Emotion recognition has emerged as an important research area which may reveal some valuable input to a variety of purposes. People express their emotions directly or indirectly through their speech, facial expressions, gestures or writings. Many different sources of information, such as speech, text and visual can be used to analyze emotions. Nowadays, writings take many forms of social media posts, micro-blogs, news articles, etc., and the content of these posts can be useful resource for text mining to discover and unhide various aspects, including emotions. Extracting emotions behind these postings is an immense and complicated task. To tackle this problem, researchers from diverse fields are trying to find an efficient way to more precisely detect human emotions from various sources, including text and speech. In this sense, different word-based and sentence-based techniques, machine learning, natural language processing methods, etc., have been used to achieve better accuracy. Analyzing emotions can be helpful in many different domains. One such domain is human computer interaction. With the help of emotion recognition, computers can make better decisions to help users. With the increase in popularity of robotic research, emotion recognition will also help making human–robot interaction more natural. This survey covers existing emotion detection research efforts, emotion models, emotion datasets, emotion detection techniques, their features, limitations and some possible future directions. We focus on reviewing research efforts analyzing emotions based on text and speech. We investigated different feature sets that have been used in existing methodologies. We summarize basic achievements in the field and highlight possible extensions for better outcome.

Emotion detection from text and speech: a survey

A new optimized bowl-shaped mono-core surface plasmon resonance based cancer sensor is proposed for the rapid detection of different types of cancer affected cell. By considering the refractive index of each individual cancer contaminated cell with respect to their normal cell, some major optical parameters variation are observed. Moreover, the cancerous cell concentration is considered at 80% in liquid form and the detection method is finite element method with 2 100 390 mesh elements. The variation of spectrum shift is obtained by plasmonic band gap between the silica and cancer cell part which is separated by a thin (35 nm) titanium film coating. The proposed sensor depicts a high birefringence of 0.04 with a maximum coupling length of 66 $\mu$ m. However, the proposed structure provides an optimum wavelength sensitivity level between about 10 000 nm/RIU and 17 500 with a resolution of the sensor between 1.5 × 10−2 and 9.33 × 10−3 RIU. Also, the transmittance variance of the cancerous cell ranges from almost 3300 to 6100 dB/RIU and the amplitude sensitivity ranges nearly between −340 and −420 RIU $^{-1}$ for different cancer cells in major polarization mode with the maximum detection limit of 0.025. Besides, the overall sensitivity performance is measured with respect to their normal cells which can be better than any other prior structures that have already proposed.

/pdf/surface-plasmon-resonance-based-titanium-coated-biosensor-381hqghsyq.pdf

Surface Plasmon Resonance Based Titanium Coated Biosensor for Cancer Cell Detection

This paper proposes a novel cancer sensor based on dual core photonic crystal fiber for the detection of cancer cells in cervical, breast, and basal parts. The samples are taken in fluid form and infiltrated into the farmed cavity using selective infiltration method. Each fluid form has its own refractive index values which give the various responses in the transmission and loss spectrum. The spectral shift is obtained by inducing the coupling mechanism between silica core and cancer cell core for its launching input optical field which is investigated by finite element method. The proposed structure is also optimized with its structural dimensional property for enhancing the sensitivity. The sensing performances for the cervical cancer cell are obtained as high as 7916 nm/RIU for $x$ -polarization and 10625 nm/RIU for $y$ -polarization with the detection limit of 0.024. The sensitivity to breast cancer cells for $x$ - and $y$ -polarization is 5714.28 and 7857.14 nm/RIU, respectively, with detection limit of 0.014. Similarly, the sensitivity to basal cells can also reach 4500 nm/RIU for $x$ -polarization and 6000 nm/RIU for $y$ -polarization. To the best of our knowledge, such sensitivities are the highest reported thus so far.

Photonic Crystal Fiber-Based Refractive Index Sensor for Early Detection of Cancer

