to detect the hot-spots that have a higher risk of crime occurrence. Second, for crime prediction, Seasonal Auto-Regressive Integrated Moving Average (SARIMA) is exploited in each dense crime region to predict the number of crime incidents in the future with spatial and temporal information. The proposed HDBSCAN and SARIMA based crime prediction model is evaluated on ten years of crime data (2008-2017) for New York City (NYC) . The accuracy of the model is measured by considering different time scenarios such as the year-wise, (i.e., for each year), and for the total considered duration of ten years using an 80:20 ratio. The 80% of data was used for training and 20% for testing. The proposed approach outperforms with an average Mean Absolute Error (MAE) of 11.47 as compared to the highest scoring DBSCAN based method with MAE 27.03.

/pdf/spatio-temporal-crime-predictions-by-leveraging-artificial-4f8hl0bds6.pdf

Spatio-Temporal Crime Predictions by Leveraging Artificial Intelligence for Citizens Security in Smart Cities

Tropical deforestation varies temporally and spatially which can inhibit the ability of existing protected areas to stem forest loss. Identifying the spatial-temporal distribution of deforestation and its concentration can help decision makers decide conservation priorities and leverage limited resources. This study assessed how topographic and anthropogenic variables affect deforestation patterns within and outside protected areas on the islands of Sumatra and Kalimantan in Indonesia. Emerging hotspot analysis (EHA) was used to evaluate spatial and temporal trends of forest loss on the Hansen annual forest loss data for these islands from 2001-2018. For the two islands, most hotspots were detected outside protected areas; those within protected areas were mainly concentrated at boundaries, where lower elevation/slope and high human pressure could be observed. New hotspots were identified within the three PAs in Sumatra, while three kinds of hotspots (consecutive, oscillating, and sporadic) were found in the two PAs of Kalimantan (Kutai and Teluk Kelumpang). Areas with high human pressure (average human footprint higher than 12) were covered by a high density of hotspots. The results identify specific areas where forest loss has emerged recently, which could indicate a conservation priority. It is suggested that new protected areas be established in locations showing intensifying and persistent hotspots-those where deforestation has occurred for ≥16 of 18 years of the study period.

Spatial-temporal variations in deforestation hotspots in Sumatra and Kalimantan from 2001-2018.

/pdf/the-efficacy-of-machine-learning-supported-smart-system-for-1xzp3ra7.pdf

The Efficacy of Machine-Learning-Supported Smart System for Heart Disease Prediction

A Clustering Based Hotspot Identification Approach For Crime Prediction

Machine learning classification techniques are extremely useful in the medical field by providing accurate results and quick diagnosis of diseases. Hence, these techniques save lot of time for both doctors and patients. The neural networks can be used as classifiers predict the diagnosis of Cardiovascular Heart disease. This research has explored neural networks, where it has analyzed many optimizing algorithms and weight initializing techniques in this research. The most common algorithms are used and observed their effect on the accuracy of the model. The coronary heart disease dataset is used in the thesis as data to work on. In order to compare results, further analysis has been done and results are compared with performance of other classifiers.

Prediction of Heart disease using DNN

A conversational agent (chatbot) is computer software capable of communicating with humans using natural language processing. The crucial part of building any chatbot is the development of conversation. Despite many developments in Natural Language Processing (NLP) and Artificial Intelligence (AI), creating a good chatbot model remains a significant challenge in this field even today. A conversational bot can be used for countless errands. In general, they need to understand the user's intent and deliver appropriate replies. This is a software program of a conversational interface that allows a user to converse in the same manner one would address a human. Hence, these are used in almost every customer communication platform, like social networks. At present, there are two basic models used in developing a chatbot. Generative based models and Retrieval based models. The recent advancements in deep learning and artificial intelligence, such as the end-to-end trainable neural networks have rapidly replaced earlier methods based on hand-written instructions and patterns or statistical methods. This paper proposes a new method of creating a chatbot using a deep neural learning method. In this method, a neural network with multiple layers is built to learn and process the data.

Chatbot: A Deep Neural Network Based Human to Machine Conversation Model

The proposed research work has used a Multilayer Perceptron (MLP) based deep learning model for deploying a gender-based user classification. The input to proposed model is a set of acoustics features, which was extracted by various packages. This work has developed a dataset consisting of 3168 data points, which were extracted from the recorded voice samples of both men and women. The voice samples are produced by using acoustics analysis. The proposed model is trained with different set of parameters and finally comes up with an MLP model that achieves an accuracy of 96 percent on the test dataset.

Voice Gender Recognizer Recognition of Gender from Voice using Deep Neural Networks

Decades of study have firmly established that crime shows geographical (ie, spatial) patterns [1]. Analysis of spatial patterns is a standard research approach in criminology, just as it is in ecology, epidemiology, and other fields. Spatial patterns may have different dimensionalities, as they can involve points, lines, or areas; they may also vary with resolution. Crime-pattern analysis may be conducted at the level of census tracts, zip-code units, street segments, counties, states, or countries. In this work, after considering a number of possible resolutions, we find and utilize one that seems optimal for crime prediction. Spatial pattern analysis can be density-based (area-based) or distance-based. However, Euclidean distance is not always useful in identifying urban crime patterns: Places that are close together on a map (in terms of Euclidean distance) may in fact be very isolated from each other if they are not joined by streets, are on opposite sides of a river with few bridges, or are in neighborhoods separated by some invisible economic or social barrier that keeps residents apart. On the other hand, densityor area-based spatial pattern analysis seems to fit naturally with the intuitive concept that cities are built up of neighborhoods. Density-based analysis can be further categorized as global or local. The first considers the ratio of observed crime events to the area of the region under study; the latter measures crime incidence for different units within that region. The spatial pattern is only one aspect of the distribution of crime; there are also temporal patterns. Many researchers have studied variation in crime rates between day and night, weekday and weekend, or among different seasons of the Received: 5 December 2019 | Revised: 21 April 2020 | Accepted: 6 May 2020 DOI: 10.4218/etrij.2019-0306

https://onlinelibrary.wiley.com/doi/pdf/10.4218/etrij.2019-0306

Gaurav Hajela

Papers

A Clustering Based Hotspot Identification Approach For Crime Prediction

Prediction of Heart disease using DNN

Chatbot: A Deep Neural Network Based Human to Machine Conversation Model

Voice Gender Recognizer Recognition of Gender from Voice using Deep Neural Networks

A multi‐dimensional crime spatial pattern analysis and prediction model based on classification