In this paper, a novel partial type-b crystalline core with more compact cladding in hexagonal packing photonic crystal fiber (CC-PCF)-based optical sensor has been proposed for sensing different blood components. This fiber has investigated in terahertz (THz) region from 1.5 to 3.50 THz, intending to superior relative sensitivity with low confinement loss (CL). Circular air holes have been employed in the formation of the partial type-b crystalline core in a symmetric manner. A significant relative sensitivity response of 80.93%, 80.56%, 80.13%, 79.91%, and 79.39% are achieved for the targeted analytes such as RBCs, hemoglobin, WBCs, plasma, and water at frequency ${f} = 1.5$ THz. In X-polarization mode, a negligible CL of $1.23\times 10^{-11}$ dB/m, $8.63\times 10^{-12}$ dB/m, $4.93\times 10^{-12}$ dB/m, $2.93\times 10^{-12}$ dB/m, and $1.13\times 10^{-12}$ dB/m are also gained, respectively, for same analytes and at same THz frequency. Moreover, effective area ( A eff), V-Parameter ( $V_{\mathrm{ eff}}$ ), dispersion ( $\beta _{2}$ ), spot size ( $W_{\mathrm{ eff}}$ ), and beam divergence ( $\theta $ ) have been determined over the investigated region. The improved outcomes are anticipated that the proposed CC-PCF sensor will be opened a new epoch in biomedical sensing purposes.

Refractive Index-Based Blood Components Sensing in Terahertz Spectrum

A plethora of research in recent years has been reported on biosensing in the surface plasmon resonant systems. However, very little research has reported a tunable and highly sensitive biosensor in a nanoscale platform. In this regard, we propose a nanoscale hyperbolic metamaterial (HMM)-based prism coupled waveguide sensor (PCWS) in the near-infrared range. The HMM layer makes up one of the constituents of the PCWS—comprised of a periodically arranged assembly of silver nanostrips. The structure is numerically simulated by the finite difference time domain method. It is demonstrated that the sensitivity of the reflected light can be tuned through the refractive index (RI) of the solution. Moreover, the effects of alteration of constituents of PCWS on the sensitivity have been analyzed. Results show that the sensitivity of PCWS can be harnessed by altering the thickness, slant angle of HMM layer, volume fraction (f) of metal in the HMM layer, and the incidence angle of light. For this purpose, the structure is numerically simulated by the finite difference time domain method. In the optimum design of the proposed sensor, the maximum value of sensitivity is achieved as high as S=3450  nm/refractive index unit with θ=10° and ϕ=10° and a metamaterial thickness of 250 nm. Moreover, the structure has a nanoscale footprint of 600  nm×400  nm×200  nm.

Nanoscale, tunable, and highly sensitive biosensor utilizing hyperbolic metamaterials in the near-infrared range.

In this paper, we have demonstrated and designed a 2D photonic crystal-based biosensor with line defect, which can detect glucose concentration in urine. Simulation and analysis have been done in order to detect glucose concentration in normal urine (0-15 mg/dL), urine with 0.625, 1.25, 2.5, 5, and 10 gm/dL of glucose concentration in the wavelength range of 1530-1565 nm. Finite-difference time-domain method has been used for the analysis. Massachusetts Institute of Technology electromagnetic equation propagation and MIT photonic bands simulation tools have been used for modeling and designing of photonic crystal, and IPKISS software framework has been used for generation of mask design, which can be used for the fabrication of the photonic crystal sensor. It has been observed from the band structure that for little change in refractive index, there will be a moderate shift in the frequency and transmitted output power and hence it acts as a sensor. This indicates that it is highly sensitive for the change in refractive index.

Design of Photonic Crystal-Based Biosensor for Detection of Glucose Concentration in Urine

Design of photonic crystal based ring resonator for detection of different blood constituents

This paper tells about the early detection of cancer cell by using photonic band gap method. System level cancer cell detection has been done with the dielectric constant(at optical frequency) as the input. Comparison of normal cell and cancerous cell has been done and a precise frequency shift has been observed. The input dielectric constant values of normal cell varies from 1.8225 to 1.8769 and for cancer cell it varies from 1.9376 to 1.9628. Even though the change in the input is very small, a micron change in the frequency has been observed. Thus, photonic crystal based sensor will differentiate the normal cells from cancerous cell.

Design and modelling of photonic sensor for cancer cell detection

In this paper, a 2D photonic crystal sensor using gratings has been designed for the analysis of Basal, Breast and Cervical cancer cells. The grating design, incorporated in the photonic crystal waveguide increases the efficiency and sensitivity of the designed sensor. The fact that index of refraction of the cancer cells differs from the normal cell, it can be differentiated and detected using optical techniques. The shift in the wavelength and intensity levels in the reflection spectrum has been observed for cancer and normal cells. FDTD method has been used for analyzing cells. MEEP simulation tool has been used for modeling and designing of sensor.

Preeta Sharan

Papers

Design of Photonic Crystal-Based Biosensor for Detection of Glucose Concentration in Urine

Design of photonic crystal based ring resonator for detection of different blood constituents

Design and modelling of photonic sensor for cancer cell detection

A photonic crystal sensor for analysis and detection of cancer cells

Photonic crystal ring resonator structure for temperature measurement